Social relationship determination method, device, equipment and storage medium

By analyzing interaction patterns and location records in images of people, social relationships are automatically determined, solving the problems of accuracy and timeliness in social relationship determination in existing technologies and achieving efficient social relationship updates.

CN113822767BActive Publication Date: 2024-11-01ZHEJIANG UNIVIEW TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010529644.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-06-11
Publication Date
2024-11-01
Estimated Expiration
2040-06-11

AI Technical Summary

Technical Problem

In existing technologies, the methods for determining social relationships rely on manually inputted social information or official registrations, which cannot guarantee the accuracy, timeliness, and scalability of the data.

Method used

By acquiring interaction patterns and location records from images of people, the system automatically analyzes social relationship data between target individuals and related individuals, and combines this with preset mapping relationships to determine the type and score of social relationships, thus achieving automatic and accurate identification of social relationships.

Benefits of technology

It improves the accuracy and efficiency of social relationship determination, realizes the automatic improvement and updating of social relationships, and reduces reliance on manual input.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113822767B_ABST
    Figure CN113822767B_ABST
Patent Text Reader

Abstract

The embodiments of the present application disclose a method, device, equipment and storage medium for determining social relations. The method includes: obtaining a person image containing a target person and at least one associated person; determining the first social relationship data between the target person and each associated person according to the interaction mode between the target person and at least one associated person in the person image; and determining the second social relationship data between the target person and each associated person according to the positioning record information of the person image; determining the social relationship information between the target person and each associated person according to the first social relationship data and the second social relationship data. The above scheme determines the interaction mode and positioning record information of the target person and the associated person through the person image, thereby automatically and accurately determining the social relationship between the target person and the associated person, and realizing automatic improvement and update.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the field of security technology, and in particular to a method, device, equipment and storage medium for determining social relations. Background Art

[0002] Social relations are the general term for the mutual relations formed by people in the process of common material and spiritual activities, that is, all relations between people. From the perspective of both sides of the relationship, social relations include the relationship between individuals, the relationship between individuals and groups, and the relationship between individuals and the state; generally, they also include the relationship between groups and the relationship between groups and the state.

[0003] At present, the way to determine social relations is to establish interpersonal connections through social information or registered official information, such as company responsibility connections, family information registration, etc., and the registration of information can be manually input, and the accuracy, timeliness and extensibility of the data cannot be guaranteed. Summary of the invention

[0004] The embodiments of the present application provide a social relationship determination method, apparatus, device and storage medium to accurately and timely determine social relationships and achieve automatic improvement and update.

[0005] In one embodiment, the present application provides a method for determining social relationships, the method comprising:

[0006] Acquire a person image including a target person and at least one associated person;

[0007] Determining first social relationship data between the target person and each associated person according to the interaction mode between the target person and at least one associated person in the person image; and determining second social relationship data between the target person and each associated person according to the positioning record information of the person image;

[0008] The social relationship information between the target person and each associated person is determined according to the first social relationship data and the second social relationship data.

[0009] In another embodiment, the present application also provides a social relationship determination device, the device comprising:

[0010] A personnel image acquisition module, used to acquire a personnel image including a target person and at least one associated person;

[0011] a relationship data determination module, configured to determine first social relationship data between the target person and each associated person according to an interaction mode between the target person and at least one associated person in the person image; and to determine second social relationship data between the target person and each associated person according to positioning record information of the person image;

[0012] A social relationship information determination module is used to determine the social relationship information between the target person and each associated person based on the first social relationship data and the second social relationship data.

[0013] In yet another embodiment, the present application also provides a device, including: one or more processors;

[0014] A memory for storing one or more programs;

[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement the social relationship determination method described in any one of the embodiments of the present application.

[0016] In yet another embodiment, the present application also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, a social relationship determination method as described in any one of the embodiments of the present application is implemented.

