巴西专利BR112015000039B1 METHOD AND DEVICE FOR RECOMMENDING MULTIMEDIA CONTENT

专利PDF首页>>巴西专利

专利附录

专利说明

权利要求

类似技术

同族专利

引用文献

法律状态

优先权

专利摘要:
method to recommend multimedia resource and device of the same. The present disclosure provides a method for recommending a multimedia resource and a device thereof, which belong to the field of multimedia resource technology. the method includes: acquiring user preview data of a multimedia resource to be recommended in an evaluation playback track; analyze user view data, obtain user action data that match the multimedia resource to be recommended; calculate a first user preference score of the multimedia resource to be recommended according to the user action data that corresponds to the multimedia resource to be recommended; acquiring second user preference scores from a plurality of recommended multimedia resources; and recommend the multimedia resource to be recommended according to the first user preference score and the second user preference scores. as the user preference score of the multimedia resource to be recommended is calculated according to the user action data that corresponds to the multimedia resource to be recommended, and the user action data may reflect the users' actual degree of preference to the multimedia resource, the recommendation accuracy of the multimedia resource to be recommended according to the user preference score of the multimedia resource to be recommended is relatively high.
公开号:BR112015000039B1
申请号:R112015000039-8
申请日:2014-10-23
公开日:2022-01-18
发明作者:Bin Lin；Bo Zhang
申请人:Xiaomi Inc；
IPC主号:

专利说明:

