• 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 and apparatus for recognizing target object on the machine side in human-machine interaction. The present invention relates to a method and a device for target object recognition on a machine side in human-machine interaction. wherein the method comprises: a graphical mark overlay module which overlays a graphical mark on a target object on a target image in accordance with an instruction sent by a user and which determines a display parameter for the graphical mark; tag information that adds the module that adds the tag information to the graphic tag; a storage control module that stores the graphic tag display parameter and the tag information thereof in a linked manner in a storage medium related to the target image; a first display module that displays the target image; a second display module which acquires the corresponding display parameter of the graphic tag and the tag information thereof from the storage medium related to the target image; which displays the graphical tag on the target object in the target image according to the display parameter of the graphical tag and which displays the tag information corresponding to the graphical tag at the same time. by means of the present invention, the user can conveniently recognize a target object of an engraving, thereby reducing resource occupancy on a machine side.
    公开号:BR112014001165B1
    申请号:R112014001165-6
    申请日:2012-06-07
    公开日:2021-08-10
    发明作者:Ying Wang；Shuang Qin；Chao Lin；Liucheng ZHANG；Hao Wu
    申请人:Tencent Technology (Shenzhen) Company Limited；
    IPC主号:
    专利说明:

    [0001] This application is a continuation of International Application No. PCT/CN2012/076596, filed on June 7, 2012, which claims priority over Chinese Patent Application No. 201110204966.3, entitled "method and apparatus for recognizing target object at machine side in human-machine interaction" and filed on July 21, 2011, the complete contents of which are incorporated herein by reference in their entirety for all purposes. FIELD OF TECHNIQUE
    [0002] The present invention relates to human-machine interaction technologies and, more particularly, to a method and apparatus to recognize a target object on a machine side in human-machine interaction. BACKGROUND
    [0003] Currently, in several internet services that provide human-machine interaction services, for example, virtual community services, a target object is always identified using pure characters on a machine side. The target object can be a certain person or a certain thing, and the certain person is taken as an example in the descriptions below. For example, a certain person can be identified by combining a specific symbol with a name or designation to quickly locate a page of person information or provide other human-machine interaction operations. However, the Internet provided on the machine side includes text and a lot of image data. A certain person or a certain thing is progressively represented using an image. The following problems are caused when the target object is still identified using pure characters.
    [0004] Characters to recognize the target object may not be associated with an image that includes the target object. For example, when the user wants to recognize a person from a machine-side image, the user needs to look up the text input page related to the image and then determine or assume who the person in the image is. On the other hand, the information provided by the machine side is monotonous and it is not convenient for the user to recognize a certain target object from the vast amounts of text data and image data on the machine side. In most cases, the user cannot recognize the target object from the images correctly, therefore, the user's human-machine interaction experiences are bad. On the other hand, the user has to perform more human-machine interaction operations to get more text information to recognize the target object of the images. Each human-machine interaction operation includes sending the request information, which triggers a computation process and which generates response information and thus a great deal of resources on the machine side, eg client resources, server resources and network bandwidth resources are occupied. Specifically, when an image includes multiple target objects, for example, the image includes multiple people, the person recognition procedure using pure characters is more complicated and more human-machine interaction operations are needed and more resources on the side. machine are busy. SUMMARY
    [0005] The examples of the present disclosure provide a method and apparatus for recognizing a target object on a machine side in human-machine interaction, so that it is convenient for a user to recognize a target object from an image and reduce the occupation of resources on the machine side.
    [0006] The technical solutions of the present disclosure are implemented as follows.
    [0007] A method for recognizing a target object on a machine side in human-machine interaction, applied to recognize a target object on a target image on a machine side includes: recognition processing and display processing; recognition processing comprises: superimposing a graphic label on a target object on a target image displayed in accordance with an instruction sent by a user, determining a graphic label display parameter; add identifying information to the graphic label; storing the graphic tag display parameter and the graphic tag identifying information in a storage medium related to the target image; the display processing comprises: obtaining the graphic tag display parameter and the graphic tag identifying information from the storage medium related to the target image; display the graphic label on the target object in the target image according to the graphic label display parameter; and display the graphic label identifying information. An apparatus for recognizing a target object on a machine side in human-machine interaction includes: a first display module, configured to display a target image. a graphical label overlay module configured to overlay a graphical label on a target object on the target image in accordance with an instruction sent by a user; and determining a graphic label display parameter; an identifying information adding module configured to add the identifying information to the graphic label; a storage control module configured to store the graphic label display parameter and graphic label identifying information in a storage medium related to the target image; and a second display module for obtaining, configured, the graphic tag display parameter and the graphic tag identifying information from the storage medium related to the target image; display the graphic label on the target object in the target image according to the graphic label display parameter; and display the graphic label identifying information.
