CN106777030B - Information pushing method and device - Google Patents
Information pushing method and device Download PDFInfo
- Publication number
- CN106777030B CN106777030B CN201611124599.5A CN201611124599A CN106777030B CN 106777030 B CN106777030 B CN 106777030B CN 201611124599 A CN201611124599 A CN 201611124599A CN 106777030 B CN106777030 B CN 106777030B
- Authority
- CN
- China
- Prior art keywords
- image
- target
- person
- target image
- subject
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000004891 communication Methods 0.000 claims abstract description 71
- 238000004364 calculation method Methods 0.000 claims description 14
- 230000006855 networking Effects 0.000 claims description 13
- 238000000926 separation method Methods 0.000 claims description 9
- 230000001815 facial effect Effects 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001936 parietal effect Effects 0.000 description 2
- 241001424438 Surendra Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/30—Scenes; Scene-specific elements in albums, collections or shared content, e.g. social network photos or video
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The disclosure relates to an information pushing method and an information pushing device, wherein the information recommending method comprises the following steps: acquiring a first target image, wherein the first target image comprises an image of a first shot person; determining a second photographer other than the first photographer by performing image recognition on the first target image; acquiring target communication information corresponding to the second shot person; and recommending the second shot person to the first shot person according to the target communication information. According to the information pushing method and device, information is pushed and pushed through image recognition, so that the accuracy and pertinence of information pushing can be improved; more social possibilities are provided for the publisher, and the user experience is improved.
Description
Technical Field
The present disclosure relates to the field of communications technologies, and in particular, to an information pushing method and apparatus.
Background
With the increasing popularization of intelligent communication terminals such as mobile phones, tablet computers and personal computers, more and more people communicate and exchange through social network applications. Meanwhile, as the number of users of social networking applications continues to grow, it becomes increasingly difficult for users to find suitable friends in social networks.
In the related art, a social network site or a system pushes friends to a user according to information such as registration information, a group to which the user belongs, a position where the user is located and the like of the user. For example, a alumni belonging to an education institution is pushed to the user, or a friend is matched and pushed according to a friend query condition selected by the user.
Disclosure of Invention
In order to overcome the problems in the related art, the present disclosure provides an information pushing method and apparatus.
According to a first aspect of the embodiments of the present disclosure, there is provided an information pushing method, including:
acquiring a first target image, wherein the first target image comprises an image of a first shot person;
determining a second photographer other than the first photographer by performing image recognition on the first target image;
acquiring target communication information corresponding to the second shot person;
and recommending the second shot person to the first shot person according to the target communication information.
Optionally, the determining a second subject other than the first subject by performing image recognition on the first target image includes:
acquiring a first person feature of the first shot person;
acquiring a second person characteristic of the second photographed person;
determining candidate human features with the similarity higher than a preset similarity with the first human feature in the second human features;
determining the shot person corresponding to the candidate character feature as the second shot person;
wherein the proportion of the second shot person to the first target image is smaller than the proportion of the first shot person to the first target image.
Optionally, the first or second human characteristic is indicative of at least one of: age, sex, interests.
Optionally, the acquiring target communication information corresponding to the second subject includes:
acquiring a third person characteristic of the second person;
acquiring a communication database, wherein the communication database comprises a corresponding relation between character characteristics and communication information;
acquiring target communication information corresponding to the third person characteristic information according to the communication database;
wherein the third personality characteristic is indicative of at least one of: facial features, appearance features.
Optionally, the method further comprises:
acquiring a second target image including the second shot person according to a fourth person feature of the second shot person;
calculating the image similarity of the first target image and the second target image;
and carrying out information pushing on the first shot person and the second shot person according to the image similarity, wherein the first shot person is a publisher of the first target image, and the second shot person is a publisher of the second target image.
Optionally, the step of calculating the image similarity of the first target image and the second target image includes:
respectively carrying out background separation on the first target image and the second target image to obtain a first background area and a second background area;
when the image similarity of the first background area and the second background area meets a preset condition, acquiring a first target area in the first target image and a second target area in the second target image, wherein the first target area and the second target area both comprise a first photographer and a second photographer;
and determining the image similarity of the first target image and the second target image according to the image similarity of the first target area and the second target area.
Optionally, the recommending the second photographer to the first photographer according to the target communication information includes:
and sending a friend adding request to a terminal corresponding to the second photographed person according to the target communication information.
In a second aspect, an information pushing apparatus is provided, including:
a target image acquisition module configured to acquire a first target image including an image of a first subject;
a subject determination module configured to determine a second subject other than the first subject by performing image recognition on the first target image;
a communication information acquisition module configured to acquire target communication information corresponding to the second subject;
a recommending module configured to recommend the second subject to the first subject according to the target communication information.