[0001] This application is based on and claims priority from Patent Application No. CN 201410230541.3, filed on May 28, 2014, the entire contents of which are incorporated herein by reference. FIELD OF TECHNIQUE
[0002] The present disclosure relates generally to the field of multimedia resource technology, and particularly to a method for recommending a multimedia resource and a device thereof. BACKGROUND
[0003] In the information age, during courses in which a user visits the internet or watches a video program, if the multimedia resources in which the user is interested are recommended to him, it will not only facilitate operations such as browsing or pay attention to relevant products by the user, in turn, achieving a goal of enhancing the user experience, but it can also allow a provider of multimedia resources to assess the extent of attention to multimedia resources. Therefore, it is those skilled in the art who are interested in how to accurately recommend multimedia resources to an appropriate group of users.
[0004] In the related technique, a multimedia resource is typically recommended as follows. First, the multimedia resource to be recommended is scored with a degree of preference, and then the multimedia resource is recommended according to the multimedia resource score. Scoring the degree of preference can be done as follows: first, a multimedia resource similar to the multimedia resource to be recommended is determined according to the type of multimedia resource to be recommended; and a user preference score of the multimedia resource to be recommended is determined according to a user preference score of the similar multimedia resource. Wherein the user preference score of the similar multimedia resource is obtained as follows: the similar multimedia resource is released on a plurality of devices that reproduce the similar multimedia resource; sensors are mounted on or in the vicinity of a plurality of playback devices; the number of users and the user's length of time are statistically processed through the sensors; and the user preference score of the similar multimedia resource is calculated based on the number of users and the length of time the user spends.
[0005] In implementing the present disclosure, the inventors have found at least the following problem existing in the related art:
[0006] Since the multimedia resource is scored based on the simple user data acquired (including the number of users and user dwell time), then the scoring mode has a low precision defect. SUMMARY
[0007] In order to solve the problem in the related art, a method for recommending a multimedia resource and apparatus thereof is provided by the present disclosure.
[0008] In accordance with a first aspect of the modalities of the present disclosure, a method for recommending a multimedia resource is provided, which includes:
[0009] acquire user view data from a multimedia resource to be recommended in an evaluation playback track, wherein the user view data includes at least user video and audio data and user video depth data;
[0010] analyze user view data to obtain user action data that match the multimedia resource to be recommended;
[0011] calculate a first user preference score of the multimedia resource to be recommended according to the user action data that corresponds to the multimedia resource to be recommended;
[0012] acquire second user preference scores from a plurality of recommended multimedia resources; and
[0013] recommend the multimedia resource to be recommended according to the first user preference score and the second user preference scores.
[0014] Optionally, calculating the first user preference score of the multimedia resource to be recommended according to the user action data that corresponds to the multimedia resource to be recommended includes:
[0015] determine at least one user action included in each part of the user action data;
[0016] search pre-stored matching relationships between user actions and user preference values, to obtain a user preference value that corresponds to at least one user action;
[0017] determine a weight that corresponds to each of the user actions according to a ratio of a user action duration time to an extension of playback time of a recommended multimedia resource; and
[0018] calculate the first user preference score of the multimedia resource to be recommended according to the user preference value and the weight that corresponds to each of the user actions.
[0019] Optionally, before searching pre-stored matching relationships between user actions and user preference values, to obtain a user preference value that matches at least one user action, the method additionally includes:
[0020] for each of the user actions, preset a user preference value for the user action; and
[0021] Store the corresponding relationships between user actions and user preference values.
[0022] Optionally, the recommendation of the multimedia resource to be recommended according to the first user preference score and the second user preference scores, includes:
[0023] between the second user preference scores, determine a third user preference score that is similar to the first user preference score;
[0024] determine a multimedia resource receiving user to be recommended according to the third user preference score; and
[0025] send the multimedia resource to be recommended to a receiving user's playback device,
[0026] wherein second user preference scores are calculated according to data collected by second sensors that are mounted on or in the vicinity of a plurality of playback devices that correspond to recommended multimedia resources.
[0027] Optionally, the determination of a user receiving the multimedia resource to be recommended according to the third user preference score includes:
[0028] among third user preference scores, determine a user preference score that is greater than a predefined threshold; and
[0029] Determine a user that matches the user preference score that is greater than the predefined threshold as the receiving user of the multimedia resource to be recommended.
[0030] Optionally, after sending the multimedia resource to be recommended to a playback device of the receiving user, the method additionally includes:
[0031] acquire user view data collected by a third sensor that corresponds to the multimedia resource to be recommended;
[0032] analyze the user view data collected by the third sensor, to obtain a plurality of user action data pieces that correspond to the multimedia resource to be recommended;
[0033] according to each part of the user action data,update a user preference score of the multimedia resource to be recommended; and
[0034] determine validity of multimedia resource to be recommended according to updated user preference score.
[0035] Optionally, user viewing data is collected by first sensors that are mounted on or in the vicinity of a plurality of playback devices in the evaluation playback track.
[0036] In accordance with a second embodiment aspect of the present disclosure, an apparatus is provided for recommending a multimedia resource, which includes:
[0037] An acquisition module for user view data, configured to acquire user view data from a multimedia resource to be recommended in an evaluation playback track, where the user view data includes at least video data and user audio and user video depth data;
[0038] an acquisition module for user action data, configured to analyze user view data, to obtain user action data that corresponds to the multimedia resource to be recommended;
[0039] a calculation module for a user preference score, configured to calculate a first user preference score of the multimedia resource to be recommended according to the user action data that corresponds to the multimedia resource to be recommended;
[0040] an acquisition model for a user preference score, configured to acquire second user preference scores from a plurality of recommended multimedia resources; and
[0041] A recommendation module for a multimedia resource, configured to recommend the multimedia resource to be recommended according to the first user preference score and the second user preference scores.
[0042] Optionally, the calculation module for a user preference score includes:
[0043] a determination unit for a user action, configured to determine, for each user action data part, at least one user action included in the user action data part;
[0044] An acquisition unit for a user preference value, configured to look up pre-stored matching relationships between user actions and user preference values, to obtain a user preference value that corresponds to at least one user action user;
[0045] a weight determination unit, configured to determine a weight that corresponds to each of the user's actions according to a ratio of a user action duration time to an extension of playback time of a recommended multimedia resource; and
[0046] A calculation module for a user preference score, configured to calculate the first user preference score of the multimedia resource to be recommended according to the user preference value and the weight that corresponds to each of the user actions user.
[0047] Optionally, the device additionally includes:
[0048] a definition module for a user preference value, configured to predefine, for each of the user actions, a user preference value for the user action; and
[0049] A storage module, configured to store the corresponding relationships between user actions and user preference values.
[0050] Optionally, the recommendation module for a multimedia resource includes:
[0051] a determining unit for a user preference score, configured to, among the second user preference scores, determine a third user preference score that is similar to the first user preference score;
[0052] a determination unit for a receiving user, configured to determine a receiving user of the multimedia resource to be recommended according to the third user preference score; and
[0053] a sending module for a multimedia resource, configured to send the multimedia resource to be recommended to a receiving user's playback device,
[0054] wherein second user preference scores are calculated according to data collected by second sensors that are mounted on or in the vicinity of a plurality of playback devices that correspond to recommended multimedia resources.
[0055] Optionally, the determination unit for a receiving user is configured to, among third user preference scores, determine a user preference score that is greater than a predefined threshold; and determining a user that matches the user preference score that is greater than the predefined threshold as the receiving user of the multimedia resource to be recommended.
[0056] Optionally, the device additionally includes:
[0057] an acquisition module for sensor data, configured to acquire user view data collected by a third sensor that corresponds to the multimedia resource to be recommended;
[0058] the user action module, configured to analyze the user view data collected by the third sensor, to obtain a plurality of user action data pieces that correspond to the multimedia resource to be recommended;
[0059] an update module for a user preference score, configured to update, for each piece of user action data, a user preference score of the multimedia resource to be recommended; and
[0060] a validity determination module, configured to determine validity of the multimedia resource to be recommended according to the updated user preference score.
[0061] Optionally, user viewing data is collected by first sensors that are mounted on or in the vicinity of a plurality of playback devices in the evaluation playback track.
[0062] Some beneficial effects brought about by the technical solutions provided by the embodiments of the present disclosure may include:
[0063] After the user view data of the multimedia resource to be recommended in the evaluation playback track is analyzed to obtain the user action data that corresponds to the multimedia resource to be recommended, the first user preference score of the multimedia resource to be recommended is calculated according to user action data, then the multimedia resource to be recommended is recommended according to the first user preference score and the second user preference scores from the plurality of recommended multimedia resources . Since the user preference score of the multimedia resource to be recommended is calculated according to the user action data that corresponds to the multimedia resource to be recommended, and the user action data may reflect users' actual degree of preference over multimedia resource, the recommendation accuracy of the multimedia resource to be recommended according to the user preference score of the multimedia resource to be recommended and the user preference scores of the recommended multimedia resources are relatively high.
[0064] It should be understood that the above general description and the detailed description below are exemplary only, and do not limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0065] The accompanying drawings, which are incorporated into and form a part of this specification, illustrate embodiments consistent with the application and, together with the description, serve to explain the principles of the application.