    [0008] A non-transient computer readable storage medium stores the computer program to perform the above method.
    [0009] According to the solutions of the present disclosure, the target object is recognized using the graphic label on the target image displayed on the machine side and the identifying information is added, so that the identifying information of the target object is associated with the image that includes the target object, in order to make it convenient for the user to recognize the target object from the image, reduce the number of human-machine interaction operations, thus reducing the occupation of resources on the machine side, the which facilitates user operation. BRIEF DESCRIPTION OF THE DRAWINGS
    [00010] Figure 1 is a schematic flowchart illustrating a method according to several examples of the present invention.
    [00011] Figures 2a to 2k are schematic diagrams illustrating "one person circulation" interfaces according to various examples of the present invention.
    [00012] Figure 3 is a schematic diagram illustrating an apparatus according to several examples of the present invention.
    [00013] Figure 4 is a schematic diagram illustrating an apparatus according to several examples of the present invention. DETAILED DESCRIPTION
    [00014] The following description is merely illustrative in nature and is not intended in any way to limit the disclosure, its applications or its uses. The broad teachings of revelation can be implemented in a variety of ways. Therefore, while this disclosure includes specific examples, the true scope of the disclosure should not be limited to that much as other modifications will become apparent upon study of the drawings, descriptive report, and embodiments below.
    [00015] Figure 1 is a schematic flowchart illustrating a method according to several examples of the present invention. As shown in Figure 1, in the method, a target object is recognized in a target image on a machine side and recognition processing and display processing are included.
    [00016] In which recognition processing is as follows.
    [00017] In 101, a graphic label is superimposed on a target object in a target image according to an instruction sent by a user. In the example, the graphic label can be any graphic, for example a rectangle or circle. A graphic label display parameter is determined. In the example, the display parameter can include a graphic label size and the graphic label location coordinates in the target image.
    [00018] At 102, identifying information is added to the graphic label. Identifying information can be generated according to an instruction sent by the user. The identifying information can be an identifier of the target object, for example a name or a code name, or the comment information that corresponds to the target object, in order to implement a local comment function.
    [00019] At 103, the graphic tag display parameter and the graphic tag identifying information are stored in a storage medium related to the target image.
    [00020] In which display processing is as follows.
    [00021] At 104, the target image is displayed.
    [00022] According to an example, processing on 104 can be performed before recognition processing.
    [00023] At 105, the graphic tag display parameter and the graphic tag identifying information are obtained from the storage medium related to the target image. The graphic tag is displayed on the target object in the target image according to the graphic tag display parameter and the graphic tag identifying information is also displayed.
    [00024] For the purpose of improved interactivity, in an example of the present disclosure, the following operations are included in display processing. A comment warning box is displayed, and comment information submitted by a user who has comment permission is received. Comment information is stored on the storage medium related to the target image and the comment information is displayed on a web page related to the target image. The web page related to the target image can be, for example, a home info center interface of a user who is allowed to interact with the recognized target object or a target image detail page. The user who has comment permission includes the user who sends the instruction in recognition processing at 101, for example, an owner of the target image, the target object recognized in the target image, a friend of the target object, and so on.
    [00025] For the purpose of implementing an imaging function based on the person information, in an example of the present disclosure, the method further includes the following processing. It is determined whether at least two target images that are overlaid with the graphic tags and the identifying information of the graphic tags are identical. If at least two target images that are superimposed with the graphic tags and the graphic tag identifying information are identical, for example, the same name of a person is added to two graphic tags superimposed on two target images respectively, all target images that corresponding to the same identifying information is stored or displayed as a category of target images and the identifying information is taken as identifying information of the category of target images. Therefore, it is convenient for the user to see target images that include the same target object.
    [00026] According to an example, the graphic tag is a geometric pattern and thus may coincide with another graphic tag. Therefore, when more than one target object (eg people) are included in an image, each target object can be recognized and identifying information can be added for each target object. When the target image includes more than one target object, processing is performed at 101, 102 and 103 for the more than one target object according to the user's instructions, respectively, and the graphic labels and identifying information of the more than a target object are displayed in the target image.
    [00027] Furthermore, for the purpose of leading the user to perform recognition processing using both the image and the text, upon receipt of the user's instruction, if there is a face target object that is recognized, and a label graphic is superimposed on the face target object if the face target object exists.