[0017] In an embodiment of the present application, the first social relationship data between the target person and each associated person is determined based on the interaction mode between the target person and at least one associated person in the person image; and the second social relationship data between the target person and each associated person is determined based on the positioning record information of the person image; and the social relationship information between the target person and each associated person is determined based on the first social relationship data and the second social relationship data, thereby automatically and accurately determining the social relationship between the target person and the associated persons, and realizing automatic improvement and updating. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flow chart of a method for determining social relations provided by an embodiment of the present invention;

[0019] Figure 2 A flowchart of a method for determining social relations provided by another embodiment of the present invention;

[0020] Figure 3 A schematic diagram of a social relationship information structure provided by another embodiment of the present invention;

[0021] Figure 4 A flowchart of a method for determining social relations provided by another embodiment of the present invention;

[0022] Figure 5 A schematic diagram of the structure of a social relationship determination device provided by an embodiment of the present invention;

[0023] Figure 6 A schematic diagram of the structure of a social relationship determination device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0025] Figure 1 This is a flowchart of a social relationship determination method provided by an embodiment of the present invention. The social relationship determination method provided by this embodiment can be applied to the situation of determining the social relationship between people. Typically, this embodiment of the application can be applied to the situation of determining the social relationship between the target person and the associated person based on the collected image of the person. The method can be specifically executed by a social relationship determination device, which can be implemented by software and / or hardware, and the device can be integrated in a social relationship determination device. See Figure 1 , the method of the embodiment of the present application specifically includes:

[0026] S110: Acquire a person image including a target person and at least one associated person.

[0027] The image may be an image collected by an image collector in a monitoring scene, or may be an image obtained from a video, and the monitoring scene may be a shopping mall, a residential area, an office building, a restaurant, or the like. The target person may be any person appearing in the image, that is, any person may be used as a target person for social relationship analysis. The associated person is a person in the same person image as the target person, and / or a person in the same position as the target person, that is, when a person and the target person appear in the same image, the person is determined to be an associated person of the target person, and / or when a person and the target person appear in the same position, the person is determined to be an associated person of the target person.

[0028] In an embodiment of the present application, in order to analyze the social relationship between the target person and the associated persons, a person image containing the target person and at least one associated person is obtained from the image captured by the image collector, and then the person image containing the target person and at least one associated person is analyzed to determine the social relationship between the target person and at least one associated person. Specifically, the image containing the target person may not contain all the associated persons of the target person, and may contain only the target person in the image. Therefore, an image containing at least two persons, one of whom is the target person, is obtained from the image collector, which is a person image containing the target person and at least one associated person, so as to facilitate the analysis of the social relationship between the target person and other persons, that is, the associated persons.

[0029] S120. Determine the first social relationship data between the target person and each associated person based on the interaction mode between the target person and at least one associated person in the person image; and determine the second social relationship data between the target person and each associated person based on the positioning record information of the person image.

[0030] Among them, the interactive mode may include interactive actions or states such as face-to-face, holding hands, and hugging. The first social relationship data may include a first social relationship type and a first score. The first social relationship type may be a relationship type such as friends, colleagues, lovers, and couples, and the first score may be a probability score corresponding to each type. The interactive mode may also include feature description information such as gender, age, and features, so as to assist in determining the probability score of the social relationship type corresponding to the interactive mode. The positioning record information may be the positioning record information determined according to the positioning of the image collector, the direction of the image collector, and the image acquisition angle of the image collector that collects the image of the person, and may include information such as longitude and latitude positioning, time information, the number of times appearing at the positioning location, and the frequency per unit time. The second social relationship data may include a second social relationship type and a second score. The second social relationship type may be a relationship type such as friends, colleagues, lovers, and couples, and the second score may be a probability score corresponding to each type.

[0031] In an embodiment of the present application, training image samples can be obtained, and the training image samples can be classified and clustered. Model training is performed according to face-to-face angles, distances between human bodies, degree of smile, overlapping areas between human bodies, etc., to obtain an interaction mode recognition model, and the obtained personnel image including the target person and at least one associated person is input into the interaction mode recognition model, thereby obtaining the interaction mode between the target person and at least one associated person in the personnel image. It is also possible to directly perform intelligent analysis on the personnel image containing the target person and at least one associated person, and analyze the interaction mode between the target person and at least one associated person through the characteristics of the state, distance, relative orientation, facial expression, gender, height, and wearing items of the face or human body. Through the interaction mode, the first social relationship information of the target person and at least one associated person is determined. For example, if the interaction mode is holding hands, the first social relationship type may be a couple, and the corresponding first score is determined. If the interaction mode is hugging, the height feature is one tall and one short, and the age feature is one old and one young, the first social relationship type may be a relative, and the corresponding first score is determined.