[0066] Figure 1 is a flowchart that shows a method to recommend a multimedia resource according to an exemplary modality;
[0067] Figure 2 is a flowchart showing a method for recommending a multimedia resource according to an exemplary embodiment;
[0068] Figure 3 is a block diagram showing an apparatus for recommending a multimedia resource according to an exemplary embodiment; and
[0069] Figure 4 is a block diagram showing a server according to an exemplary embodiment. DETAILED DESCRIPTION
[0070] Reference will now be made in detail to exemplary modalities, examples of which are illustrated in the accompanying drawings. The following description refers to the accompanying drawings in which the same numerals in different drawings represent the same or similar elements unless represented otherwise. The deployments set forth in the following description of exemplary embodiments do not represent all deployments consistent with the order. Rather, they are merely examples of apparatus and methods consistent with aspects relating to the order as cited in the accompanying embodiments.
[0071] Figure 1 is a flowchart that shows a method to recommend a multimedia resource, according to an exemplary modality. As shown in Figure 1, the method for recommending a multimedia resource is performed on a server, and includes the following steps.
[0072] In step 101, the user view data of a multimedia resource to be recommended in an evaluation playback track is acquired, where the user view data includes at least user video and audio data and user data. user video depth.
[0073] In step 102, the user view data is analyzed, to obtain the user action data that corresponds to the multimedia resource to be recommended.
[0074] In step 103, a first user preference score of the multimedia resource to be recommended is calculated according to the user action data that corresponds to the multimedia resource to be recommended.
[0075] In step 104, second user preference scores from a plurality of recommended multimedia resources are acquired.
[0076] In step 105, the multimedia resource to be recommended is recommended according to the first user preference score and the second user preference scores.
[0077] In the method provided by the modalities of the present disclosure, after the user view data of the multimedia resource to be recommended in the evaluation playback track is analyzed to obtain the user action data that corresponds to the multimedia resource to be recommended, the The first user preference score of the multimedia resource to be recommended is calculated according to the user action data, and then the multimedia resource to be recommended is recommended according to the first user preference score and the second user preference scores. user preference from the plurality of recommended multimedia resources. Since the user preference score of the multimedia resource to be recommended is calculated according to the user action data that corresponds to the multimedia resource to be recommended, and the user action data may reflect users' actual degree of preference over multimedia resource, the recommendation accuracy of the multimedia resource to be recommended according to the user preference score of the multimedia resource to be recommended and the user preference scores of the recommended multimedia resource is relatively high.
[0078] Optionally, calculating the first user preference score of the multimedia resource to be recommended according to the user action data that corresponds to the multimedia resource to be recommended includes:
[0079] for each user action data part, at least one user action included in the user action data part is determined;
[0080] the pre-stored matching relationships between user actions and user preference values are searched for a user preference value that matches at least one user action;
[0081] a weight corresponding to each of the user actions is determined according to a ratio of a user action duration time to an extension of playback time of a recommended multimedia resource; and
[0082] The first user preference score of the multimedia resource to be recommended is calculated according to the user preference value and the weight that corresponds to each of the user actions.
[0083] Optionally, before the pre-stored matching relationships between user actions and user preference values are searched for the user preference value that corresponds to at least one user action, the method additionally includes:
[0084] for each of the user actions, a user preference value is predefined for the user action; and
[0085] Corresponding relationships between user actions and user preference values are stored.
[0086] Optionally recommend the multimedia resource to be recommended according to the first user preference score and the second user preference scores, includes:
[0087] Among the second user preference scores, a third user preference score that is similar to the first user preference score is determined;
[0088] a multimedia resource receiving user to be recommended is determined according to the third user preference score; and
[0089] the multimedia resource to be recommended is sent to a receiving user's playback device,
[0090] wherein second user preference scores are calculated according to data collected by second sensors that are mounted on or in the vicinity of a plurality of playback devices that correspond to recommended multimedia resources.
[0091] Optionally, determining the receiving user of the multimedia resource to be recommended according to the third user preference score, includes:
[0092] Among third user preference scores, a user preference score that is greater than a predefined threshold is determined; and
[0093] A user that matches the user preference score that is greater than the predefined threshold is determined as the receiving user of the multimedia resource to be recommended.
[0094] Optionally, after the multimedia resource to be recommended is sent to the receiving user's playback devices, the method additionally includes:
[0095] User viewing data collected by a third-party sensor that corresponds to the multimedia resource to be recommended is acquired;
[0096] The user view data collected by the third-party sensor is analyzed to obtain a plurality of pieces of user action data that correspond to the multimedia resource to be recommended;
[0097] According to each piece of user action data, a user preference score of the multimedia resource to be recommended is updated; and
[0098] The validity of the multimedia resource to be recommended is determined according to the updated user preference score.
[0099] Optionally, user visualization data is collected by first sensors that are mounted on or in the vicinity of a plurality of playback devices in the evaluation playback track.
[00100] All of the above optional technical solutions may form other optional embodiments of the present disclosure in an arbitrary combination thereof, and the description thereof will not be repeated herein.
[00101] Figure 2 is a flowchart showing a method for recommending a multimedia resource according to an exemplary modality. As shown in Figure 2, the method for recommending a multimedia resource is performed on a server, and includes the following steps.
[00102] In step 201, user view data of a multimedia resource to be recommended in an evaluation playback track is acquired, wherein user view data is collected by first sensors which are mounted on a plurality of playback devices or in close proximity to them in the evaluation playback track.
[00103] Where the evaluation playback track refers to a small track for evaluation playback of the multimedia resource to be recommended. For example, if a provider of the multimedia resource to be recommended intends to release the multimedia resource to be recommended nationwide, the evaluation playback track may be a province or a city; and if the provider of the multimedia resource to be recommended intends to release the multimedia resource to be recommended throughout the city, the evaluation playback track may be a district in the city.
[00104] In addition, user view data includes at least user video and audio data and user video depth data acquired by sensors within their coverage range. The number of users, an identity of each user, a specific property of each user (gender and approximate age), a specific action of each user, and so on within the coverage range of the sensors can be acquired through the visualization data. of user.
[00105] In the modalities of the present disclosure, the multimedia resource to be recommended corresponds to an identifier (ID) that can uniquely identify the multimedia resource to be recommended. In the embodiments of the present disclosure, in order to identify and distinguish numerous multimedia resources, each multimedia resource is provided with an identifier in the embodiments of the present disclosure. Wherein the identifier may be composed of numerals or characters, or numerals and characters, the form of which is not specifically limited in the embodiments of the present disclosure.
[00106] In addition to the identifier, any multimedia resource may additionally include other properties such as a type to which the multimedia resource belongs, a way of playing the multimedia resource, different versions of the multimedia resource, playing time of the multimedia resource, an extension of multimedia resource playback time, a multimedia resource playback device, and so on. Where multimedia resource types may include household appliances, food, locker room, sporting goods, shoes and hats, etc., ways of playing multimedia resources may be videos, images, audios, etc. multimedia refers to what specific time in a specific range of time the multimedia resource is played, the length of playing time of the multimedia resource may equal the length of time of the multimedia resource itself, or it may be more than the length of time of the multimedia resource itself, and the playback devices of a multimedia resource may include multimedia playback devices in public areas, and may also include multimedia playback devices in private areas.
[00107] In the embodiments of the present disclosure, the first sensors are provided on or in the vicinity of a plurality of playback devices in the playback range of evaluation of the multimedia resource to be recommended. Where first sensors refer to at least one sensor, and the term first sensor is only used to refer to sensors that correspond to recommended multimedia resources. Where for a playback device such as a smart TV or a smart computer is typically provided with a built-in sensor, or provided with a built-in camera that has a capture function in addition to a built-in camera, so for that device, the sensor is arranged on the playback device. For a playback device such as a regular TV or a multimedia feature display booth in a public area, it has no built-in sensor, so the sensor needs to be mounted on the playback device or nearby to collect viewing data from user through the sensor. Where, a sensor may include a microphone, a camera, a visual sensor with depth information, a sensor that emits near-infrared light, a distance sensor, an optical sensor, and so on. Sensor types are not specifically limited in the embodiments of the present disclosure.
[00108] In step 202, the user view data of the multimedia resource to be recommended is analyzed to obtain user action data that corresponds to the multimedia resource to be recommended.
[00109] In the embodiments of the present disclosure, the plurality of playback devices in the evaluation playback range of the multimedia resource to be recommended can play tens of, even hundreds of multimedia resources in a period of time. The first sensors provided on or near the plurality of playback devices will, in turn, collect dozens, even hundreds of pieces of user viewing data that correspond to the multimedia resources. These pieces of user view data are fully mixed, so the user view data of the multimedia resource to be recommended needs to be acquired from the numerous user view data pieces. The acquisition of the user view data of the multimedia resource to be recommended can be specifically implemented as follows:
[00110] Multimedia resource playback time to be recommended is acquired; the user view data within a time period of the playback time is acquired from the numerous pieces of user view data according to the playback time; and the user view data acquired is considered as the user view data of the multimedia resource to be recommended.
[00111] However, in addition to the above way of acquiring the multimedia resource to be recommended, other modes of acquisition can be adopted, which are not limited by the modalities of the present disclosure. After the user view data of the multimedia resource to be recommended is acquired, a plurality of pieces of user action data that correspond to the multimedia resource to be recommended can be obtained by analyzing the user view data. Wherein the specific implementation of obtaining user action data according to user view data belongs to the existing known technology, and can be carried out through specific algorithm of the related technique, which will not be repeated in the present document. Where a user corresponds to a user action data part, and the user action data part encompasses at least one user action. Where user actions may include entering or leaving the coverage range of a first sensor, watching a device playing the multimedia resource to be recommended, talking, laughing, a large gesture action, a large body action, sleeping , sit, walk, and so on. The contents of user actions are not specifically limited in the modalities of the present disclosure.