    [00028] In the following example, the method is implemented in a virtual Internet community on the machine side. In the example, a target image can be stored on any web page capable of displaying an image in the virtual Internet community on the machine side, for example, an album page, a "talk" page, a sharing page, the image content on a blog and so on. according to one example, the "conversation" page is a web page to describe a user's mood and may include text, images, video, and so on. The target object in the target image can be a person, for example, a friend or classmate of the current user, or a celebrity followed by the current user. The target object can be something, for example a certified space. The certified space can be a network space that provides more specific functions for famous brands, agencies, media and celebrities. In the example, the person in the target image is recognized and the operations of recognizing the person in the target image are called "a person circulation".
    [00029] Figures 2a to 2k are schematic diagrams illustrating "one person circulation" interfaces according to various examples of the present invention.
    [00030] Firstly, the "person circulation" operations include the processing of (11) to (14).
    [00031] In (11), as shown in Figure 2a, on an info center page or a virtual community album photo detail page, a "one person circle" button 201 is clicked by a user and an instruction is sent to the machine side so as to request an operator interface to perform "one person movement" operations for a person on a target image 200. According to an example, permission to perform the operations of "circulation of a person" can be configured in a specific permission configuration page. The user can configure whether to allow the "circle one person" operation to be performed for the album, if the "circle one person" operation requires a second confirmation, the people who will be shown the target image and so on.
    [00032] In (12), as shown in Figure 2b, when the target image is in a gray state, the user can drag the mouse on the target image or click a necessary location to be circled in the target image, so as to send a recognition instruction for the machine side to recognize a certain target object by overlaying a graphic label. As shown in Figure 2c, a graphic label 202 of a rectangular shape is superimposed on the target image 200 and a target object is recognized, i.e., the target object is a person in the middle of the image. Other graphic label formats 202 can be used, for example, a circular shape, an elliptical shape, and so on. The size and location of the graphic label 202 can be adjusted in accordance with the user's operating instructions. After the adjustment is completed and confirmed, the graphic label display parameter 202 can be determined. According to an example, the display parameter may include the size of the graphic label 202 and the coordinates of the graphic label 202 in the target image 202.
    [00033] In (13), as shown in Figure 2c, after the graphic label display parameter 202 is determined, the graphic label identifying information is added. For example, identifying information can be object-identifying information, for example, a person's name, which can be set using a friend picker. In Figure 2c, a friend selector 203 of the user that sends the acknowledgment instruction is shown. Friend picker 203 displays information for users who are allowed to interact with the user who sends the recognition instruction, for example, friends, classmate, followed celebrities, or certified space users. The friend selector 203 can display the identifying information of these users, for example, avatars, names, names of schools or companies, in order to facilitate the selection of a certain user. The identifying information of the selected user can be taken as the identifying information of the graphic label that corresponds to the target object.
    [00034] Additionally, according to an example, a driving function is implemented to add friends. When a name entry in the friend picker doesn't match any friend, classmate, or celebrity next, the user is prompted to enter a user account. After the user's account is verified by a system on the machine side, the user can perform the operations to add a friend.
    [00035] In (14), as shown in Figure 2d, after adding the identifying information 204, for example, the friend's name, the operations of "circle a person" are completed. The user can send a finishing instruction. On the machine side, the graphic label display parameter 202 and the identifying information 204 are stored in a storage medium related to the target image 200. The storage medium related to the target image 200 may be a storage medium for storing the image target, for example, a local storage server, or it can be a storage medium located on a network side. The storage medium located on the network side needs to be associated with the target image.
    [00036] In addition, there is a procedure for displaying the target image and a procedure for notifying "one person movement" operations is included. According to an example, at least one of the following processing of (21) and (22) can be included.
    [00037] In (21), dynamic information is generated in the name of the recognized target object to indicate recognition processing. Dynamic information is displayed on a web page of a user who has permission to interact with the target object, for example, friends, classmate, and followed users. For example, dynamic information can be displayed on an information center page. The user who has the permission to interact with the target object can see dynamic information corresponding to the identified target object.
    [00038] As shown in Figure 2e, the dynamic information includes the name of the user performing the "circling a person" operation 205, the target object name 206 and a target image thumbnail 207. After the thumbnail is clicked, a normal image is displayed, as shown in Figure 2f. According to an example, the target image 200 is displayed first. The graphic tag display parameter and the graphic tag identifying information are obtained from the storage medium related to the target image and the graphic tag 202 is displayed on the target object in the target image according to the graphic tag display parameter and graphic label identifying information 204 is also displayed. In one example, the identifying information 204 may be displayed next to the graphic label 202 in the target image, for example, the location of the identifying information 204, as shown in Figure 2d.