Optionally, the subject determination module includes:
a first obtaining sub-module configured to obtain a first human feature of the first subject;
a second acquisition sub-module configured to acquire a second person feature of the second subject;
a similarity determination submodule configured to determine candidate character features having a similarity higher than a predetermined similarity with the first character feature among the second character features;
a determination sub-module configured to determine a subject corresponding to the candidate character feature as the second subject;
wherein the proportion of the second shot person to the first target image is smaller than the proportion of the first shot person to the first target image.
Optionally, the communication information obtaining module includes:
a third acquisition sub-module configured to acquire a third person feature of the second subject;
a communication database acquisition sub-module configured to acquire a communication database including a correspondence between character features and communication information;
a target communication information obtaining sub-module configured to obtain target communication information corresponding to the third person feature information according to the communication database;
wherein the third personality characteristic is indicative of at least one of: facial features, appearance features.
Optionally, the apparatus further comprises:
a second target image acquisition module configured to acquire a second target image including the second subject according to a fourth human feature of the second subject;
an image similarity obtaining module configured to perform image similarity calculation on the first target image and the second target image;
and the information pushing module is configured to push information to the first shot person and the second shot person according to image similarity, wherein the first shot person is a publisher of the first target image, and the second shot person is a publisher of the second target image.
Optionally, the image similarity obtaining module includes:
a background separation sub-module configured to perform background separation on the first target image and the second target image respectively to obtain a first background area and a second background area;
a target area obtaining sub-module configured to obtain a first target area in the first target image and a second target area in the second target image when image similarity of the first background area and the second background area satisfies a preset condition, wherein the first target area and the second target area both include the first photographer and the second photographer;
an image similarity determination submodule configured to determine an image similarity of the first target image and the second target image according to the image similarity of the first target region and the second target region.
In a third aspect, an information pushing apparatus is provided, including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to:
acquiring a first target image, wherein the first target image comprises an image of a first shot person; determining a second photographer other than the first photographer by performing image recognition on the first target image; acquiring target communication information corresponding to the second shot person; recommending the second shot person to the first shot person according to the target communication information;
the determining a second subject other than the first subject by performing image recognition on the first target image includes:
acquiring a first person feature of the first shot person;
acquiring a second person characteristic of the second photographed person;
determining candidate human features with the similarity higher than a preset similarity with the first human feature in the second human features;
determining the shot person corresponding to the candidate character feature as the second shot person;
wherein the proportion of the second shot person to the first target image is smaller than the proportion of the first shot person to the first target image.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects: information pushing is carried out through image recognition, so that the accuracy and pertinence of information pushing can be improved; more social possibilities are provided for the publisher, user experience is improved, and the life of the publisher is enriched; the information of strangers appearing in the own image can be acquired, and more social opportunities are provided.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
FIG. 1 is an architectural diagram illustrating a social network, according to an example embodiment.
Fig. 2 is a flowchart illustrating an information pushing method according to an exemplary embodiment.
Fig. 3 is a flowchart illustrating a process of determining a second subject other than a first subject according to an exemplary embodiment.
Fig. 4 is a flowchart illustrating an information push method according to another exemplary embodiment.
Fig. 5 is a flowchart illustrating an information push method according to yet another exemplary embodiment.
Fig. 6 is a flowchart illustrating image similarity calculation for a first target image and a second target image according to an exemplary embodiment.
FIG. 7a is a schematic illustration of a first image published by a first publisher in an exemplary embodiment.
FIG. 7b is a diagram of a second image published by a second publisher of an exemplary embodiment.
FIG. 8 is a diagram of a second image published by a second publisher of another exemplary embodiment.
Fig. 9 is a flowchart illustrating an information push method according to another exemplary embodiment.
Fig. 10 a-10 d are schematic diagrams illustrating the information pushing effect according to an exemplary embodiment.
Fig. 11 is a block diagram illustrating an information pushing apparatus according to an example embodiment.
Fig. 12 is a block diagram illustrating an apparatus for an information push method according to an example embodiment.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
Referring to FIG. 1, an architectural diagram of a social network is shown, according to an example embodiment. The social network 100 includes: one or more user devices 110, a social networking system 120, and a network 130.
User device 110 may receive input from a publisher and may send and receive data via network 130. The user device 110 may be a smartphone, tablet, personal digital assistant, mobile phone, or like device. In some embodiments, user device 110 may execute a browser application or the like that interacts with social-networking system 120. In other embodiments, the user device 110 may interact with the social-networking system 120 through an Application (APP) running on a local operating system (e.g., an android operating system or ios operating system, etc.). The user device 110 may communicate with the social-networking system 120 via the network 130 using wired and/or wireless communication.
Network 130 may include any combination of local area networks and/or wide area networks. In one embodiment, network 130 may include links using technologies such as Ethernet, 802.11, 3G, 4G, 5G, GSM, Digital Subscriber Line (DSL), Worldwide Interoperability for Microwave Access (WiMAX), and the like.