[00112] In step 203, at least one user action included in the part of each of the user action data is determined, and the corresponding pre-stored relationships between the user actions and user preference values are searched for a user preference value that matches at least one user action.
[00113] Where a user's user action data can include one or more user actions. For example, for a user, he can laugh with a big gesture action (clap) while watching the multimedia resource to be recommended. A user preference value represents a user's degree of preference for the multimedia resource to be recommended. In embodiments of the present disclosure, before a user preference value corresponding to at least one user action is obtained, a process of establishing corresponding relationships between user actions and user preference values is additionally included, specifically as Next.
[00114] For each of the user actions, a user preference value is predefined for the user action; and the corresponding relationships between user actions and user preference values are stored.
[00115] Preset user preference values for user actions can be specifically deployed in the following two modes.
[00116] In a first way, according to empirical values, different user preference values are directly specified for different user actions.
[00117] During a course where a user is watching a multimedia resource, if the user smiles or produces a large body action, the user apparently shows preference to the multimedia resource, and if the user is asleep or leaves immediately, the user apparently shows dislike to the multimedia feature. In the first mode, different user preference values are directly specified for different user actions based on such empirical values. However, in the first mode, the definition of user preference values has low precision.
[00118] In a second way, through machine learning, a large amount of user action data is collected, and a large amount of user action data is analyzed and statistically processed, different user preference values are specified for different user actions. user according to the results of statistical processing and analysis.
[00119] In the second mode, since a large amount of user action data is analyzed by machine learning, the definition user preference values for different user actions have relatively high precision.
[00120] In step 204, a weight corresponding to each of the user actions is determined according to a ratio of a user action duration time to an extension of playback time of a multimedia resource to be recommended.
[00121] In the modalities of the present disclosure, for a user, at an initial moment of playing the multimedia resource to be recommended, the user may be attracted by the resplendent start of the same, laugh and gradually approach the playback device of the multimedia resource to be recommended. After starting, the user may suddenly lose interest in the recommended subject or product shown by the multimedia resource to be recommended, and can directly walk away. In that case, in order to accurately determine degrees of preference of a plurality of users to the multimedia resource to be recommended, in the embodiments of the present disclosure, a step of defining a weight for each of the user actions is additionally included.
[00122] When setting a weight for each of the user actions, the weight can be set according to the ratio of the user action duration time to the length of playback time of the multimedia resource to be recommended. For a user action, the greater the ratio of its duration time to the length of playback time of the multimedia resource to be recommended is, the greater the corresponding weighting. Assuming that the playback time span of the multimedia resource to be recommended is 30 seconds, during which time a user first produces a large gestural action (clapping dramatically) and then converses with others and no longer watches the multimedia resource to be recommended. However, the duration time of the big gesture action is only 5 seconds, and the reason for the length of playing time of multimedia resource to be recommended is 1/6, and the duration time of talking with others and not watching the resource multimedia resource to be recommended is 25 seconds, and the ratio for the length of playback time of the multimedia resource to be recommended is 5/6. Therefore, the weight of the latter is by far greater than the weight of the former when setting weights for the above two user actions.
[00123] In step 205, the first user preference score of the multimedia resource to be recommended is calculated according to the user preference value and the weight that corresponds to each of the user actions.
[00124] In the embodiments of the present disclosure, after a user preference value and a weight corresponding to each of the user actions are obtained in accordance with step 203 and step 204 above, the first user preference score of the resource multimedia played against a plurality of users can be obtained according to the following formula (1).
Where S refers to a first user preference score, each from a1 to an refers to a user preference value that corresponds to each of the user actions, each from r1 to rn refers to a weight that corresponds to each of the user actions, and en refers to the number of user actions.
[00125] It should be noted that through the process illustrated by the above steps 201 to 205, the first user preference score of the multimedia resource to be recommended can be obtained. In a subsequent process, before the multimedia resource to be recommended is played, the multimedia resource to be recommended can be recommended according to the first user preference score above that corresponds to the multimedia resource to be recommended, to improve the accuracy of the recommendation of a multimedia resource.
[00126] In step 206, the second user preference scores of a plurality of recommended multimedia resources are acquired.
[00127] In the embodiments of the present disclosure, after the plurality of recommended multimedia resources is released, the server may continue to modify the user preference scores of the plurality of recommended multimedia resources to obtain the second user preference scores according to data from user viewing of the plurality of recommended multimedia resources collected by the sensors through the process of the above steps 201 to 205, and storing the same on the storage medium thereof. Since each multimedia resource corresponds to an identifier, the second user preference scores of the plurality of recommended multimedia resources can be acquired on the storage medium according to the identifiers. Wherein the storage medium can be a memory or a hard disk and the like. The type of storage medium is not specifically limited by the embodiments of the present disclosure.
[00128] In step 207, among the plurality of second user preference scores, a third user preference score that is similar to the first user preference scores is determined.
[00129] In the embodiments of the present disclosure, for each multimedia resource, according to the process provided in steps 201 to 205 above, a user preference score with respect to each user to the multimedia resource within a coverage range of a sensor corresponding can be purchased. Thus, for a multimedia resource, it may correspond to a plurality of user preference scores, and user preference scores are obtained by analyzing user actions of different users during the time that the multimedia resource is played. In embodiments of the present disclosure, the first user preference score includes a user preference score with respect to at least one user for the multimedia resource to be recommended, and a second user preference score includes a user preference score in at least one user to a recommended multimedia resource.
[00130] Wherein, similar means being a difference between user preference scores is less than a particular first value, or all user preference scores are greater than a particular second value. Where the second particular value is greater than the first particular value. However, similar user preference scores may be expressed in ways other than the aforementioned ways, which are not specifically limited in the present embodiments of the present disclosure. Determining whether the first user preference scores are similar to the second user preference scores can be specifically deployed in the following two ways.
[00131] In a first way, an average value of the first user preference scores against a plurality of users to the multimedia resource to be recommended is calculated, an average value of the second user preference scores against a plurality of users to a recommended multimedia resource is calculated, and on a plurality of average values that correspond to the second user preference scores, an average value that is similar to the average value that corresponds to the first user preference scores is determined, then a user preference score that corresponds to the similar average value is a third user preference score.
[00132] In a second way, after the first preference scores are acquired, the user preference scores against a plurality of users to the multimedia resource to be recommended and the recommended multimedia resources can be categorized according to a plurality of properties such as age, gender, etc. For example, if user preference scores are categorized into ages, user preference scores against each age group for the multimedia resource to be recommended are statistically processed. For example, user preference scores against 10-20 year olds for the multimedia resource to be recommended, user preference scores against 20-30 year olds for the multimedia resource to be recommended, user preference scores against 30-40 year olds for the multimedia resource to be recommended, user preference scores against 40-50 year olds for the multimedia resource to be recommended, the preference scores of user versus users 50 to 60 years of age to the multimedia resource to be recommended, and user preference scores relative to users 60 years of age and above to the multimedia resource to be recommended are respectively processed statistically. User preference scores against users in each age group for the multimedia resource to be recommended are considered as the user preference scores for the multimedia resource to be recommended. After the second user preference scores are acquired, the user preference scores against a plurality of users to the recommended multimedia resources can also be categorized in the above way. For a second user preference score, if a user preference score from a category that matches the second user preference score is similar to a user preference score from the category that corresponds to the multimedia resource to be recommended, the score user preference score is a third user preference score similar to the first user preference score.
[00133] Also, when calculating a user preference score against each age group to the recommended multimedia resource, among the user preference scores against all users in the age group, the user preference scores that are less than a first value and user preference scores that are greater than a second value are excluded, an average value of the remaining user preference scores is calculated, and the resulting average value is taken as the user preference score. user matching the age group. However, in addition to the above way of calculating the user preference score in relation to users of each age group to the recommended multimedia resource, other ways of calculating can also be adopted which are not specifically limited in the modalities of the present disclosure.
[00134] In step 208, a receiving user of the multimedia resource to be recommended is determined according to the third user preference score, and the multimedia resource to be recommended is sent to playback devices of a plurality of receiving users .
[00135] In the embodiments of the present disclosure, determining a plurality of users receiving the multimedia resource to be recommended in accordance with the user preference scores of the multimedia resource to be recommended, may be specifically implemented as follows: between a plurality of user preference scores that correspond to the multimedia resource to be recommended, user preference scores that are greater than a predefined threshold are determined, and users that correspond to user preference scores that are greater than the predefined threshold are determined as reception users of the multimedia feature to be recommended.
[00136] Wherein a predefined threshold size may be 10, 100, or other values, which is not specifically limited in the embodiments of the present disclosure. The size of the predefined threshold can be decided depending on the user preference and weighting value setting.