    [00039] In (22), a dynamic notification is sent to the recognized target object, for example, the circled person, and to an owner of the target image, for example, a photo owner. Dynamic notification is a notification directly sent to the receiver and is displayed in a page window regardless of whether the receiver wants to receive the notification, as shown in Figure 2g. Dynamic notification is used to indicate recognition processing. When a dynamic notification preview button 208 is clicked, a normal image is displayed, as shown in Figure 2f. According to the example, target image 200 is displayed first. The graphic tag display parameter and the graphic tag identifying information are obtained from the storage medium related to the target image and the graphic tag 202 is displayed on the target object in the target image according to the graphic tag display parameter and graphic label identifying information 204 is also displayed.
    [00040] Finally, interactive comment can be provided for the target object recognized in the target image.
    [00041] A comment warning box is displayed. Comment information submitted by a user who has comment permission is received. The user who has the comment permission can be the user who performs "circling a person" operations, for example, the owner of the photo, the target object, or the friend of the target object. Comment information is stored on the storage medium related to the target image and is displayed on a web page related to the target image. The web page related to the target image can be, for example, a user's home information center interface that is allowed to interact with the target person, or a target image detail page.
    [00042] According to another example, when a certain user submits the comment information, a message is triggered on the "talk" page and all items of the comment information are stored on the target image detail page.
    [00043] Furthermore, since the target image 200 includes more than one target object, ie three people, the user can perform the "one person circulation" operations described (11) to (14) repeatedly and two or three people can be recognized. In display processing, graphic tags that correspond to more than one target object and the identifying information for each of the graphic tags are displayed in the target image 200, as shown in Figure 2h.
    [00044] Additionally, when more than one friend of the user is recognized in the same photo, dynamic information is sent under the name of the last recognized user, as shown in Figure 2e, and object identifying information that corresponds to other recognized friends is displayed together, as shown in Figure 2i.
    [00045] In addition, each time the user recognizes the person, the system can store the target images that correspond to the same object identifying information together, that is, all among the photos in which the same user is recognized are displayed together, so that an imaging function based on person information is implemented and better scalability of community-based interaction is achieved.
    [00046] According to the examples, the operations of "circulation of one person" can be applied for many cases. In addition to the user's album and the user's friend's album, the user can also perform "circling a person" operations on the "chat" page, blog page, or shared image.
    [00047] According to an example, "one person circulation" operations can be applied to many objects. In addition to the user's friend and classmate, "one person circulation" operations can be performed for the celebrity followed by the user or the certified space. If the user does not have permission to recognize a person, the user can send a request to add the person as a friend.
    [00048] Also, according to an example, when the user uploads a photo or views a photo, if the user does not trigger the "circling a person" operation directly, if there is a target face object that can be determined by recognizing a person's face according to face recognition technologies. If the photo includes the face target object, a graphic label is superimposed on the face target object in the photo, so as to direct the user to perform the "one person circling" operations. Face recognition technology can be any conventional technologies.
    [00049] In the example above, the identifying information added to the graphic tag is the object identifying information, for example, the person's name.
    [00050] According to another example, the identifying information can be the comment information, as shown in Figure 2j. After the graphic tag 202 is superimposed on the target object, a comment input box 209 is directly displayed next to the graphic tag 202 and comment information can be entered. After the comment information is entered and a confirmation instruction is received, in the display procedure, the comment information 210 is taken as the identifying information and is displayed next to the graphic label 202, as shown in Figure 2k, or the information of comment 210 can be displayed as another location on the web page. According to the example, the function of providing the comment for part of the target image is implemented.
    [00051] After the user provides comments for a certain target image, a dynamic notification similar to the dynamic notification in (22) is sent to the owner of the target image. Dynamic notification is directly sent to the receiver in a one-to-one fashion. Dynamic notification is used to indicate the operations of the recognition process, that is, the common operations for part of the target image. Dynamic notification includes a thumbnail and comment information for part of the target image. After the thumbnail is clicked, a normal image is displayed.
    [00052] According to an example, an apparatus is provided to recognize a target object on a machine side in human-machine interaction. Figure 3 is a schematic diagram illustrating an apparatus in accordance with various examples of the present invention. As shown in Figure 3, the apparatus includes a graphic label overlay module 301, an identifier information add module 302, and a storage control module 303, a first display module 304 and a second display module 305.