[0032] If the target person and at least one associated person have appeared in the same place, the two may also have a certain relationship, and their social relationship needs to be determined. In the embodiment of the present application, the second social relationship data between the target person and each associated person is determined based on the location record information of the person image. For example, if the target person and the associated person have the same location, which is an office building, it can be determined that the second social relationship type between the target person and the associated person can be colleagues, and the corresponding second score is determined.

[0033] S130: Determine the social relationship information between the target person and each associated person according to the first social relationship data and the second social relationship data.

[0034] Among them, the social relationship information includes the social relationship type and the corresponding score. Specifically, for a social relationship type, determine the first score corresponding to the social relationship type in the first social relationship data, and determine the second score corresponding to the social relationship type in the second social relationship data, and determine the score corresponding to the social relationship type according to the first score and the second score. Determine all possible social relationship types and corresponding scores between the target person and the associated persons as the social relationship information between the target person and the associated persons. And analyze the social relationship information of the target person and each associated person according to the above method, so as to automatically and accurately determine the associated information between the target person and other associated persons, so as to facilitate the departments in need to conduct reference analysis without relying on manual input information to determine the social relationship, thereby improving the efficiency of social relationship determination.

[0035] In an embodiment of the present application, the first social relationship data between the target person and each associated person is determined based on the interaction mode between the target person and at least one associated person in the person image; and the second social relationship data between the target person and each associated person is determined based on the positioning record information of the person image; and the social relationship information between the target person and each associated person is determined based on the first social relationship data and the second social relationship data, thereby automatically and accurately determining the social relationship between the target person and the associated persons, and being able to automatically improve and update the social relationship based on the update of the image.

[0036] Figure 2 This is a flow chart of a method for determining social relations provided by another embodiment of the present invention. This embodiment of the present application is an optimization based on the above embodiment. For details not described in detail in this embodiment, please refer to the above embodiment. Figure 2 The social relationship determination method provided in this embodiment may include:

[0037] S210: Acquire a person image including a target person and at least one associated person.

[0038] S220. Determine the first social relationship data between the target person and each associated person based on the interaction mode between the target person and at least one associated person in the person image; and determine the second social relationship data between the target person and each associated person based on the positioning record information of the person image.

[0039] In an embodiment of the present application, the first social relationship data includes a first social relationship type and a first score; accordingly, based on the interaction mode between the target person and at least one associated person in the personnel image, the first social relationship data between the target person and each associated person is determined, including: based on the interaction mode, and a mapping relationship between a preset interaction mode, the first social relationship type and the first score, determining the first social relationship type and the first score between the target person and the associated person.

[0040] Specifically, a plurality of interaction modes and a mapping relationship between the first social relationship and the first score can be preset. When the interaction mode between the target person and the associated person is determined based on the person image containing the target person and the associated person, the first social relationship type and the first score corresponding to the interaction mode are determined based on the preset mapping relationship. As shown in Table 1, the preset first score can be set according to actual conditions. For example, for the same first social relationship type "friend", the first score corresponding to the "face-to-face" interaction mode is less than the first score corresponding to the "hand-holding" interaction mode, thereby indicating the difference in the possibility of the first social relationship type determined by different interaction modes. The specific value of the first score is not limited.

[0041] Table 1

[0042]

[0043] In an embodiment of the present application, the second social relationship data includes a second social relationship type and a second score; accordingly, based on the positioning record information of the personnel image, the second social relationship data between the target person and each associated person is determined, including: determining map annotation information based on the positioning record information of the personnel image; determining the second social relationship type and the second score between the target person and the associated persons based on the map annotation information, and a mapping relationship between the preset map annotation information, the second social relationship type and the second score.