[00137] For the first mode in the above step 207, the third user preference score determined can be more than one, thus, the user preference scores can be further filtered through the predefined threshold threshold, in order to improve the accuracy in recommending the multimedia resource according to the user preference scores subsequently. When recommending the multimedia resource to be recommended, users who match user preference scores that are greater than the predefined threshold can be directly determined as the receiving users of the multimedia resource to be recommended.
[00138] For the second mode in the above step 207, if the preference scores against users of each age group to the multimedia resource to be recommended are categorized, among the user preference scores against each category that correspond to user preference scores that are greater than the predefined threshold, user preference scores that are greater than the predefined threshold are determined, in turn, an age group that corresponds to user preference scores that are greater than the predefined threshold. predefined threshold is determined and finally all users in the age group are considered as the receiving users of the multimedia resource to be recommended.
[00139] It should be noted that the recommendation of the multimedia resource to be recommended can be completed through above steps 201 to 208. After the multimedia resource to be recommended is recommended, the user preference scores of the multimedia resource to be recommended can be be updated through user viewing data collected by third-party sensors mounted on the playback devices of the multimedia resource to be recommended, whose specific process is as per the following step 209.
[00140] In step 209, user view data collected by third-party sensors that corresponds to the multimedia resource to be recommended is acquired, user-view data collected by third-party sensors is analyzed, to obtain a plurality of action data pieces corresponding to the multimedia resource to be recommended, and according to each piece of user action data, the user preference score of the multimedia resource to be recommended is updated.
[00141] In this step, the specific processes of acquiring user view data, acquiring user action data according to user view data, and updating the user preference score of the multimedia resource to be recommended according to user action data can be referenced in above steps 201 to 205, which are not repeated in this document. After the user preference score is updated, the validity of the multimedia resource to be recommended is determined according to the updated user preference score. That is, after the multimedia resource to be recommended is actually released in a real environment, the popularity of the multimedia resource to be recommended can be evaluated according to the updated user preference score. Additionally, in combination with user properties, the degrees of preference of different groups of users for the multimedia resource to be recommended, for example, degrees of preference respectively of young, middle-aged and elderly users for the multimedia resource to be recommended, can be statistically processed. In combination with information about playback devices, the popularity of the multimedia resource to be recommended during the time it is played on different playback devices can be further processed statistically, and so on. All these statistical processes can be performed separately or in combination with each other.
[00142] In the method provided by the modalities of the present disclosure, after the user view data of the multimedia resource to be recommended in the evaluation playback track is analyzed to obtain the user action data that corresponds to the multimedia resource to be recommended, the first user preference score of the multimedia resource to be recommended is calculated according to the user action data, and then the multimedia resource to be recommended is recommended according to the first user preference score and the second scores user preference from the plurality of recommended multimedia resources. Since the user preference score of the multimedia resource to be recommended is calculated according to the user action data that corresponds to the multimedia resource to be recommended, and the user action data may reflect the users' actual degree of preference over multimedia resource, the recommendation accuracy of the multimedia resource to be recommended according to the user preference score of the multimedia resource to be recommended and the user preference scores of the recommended multimedia resource is relatively high.
[00143] Figure 3 is a block diagram showing an apparatus for recommending a multimedia resource according to an exemplary embodiment. Referring to Figure 3, the apparatus includes an acquisition module 301 for user display data, an acquisition module 302 for user action data, a calculation module 303 for a user preference score, a acquisition 304 for a user preference score and a recommendation module 305 for a multimedia resource.
[00144] Wherein the acquisition module 301 for user view data is coupled to the acquisition module 302 for user action data, and configured to acquire user view data from a multimedia resource to be recommended on a playback track of evaluation, wherein the user view data includes at least user video and audio data and user video depth data; the acquisition module 302 for user action data is coupled to the calculation module 303 for a user preference score, and configured to analyze the user view data to obtain user action data corresponding to the multimedia resource a be recommended; the calculation module 303 for a user preference score is coupled to the acquisition model 304 for a user preference score, and configured to calculate a first user preference score of the multimedia resource to be recommended according to data from user action that corresponds to the multimedia resource to be recommended; acquisition model 304 for a user preference score is coupled to recommendation module 305 for a multimedia resource, and configured to acquire second user preference scores from a plurality of recommended multimedia resources; and the recommendation module 305 for a multimedia resource is configured to recommend the multimedia resource to be recommended according to the first user preference score and the second user preference scores.
[00145] Optionally, the calculation module for a user preference score includes:
[00146] a determination unit for a user action, configured to determine at least one user action included in each part of the user action data;
[00147] An acquisition unit for a user preference value, configured to look up pre-stored matching relationships between user actions and user preference values, to obtain a user preference value that matches at least one action of user;
[00148] A weight determination unit, configured to determine a weight that corresponds to each of the user's actions according to a ratio of a user action duration time to an extension of playback time of a recommended multimedia resource ; and
[00149] A calculation module for a user preference score, configured to calculate the first user preference score of the multimedia resource to be recommended according to the user preference value and the weight that corresponds to each of the actions of user.
[00150] Optionally, the device additionally includes:
[00151] a definition module for a user preference value, configured to predefine, for each of the user actions, a user preference value for the user action; and
[00152] A storage module, configured to store the corresponding relationships between user actions and user preference values.
[00153] Optionally, the recommendation module for a multimedia resource includes:
[00154] a determining unit for a user preference score, configured to, among the second user preference scores, determine a third user preference score that is similar to the first user preference score;
[00155] a determination unit for a receiving user, configured to determine a receiving user of the multimedia resource to be recommended according to the third user preference score; and
[00156] a send module for a multimedia resource, configured to send the multimedia resource to be recommended to a receiving user's playback device,
[00157] wherein second user preference scores are calculated according to data collected by second sensors that are mounted on or in the vicinity of a plurality of playback devices that correspond to recommended multimedia resources.
[00158] Optionally, the determination unit for a receiving user is configured to determine, among third user preference scores, a user preference score that is greater than a predefined threshold, and to determine a user that matches the user preference score. user preference that is greater than the predefined threshold as the receiving user of the multimedia resource to be recommended.
[00159] Optionally, the device additionally includes:
[00160] an acquisition module for sensor data, configured to acquire user view data collected by a third sensor that corresponds to the multimedia resource to be recommended;
[00161] a user action module, configured to analyze the user view data collected by the third sensor, to obtain a plurality of user action data pieces that correspond to the multimedia resource to be recommended;
[00162] an update module for a user preference score, configured to, according to each piece of user action data, update a user preference score of the multimedia resource to be recommended; and
[00163] a validity determination module, configured to determine the validity of the multimedia resource to be recommended according to the updated user preference score.
[00164] Optionally, user viewing data is collected by first sensors that are mounted on or in the vicinity of a plurality of playback devices in the evaluation playback track. With respect to the apparatus in the above modalities, the specific operations performed by each of the modules have been described in detail in the modalities of the related methods, which are not repeated in the present document.
[00165] In the apparatus provided by the modalities of the present disclosure, after the user viewing data of the multimedia resource to be recommended in the evaluation playback track is analyzed to obtain the user action data that corresponds to the multimedia resource to be recommended, the The first user preference score of the multimedia resource to be recommended is calculated according to the user action data, and then the multimedia resource to be recommended is recommended according to the first user preference score and the second user preference scores. User preference of the plurality of multimedia resources recommended. Since the user preference score of the multimedia resource to be recommended is calculated according to the user action data that corresponds to the multimedia resource to be recommended, and the user action data may reflect users' actual degree of preference over multimedia resource, the recommendation accuracy of the multimedia resource to be recommended according to the user preference score of the multimedia resource to be recommended and the user preference scores of the recommended multimedia resource is relatively high.
[00166] Figure 4 is a block diagram showing a server according to an exemplary embodiment, configured to perform the above methods to recommend a multimedia resource. Server 400 can vary significantly in configuration or capabilities, and can include one or more central processing units (CPU) 422 (e.g., one or more processors), and memory 432, one or more storage media 430 ( for example, one or more mass storage devices) for storing application program 442 or data 444. Wherein memory 432 and storage medium 430 may be transient or persistent storage. Programs stored on storage medium 430 may include one or more modules (not shown in the Figures) each corresponding to a series of instructions on the server. Additionally, the central processing unit 422 is configured to communicate with the storage medium 430 and execute the series of instructions on the storage medium 430 in the server 400.
[00167] Server 400 may additionally include one or more power supplies 426, one or more wired or wireless network interfaces 450, and one or more input/output interfaces 458, one or more keyboards 456, and/or one or more 441 operating systems, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM and the like.
[00168] Other embodiments of the application will be apparent to those skilled in the art from consideration of the application specification and practice disclosed herein. This application is intended to cover any variations, uses or adaptations of the application following the general principles thereof and including such departures from the present disclosure as is within known or customary practice in the art. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the application being indicated by the following embodiments.
[00169] It will be appreciated that the present application is not limited to the exact construction that has been described above and illustrated in the attached drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is intended to be limited only by the enclosed embodiments.

权利要求:
Claims (9)
[0001]
1. Method for recommending a multimedia content, characterized in that the method comprises the steps of: acquiring (101) data from a user view of a multimedia content to be recommended in an evaluation playback track, in which the data of user preview comprises at least user audio, video data and user video depth data, the evaluation playback track being an area for evaluation playback of the multimedia content to be recommended; analyze (102) the evaluation data user view, to obtain user action data corresponding to the multimedia content to be recommended; calculate (103) a first user preference score of the multimedia content to be recommended according to the user action data corresponding to the multimedia content to be recommended be recommended; acquire (104) second user preference scores from a plurality of recommended multimedia content; and recommend (105) the multimedia content to be recommended according to the first user preference score and the second user preference scores, wherein the step of calculating (103) the first user preference score of the multimedia content comprises: determine at least one user action comprised in each piece of user action data; look up pre-stored corresponding relationships between user actions and user preference values, to obtain a user preference value corresponding to at least one action of user; determining a weight corresponding to each of the user actions according to a ratio of a user action duration time to a playback time extension of a recommended multimedia content; calculate the first user preference score of the multimedia content to be recommended according to the user preference value and weight corresponding to each of the user actions.
[0002]
2. Method according to claim 1, characterized in that, before searching pre-stored corresponding relationships between user actions and user preference values, to obtain a user preference value corresponding to at least one user action, the method further comprises the steps of: for each of the user actions, predefine a user preference value for the user action; and store the corresponding relationships between user actions and user preference values.
[0003]
3. Method according to claim 1 or 2, characterized in that the step of recommending (105) the multimedia content to be recommended according to the first user preference score and the second user preference scores comprises :among the second user preference scores, determine a third user preference score that is similar to the first user preference score; determine a user receiving multimedia content to be recommended according to the third user preference score ; and send the multimedia content to be recommended to a receiving user's playback device, wherein the second user preference scores are calculated according to data collected by second sensors that are mounted on a plurality of playback devices or in the vicinity of the corresponding to the recommended multimedia contents.
[0004]
4. Method according to claim 3, characterized in that the step of determining a user to receive the multimedia content to be recommended according to the third user preference score comprises: among third user preference scores, determining a user preference score that is greater than a predefined threshold; edetermine a user matching user preference score that is greater than the predefined threshold as the user receiving the multimedia content to be recommended.
[0005]
5. Method according to any one of claims 1 to 4, characterized in that the user viewing data is collected by first sensors that are mounted on a plurality of playback devices or in the vicinity thereof in the playback range of evaluation.
[0006]
6. Device for recommending a multimedia content, characterized in that the device comprises: an acquisition module for user visualization data, configured to acquire user visualization data of a multimedia content to be recommended in a playback track of evaluation, wherein the user view data comprises at least user audio, video data, and user video depth data, the evaluation playback track being an area for evaluation playback of the multimedia content to be recommended; a acquisition module for user action data, configured to analyze user view data, to obtain user action data corresponding to multimedia content to be recommended; a calculation module for a user preference score, configured to calculate a first user preference score of the multimedia content to be recommended according to the action data of user matching the multimedia content to be recommended; an acquisition model for one user preference score, configured to acquire second user preference scores from a plurality of recommended multimedia content; and a recommendation module for a multimedia content, configured to recommend the multimedia content to be recommended according to the first user preference score and the second user preference scores; wherein the calculation module for a user preference score comprises: a determination unit for a user action, configured to, for each user action data part, determine at least one user action comprised in the user action data part; an acquisition unit for a value of user preference, configured to look up pre-stored matching relationships between user actions and user preference values, to obtain a user preference value corresponding to at least one user action; a weighting determination unit, configured to determine a weight corresponding to each of the user actions according to a ratio of a duration time from user action to an extension of playback time of recommended multimedia content; and a calculation module for a user preference score, configured to calculate the first user preference score of the multimedia content to be recommended according to the user preference value and the weight corresponding to each of the user actions.
[0007]
7. Device according to claim 6, the device characterized in that the device further comprises: a definition module for a user preference value, configured to, for each of the user actions, predefine a value of user preference for user action; and a storage module, configured to store the corresponding relationships between user actions and user preference values.
[0008]
8. Device according to claim 6 or 7, characterized in that the recommendation module for a multimedia content comprises: a determination unit for a user preference score, configured for, among the second preference scores of user, determine a third user preference score that is similar to the first user preference score; a determination unit for a receiving user, configured to determine a receiving user of the multimedia content to be recommended according to the third score user preference; and a sending module for a multimedia content, configured to send the multimedia content to be recommended to a receiving user's playback device, where the second user preference scores are calculated according to data collected by second sensors that are mounted on a plurality of playback devices or in the vicinity thereof corresponding to recommended multimedia contents.
[0009]
9. Apparatus according to claim 8, characterized in that the determination unit for a receiving user is configured to, among third user preference scores, determine a user preference score that is greater than one predefined threshold; and determining a user matching user preference score that is greater than the predefined threshold as the user receiving the multimedia content to be recommended.