    [00053] Graphic label overlay module 301 shall overlay a graphic label on a target object on a target image according to an instruction sent by a user and determine a graphic label display parameter.
    [00054] The identifier information addition module 302 shall add the identifier information to the graphic label.
    [00055] Storage control module 303 shall store the graphic tag display parameter and graphic tag identifying information in a storage medium related to the target image.
    [00056] The first display module 304 shall display the target image.
    [00057] The second display module 305 shall obtain the graphic label display parameter and graphic label identifying information from the storage medium related to the target image, display the graphic label on the target object in the target image in accordance with the graphic label display parameter and display the graphic label identifier information.
    [00058] Figure 4 is a schematic diagram illustrating an apparatus according to several examples of the present invention.
    [00059] In addition to the components in the example shown in Figure 3, the apparatus additionally includes a comment module 306. The comment module 306 should display a comment warning box, receive comment information submitted by a user who has permission to comment; store the comment information on the storage medium related to the target image; and display the comment information on a web page related to the target image.
    [00060] The apparatus may additionally include an image aggregation module 307. The image aggregation module 307 must determine if at least two target images that are overlaid with the graphic tags and the identifying information of the graphic tags are identical. If at least two target images that are overlaid with the graphic tags and the graphic tag identifying information is identical, the image aggregation module 307 must store or display the at least two target images as a category of target images and take the information identifiers as identifying information of the category of target images.
    [00061] The graphic tag overlay module 301 additionally includes a face recognition module 308. The face recognition module 308 must recognize if there is a target face object before the instruction sent by the user is received, which overlay a graphic tag on the face target object if the face target object exists.
    [00062] Each example of the present disclosure can be implemented by a data processing program executed by a data processing device, for example, a computer. The data processing program is included in the examples of the present disclosure. Generally speaking, the data processing program stored on the storage medium can directly read a program from the storage medium or can install or copy the program to a storage device of the data processing device (eg, a disk hard drive or a memory). Thus, the storage medium is included in the examples of the present disclosure. The storage medium can use any recording mode, eg a page storage medium (eg tape), magnetic storage media (eg floppy disks, hard disks, flash), optical storage medium (eg , CD-ROM) or magnetic-optical storage medium (eg MO).
    [00063] According to an example, a storage medium is also provided, which must store the data processing program to make a machine execute a method as described in this document.
    [00064] According to the solutions of the present disclosure, the target object is recognized using the graphic label on the target image displayed on the machine side and the identifying information is added, so that the identifying information of the target object is associated with the image that includes the target object, in order to make it convenient for the user to recognize the target object from the image, which reduces the number of human-machine interaction operations, thus reducing the occupation of resources on the machine side , which facilitates the user's operation.
    [00065] Furthermore, comments can be provided after the target object of the target image is recognized using the graphic tag. Input of comment information by the related user can be stored and displayed. Additionally, the identifying information added to the graphic tag can be comment information, so that multiple comments from multiple users for the target object are gathered. Therefore, the user can provide the comment information for part of the image and the interactivity is improved, the related information of the target object is enriched and the user can get more information of the target object from the same web page. Furthermore, all of the target images that correspond to the same identifying information are stored and displayed together, it is convenient for the user to see the target images that correspond to the same target object. According to the above solutions, the number of human-machine interaction operations to search for information related to the target object is reduced and the resource occupation on the machine side is reduced.
    [00066] Also, since the graphic tag can match other graphic tags, when the image includes more than one target object, each target object can be recognized and descriptions are added respectively, so that it is easy for the user recognize a certain target object from the image that includes more than one target object, thereby further facilitating the user's operation.
    [00067] When the solutions of the present disclosure are applied to Internet services that provide multiple human-machine services, for example, the virtual community service, the interactivity between people is improved, it is easy for the user to get more intuitive information , plain text interaction is replaced by parallel text-graphic interactions, less resources are occupied to exchange more information.
    [00068] The aforementioned are only preferred examples of the present invention and are not used to limit the scope of protection of the present invention. Any modification, equivalent replacement and improvement are within the scope of protection of the present invention.
    权利要求:
    Claims (15)
    [0001]
    1. Method for recognizing a target object on a machine side in human-machine interaction, applied to recognize a target object on a target image on a machine side, characterized by the fact that it comprises: recognition processing and display processing; wherein the recognition processing comprises: superimposing (101) a graphic tag on a target object on a target image in accordance with an operation performed by a user, determining a graphic tag display parameter; add (102) identifying information to the graphic tag, which comprises displaying a friend selector that displays identifying information of users having permission to interact with the user, and selecting identifying information of a user from the identifying information of users as the identifying information for the graphic label; and storing (103) the graphic tag display parameter and the graphic tag identifying information in a storage medium related to the target image; the display processing comprises: displaying (104) the target image; obtaining (105) the graphic tag display parameter and the graphic tag identifying information from the storage medium related to the target image; display (105) the graphic tag on the target object in the target image in accordance with the graphic tag display parameter; and display (105) the graphic tag identifying information.
    [0002]
    2. Method according to claim 1, characterized in that the display processing further comprises: displaying a comment warning box; receive comment information submitted by a user having comment permission; store the comment information on the storage medium related to the target image; and display the comment information on a web page related to the target image.
    [0003]
    3. Method according to claim 2, characterized in that the user having comment permission comprises: the user performing the operation in recognition processing, an owner of the target image, the target object in the target image, and a friend of the target object.
    [0004]
    4. Method according to claim 1, characterized in that it further comprises: determining if at least two target images are overlaid with graphic tags and the identifying information of the graphic tags are identical; if at least two target images are overlaid with the graphic tags and the identifying information for the graphic tags is identical, store or display the at least two target images as a category of target images, and take the identifying information as identifying information for the category of images targets.
    [0005]
    5. Method according to claim 1, characterized in that it further comprises: when the target image comprises at least two target objects, perform recognition processing for each of the at least two target objects according to operations performed by the user respectively; display graphical labels corresponding to the at least two target objects and identifying information from the graphical labels in the target image, in display processing.
    [0006]
    6. Method according to claim 1, characterized in that it further comprises: before the operation performed by the user is received in the recognition processing, recognizing if there is a face target object; superimpose a graphic label on the face target object, if the face target object exists.
    [0007]
    7. Method according to any one of claims 1 to 6, characterized in that the identifying information comprises object identifying information or comment information.
    [0008]
    8. Method according to claim 1, characterized in that the identifying information is the object identifying information; and wherein the method further comprises: after recognition processing and before display processing, generating dynamic information in the name of the target object to indicate recognition processing; dynamic information being displayed on a web page of a user having permission to interact with the target object; dynamic information comprising a thumbnail of the target image; where display processing is performed after the thumbnail is clicked.
    [0009]
    9. Method according to claim 1, characterized in that the identifying information is the object identifying information; and wherein the method further comprises: after recognition processing and before display processing, sending a dynamic notification to the target object and an owner of the target image to indicate recognition processing; where display processing is performed after the dynamic notification is viewed.
    [0010]
    10. Method according to claim 1, characterized in that the identifying information is the comment information; and wherein the method further comprises: after recognition processing and before display processing, sending a dynamic notification in the name of a trigger of recognition processing to an owner of the target image to indicate recognition processing; dynamic notification comprising a thumbnail of the target image and comment information; where display processing is performed after the thumbnail is clicked.
    [0011]
    11. Apparatus for recognizing a target object on a machine side in human-machine interaction, characterized in that it comprises: a graphic label overlay module (301), configured to overlay a graphic label on a target object on an image target according to an operation performed by a user; and determining a graphic label display parameter; an identifying information adding module (302) configured to add identifying information to the graphic label, comprising displaying a friend selector that displays identifying information of users having permission to interact with the user, and selecting identifying information of a user to from the identifying information of the users as the identifying information for the graphic label; a storage control module (303) configured to store the graphic tag display parameter and the graphic tag identifying information in a storage medium related to the target image; a first display module (304) for displaying the target image; and a second display module (305), configured to obtain the graphic tag display parameter and the graphic tag identifying information from the storage medium related to the target image; display the graphic label on the target object in the target image according to the graphic label display parameter; and display the graphic label identifying information.
    [0012]
    12. Apparatus according to claim 11, further comprising: a comment module (306) configured to display a comment warning box; receive comment information submitted by a user having comment permission; store the comment information on the storage medium related to the target image; and display the comment information on a web page related to the target image.
    [0013]
    13. Apparatus according to claim 11, further comprising: an image aggregation module (307) configured to determine whether at least two target images are overlaid with the graphic tags and tag identifying information graphics are identical; if at least two target images are overlaid with the graphic tags and the identifying information for the graphic tags is identical, store or display the at least two target images as a category of target images, and take the identifying information as identifying information for the category of images targets.
    [0014]
    14. Apparatus according to claim 11, characterized in that the graphic label overlay module further comprises: a facial recognition module (308), configured to recognize if there is a face target object before the instruction sent by the user is received, superimpose a graphic label on the face target object, if the face target object exists.
    [0015]
    15. Storage medium characterized in that it stores a method as defined in any one of claims 1 to 10.
    类似技术:
    公开号 | 公开日 | 专利标题
    BR112014001165B1|2021-08-10|METHOD AND APPARATUS TO RECOGNIZE TARGET OBJECT ON THE MACHINE SIDE IN HUMAN-MACHINE INTERACTION, AND STORAGE MEANS
    US10382404B2|2019-08-13|Secure cloud-based clipboard for touch devices
    US10484315B2|2019-11-19|Method, system and apparatus for adding network comment information
    JP6417408B2|2018-11-07|Joint system with spatial event map
    US10958694B2|2021-03-23|Sharing content between collocated mobile devices in an ad-hoc private social group
    US9134947B2|2015-09-15|Annotating digital files of a host computer using a peripheral device
    US9026935B1|2015-05-05|Application user interface with an interactive overlay
    CN107438840A|2017-12-05|Support the integrated working space of Shared Folders
    US20100332980A1|2010-12-30|Managing document interactions in collaborative document environments of virtual worlds
    US20140372911A1|2014-12-18|Interactive interface display control method, instant communication tool and computer storage medium
    KR20170098830A|2017-08-30|Persistent viewports
    US9026900B1|2015-05-05|Invisible overlay for dynamic annotation
    US9141709B1|2015-09-22|Relevant file identification using automated queries to disparate data storage locations
    TW201535257A|2015-09-16|Identifying relationships between message threads
    US20160342449A1|2016-11-24|Data exchange across multiple computing devices through a proactive intelligent clipboard
    US10901612B2|2021-01-26|Alternate video summarization
    TW201608393A|2016-03-01|Hierarchical privacy settings for comments and markups in a shared document
    US20080116255A1|2008-05-22|Seamless screen labeling for branding, access control and content management
    WO2019105191A1|2019-06-06|Multi-element interaction method, apparatus and device, and storage medium
    JP6056648B2|2017-01-11|Information processing apparatus and information processing program
    JP2020516983A|2020-06-11|Live ink for real-time collaboration
    JP2015095066A|2015-05-18|Information processing apparatus and information processing program
    KR20180003932A|2018-01-10|Posting method of contents and posting apparatus
    JP6156054B2|2017-07-05|Information processing apparatus and program
    JP2016167206A|2016-09-15|Access right estimation device and access right estimation program
    同族专利:
    公开号 | 公开日
    JP2014521175A|2014-08-25|
    JP5791799B2|2015-10-07|
    KR20140051334A|2014-04-30|
    CN102890604A|2013-01-23|
    KR101643678B1|2016-07-28|
    WO2013010411A1|2013-01-24|
    BR112014001165A2|2017-02-21|
    US20140132634A1|2014-05-15|
    CN102890604B|2015-12-16|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    US20020087546A1|2000-01-31|2002-07-04|Michael Slater|Apparatus, methods, and systems for digital photo management|
    AUPQ717700A0|2000-04-28|2000-05-18|Canon Kabushiki Kaisha|A method of annotating an image|
    US20020093678A1|2000-10-17|2002-07-18|Skidgel John M.|Managing and searching digital images|
    US6804684B2|2001-05-07|2004-10-12|Eastman Kodak Company|Method for associating semantic information with multiple images in an image database environment|
    JP4170318B2|2005-07-12|2008-10-22|シャープ株式会社|Image forming apparatus, control method, control program, and computer-readable recording medium|
    US20080034284A1|2006-07-28|2008-02-07|Blue Lava Technologies|Method and system for displaying multimedia content|
    US7945653B2|2006-10-11|2011-05-17|Facebook, Inc.|Tagging digital media|
    JP5121285B2|2007-04-04|2013-01-16|キヤノン株式会社|Subject metadata management system|
    US8189880B2|2007-05-29|2012-05-29|Microsoft Corporation|Interactive photo annotation based on face clustering|
    JP2008305104A|2007-06-06|2008-12-18|Dowango:Kk|Comment distribution system, server, terminal equipment, comment distribution method, comment display method and program|
    JP4453721B2|2007-06-13|2010-04-21|ソニー株式会社|Image photographing apparatus, image photographing method, and computer program|
    US8867779B2|2008-08-28|2014-10-21|Microsoft Corporation|Image tagging user interface|
    JP2010086221A|2008-09-30|2010-04-15|Fujifilm Corp|Image editing method and device, and computer readable recording medium storing program for implementing the method|
    JP2011133638A|2009-12-24|2011-07-07|Toshiba Corp|Device, system and method for displaying image|
    WO2011147089A1|2010-05-27|2011-12-01|Nokia Corporation|Method and apparatus for expanded content tag sharing|
    US20110292230A1|2010-05-28|2011-12-01|Winters Dustin L|Method for managing privacy of digital images|
    US8824748B2|2010-09-24|2014-09-02|Facebook, Inc.|Auto tagging in geo-social networking system|KR20150011651A|2013-07-23|2015-02-02|주식회사 케이티|Apparatus and method for creating story telling contents|
    CN104461477A|2013-09-13|2015-03-25|腾讯科技（北京）有限公司|Method, system and corresponding device for adding network comment information|
    CN104598468A|2013-10-30|2015-05-06|腾讯科技（深圳）有限公司|Web image display method and device|
    CN104731829B|2013-12-24|2019-06-21|腾讯科技（深圳）有限公司|A kind of interactive approach and device of network picture|
    CN105302428B|2014-07-29|2020-07-28|腾讯科技（深圳）有限公司|Dynamic information display method and device based on social network|
    CN104901994B|2014-10-22|2018-05-25|腾讯科技（深圳）有限公司|Attribute value transfer method, the apparatus and system of user in network system|
    WO2016134516A1|2015-02-26|2016-09-01|刘一佳|Method for photograph management and display and mobile terminal|
    WO2016134507A1|2015-02-26|2016-09-01|刘一佳|Method for feature reminder when displaying photograph in moments and photograph displaying device|
    CN104796487B|2015-04-30|2019-02-22|广州华多网络科技有限公司|A kind of social interaction method and relevant device|
    CN104952095A|2015-07-16|2015-09-30|成都九米乐科技有限公司|Method and device for marking picture comments|
    CN105187715A|2015-08-03|2015-12-23|杨珊珊|Method and device for sharing aerial photography content, and unmanned aerial vehicle|
    CN105120355A|2015-08-24|2015-12-02|天脉聚源（北京）科技有限公司|Television interactive system interactive information detection method|
    CN105120356A|2015-08-24|2015-12-02|天脉聚源（北京）科技有限公司|Interactive information push method used for television interactive system|
    CN105117108B|2015-09-11|2020-07-10|百度在线网络技术（北京）有限公司|Information processing method, device and system|
    CN105654533A|2015-12-28|2016-06-08|小米科技有限责任公司|Picture editing method and picture editing device|
    EP3407246A4|2017-03-27|2018-11-28|Shenzhen Goodix Technology Co., Ltd.|Method and electronic device for prompting for fingerprint operation|
    CN107562838A|2017-08-24|2018-01-09|百度在线网络技术（北京）有限公司|A kind of method and apparatus for image information collecting|
    CN108520013B|2018-03-21|2021-10-22|Oppo广东移动通信有限公司|Atlas display method and device, mobile terminal and storage medium|
    CN108984242A|2018-06-06|2018-12-11|珠海格力电器股份有限公司|A kind of virtual note display methods, device, storage medium and mobile terminal|
    CN109522925B|2018-09-30|2021-08-06|咪咕文化科技有限公司|Image recognition method, device and storage medium|
    CN110096665B|2019-04-28|2022-03-04|北京字节跳动网络技术有限公司|Method, device, equipment and medium for displaying picture comment data|
    CN111078082A|2019-06-09|2020-04-28|广东小天才科技有限公司|Point reading method based on image recognition and electronic equipment|
    法律状态:
    2018-12-11| B06F| Objections, documents and/or translations needed after an examination request according [chapter 6.6 patent gazette]|
    2019-11-05| B06U| Preliminary requirement: requests with searches performed by other patent offices: procedure suspended [chapter 6.21 patent gazette]|
    2021-04-06| B06A| Patent application procedure suspended [chapter 6.1 patent gazette]|
    2021-06-22| B09A| Decision: intention to grant [chapter 9.1 patent gazette]|
    2021-08-10| 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 07/06/2012, OBSERVADAS AS CONDICOES LEGAIS. |
    优先权:
    申请号 | 申请日 | 专利标题
    CN201110204966.3|2011-07-21|
    CN201110204966.3A|CN102890604B|2011-07-21|2011-07-21|At the method for machine side mark destination object and device in man-machine interaction|
    PCT/CN2012/076596|WO2013010411A1|2011-07-21|2012-06-07|Method and device of target object recognition on machine side in human-machine interaction|
    [返回顶部]