Social-networking system 120 includes one or more computing devices (e.g., servers) of a social network that store a plurality of users and enable users in the social network to communicate and interact with other users in the social network.
Through the communicative interaction of the user device 110 with the social networking system 120, a publisher may publish user information, images (e.g., photos or any type of drawings), personalized content, and the like to the social networking system 120, and other users may browse the published content by accessing the social networking system 120.
The image identification is carried out by utilizing the image published to the social network system 120 by the publisher, so that the information push is carried out, and the accuracy and pertinence of the information push can be improved.
Referring to fig. 2, a flowchart of an information pushing method according to an exemplary embodiment is shown.
The pushing method comprises the following steps:
in step 201, a first target image is acquired, the first target image including an image of a first subject.
In an embodiment of the present disclosure, the first target image may be an image published to the social network by a publisher, or may be an image captured by an image capturing device (e.g., a camera). The first target image comprises a first shot person.
In step 202, a second subject other than the first subject is determined by performing image recognition on the first target image.
Referring to fig. 3, in an embodiment of the present disclosure, the second subject other than the first subject may be determined by:
in step 301, a first person feature of a first subject is acquired.
In step 302, a second person feature of a second subject is acquired.
In one embodiment, the face recognition may be performed on the recognized first and second subjects to obtain information of the first and second subjects. Thus, the first person characteristic of the first photographed person and the second person characteristic of the second photographed person can be acquired in the registration information database of the social networking system.
In one embodiment, the first or second human characteristic is indicative of at least one of: age, sex, interests.
In step 303, candidate human features having a similarity higher than a predetermined similarity with the first human feature are determined among the second human features.
In step 304, the subject corresponding to the candidate character feature is determined as the second subject.
In the embodiment of the disclosure, in order to improve the pertinence of information recommendation, candidate person features having a similarity higher than a predetermined similarity with the first person feature are determined among the second person features, and the second photographer is determined according to the similarity.
In step 203, target communication information corresponding to the second subject is acquired.
In an embodiment of the present disclosure, the target communication information of the second subject is acquired by: acquiring a third person characteristic of a second photographed person; acquiring a communication database, wherein the communication database comprises a corresponding relation between character characteristics and communication information; acquiring target communication information corresponding to the third person characteristic information according to the communication database; wherein the third personality characteristic is indicative of at least one of: facial features, appearance features.
The target communication information may be account information, contact information, and the like. The target communication information may be obtained from the social networking system based on a third person characteristic of the second subject.
In step 204, the second subject is recommended to the first subject based on the target communication information.
After the target communication information of the second subject is acquired, the second subject may be recommended to the first subject. In one embodiment, a friend adding request is sent to a terminal corresponding to the second photographed person according to the target communication information. Therefore, the information pushing method implemented by the disclosure can improve the accuracy and pertinence of information pushing according to the information pushing of the shot person in image recognition; more social possibilities are provided for the user, and the user experience is improved.
Referring to fig. 4, a flowchart of an information pushing method according to another exemplary embodiment is shown.
The pushing method comprises the following steps:
in step 401, images published by one or more publishers are obtained.
In an embodiment of the present disclosure, the publisher publishes to the social networking system 120, and is to be stored in a storage area of the social networking system 120, and pushed to a subscribing user or pushed to a preset website, etc.
The image published by the publisher may be an image captured by a capturing device (e.g., a mobile terminal, a camera, etc.), or may be an image downloaded from a network server or acquired by other user devices through wireless/wired transmission.
In some embodiments of the present disclosure, the image may be a video image, a picture, or the like.
In an embodiment of the present disclosure, the image may be acquired according to the time of image release. For example, images are acquired for a preset time period (for example, a time period of 07:00 to 21: 00). In still other embodiments, a target demographic, a target location, keywords, etc. may also be set such that images posted by the target demographic (e.g., VIP registered members of a social application), images posted at the target location (e.g., attraction a), images associated with the set keywords (e.g., M's concert), etc. may be obtained.
It should be understood that in the embodiment of the present disclosure, when a user publishes an image, text information is usually added for description, and thus, set keyword information may be acquired from the text information to acquire an image associated with the set keyword. For example, all images of "concert of M" included in the text information are acquired.
In step 402, image similarity calculation is performed based on the acquired images.
In the embodiment of the present disclosure, the image similarity mainly calculates the similarity of the acquired image contents to obtain an image similarity value, and the higher the image similarity value is, the more similar the contents of the two pictures are. The image similarity may be calculated by using visual features of the two pictures, the visual features may specifically be color RGB (Red Green Blue, three primary colors) features, texture features, histogram features, SIFT (Scale-invariant feature transform) features, and the like, and since calculating the image similarity between the pictures by using the visual features belongs to the prior art known to those skilled in the art, the description thereof is omitted here.
In the embodiment of the present disclosure, the calculation of the image similarity may be performed in the following two ways:
the first method is as follows: compare one by one
And selecting a target image, comparing the acquired images with the target image in sequence, and acquiring the image similarity of each image and the target image.