类似技术:

公开号 | 公开日 | 专利标题

BR112015000039B1|2022-01-18|METHOD AND DEVICE FOR RECOMMENDING MULTIMEDIA CONTENT

EP3488618B1|2021-01-13|Live video streaming services with machine-learning based highlight replays

CN103760968B|2015-05-13|Method and device for selecting display contents of digital signage

JP6267861B2|2018-01-24|Usage measurement techniques and systems for interactive advertising

US20160105520A1|2016-04-14|Method, apparatus, and system for pushing network content

CN108012162B|2020-12-04|Content recommendation method and device

CN107404656B|2019-01-29|Live video recommended method, device and server

CN104021162B|2017-09-22|A kind of method and device given a mark for multimedia resource

CN108683952B|2020-10-27|Video content segment pushing method and device based on interactive video

CN103365936A|2013-10-23|Video recommendation system and method thereof

US10909386B2|2021-02-02|Information push method, information push device and information push system

BR112021005620A2|2021-06-22|method and system for generating media content, and readable media.

ES2648368A1|2018-01-02|Video recommendation based on content |

WO2019134587A1|2019-07-11|Method and device for video data processing, electronic device, and storage medium

De Pessemier et al.2016|Enhancing recommender systems for TV by face recognition

CN107392138A|2017-11-24|A kind of display methods and device

WO2018072335A1|2018-04-26|Method and apparatus for recommending friending object

US20210204023A1|2021-07-01|Methods and systems for improving user experience

US20180293311A1|2018-10-11|Database comparison operation to identify an object

CN105744305A|2016-07-06|Monitoring methods and monitoring apparatuses for watching users of digital media terminal

WO2019192455A1|2019-10-10|Store system, article matching method and apparatus, and electronic device

BR112019019430A2|2020-04-14|computer program system, method and product

TWI515033B|2016-01-01|Method for generating beat chart according to music data

WO2018035830A1|2018-03-01|Level-based advertisement video file search method

WO2018035831A1|2018-03-01|Advertisement video playback system

同族专利:

公开号 | 公开日

US10289621B2|2019-05-14|

CN104035982A|2014-09-10|

EP2950551A1|2015-12-02|

RU2014151407A|2016-08-20|

WO2015180385A1|2015-12-03|

KR20160000399A|2016-01-04|

CN104035982B|2017-10-20|

MX2015000199A|2016-03-03|

EP2950551B1|2017-11-15|

US20150347416A1|2015-12-03|

MX359702B|2018-10-05|

KR101732591B1|2017-05-04|

BR112015000039A2|2017-06-27|

JP2016524768A|2016-08-18|

JP6110030B2|2017-04-05|

RU2611260C2|2017-02-21|

引用文献:

公开号 | 申请日 | 公开日 | 申请人 | 专利标题

US8751957B1|2000-11-22|2014-06-10|Pace Micro Technology Plc|Method and apparatus for obtaining auditory and gestural feedback in a recommendation system|

US20030014407A1|2001-04-11|2003-01-16|Green Arrow Media, Inc.|System and method for making media recommendations|

CN1788280A|2003-05-12|2006-06-14|皇家飞利浦电子股份有限公司|Apparatus and method for performing profile based collaborative filtering|

KR100493902B1|2003-08-28|2005-06-10|삼성전자주식회사|Method And System For Recommending Contents|

US7716194B2|2005-01-12|2010-05-11|Microsoft Corporation|File management system employing time line based representation of data|

JP2006325011A|2005-05-19|2006-11-30|Hitachi Ltd|Support method of selecting program to be video recorded and video recording and reproducing apparatus|

RU2427975C2|2005-07-21|2011-08-27|Конинклейке Филипс Электроникс Н.В.|Combining device and method to make it possible for user to select combined content|

US9514436B2|2006-09-05|2016-12-06|The Nielsen Company , Llc|Method and system for predicting audience viewing behavior|

EP2763056A1|2007-03-31|2014-08-06|Sony Deutschland Gmbh|Method for content recommendation|

US8549550B2|2008-09-17|2013-10-01|Tubemogul, Inc.|Method and apparatus for passively monitoring online video viewing and viewer behavior|

JP2009081637A|2007-09-26|2009-04-16|Brother Ind Ltd|Program information selecting device and program information selecting program|

JP4538756B2|2007-12-03|2010-09-08|ソニー株式会社|Information processing apparatus, information processing terminal, information processing method, and program|

JP2009267445A|2008-04-21|2009-11-12|Toshiba Corp|Preference information managing device, and preference information managing method|

KR20090121016A|2008-05-21|2009-11-25|박영민|Viewer response measurement method and system|

CN101763351A|2008-12-23|2010-06-30|未序网络科技（上海）有限公司|Data fusion based video program recommendation method|

EP2275984A1|2009-07-17|2011-01-19|Axel Springer Digital TV Guide GmbH|Automatic information selection based on involvement classification|

JP2011130279A|2009-12-18|2011-06-30|Sony Corp|Content providing server, content reproducing apparatus, content providing method, content reproducing method, program and content providing system|

JP2011166572A|2010-02-12|2011-08-25|Nec Personal Products Co Ltd|Apparatus for estimation of program preference, image viewing system, program viewing confirmation method, and program|

CN101901450A|2010-07-14|2010-12-01|中兴通讯股份有限公司|Media content recommendation method and media content recommendation system|

US20120222057A1|2011-02-27|2012-08-30|Richard Scott Sadowsky|Visualization of affect responses to videos|

CN102780920A|2011-07-05|2012-11-14|上海奂讯通信安装工程有限公司|Television program recommending method and system|

US20130110618A1|2011-11-02|2013-05-02|Yahoo! Inc.|Online article syndication via content packages|

JP2013109537A|2011-11-21|2013-06-06|Nippon Hoso Kyokai <Nhk>|Interest degree estimation device and program thereof|

CN102402625A|2011-12-28|2012-04-04|深圳市五巨科技有限公司|Method and system for recommending music|

CA2775700C|2012-05-04|2013-07-23|Microsoft Corporation|Determining a future portion of a currently presented media program|

US20140026156A1|2012-07-18|2014-01-23|David Deephanphongs|Determining User Interest Through Detected Physical Indicia|

CN103136351B|2013-02-25|2017-04-19|Tcl集团股份有限公司|Media system and media file pushing method thereof|

CN103324729B|2013-06-27|2017-03-08|小米科技有限责任公司|A kind of method and apparatus for recommending multimedia resource|

CN103327111A|2013-07-01|2013-09-25|百度在线网络技术（北京）有限公司|multimedia file recommendation method, system thereof and server|

CN103514255B|2013-07-11|2017-04-05|江苏谐云智能科技有限公司|A kind of collaborative filtering recommending method based on project stratigraphic classification|

US9264770B2|2013-08-30|2016-02-16|Rovi Guides, Inc.|Systems and methods for generating media asset representations based on user emotional responses|

CN103544212B|2013-09-09|2017-04-05|Tcl集团股份有限公司|A kind of content recommendation method and system|

CN103500215A|2013-09-30|2014-01-08|乐视网信息技术（北京）股份有限公司|Multi-media file recommending method and device|

US9338489B2|2014-04-23|2016-05-10|Netflix, Inc.|Recommending media items based on take rate signals|

CN104035982B|2014-05-28|2017-10-20|小米科技有限责任公司|Multimedia resource recommends method and device|CN104035982B|2014-05-28|2017-10-20|小米科技有限责任公司|Multimedia resource recommends method and device|

US9621955B2|2014-12-31|2017-04-11|Google Inc.|Identifying media channels that have a high likelihood of multiple consumptions by one or more users|

US20160274744A1|2015-03-17|2016-09-22|Comcast Cable Communications, Llc|Real-Time Recommendations and Personalization|

US20160379255A1|2015-06-25|2016-12-29|Sony Corporation|System and method for multimedia promotion and content prioritization|

CN105245957A|2015-11-05|2016-01-13|京东方科技集团股份有限公司|Video recommendation method, device and system|

CN106909589A|2015-12-23|2017-06-30|北京奇虎科技有限公司|A kind of data recommendation method and device|

CN105574199B|2015-12-28|2020-04-21|合一网络技术有限公司|Method and device for identifying false search behavior of search engine|

US10664500B2|2015-12-29|2020-05-26|Futurewei Technologies, Inc.|System and method for user-behavior based content recommendations|

CN105719164A|2016-01-21|2016-06-29|海信集团有限公司|Paid multimedia resource recommending method and paid multimedia resource recommending device|

CN107133232A|2016-02-29|2017-09-05|惠州华阳通用电子有限公司|A kind of vehicle-mounted Online Music recommends method and device|

US9659068B1|2016-03-15|2017-05-23|Spotify Ab|Methods and systems for providing media recommendations based on implicit user behavior|

CN105843876B|2016-03-18|2020-07-14|阿里巴巴（中国）有限公司|Quality evaluation method and device for multimedia resources|

CN105975535A|2016-04-29|2016-09-28|合网络技术（北京）有限公司|Recommendation method and device for multimedia resource|

CN106060590B|2016-07-07|2020-01-31|青岛海信电器股份有限公司|Display method, device and system of recommendation information|

CN106294830A|2016-08-17|2017-01-04|合智能科技（深圳）有限公司|The recommendation method and device of multimedia resource|

CN106326391B|2016-08-17|2020-02-14|合一智能科技（深圳）有限公司|Multimedia resource recommendation method and device|

CN106339489A|2016-08-31|2017-01-18|南京炫佳网络科技有限公司|Evaluation algorithm for cartoon IP user preference degree|

CN107547922B|2016-10-28|2019-12-17|腾讯科技（深圳）有限公司|Information processing method, device, system and computer readable storage medium|

US10609453B2|2017-02-21|2020-03-31|The Directv Group, Inc.|Customized recommendations of multimedia content streams|

CN106951137A|2017-03-02|2017-07-14|合网络技术（北京）有限公司|The sorting technique and device of multimedia resource|

CN107592572B|2017-09-21|2021-05-14|广州方硅信息技术有限公司|Video recommendation method, device and equipment|

CN107786899A|2017-10-17|2018-03-09|北京小米移动软件有限公司|Program commending method and device|

CN109327739B|2018-11-27|2022-02-25|广州虎牙信息科技有限公司|Video processing method and device, computing equipment and storage medium|

CN113014938A|2021-02-24|2021-06-22|北京金和网络股份有限公司|Multi-dimensional live video recommendation method and device|

CN113918738A|2021-12-07|2022-01-11|北京达佳互联信息技术有限公司|Multimedia resource recommendation method and device, electronic equipment and storage medium|

法律状态:
2018-11-06| B06F| Objections, documents and/or translations needed after an examination request according [chapter 6.6 patent gazette]|

2020-04-22| B06U| Preliminary requirement: requests with searches performed by other patent offices: procedure suspended [chapter 6.21 patent gazette]|

2021-11-09| B09A| Decision: intention to grant [chapter 9.1 patent gazette]|

2022-01-18| B16A| Patent or certificate of addition of invention granted [chapter 16.1 patent gazette]|Free format text: PRAZO DE VALIDADE: 20 (VINTE) ANOS CONTADOS A PARTIR DE 23/10/2014, OBSERVADAS AS CONDICOES LEGAIS. |

优先权:

申请号 | 申请日 | 专利标题

CN201410230541.3A|CN104035982B|2014-05-28|2014-05-28|Multimedia resource recommends method and device|

CN201410230541.3|2014-05-28|

PCT/CN2014/089247|WO2015180385A1|2014-05-28|2014-10-23|Multimedia resource recommendation method and device|

[返回顶部]