[0044] Specifically, the mapping relationship between the map annotation information, the second social relationship type, and the second score can be preset. The location record information of the target person and the associated person is determined, and the second social relationship type and the second score corresponding to the map annotation information are determined according to the map annotation information corresponding to the location record information. Since the location record information includes the longitude and latitude information of the location, it can collide with the POI (Point of Information) in the map to determine the map annotation information of the location, and then determine the corresponding second social relationship type and the second score according to the map annotation information. For example, according to the longitude and latitude in the location record information of the same location of the target person and the associated person, the map annotation corresponding to the longitude and latitude in the map is determined, for example, school, then it can be determined that the second social relationship type between the target person and the associated person can be classmates, and the corresponding second score is determined, as shown in Table 2.

[0045] Table 2

[0046]

[0047] In an embodiment of the present application, before determining the social relationship information between the target person and each associated person based on the first social relationship data and the second social relationship data, the method also includes: determining the positioning record information of the target person based on the person image of the target person, and determining the positioning record information of the associated person based on the person image of the associated person; if the positioning record information of the target person and the positioning location in the positioning record information of the associated person are the same, then determining the second social relationship data between the target person and each associated person based on the positioning record information.

[0048] The positioning record information also includes the frequency and / or duration of being located at the positioning location; accordingly, based on the positioning record information of the personnel image, the second social relationship data between the target person and each associated person is determined, including: if the frequency of the target person and the associated person being located at the same positioning location is greater than a preset frequency threshold, and / or the duration is greater than a preset duration threshold, then the second social relationship data between the target person and the associated person is determined.

[0049] Specifically, the target person and the related persons may not appear in the same image, but have appeared at the same positioning location, and there may be a certain social relationship between them. Therefore, the positioning locations where each person has appeared are analyzed. If the target person has the same positioning location as other persons, the frequency of appearing at the positioning location is determined, such as the number of times the target person appears at the positioning location in a month, and / or the duration, such as the total duration of appearing at the positioning location in a month. If the frequency is greater than the preset frequency threshold, and / or the duration is greater than the preset duration threshold, the map annotation of the positioning location is determined based on the latitude and longitude information of the positioning location, and then the second social relationship type and the second score corresponding to the map annotation are determined.

[0050] S230: Determine a target social relationship type according to the first social relationship type in the first social relationship data and / or the second data relationship type in the second social relationship data.

[0051] Exemplarily, the first social relationship type included in the first social relationship data and the second social relationship type included in the second social relationship data are taken as target social relationship types and analyzed one by one.

[0052] S240: Determine a first score and corresponding to the target social relationship type according to the first social relationship data.

[0053] Exemplarily, for a target social relationship, the first score and corresponding to the target social relationship type in the first social relationship data are determined. For example, in Table 1, for the target social relationship type "couple", the corresponding first score includes m 3 and m 6 , then the first score sum is m 3 +m 6 .

[0054] S250: Determine a second score and corresponding to the target social relationship type according to the second social relationship data.

[0055] For the target social relationship type, determine its corresponding second score and in the second social relationship data. For example, in Table 2, for the target social relationship type "couple", the corresponding second score includes n 6, then the second score sum is n 6 .

[0056] S260: taking the sum of the first score sum and the second score sum, and the target social relationship type, as the social relationship information between the target person and the associated person.

[0057] Specifically, the following formula can be used to determine social relationship information:

[0058] (tagid1, tagid2, SR:S)S=∑m i +∑n j .

[0059] Among them, tagid1 is the target person ID, tagid2 is the associated person ID, SR is the target social relationship type, and S is the corresponding score. i is the first score corresponding to the target social relationship SR, n j is the second score corresponding to the target social relationship SR. M is the number of first scores corresponding to the target social relationship type in the first social relationship data, and N is the number of second scores corresponding to the target social relationship type in the second social relationship data.

[0060] For example, Figure 3 A schematic diagram of a social relationship information structure provided by another embodiment of the present invention is shown in FIG. Figure 3 As shown, for the target social relationship type “couple”, the sum of the first score and the second score is determined, that is, m 3 +m 6 +n 6 , as the score corresponding to the target social relationship type, a corresponding relationship is established. And all possible target social relationship types and corresponding scores are determined, and finally all possible target social relationship types and corresponding scores constitute the social relationship information between the target person and the associated person.