The second method comprises the following steps: overall contrast
And carrying out image similarity calculation on the whole acquired image to obtain the similarity of all the images.
In step 403, information is pushed to one or more publishers according to the image similarity.
The image similarity can reflect the common interests, social circles and other conditions of the users, and therefore in the embodiment of the disclosure, more accurate information pushing can be provided for the users by obtaining the image similarity and pushing the information.
In an embodiment of the present disclosure, the information pushing includes at least one of the following: friend information pushing, character information pushing and preset related information pushing.
When the image similarity calculation is performed by adopting the first method, the obtained image similarities can be sorted, and the information of the publisher corresponding to the image with the image similarity within the preset range is pushed to the publisher corresponding to the target image as the friend information. In one embodiment, the person information included in the image with the image similarity within the preset range can be acquired and pushed to the corresponding publisher of the target image.
When the image similarity calculation is performed in the second manner, when the image similarity values of all the images satisfy the preset threshold, the information of the other publishers except the publisher themselves may be pushed to the publisher themselves as friend information. For example, if the similarity of the image published by the publisher a, the image published by the publisher B, the image published by the publisher C and the image published by the publisher D meets a preset threshold, pushing the information of the publisher B, the information of the publisher C and the information of the publisher D to the publisher a as friend information; pushing the information of the publisher A, the information of the publisher C and the information of the publisher D serving as friend information to the publisher B; pushing the information of the publisher A, the information of the publisher B and the information of the publisher D serving as friend information to the publisher C; and pushing the information of the publisher A, the information of the publisher B and the information of the publisher C to the publisher D as friend information.
In one embodiment, the information of the publisher may include at least one of the following information: account information, gender, age, contact details, etc. The social networking system 120 stores the information provided by each publisher when registering and filling in the related information.
In one embodiment, the persona information may include at least one of the following: account information, gender, age, contact information. In an embodiment of the present disclosure, in order to improve security, the persons included in the image are obtained through a reasonable approach, for example, information provided by a user corresponding to the related person through registration, filling in a related form, and the like.
In one embodiment, the predetermined related information may be news information, merchandise information, or event information. When the related information is pushed for the publisher, the publisher can be used as a target publisher, the feature information in the image published by the target publisher is identified, and information matching is carried out according to the feature information to obtain preset related information. And pushing the matched preset related information for the publisher with high similarity of the published image. Therefore, the same preset related information can be pushed for the publishers with high image similarity, and the information pushing efficiency is improved.
Therefore, the information pushing method can push the information according to the image similarity published by the publisher, and can improve the accuracy and pertinence of the pushed information; more social possibilities are provided for the publisher, user experience is improved, and the life of the publisher is enriched.
Referring to fig. 5, a flowchart illustrating an information push method according to yet another exemplary embodiment is shown. This embodiment is based on the embodiment shown in fig. 2 and 4, and acquires the second target image including the second subject according to the fourth person feature of the second subject, and when the second subject is a publisher of the second target image (i.e., the second publisher) and the first subject is a publisher of the first target image (i.e., the first publisher), the push method of this embodiment includes the following steps:
in step 501, image similarity calculation is performed for the first target image and the second target image.
Referring to fig. 6, in an embodiment of the present disclosure, performing image similarity calculation on a first target image and a second target image includes the following steps:
in step 601, background separation is performed on the first target image and the second target image respectively to obtain a first background area and a second background area.
In embodiments of the present disclosure, the image may be a video image or a picture. For video images, a background can be extracted by using a Surendra algorithm to obtain a background area. For the picture, the background region can be obtained by image segmentation, edge extraction and the like.
By acquiring the image similarity of the background area of the image, the condition of the background area of the image can be acquired. In practice, images obtained as a background at the same position (e.g., the same sight spot a), the same seat/scene (e.g., a evening, a concert, a party, etc.), and the like have a high degree of image similarity in the background area.
In step 602, when the image similarity of the first background area and the second background area satisfies a preset condition, the image similarity of the first target area of the first target image and the second target area of the second target image is obtained.
In an embodiment of the present disclosure, the preset condition may be set as: the image similarity is greater than 50%. Referring to fig. 7a and 7b, in one embodiment, fig. 7a is a first target image published by a first publisher, and fig. 7b is a second target image published by a second publisher. The image similarity of the background areas of the two images meets the preset condition.
In the embodiment of the present disclosure, when the image similarity of the first background area and the second background area satisfies the preset condition, it is described that the first target image and the second target image have similar backgrounds, and thus it can be further inferred that the first publisher and the second publisher are interested in the same scene, or have performed activities, photographs, and the like in the same scene.
The first target region may be a foreground region or a person region of the first target image. The same second target area may be a foreground area or a person area of the second target image. The foreground region may be obtained by subtracting the background region. The human figure region can be obtained through feature extraction, edge detection and the like.
In step 502, information is pushed to the first subject and the second subject according to the image similarity.
In one embodiment of the present disclosure, the first target area is an area including at least a first person and a second person. The second target area is an area including at least a third person and a fourth person. When the image similarity calculation of the first target area and the second target area is performed, the first person, the second person, the third person and the fourth person are compared respectively.
In an embodiment of the present disclosure, character features of a first character, a second character, a third character, and a fourth character are extracted. The character features include at least one of: hair style, clothing, and facial features. In the comparison, the character characteristics of the first person can be compared with the character characteristics of the third person and the character characteristics of the fourth person respectively to judge the similarity between the first person and the third person or the similarity between the first person and the fourth person. And comparing the character characteristics of the second person with the character characteristics of the third person and the character characteristics of the fourth person respectively to judge the similarity of the second person with the third person or the fourth person.
Referring to fig. 7a and 7b, in one embodiment, fig. 7a illustrates a first image published by a first publisher; fig. 7b is a second image published by a second publisher. Wherein A is a first person in the first image, B is a second person in the first image, A 'is a third person in the second image, and B' is a fourth person in the second image. By comparing the character characteristics of the first character, the second character, the third character and the fourth character, the similarity between the first character A and the third character A 'and the similarity between the second character B and the fourth character B' can be obtained.
Thus, by comparing the persons in the first target image and the second target image, the similarity of the persons in the first target image and the second target image can be obtained. When the similarity of the first target image and the second target image meets a preset condition, information can be pushed.
In an embodiment of the present disclosure, the pushing of the information includes at least one of: friend information pushing, character information pushing and preset related information pushing.
In one embodiment, the relationship between the person (i.e., subject) and the publisher in the image published by the publisher may be confirmed by:
when a publisher registers with social-networking system 120, a picture of the publisher's actual person is provided. Thus, it is possible to determine whether the person in the image to be distributed is the same person as the publisher by performing person feature extraction and comparison of the person in the image to be distributed with the personal picture of the publisher provided at the time of registration.
In one embodiment, when the image similarity between the first target area of the first target image and the second target area of the second image satisfies a preset condition, and the first publisher of the first target image is the first person or the third person (the photographed person), and the second publisher of the second image is the second person or the fourth person (the photographed person), the information pushed to the first publisher (i.e., the first photographed person) includes information of the second publisher (i.e., the second photographed person), and the information pushed to the second publisher includes information of the first publisher. Thus, because the first publisher and the second publisher appear in the same scene, indicating that both may have a common interest (e.g., like the same attraction A, like the same type of evening party, etc.) or may have a common acquaintance (e.g., attending the same party), the first publisher is pushed information of the second publisher and the second publisher is pushed information of the first publisher. Therefore, the pertinence and the accuracy of the push information can be improved, the publishers can acquire more interesting push information, and the possibility of further familiarity, understanding and interaction between the two publishers can be greatly improved.
The information of the first publisher and the information of the second publisher may be obtained from registration information or from history information (e.g., authentication information input by the publisher, etc.).
In other embodiments, the first target area or the second target area may include only one person. Referring to fig. 7a and 8, only the person B' is included in the second target region in the second target image. Then, when performing the image similarity calculation between the first target region and the second target region, only the person in the second target region may be compared with the person in the first target region. Therefore, as long as the similarity between the person in the second target area and any person in the first target area meets the preset requirement, information push can be carried out.
In one embodiment, the information pushing method of this embodiment further includes: when information is pushed to the first publisher and the second publisher, the pushing reason is pushed at the same time.
The push reasons may include: related images and/or related text descriptions. Referring to fig. 7a and 7b, in one embodiment, when pushing information of a second publisher to a first publisher, a second target image shown in fig. 7b may be pushed to the first publisher at the same time as a push reason. And the word descriptions such as 'you have taken a picture in the same place and appeared in the lens of the other party' can be pushed as the push reason at the same time.
Referring to fig. 9, on the basis of the push method shown in fig. 6, the information push method according to still another embodiment of the present disclosure further includes:
in step 901, the ratio of the first person to the first area of the first target image is detected.
In one embodiment, the person areas of the first person and the second person may be obtained by an edge detection algorithm, and compared with the total area of the first target image to obtain the ratio of the first image to the second image.
In step 902, the ratio of the third person to the second area of the second target image is detected.
In the same manner as the step 901, the proportions of the third person and the fourth person in the second target image can be obtained respectively.
In step 903, push information is determined according to the ratio of the first area and the ratio of the second area.
In a scenario where the second person is only a background person in the first target image, that is, the first person is a leading role, the second person appears in the first target image because the second person is shoplifted in an image captured by another person due to accident or due to various reasons (for example, a situation where people are many, the person just passes by, etc.), in which case, the proportion occupied by the second person will be smaller than the proportion occupied by the first person. In the second target image, the third person similar to the first person is used as the background person, and the fourth person similar to the second person is used as the hero, and at this time, the proportion of the third person is smaller than that of the fourth person. Thus, the information of the first person can be pushed to the second publisher and the information of the second person can be pushed to the first publisher, so that the first publisher and the second publisher can obtain the information of the person who appears "accidentally" in the image.