[0061] The technical solution of the embodiment of the present application determines the score corresponding to the target social relationship type through the first score and the second score corresponding to the target social relationship type, determines the social relationship information between the target person and the related persons, and thus accurately determines the possibility that the relationship between the target person and the related persons is the target social relationship type, which facilitates the analysis of the social relationship of the target person.

[0062] Figure 4 This is a flow chart of a method for determining social relations provided by another embodiment of the present invention. This embodiment of the present application is an optimization based on the above embodiment. For details not described in detail in this embodiment, please refer to the above embodiment. Figure 4 The social relationship determination method provided in this embodiment may include:

[0063] S310: Perform face recognition on the candidate image to obtain a face image.

[0064] Exemplarily, the candidate images may be all images collected by the image collector. Face recognition is performed on the candidate images to obtain face images, thereby facilitating the determination of the identities of the personnel.

[0065] S320: Match the facial images, and set the same identifier for the facial images that have been matched successfully.

[0066] In order to determine the person corresponding to each facial image in the candidate image, the faces are matched by similarity. If the similarity is greater than the preset similarity threshold, the match is successful, and it is determined that the successfully matched facial images correspond to the same person. Therefore, the successfully matched facial images are set with the same identifier, which can be represented by tagid, to indicate that they belong to the same person, making it easier to search for person images based on the same identifier.

[0067] S330: If the facial image of the target person matches any facial image in the candidate images, the identifier of the facial image in the candidate images is used as the target identifier of the target person.

[0068] Specifically, when it is necessary to perform social relationship analysis on a specific person, the person is identified as a target person, and the facial image of the target person is matched with the facial image in the candidate image. If the match is successful, the identifier of the facial image in the candidate image is used as the target identifier of the target person.

[0069] S340: Determine the candidate image corresponding to the facial image with the target identifier as a person image containing the target person.

[0070] Exemplarily, among the candidate images, a search is performed based on the target identifier, and the candidate images having the target identifier are extracted as the person images containing the target person.

[0071] S350: Analyze the person image containing the target person.

[0072] S360: If there is at least one associated person, determine that the person image is a person image including the target person and at least one associated person.

[0073] Specifically, the person image containing the target person is analyzed, such as face recognition or body recognition, to determine the number of persons contained therein. If at least two persons are contained therein, and because the target person is contained therein, it can be determined that at least one associated person is contained therein, and therefore, the image is determined to be a person image containing the target person and at least one associated person.

[0074] S370. Determine the first social relationship data between the target person and each associated person based on the interaction mode between the target person and at least one associated person in the person image; and determine the second social relationship data between the target person and each associated person based on the positioning record information of the person image.

[0075] S380: Determine the social relationship information between the target person and each associated person according to the first social relationship data and the second social relationship data.

[0076] The technical solution of the embodiment of the present application marks the same person by setting the same identifier, which facilitates the retrieval of the person image of the target person, and obtains the person image containing the target person and at least one related person by analyzing the person image containing the target person, which facilitates the analysis of the social relationship between the target person and other related persons.

[0077] Figure 5 This is a schematic diagram of the structure of a social relationship determination device provided by an embodiment of the present invention. The device may be applicable to situations where the identity of a person is verified. Typically, the embodiment of the present application may be applicable to situations where the social relationship between persons is determined. Typically, the embodiment of the present application may be applicable to situations where the social relationship between a target person and associated persons is determined based on the collected images of the person. The device may be implemented by software and / or hardware, and the device may be integrated in a social relationship determination device. See Figure 5 , the device specifically comprises:

[0078] A personnel image acquisition module 410 is used to acquire a personnel image including a target person and at least one associated person;

[0079] The relationship data determination module 420 is used to determine the first social relationship data between the target person and each associated person according to the interaction mode between the target person and at least one associated person in the person image; and determine the second social relationship data between the target person and each associated person according to the positioning record information of the person image;

[0080] The social relationship information determination module 430 is used to determine the social relationship information between the target person and each associated person according to the first social relationship data and the second social relationship data.