In an embodiment of the present disclosure, in order to improve security, the information of the first person and the second person is obtained through a reasonable approach, for example, the user corresponding to the first person (or the second person) is provided by registering, filling in a relevant form, and the like.
By distinguishing the area ratio of the first person, the second person, the third person and the fourth person, the nature of the persons can be determined, information of strangers appearing in own images can be acquired, more social opportunities are provided, and the method and the device can be used for appointment push and the like.
Fig. 10a to 10d are schematic diagrams illustrating the information pushing effect according to an exemplary embodiment. FIG. 10a is an image P1 of publisher a publishing to a social application through a user device, and FIG. 10b is an image P2 of publisher b publishing a social application through a user device. The image P1 is a person who is captured by the publisher a at the sight point J, a in the image P1 is the publisher a, and B in the image P1 is a person who is not acquainted with the publisher a when the image P1 is captured by the publisher a. This image P1 was posted to the social application by the poster a, in image P1 the poster a is the lead/focus and b, which was "carelessly" captured in image P1, is the parietal/background.
In the image P2 distributed by the publisher b, the publisher b is the chief actor/focus, and a is the parietal/background which is "carelessly" captured in the image P2.
Since the publisher a and the publisher b appear in the same scene at almost the same time, indicating that both people may have a common taste (e.g., like a tour), referring to fig. 10c and 10d, it is possible to push the information of the publisher b to the publisher a and the information of the publisher a to the publisher a based on the acquisition of the image similarity of the image P1 and the image P2. Thus, a "sentimental" feeling is created for publishers a and b, increasing the likelihood of adding friends and further becoming familiar, knowledgeable, or affiliated.
Referring to fig. 10c and 10d, when information is pushed, similar photos of the other party are displayed to the publisher as a pushing reason, so that the social possibility is further increased.
Fig. 11 is a block diagram illustrating an information pushing apparatus according to an example embodiment. Referring to fig. 11, the apparatus 1100 includes:
a target image acquisition module 1101 configured to acquire a first target image including an image of a first subject;
a subject determination module 1102 configured to determine a second subject other than the first subject by performing image recognition on the first target image;
a communication information acquisition module 1103 configured to acquire target communication information corresponding to the second subject;
a recommending module 1104 configured to recommend the second subject to the first subject according to the target communication information.
In one embodiment, the photographer determining module 1102 includes:
a first obtaining sub-module configured to obtain a first human feature of the first subject;
a second acquisition sub-module configured to acquire a second person feature of the second subject;
a similarity determination submodule configured to determine candidate character features having a similarity higher than a predetermined similarity with the first character feature among the second character features;
a determination sub-module configured to determine the subject corresponding to the candidate character feature as the second subject.
In one embodiment, the communication information obtaining module 1103 includes:
a third acquisition sub-module configured to acquire a third person feature of the second subject;
a communication database acquisition sub-module configured to acquire a communication database including a correspondence between character features and communication information;
a target communication information obtaining sub-module configured to obtain target communication information corresponding to the third person feature information according to the communication database;
wherein the third personality characteristic is indicative of at least one of: facial features, appearance features.
In one embodiment, the apparatus 1100 further comprises:
a second target image obtaining module 1105 configured to obtain a second target image including the second photographer according to a fourth human feature of the second photographer;
an image similarity obtaining module 1106, configured to perform image similarity calculation on the first target image and the second target image;
an information pushing module 1107 configured to push information to the first subject and the second subject according to image similarity, where the first subject is a publisher of the first target image, and the second subject is a publisher of the second target image.
In one embodiment, the image similarity obtaining module 1106 includes:
a background separation sub-module configured to perform background separation on the first target image and the second target image respectively to obtain a first background area and a second background area;
a target area obtaining sub-module configured to obtain a first target area in the first target image and a second target area in the second target image when image similarity of the first background area and the second background area satisfies a preset condition, wherein the first target area and the second target area both include the first photographer and the second photographer;
an image similarity determination submodule configured to determine an image similarity of the first target image and the second target image according to the image similarity of the first target region and the second target region.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 12 is a block diagram illustrating an apparatus 1200 for an information push method according to an example embodiment. For example, the apparatus 1200 may be provided as a server. Referring to fig. 12, the apparatus 1200 includes a processing component 1201 that further includes one or more processors and memory resources, represented by memory 1202, for storing instructions, such as applications, executable by the processing component 1201. The application programs stored in memory 1202 may include one or more modules that each correspond to a set of instructions. Furthermore, the processing component 1201 is configured to execute instructions to execute the above-mentioned goods pushing method
The apparatus 1200 may also include a power component 1203 configured to perform power management of the apparatus 1200, a wired or wireless network interface 1204 configured to connect the apparatus 1200 to a network, and an input output (I/O) interface 1205. The apparatus 1200 may operate based on an operating system stored in the memory 1202, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.
In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 1202 comprising instructions, executable by the processing component 1201 of the apparatus 1200 to perform the information pushing method described above is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
In an exemplary embodiment, the apparatus 1200 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described information push methods.
In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 1202 comprising instructions, executable by the processing component 1202 of the apparatus 1200 to perform the information pushing method described above is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (11)
1. An information pushing method applied to a social networking system includes:
acquiring a first target image, wherein the first target image comprises an image of a first photographed person, and the first target image is an image published to the social network system by a publisher;
determining a second photographer other than the first photographer by performing image recognition on the first target image;
acquiring target communication information corresponding to the second shot person;
recommending the second shot person to the first shot person according to the target communication information;
the determining a second subject other than the first subject by performing image recognition on the first target image includes:
acquiring a first person feature of the first shot person;
acquiring a second person characteristic of the second photographed person;
determining candidate human features with the similarity higher than a preset similarity with the first human feature in the second human features;
determining the shot person corresponding to the candidate character feature as the second shot person;
wherein the proportion of the second shot person to the first target image is smaller than the proportion of the first shot person to the first target image.
2. The method of claim 1, wherein the first human feature or the second human feature indicates at least one of: age, sex, interests.
3. The method according to claim 1, wherein the obtaining of the target communication information corresponding to the second subject includes:
acquiring a third person characteristic of the second person;
acquiring a communication database, wherein the communication database comprises a corresponding relation between character characteristics and communication information;
acquiring target communication information corresponding to the third person characteristic information according to the communication database;
wherein the third personality characteristic is indicative of at least one of: facial features, appearance features.
4. The method of claim 1, further comprising:
acquiring a second target image including the second shot person according to a fourth person feature of the second shot person;
calculating the image similarity of the first target image and the second target image;
and carrying out information pushing on the first shot person and the second shot person according to the image similarity, wherein the first shot person is a publisher of the first target image, and the second shot person is a publisher of the second target image.
5. The method of claim 4, wherein the step of performing image similarity calculations for the first target image and the second target image comprises:
respectively carrying out background separation on the first target image and the second target image to obtain a first background area and a second background area;
when the image similarity of the first background area and the second background area meets a preset condition, acquiring a first target area in the first target image and a second target area in the second target image, wherein the first target area and the second target area both comprise a first photographer and a second photographer;
and determining the image similarity of the first target image and the second target image according to the image similarity of the first target area and the second target area.
6. The method according to claim 1, wherein the recommending the second subject to the first subject according to the target communication information includes:
and sending a friend adding request to a terminal corresponding to the second photographed person according to the target communication information.
7. An information pushing apparatus applied to a server of a social networking system, comprising:
a target image acquisition module configured to acquire a first target image including an image of a first subject;
a subject determination module configured to determine a second subject other than the first subject by performing image recognition on the first target image;
a communication information acquisition module configured to acquire target communication information corresponding to the second subject;
a recommending module configured to recommend the second photographer to the first photographer according to the target communication information;
the subject determination module includes:
a first obtaining sub-module configured to obtain a first human feature of the first subject;
a second acquisition sub-module configured to acquire a second person feature of the second subject;
a similarity determination submodule configured to determine candidate character features having a similarity higher than a predetermined similarity with the first character feature among the second character features;
a determination sub-module configured to determine a subject corresponding to the candidate character feature as the second subject;
wherein the proportion of the second shot person to the first target image is smaller than the proportion of the first shot person to the first target image.
8. The apparatus according to claim 7, wherein the communication information obtaining module comprises:
a third acquisition sub-module configured to acquire a third person feature of the second subject;
a communication database acquisition sub-module configured to acquire a communication database including a correspondence between character features and communication information;
a target communication information obtaining sub-module configured to obtain target communication information corresponding to the third person feature information according to the communication database;
wherein the third personality characteristic is indicative of at least one of: facial features, appearance features.
9. The apparatus of claim 7, further comprising:
a second target image acquisition module configured to acquire a second target image including the second subject according to a fourth human feature of the second subject;
an image similarity obtaining module configured to perform image similarity calculation on the first target image and the second target image;
and the information pushing module is configured to push information to the first shot person and the second shot person according to image similarity, wherein the first shot person is a publisher of the first target image, and the second shot person is a publisher of the second target image.
10. The apparatus of claim 9, wherein the image similarity obtaining module comprises:
a background separation sub-module configured to perform background separation on the first target image and the second target image respectively to obtain a first background area and a second background area;
a target area obtaining sub-module configured to obtain a first target area in the first target image and a second target area in the second target image when image similarity of the first background area and the second background area satisfies a preset condition, wherein the first target area and the second target area both include the first photographer and the second photographer;
an image similarity determination submodule configured to determine an image similarity of the first target image and the second target image according to the image similarity of the first target region and the second target region.