[0081] In the embodiment of the present application, the device further includes:

[0082] A recognition module, used for performing face recognition on the candidate image to obtain a face image;

[0083] An identification setting module is used to match facial images and set the same identification for the facial images that have been successfully matched;

[0084] A target identification determination module, configured to use the identification of the face image in the candidate image as the target identification of the target person if the face image of the target person matches any face image in the candidate image;

[0085] The person image determination module is used to determine the candidate image corresponding to the face image with the target identification as the person image containing the target person.

[0086] In the embodiment of the present application, the device further includes:

[0087] An image analysis module, used for analyzing images of people including target people;

[0088] The image determination module is used to determine that the person image is a person image including the target person and at least one associated person if there is at least one associated person.

[0089] In the embodiment of the present application, the device further includes:

[0090] A positioning record information determination module, used to determine the positioning record information of the target person according to the person image of the target person, and to determine the positioning record information of the associated person according to the person image of the associated person;

[0091] The second social relationship data determination module is used to determine the second social relationship data between the target person and each associated person according to the positioning record information if the positioning location in the positioning record information of the target person and the positioning location in the positioning record information of the associated person is the same.

[0092] In the embodiment of the present application, the first social relationship data includes a first social relationship type and a first score;

[0093] Accordingly, the relationship data determination module 420 includes:

[0094] The first social relationship determination unit is used to determine the first social relationship type and the first score between the target person and the associated person according to the interaction mode and the mapping relationship among the preset interaction mode, the first social relationship type and the first score.

[0095] In the embodiment of the present application, the second social relationship data includes a second social relationship type and a second score;

[0096] Accordingly, the relationship data determination module 420 includes:

[0097] A second social relationship determination unit, configured to determine map annotation information according to the location record information of the person image;

[0098] The second social relationship type and the second score between the target person and the associated person are determined according to the map annotation information and the mapping relationship among the preset map annotation information, the second social relationship type and the second score.

[0099] In the embodiment of the present application, the positioning record information also includes the frequency and / or duration of being at the positioning location;

[0100] Accordingly, the relationship data determination module 420 includes:

[0101] The third social relationship determination unit is used to determine the second social relationship data between the target person and the associated person if the frequency of the target person and the associated person being at the same location is greater than a preset frequency threshold, and / or the duration is greater than a preset duration threshold.

[0102] In the embodiment of the present application, the social relationship information determination module 430 includes:

[0103] a target social relationship type determination unit, configured to determine a target social relationship type according to the first social relationship type in the first social relationship data and / or the second data relationship type in the second social relationship data;

[0104] A first scoring and determining unit, configured to determine a first scoring and corresponding to a target social relationship type according to the first social relationship data;

[0105] A second scoring and determining unit, configured to determine a second scoring and corresponding to a target social relationship type according to the second social relationship data;

[0106] The information determination unit is used to use the sum of the first score sum and the second score sum, and the target social relationship type as the social relationship information between the target person and the associated person.

[0107] In an embodiment of the present application, the associated person is a person who is located in the same person image as the target person, and / or a person who is in the same position as the target person.

[0108] The social relationship determination device provided in the embodiments of the present application can execute the social relationship determination method provided in any embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method.

[0109] Figure 6 A schematic diagram of the structure of a social relationship determination device provided by an embodiment of the present invention. Figure 6 A block diagram of an exemplary social relationship determination device 512 suitable for implementing the embodiments of the present application is shown. Figure 6The social relationship determination device 512 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0110] like Figure 6 As shown, the social relationship determination device 512 may include: one or more processors 516; a memory 528, which is used to store one or more programs. When the one or more programs are executed by the one or more processors 516, the one or more processors 516 implement the social relationship determination method provided in the embodiment of the present application, including:

[0111] Acquire a person image including a target person and at least one associated person;

[0112] Determining first social relationship data between the target person and each associated person according to the interaction mode between the target person and at least one associated person in the person image; and determining second social relationship data between the target person and each associated person according to the positioning record information of the person image;

[0113] The social relationship information between the target person and each associated person is determined according to the first social relationship data and the second social relationship data.

[0114] The components of the social relationship determination device 512 may include, but are not limited to, one or more processors or a processor 516 , a memory 528 , and a bus 518 that connects the various device components (including the memory 528 and the processor 516 ).

[0115] Bus 518 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0116] The social relationship determination device 512 typically includes a variety of computer device readable storage media. These storage media can be any available storage media that can be accessed by the social relationship determination device 512, including volatile and non-volatile storage media, removable and non-removable storage media.

[0117] The memory 528 may include computer device readable storage media in the form of volatile memory, such as random access memory (RAM) 530 and / or cache memory 532. The social relationship determination device 512 may further include other removable / non-removable, volatile / non-volatile computer device storage media. By way of example only, the storage system 534 may be used to read and write non-removable, non-volatile magnetic storage media ( Figure 6 not shown, usually called a "hard drive"). Although Figure 6 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical storage medium) may be provided. In these cases, each drive may be connected to bus 518 via one or more data storage medium interfaces. Memory 528 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of various embodiments of the present invention.

[0118] A program / utility 540 having a set (at least one) of program modules 542 may be stored, for example, in the memory 528, such program modules 542 including, but not limited to, operating devices, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 542 generally perform the functions and / or methods of the embodiments described herein.

[0119] The social relationship determination device 512 may also communicate with one or more external devices 514 (e.g., a keyboard, a pointing device, a display 526, etc.), may also communicate with one or more devices that enable a user to interact with the social relationship determination device 512, and / or communicate with any device that enables the social relationship determination device 512 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed through an input / output (I / O) interface 522. In addition, the social relationship determination device 512 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 520. Figure 6 As shown, the network adapter 520 communicates with other modules of the social relationship determination device 512 via the bus 518. It should be understood that although Figure 6 Not shown, other hardware and / or software modules may be used in conjunction with the social relationship determination device 512, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID devices, tape drives, and data backup storage devices.

[0120] The processor 516 executes various functional applications and data processing by running at least one of the other programs among the multiple programs stored in the memory 528, such as implementing a social relationship determination method provided in an embodiment of the present application.

[0121] An embodiment of the present invention provides a storage medium containing computer executable instructions, wherein the computer executable instructions are used to perform a social relationship determination method when executed by a computer processor, including:

[0122] Acquire a person image including a target person and at least one associated person;

[0123] Determining first social relationship data between the target person and each associated person according to the interaction mode between the target person and at least one associated person in the person image; and determining second social relationship data between the target person and each associated person according to the positioning record information of the person image;

[0124] The social relationship information between the target person and each associated person is determined according to the first social relationship data and the second social relationship data.

[0125] The computer storage medium of the embodiment of the present application can adopt any combination of one or more computer-readable storage media. The computer-readable storage medium can be a computer-readable signal storage medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, - but not limited to - electrical, magnetic, optical, electromagnetic, infrared, or semiconductor equipment, devices or devices, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In an embodiment of the present application, a computer-readable storage medium can be any tangible storage medium containing or storing a program, which can be used by an instruction execution device, device or device or used in combination with it.

[0126] A computer-readable signal storage medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal storage medium may also be any computer-readable storage medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution device, apparatus, or device.

[0127] The program code contained on the computer-readable storage medium may be transmitted using any appropriate storage medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0128] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or device. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0129] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for determining social relations, characterized in that: The method comprises: Acquire a person image including a target person and at least one associated person; Determine the first social relationship data between the target person and each associated person based on the interaction mode between the target person and at least one associated person in the person image; and determine the second social relationship data between the target person and each associated person based on the positioning record information of the person image; wherein the associated person is a person located in the same person image as the target person, and / or a person who has the same positioning as the target person but is not located in the same person image, wherein the first social relationship data includes a first social relationship type and a first score, and the first score is a probability score corresponding to each of the first social relationship types; the second social relationship data includes a second social relationship type and a second score, and the second score is a probability score corresponding to each of the second social relationship types; Based on the first social relationship data and the second social relationship data, determine the social relationship information between the target person and each associated person, wherein the social relationship information between the target person and each associated person is composed of all possible target social relationship types and corresponding scores, and all possible target social relationship types include the first social relationship type contained in the first social relationship data and the second social relationship type contained in the second social relationship data.

2. The method according to claim 1, characterized in that: Before determining the first social relationship data between the target person and each associated person according to the interaction mode between the target person and at least one associated person in the person image, the method further includes: Performing face recognition on the candidate image to obtain a face image; Matching facial images, and setting the same identifier for successfully matched facial images; If the face image of the target person matches any face image in the candidate images, the identification of the face image in the candidate images is used as the target identification of the target person; The candidate image corresponding to the face image with the target identification is determined as the person image containing the target person.

3. The method according to claim 2, characterized in that After determining the candidate image corresponding to the face image with the target identifier as a person image containing the target person, the method further includes: Analyzing a person image containing a target person; If there is at least one associated person, the person image is determined to be a person image including the target person and at least one associated person.

4. The method according to claim 1, characterized in that: Before determining the social relationship information between the target person and each associated person according to the first social relationship data and the second social relationship data, the method further includes: Determining the location record information of the target person according to the person image of the target person, and determining the location record information of the associated person according to the person image of the associated person; If the location of the target person's location record information is the same as the location record information of the associated persons, the second social relationship data between the target person and each associated person is determined according to the location record information.

5. The method according to any one of claims 1 to 4, characterized in that The first social relationship data includes a first social relationship type and a first score; Accordingly, determining the first social relationship data between the target person and each associated person according to the interaction mode between the target person and at least one associated person in the person image includes: According to the interaction mode and the mapping relationship among the preset interaction mode, the first social relationship type and the first score, the first social relationship type and the first score between the target person and the associated person are determined.

6. The method according to any one of claims 1 to 4, characterized in that The second social relationship data includes a second social relationship type and a second score; Accordingly, determining the second social relationship data between the target person and each associated person according to the positioning record information of the person image includes: Determining map annotation information according to the location record information of the person image; The second social relationship type and the second score between the target person and the associated person are determined according to the map annotation information and the mapping relationship among the preset map annotation information, the second social relationship type and the second score.

7. The method according to claim 6, characterized in that The positioning record information also includes the frequency and / or duration of being at the positioning location; Accordingly, determining the second social relationship data between the target person and each associated person according to the positioning record information of the person image includes: If the frequency of the target person and the associated person being located at the same location is greater than a preset frequency threshold, and / or the duration is greater than a preset duration threshold, the second social relationship data between the target person and the associated person is determined.

8. The method according to claim 1, characterized in that Determining the social relationship information between the target person and each associated person according to the first social relationship data and the second social relationship data includes: Determining a target social relationship type according to a first social relationship type in the first social relationship data and / or a second data relationship type in the second social relationship data; Determine a first score and a first score corresponding to a target social relationship type according to the first social relationship data; Determine a second score and corresponding to the target social relationship type according to the second social relationship data; The sum of the first score sum and the second score sum, as well as the target social relationship type, is used as the social relationship information between the target person and the associated person.

9. A social relationship determination device, characterized in that: The device comprises: A personnel image acquisition module, used to acquire a personnel image including a target person and at least one associated person; A relationship data determination module, used to determine the first social relationship data between the target person and each associated person according to the interaction mode between the target person and at least one associated person in the person image; and to determine the second social relationship data between the target person and each associated person according to the positioning record information of the person image; wherein the associated person is a person located in the same person image as the target person, and / or a person who has the same positioning as the target person but is not located in the same person image, wherein the first social relationship data includes a first social relationship type and a first score, and the first score is a probability score corresponding to each of the first social relationship types; the second social relationship data includes a second social relationship type and a second score, and the second score is a probability score corresponding to each of the second social relationship types; A social relationship information determination module is used to determine the social relationship information between the target person and each associated person based on the first social relationship data and the second social relationship data, wherein the social relationship information between the target person and each associated person is composed of all possible target social relationship types and corresponding scores, and all possible target social relationship types include the first social relationship type contained in the first social relationship data and the second social relationship type contained in the second social relationship data.

10. A social relationship determination device, characterized in that: The device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the social relationship determination method as described in any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the social relationship determination method as described in any one of claims 1 to 8 is implemented.