11. An information pushing apparatus applied to a server of a social networking system, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to:
acquiring a first target image, wherein the first target image comprises an image of a first shot person; determining a second photographer other than the first photographer by performing image recognition on the first target image; acquiring target communication information corresponding to the second shot person; recommending the second shot person to the first shot person according to the target communication information;
the determining a second subject other than the first subject by performing image recognition on the first target image includes:
acquiring a first person feature of the first shot person;
acquiring a second person characteristic of the second photographed person;
determining candidate human features with the similarity higher than a preset similarity with the first human feature in the second human features;
determining the shot person corresponding to the candidate character feature as the second shot person;
wherein the proportion of the second shot person to the first target image is smaller than the proportion of the first shot person to the first target image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611124599.5A CN106777030B (en) | 2016-12-08 | 2016-12-08 | Information pushing method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611124599.5A CN106777030B (en) | 2016-12-08 | 2016-12-08 | Information pushing method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106777030A CN106777030A (en) | 2017-05-31 |
CN106777030B true CN106777030B (en) | 2020-12-25 |
Family
ID=58877467
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611124599.5A Active CN106777030B (en) | 2016-12-08 | 2016-12-08 | Information pushing method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106777030B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108073724A (en) * | 2018-01-04 | 2018-05-25 | 百度在线网络技术(北京)有限公司 | For generating the method and apparatus of information |
CN110061904B (en) * | 2019-04-10 | 2022-03-01 | 北京小米智能科技有限公司 | Method, device and system for acquiring social information, electronic equipment and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1685371A (en) * | 2002-09-24 | 2005-10-19 | 皇家飞利浦电子股份有限公司 | Image recognition |
CN104254859A (en) * | 2012-04-26 | 2014-12-31 | 谷歌公司 | Creating social network groups |
CN105303150A (en) * | 2014-06-26 | 2016-02-03 | 腾讯科技(深圳)有限公司 | Method and system for implementing image processing |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130215116A1 (en) * | 2008-03-21 | 2013-08-22 | Dressbot, Inc. | System and Method for Collaborative Shopping, Business and Entertainment |
CN102637183A (en) * | 2011-02-12 | 2012-08-15 | 北京千橡网景科技发展有限公司 | Method and device for recommending friends to user in social network |
CN102355534A (en) * | 2011-11-01 | 2012-02-15 | 宇龙计算机通信科技(深圳)有限公司 | Mobile terminal and contact information recommendation method |
CN103324636B (en) * | 2012-03-22 | 2016-04-06 | 三星电子(中国)研发中心 | The system and method for commending friends in social networks |
CN103577537B (en) * | 2013-09-24 | 2016-08-17 | 上海交通大学 | Multiplex paring similarity towards images share website picture determines method |
-
2016
- 2016-12-08 CN CN201611124599.5A patent/CN106777030B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1685371A (en) * | 2002-09-24 | 2005-10-19 | 皇家飞利浦电子股份有限公司 | Image recognition |
CN104254859A (en) * | 2012-04-26 | 2014-12-31 | 谷歌公司 | Creating social network groups |
CN105303150A (en) * | 2014-06-26 | 2016-02-03 | 腾讯科技(深圳)有限公司 | Method and system for implementing image processing |
Also Published As
Publication number | Publication date |
---|---|
CN106777030A (en) | 2017-05-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10900772B2 (en) | Apparatus and methods for facial recognition and video analytics to identify individuals in contextual video streams | |
US11286310B2 (en) | Methods and apparatus for false positive minimization in facial recognition applications | |
US10885307B2 (en) | Private photo sharing system, method and network | |
US20180012386A1 (en) | Combining faces from source images with target images based on search queries | |
CN105654039B (en) | The method and apparatus of image procossing | |
CN104967554B (en) | Method for message interaction and relevant apparatus and communication system | |
WO2018177002A1 (en) | Social information display method, computer device and storage medium | |
CN106575280B (en) | System and method for analyzing user-associated images to produce non-user generated labels and utilizing the generated labels | |
KR101782590B1 (en) | Method for Providing and Recommending Related Tag Using Image Analysis | |
CA2870202A1 (en) | Creating social network groups | |
CN106777030B (en) | Information pushing method and device | |
KR101715708B1 (en) | Automated System for Providing Relation Related Tag Using Image Analysis and Method Using Same | |
KR20200009888A (en) | Method for Providing and Recommending Related Tag Using Image Analysis | |
US10135888B2 (en) | Information processing method and device | |
CN110569758A (en) | method, device and storage medium for determining user category | |
KR102278017B1 (en) | Method for social networking service based on photos | |
KR20150081395A (en) | A method for providing effective ad | |
WO2019021216A1 (en) | System and method for distributing media |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |