CN111221991A

CN111221991A - Method and device for determining personnel identity attribute and electronic equipment

Info

Publication number: CN111221991A
Application number: CN201911079417.0A
Authority: CN
Inventors: 程皓; 刘瑞伟
Original assignee: Qingdao Guangshi Technology Co Ltd; Beijing Kuangshi Technology Co Ltd
Current assignee: Beijing Kuangshi Technology Co Ltd
Priority date: 2019-11-06
Filing date: 2019-11-06
Publication date: 2020-06-02
Also published as: CN113505251A

Abstract

The invention provides a method and a device for determining personnel identity attributes and electronic equipment, wherein the method comprises the following steps: acquiring a portrait file of a person to be identified; determining file labels and/or basic attribute information according to the portrait files; and determining the personnel identity attribute of the personnel to be identified corresponding to the portrait archive according to the corresponding relation between the archive label and/or the basic attribute information and the personnel identity attribute. The method can perform multidimensional analysis on the portrait archive to obtain the archive label and/or the archive basic attribute information, and determine the personnel identity attribute of the personnel to be identified corresponding to the portrait archive based on the corresponding relation between the archive label and/or the basic attribute information and the personnel identity attribute, thereby relieving the technical problem that the identity attribute of the personnel is difficult to be effectively determined in the prior art.

Description

Method and device for determining personnel identity attribute and electronic equipment

Technical Field

The invention relates to the technical field of personnel identity identification, in particular to a method and a device for determining personnel identity attributes and electronic equipment.

Background

A face recognition system covering public areas and key parts is gradually built in China, and the face of passers-by can be snapshotted. Aiming at the established face recognition system, real-time face snapshot pictures can be aggregated through a face clustering technology, and then a face archive (a collection of snapshot pictures of the same person in essence) of each person is generated. When the identity attribute of the person corresponding to the portrait archive is determined, the identity attribute of the person corresponding to the portrait archive can be determined by matching the real-name photo library of the person and the portrait archive which are provided by relevant departments often depending on the real-name photo library of the person and the identity attribute of the person.

In practical application environments, it is difficult for the relevant department to provide a real-name photo library of all or a large number of people, and even if the relevant department provides a real-name photo library of all people who have mastered, it is impossible to completely match a large number of portrait profiles because there are a large number of people who have not been mastered (e.g., floating population, people who have not registered real information), and such people who have not been mastered are just people who need to pay attention. In addition, in the method of real-name photo library of personnel, only the identity information (for example, name information, age information, occupational information, etc.) of the personnel can be obtained generally, but the business attribute information of the personnel cannot be obtained.

In summary, it is difficult to effectively determine the identity attribute of a person in the prior art.

Disclosure of Invention

In view of this, the present invention provides a method, an apparatus and an electronic device for determining an identity attribute of a person, so as to alleviate the technical problem that it is difficult to effectively determine the identity attribute of the person in the prior art.

In a first aspect, an embodiment of the present invention provides a method for determining a person identity attribute, which is applied to a person analysis system, and includes: acquiring a portrait file of a person to be identified; the portrait archive at least comprises: the system comprises a portrait snapshot, snapshot time of the portrait snapshot and information of an image acquisition device for snapshot of the portrait snapshot, wherein each portrait file corresponds to a person to be identified; determining archive labels and/or basic attribute information according to the portrait archive; and determining the personnel identity attribute of the personnel to be identified corresponding to the portrait archive according to the corresponding relation between the archive label and/or the basic attribute information and the personnel identity attribute.

Further, the profile tag includes: at least one of an abnormal behavior type archive label, a personnel state type archive label, a presence condition type archive label and an affinity type archive label; the profile label of the abnormal behavior category comprises: a daytime and nighttime outgoing label, a frequent outgoing label, a personnel gathering label and a regional residence label; the profile label of the personnel status category comprises: a standing personnel tag, a district leaving tag and a frequent visit area tag; the profile label of the presence category includes: in a preset time, tags which are not present for a preset number of times in the same image acquisition device or the same area are generated; the profile label of the affinity category includes: tags of number of lines with persons of known person identity attributes; the step of determining profile label and/or base attribute information from the portrait profile comprises: and carrying out statistical analysis on the portrait archive to obtain the archive label and/or basic attribute information.

Further, the step of determining the personnel identity attribute of the person to be identified corresponding to the portrait archive according to the corresponding relationship between the archive label and/or the basic attribute information and the personnel identity attribute comprises: determining a target portrait file in the plurality of portrait files according to preset basic attribute information; and matching the file label of the target portrait file with the file label corresponding to the preset basic attribute information in the corresponding relation, and determining the personnel identity attribute of the personnel to be identified corresponding to the target portrait file according to the matching result.

Further, after obtaining the person identity attribute of the person to be identified corresponding to the portrait archive, the method further includes: dividing a plurality of portrait files with determined personnel identity attributes to obtain a portrait file set with personnel identity attribute information; taking the personnel identity attribute information of the portrait archive set as the group identity attribute of the personnel group corresponding to the portrait archive set; and/or carrying out multi-dimensional analysis on the portrait archives in the portrait archive set to obtain population characteristics of the personnel population; the multi-dimensional analysis includes at least one of: basic attribute analysis, archival label analysis, time dimension analysis, location dimension analysis, and affinity dimension analysis.

Further, the method further comprises: carrying out group identification on the personnel in the target personnel group corresponding to the target portrait archive set based on the group discovery conditions to obtain a personnel group; the target portrait archive set is a subset of the portrait archive set.

Further, the subset is a portrait archive set matched with a preset group identity attribute and/or a preset group characteristic in the portrait archive set.

Further, the step of carrying out group identification on the persons in the target person group corresponding to the target person image archive set based on the group discovery condition includes: determining an affinity between target persons in the target person population; the target person is any two persons in the target person group; if the intimacy between the target persons is greater than a preset intimacy threshold value, determining that the target persons are related persons; constructing a relation chain by taking the relation personnel as nodes; determining a target relationship chain among the relationship chains; the target relation chain is any one of the relation chains; and if the number of the nodes of the target relationship chain is greater than a preset threshold value, taking the related personnel corresponding to the nodes of the target relationship chain as personnel in a personnel group, and further obtaining the personnel group.

Further, the method further comprises: determining an intimacy between a person in the group of people and a person outside the group of people based on the portrait archive of the person in the group of people and the portrait archive of the person outside the group of people; and determining marginal personnel of the personnel group according to the intimacy.

Further, the method further comprises: carrying out multi-dimensional analysis on the portrait archives corresponding to the personnel groups to obtain group characteristics of the personnel groups; the multi-dimensional analysis includes at least one of: basic attribute analysis, archive label analysis, time dimension analysis, place dimension analysis and affinity dimension analysis; and determining a target personnel group in the personnel groups according to preset group characteristics.

In a second aspect, an embodiment of the present invention further provides a device for determining a person identity attribute, which is applied to a person analysis system, and includes: the acquisition unit is used for acquiring a portrait file of a person to be identified; the portrait archive at least comprises: the system comprises a portrait snapshot, snapshot time of the portrait snapshot and information of an image acquisition device for snapshot of the portrait snapshot, wherein each portrait file corresponds to a person to be identified; the first determining unit is used for determining the file label and/or basic attribute information according to the portrait file; and the second determining unit is used for determining the personnel identity attribute of the personnel to be identified corresponding to the portrait archive according to the corresponding relation between the archive label and/or the basic attribute information and the personnel identity attribute.

In a third aspect, an embodiment of the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method according to any one of the above first aspects when executing the computer program.

In a fourth aspect, an embodiment of the present invention provides a computer storage medium, on which a computer program is stored, and when the computer program runs on a computer, the computer executes the steps of the method according to any one of the first aspect.

In the embodiment of the invention, a portrait file of a person to be identified is obtained; then, determining archive labels and/or basic attribute information according to the portrait archive; and finally, determining the personnel identity attribute of the personnel to be identified corresponding to the portrait archive according to the corresponding relation between the archive label and/or the basic attribute information and the personnel identity attribute. According to the description, the method provided by the embodiment of the invention can be used for carrying out multi-dimensional analysis on the portrait archive to obtain the archive label and/or the archive basic attribute information, and determining the personnel identity attribute of the personnel to be identified corresponding to the portrait archive based on the corresponding relation between the archive label and/or the basic attribute information and the personnel identity attribute, so that the technical problem that the identity attribute of the personnel is difficult to determine effectively in the prior art is solved.

Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.

Fig. 1 is a schematic diagram of an electronic device according to an embodiment of the present invention;

fig. 2 is a flowchart of a method for determining a personal identity attribute according to an embodiment of the present invention;

fig. 3 is a flowchart of a method for determining a person identity attribute of a person to be identified corresponding to a portrait archive according to an embodiment of the present invention;

FIG. 4 is a flowchart of a method for group recognition of people in a target group of people corresponding to a target portrait archive set according to an embodiment of the present invention;

FIG. 5 is a flow chart of a community screening method according to an embodiment of the present invention;

fig. 6 is a schematic diagram of a device for determining a person identity attribute according to an embodiment of the present invention.

Detailed Description

The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Example 1:

first, an electronic device 100 for implementing an embodiment of the present invention, which may be used to execute the method for determining a person identity attribute according to embodiments of the present invention, is described with reference to fig. 1.

As shown in FIG. 1, electronic device 100 includes one or more processors 102, one or more memories 104, an input device 106, an output device 108, and a camera 110, which are interconnected via a bus system 112 and/or other form of connection mechanism (not shown). It should be noted that the components and structure of the electronic device 100 shown in fig. 1 are exemplary only, and not limiting, and the electronic device may have other components and structures as desired.

The processor 102 may be implemented in at least one hardware form of a Digital Signal Processor (DSP), a Field-Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), and an ASIC (Application Specific Integrated Circuit), and the processor 102 may be a Central Processing Unit (CPU) or other form of Processing Unit having data Processing capability and/or instruction execution capability, and may control other components in the electronic device 100 to perform desired functions.

The memory 104 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc. On which one or more computer program instructions may be stored that may be executed by processor 102 to implement client-side functionality (implemented by the processor) and/or other desired functionality in embodiments of the invention described below. Various applications and various data, such as various data used and/or generated by the applications, may also be stored in the computer-readable storage medium.

The input device 106 may be a device used by a user to input instructions and may include one or more of a keyboard, a mouse, a microphone, a touch screen, and the like.

The output device 108 may output various information (e.g., images or sounds) to the outside (e.g., a user), and may include one or more of a display, a speaker, and the like.

The camera 110 is configured to collect a portrait file of a person to be identified, where the portrait file of the person to be identified collected by the camera is processed by the method for determining the portrait attribute to obtain the portrait attribute of the person to be identified, for example, the camera may capture a portrait desired by a user, and then the portrait is processed by the method for determining the portrait attribute to obtain the portrait attribute of the person corresponding to the portrait, and the camera may further store the captured portrait in the memory 104 for use by other components.

For example, the electronic device for implementing the method for determining the identity attribute of the person according to the embodiment of the present invention may be implemented as a smart mobile terminal such as a smart phone, a tablet computer, or any other device with computing capability.

Example 2:

in accordance with an embodiment of the present invention, there is provided an embodiment of a method for determining a person identity attribute, it should be noted that the steps illustrated in the flowchart of the accompanying drawings may be performed in a computer system such as a set of computer executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.

Fig. 2 is a flowchart of a method for determining a personal identity attribute according to an embodiment of the present invention, as shown in fig. 2, the method includes the following steps:

step S202, acquiring a portrait file of the person to be identified.

In the embodiment of the invention, the method for determining the personnel identity attribute can be applied to a personnel analysis system, the personnel analysis system can be in butt joint with a portrait big data system, the portrait big data system is used for clustering the portrait snapshot of the personnel to be identified, which is collected by an image collection device, into the portrait archive according to the corresponding personnel, and then the personnel analysis system obtains the portrait archive of the personnel to be identified. The person to be identified may be a person whose identity information is known but whose service attribute information is unknown, or may be a person whose identity information and service attribute information are unknown. The identity information refers to name information, age information, identification card number information, occupation information and the like; and the service attribute information refers to information related to a specific service. For example, the service attribute information may be an r service attribute, an s service attribute, a t service attribute, and the like.

The portrait archive at least comprises: the image acquisition device information of taking a candid photograph of portrait snapshot picture, the candid photograph time of portrait snapshot picture and taking a candid photograph of portrait snapshot picture, except that including above-mentioned information, can also include in the portrait archives: the identification method comprises the steps of obtaining a portrait photo, a name corresponding to the portrait photo, an identification number corresponding to the portrait photo, an age corresponding to the portrait photo, a motor vehicle frequently driven by a person to be identified, a mobile phone number of the person to be identified, information (such as an IMEI code, an MAC address and an RFID signal) acquired by a probe and the like.

It should be noted that the number of the portrait files may be multiple, or may be one, and when the number of the portrait files is multiple, each portrait file corresponds to one person to be identified.

Step S204, determining the file label and/or basic attribute information according to the portrait file.

And after obtaining the portrait archive, performing statistical analysis and/or basic attribute analysis on the portrait archive. The statistical analysis may include time dimension analysis of the snapshot time of the portrait snapshot, location dimension analysis of the snapshot location of the portrait snapshot (which may be determined by the image acquisition device information), and intimacy dimension analysis of the intimacy of the people corresponding to different portrait archives, and through the statistical analysis, characteristics (e.g., behavior rule characteristics, activity rule characteristics, contact person characteristics, etc.) of the people to be identified corresponding to the portrait archive may be obtained, and these characteristics may be used as archive labels of the portrait archive corresponding to the people to be identified. In addition, the basic attribute analysis includes analyzing basic attributes of all the portrait snapshots in the portrait file to obtain basic attribute information (for example, gender information, age information, race information, driving or not) of the person to be identified corresponding to the portrait file. The analysis of the underlying attributes of the archive may be performed by a neural network model.

It should be noted that, a portrait archive may correspond to a plurality of archive tags, and each archive tag can represent a feature of the person to be identified corresponding to the portrait archive. In addition, the process of obtaining the archive label through the statistical analysis can be updated according to the setting of the user. For example, before updating, if the number of the snapshot images of the person A shot at night is larger than the number of the snapshot images of the person A shot in the daytime through statistical analysis, it is determined that one of the file labels of the person A is a label of the night; after updating, it needs to be statistically analyzed that when the number of the snap shots of the person a taken at night is greater than the number of the snap shots of the person a taken in the day and the number of the snap shots of the person a taken in the day is less than a preset threshold, it is determined that one of the file labels of the person a is a label that appears around the day. Specifically, the process of determining the archive label can be added or changed according to the business needs, and the process of determining the archive label is not limited by the invention.

And step S206, determining the personnel identity attribute of the personnel to be identified corresponding to the portrait archive according to the corresponding relation between the archive label and/or the basic attribute information and the personnel identity attribute.

During implementation, the personnel identity attribute of the personnel to be identified corresponding to the portrait file can be determined only according to the corresponding relation between the file label and the personnel identity attribute; the personnel identity attribute of the personnel to be identified corresponding to the portrait archive can be determined only according to the corresponding relation between the basic attribute information and the personnel identity attribute, the personnel identity attribute of the personnel to be identified corresponding to the portrait archive can be determined according to the corresponding relation between the archive label and the basic attribute information and the personnel identity attribute, and the personnel identity attribute can be specifically selected according to the requirement.

In addition, the corresponding relations are multiple, and each corresponding relation is the corresponding relation between the permutation and combination of the file labels and/or the basic attribute information and one personnel identity attribute.

The permutation combination may be an intersection of the plurality of archival tags and/or the underlying attribute information. For example, basic attribute information corresponding to r service attributes (identity attributes) is: the vehicle is normally opened for men, and the file label corresponding to the r service attribute is as follows: when the image files frequently appear at a railway station and appear at night in the daytime, namely when file labels of the image files simultaneously comprise the image files frequently appearing at the railway station and appear at night in the daytime, and basic attribute information corresponding to the image files is male and normally open vehicles, determining that the personnel identity attribute of the personnel to be identified corresponding to the image files is r business attribute;

the permutation and combination can also be a union of a plurality of archival tags and/or basic attribute information. For example, the profile label corresponding to the person with w business attribute is: the method comprises the steps that the intimacy degree of persons with the s service attribute is high or the intimacy degree of persons with the v service attribute is high, namely when the file label of the portrait file comprises a label with the intimacy degree of persons with the s service attribute or a label with the intimacy degree of persons with the v service attribute, the personnel identity attribute of a person to be identified corresponding to the portrait file is determined to be the w service attribute;

the permutation and combination may be a complement of the plurality of profile tags and/or the base attribute information. For example, the profile label corresponding to the suspicious person is: and determining the personnel identity attribute of the personnel to be identified corresponding to the portrait archive as suspicious personnel when the label of the daytime night hours is included in the archive label of the portrait archive, but the label of leaving the district is not included (which means in the district).

It should be noted that the correspondence may be set manually through experience (specifically, the correspondence may be obtained by grasping activity rules and behavior characteristics of people with different identity attributes by related people), or may be obtained by performing statistical analysis on portrait archives of people with known identity attributes to obtain basic attribute information and/or archive labels, and performing multidimensional analysis on groups of people with the same identity attributes, where a specific multidimensional analysis means will be described in detail later. The embodiment of the present invention does not limit the determination process of the correspondence relationship.

The foregoing briefly describes the method for determining the identity attribute of a person of the present invention, and the following describes the details of the method.

In this embodiment, determining the basic attribute information according to the portrait archive includes:

determining the file characteristics of the portrait file according to the portrait snapshot in the portrait file; and determining the basic attribute information of the person to be identified corresponding to the portrait archive according to the archive characteristics.

The file characteristics are used for representing the portrait characteristics of the person to be identified corresponding to the portrait snapshot; the basic attribute information includes: at least one of sex information, age information, race information, and whether to drive a car.

In consideration of the fact that the portrait snapshot in the portrait file can reflect the portrait characteristics of the person to be identified, and each portrait snapshot can only reflect part of the portrait characteristics of the person to be identified, the portrait characteristics of all the portrait snapshots in the portrait file need to be fused, so that the file characteristics of the portrait file are obtained.

During implementation, the image characteristic of the portrait snapshot with the best quality in the portrait snapshots can be used as the file characteristic of the portrait file; the image characteristics of the newly shot portrait snapshot in the portrait snapshot can also be used as the file characteristics of the portrait file; the comprehensive characteristics of the plurality of portrait snap shots can also be used as the portrait archive characteristics. When the comprehensive characteristics of a plurality of portrait snapshots are taken as the portrait archive characteristics, a weighted average mode can be adopted, for example, the image quality of the eye part of the portrait snapshot a is the best, the eye part of the portrait snapshot a can be set with a larger weight, the eye parts of other portrait snapshots are set with a smaller weight, the image quality of the nose part of the portrait snapshot b is the best, the nose part of the portrait snapshot b can be set with a larger weight, and the nose parts of other portrait snapshots are set with a smaller weight, so that the weight setting is carried out on each part of the portrait snapshot. And further, after the characteristic values of the multiple portrait snapshots are obtained, carrying out weighted average on the characteristic values of the multiple portrait snapshots according to the set weight, wherein the finally obtained weighted average result is the comprehensive characteristic. The embodiment of the invention does not specifically limit the process of determining the file characteristics of the portrait file, and the file characteristics of the portrait file can be determined in other ways.

In another embodiment, determining the base attribute information from the portrait archive comprises: and determining the basic attribute information of the person to be identified according to the portrait snapshot in the portrait archive.

The method specifically comprises the following steps: performing attribute identification on each portrait snapshot in the portrait archive through an attribute identification model so as to obtain a plurality of basic attribute information corresponding to each portrait snapshot one by one; among the plurality of pieces of basic attribute information, basic attribute information of a person to be identified is determined based on a plurality of pieces of basic attribute information of the same category.

For example, there are 5 portrait snapshots in the portrait archive, after the attribute identification is performed on the 5 portrait snapshots through the attribute identification model, 4 portraits displayed in the 5 portrait snapshots are female, 1 portrait displayed in the 5 portrait snapshots is male, and an age corresponding to each portrait snapshot is obtained at the same time, so that the gender attribute of the person to be identified corresponding to the portrait archive can be determined to be female according to the result, and further, an average value of the ages corresponding to the 5 portrait snapshots is taken as the age attribute of the person to be identified corresponding to the portrait archive.

In this embodiment, the archive label includes: at least one of an abnormal behavior type archive label, a personnel state type archive label, a presence condition type archive label and an affinity type archive label;

the profile label of the abnormal behavior category comprises: a daytime and nighttime outgoing label, a frequent outgoing label, a personnel gathering label and a regional residence label;

the profile tags for the personnel status categories include: a standing personnel tag, a district leaving tag and a frequent visit area tag;

the profile tags for the presence category include: in a preset time, tags which are not present for a preset number of times in the same image acquisition device or the same area are generated;

the profile label for the affinity category includes: tags of number of lines with persons of known person identity attributes;

the step of determining the profile label and/or the base attribute information from the portrait profile includes:

and carrying out statistical analysis on the portrait archive to obtain an archive label and/or basic attribute information.

The archive label may include only the information mentioned above, or may include detailed information such as time and place related thereto. For example, the frequent emergence tag may be only frequent emergence or frequent emergence in X places (e.g., middle customs); the people gathering label can be a people gathering label or a gathering label of N people in X places; the label of the number of times of having the same row with the person with the known person identity attribute may be 5 times of having the same row with the person with the k service attribute, or 4 times of having the same row with the person with the r service attribute, and the like.

The diurnal emission label refers to the number of times of occurrence at night is greater than the number of times of occurrence in the daytime. In implementation, if a person a to be identified is 22: 00-6: 00 are shot more than 6 times: 00-22: 00 times of shooting, determining that one file label of the person A to be identified is daytime and nighttime;

the frequent presence/absence tag is that the number of times of presence/absence exceeds Z times in a certain area within a certain time. In implementation, it may be configured that if the number of times that a person a to be identified is photographed by a camera in the central customs area (the area includes A, B, C, D, E5 cameras) is more than Z times in the time of day, it is determined that one profile label of the person a to be identified is frequently appeared or is frequently appeared in the central customs area;

the people gathering label means that people exceeding M people appear in a certain area within a certain time. In implementation, if the number of people shot by the camera in the Y area in 3 hours exceeds M, determining that one file label of the M people is gathered for people or gathered for people in the Y area;

the zone resident label means that a person continuously appears in a certain zone for a certain time. In the implementation, if the person a to be identified is continuously shot by the camera in the P area for 5 hours, it may be configured to determine that one file label of the person a to be identified is the area residence or the residence in the P area;

the frequent personnel tags refer to that the frequency of occurrence in a set area is more than Q times within a period of time. In implementation, it may be configured that if the number of times that the person a to be identified is photographed by the camera in the hai lake area of beijing is more than Q times in half a year, determining that one file label of the person a to be identified is a standing person or a person in the hai lake area;

the above-mentioned label of leaving the jurisdiction means that within a period of time, continuous O days do not appear in the setting jurisdiction. During implementation, it can be configured that if a person A to be identified is not shot by a camera in the area L within one month for O days continuously, it is determined that one file label of the person A to be identified is leaving the area L or leaving the area L;

the frequent visit zone label means that the number of days that the number of times of the visitation and the disappearance exceeds R times is more than S days in a certain zone for a certain time. In this case, it may be configured that if the number of times that the person a to be identified is captured by the camera in the lake area exceeds R times is greater than S days in a period of two months, it is determined that one file label of the person a to be identified is the regular visit area or the regular visit lake area.

In this embodiment, referring to fig. 3, an example of determining the personal identity attribute of the person to be identified corresponding to the portrait archive by using the correspondence between the combination of the archive label and the basic attribute information and the personal identity attribute specifically includes the following steps:

step S301, determining a target portrait file in a plurality of portrait files according to preset basic attribute information.

The preset basic attribute information may be basic attribute information that is relatively interested by the user, or basic attribute information related to the identity attribute that is interested by the user, and may be specifically set as required. The step S301 is mainly used to narrow the analysis range of the portrait file.

For example, if the basic attribute information is preset to be male and normally open car, then the basic attribute information is determined to be male and the portrait file of the normally open car is determined to be the target portrait file in the plurality of portrait file numbers.

Step S302, the file label of the target portrait file is matched with the file label corresponding to the preset basic attribute information in the corresponding relation, and the personnel identity attribute of the personnel to be identified corresponding to the target portrait file is determined according to the matching result.

Therefore, the target portrait file is determined, on one hand, the analysis range of the portrait file is narrowed, and on the other hand, the finally determined personnel identity attribute can be more accurate.

This process is described below by way of an example:

if the basic attribute information corresponding to the r service attribute (identity attribute) is: the vehicle is normally opened for men, and the file label corresponding to the r service attribute is as follows: if the person frequently appears at the railway station and appears at daytime and nighttime, all the portrait files are analyzed, the person identity attributes of the persons to be identified corresponding to the portrait files with daytime and nighttime appearance tags in the file tags and with frequent appearance at the railway station are determined as the identities of the r business attributes, and actually, the persons with the daytime and nighttime appearance tags and the person frequently appearing at the railway station tags not only have the r business attributes, but also possibly have the u business attributes (such as cleaning personnel). If the target portrait files of the male and the normally-open vehicle are determined in all the portrait files, then the target portrait files are analyzed, and the personnel identity attributes of the personnel to be identified corresponding to the portrait files with the daytime and nighttime appearance labels and the portrait files frequently absent from the railway station labels in the file labels are determined as the r business attributes, so that the personnel identity attributes determined to be obtained are relatively more accurate.

In addition, during specific implementation, a plurality of portrait files can be filtered through preset basic attribute information to obtain a target portrait file, and then the personnel identity attribute of the personnel to be identified is determined according to the file label of the target portrait file; or filtering the personnel identity attribute according to the file label of the portrait archive to obtain a plurality of personnel identity attributes corresponding to the file label of the portrait archive, and then determining the unique personnel identity attribute according to the preset basic attribute information. For example, possible personnel identity attributes determined from the profile tag include: the u service attribute (such as cleaning personnel) and the r service attribute, and basic attribute information of men and normally open vehicles are added, so that the identity attribute of the personnel can be determined to be the r service attribute.

In this embodiment, after obtaining the person identity attribute of the person to be identified corresponding to the portrait archive, the method further includes the following steps (1) and (2):

(1) dividing a plurality of portrait files with determined personnel identity attributes to obtain a portrait file set with personnel identity attribute information;

(2) taking the personnel identity attribute information of the portrait archive set as the group identity attribute of the personnel group corresponding to the portrait archive set; and/or carrying out multi-dimensional analysis on the portrait archives in the portrait archive set to obtain the group characteristics of the personnel groups.

Wherein the multidimensional analysis comprises at least one of: basic attribute analysis, archival label analysis, time dimension analysis, location dimension analysis, and affinity dimension analysis.

The portrait file with the determined personnel identity attribute may be a portrait file with the personnel identity attribute determined at the present moment according to the method of the present invention, may also be a portrait file with the previously determined personnel identity attribute, and may also be a portrait file with a known personnel identity attribute.

When the portrait archive is divided, the portrait archives corresponding to the same personnel identity attribute are divided together to obtain a portrait archive set with personnel identity attribute information, the personnel identity attribute information of the portrait archive set is used as the group identity attribute of the personnel group corresponding to the portrait archive set, and the personnel group corresponding to the portrait archive set is subjected to multi-dimensional analysis to obtain the group characteristics of the personnel group.

The multi-dimensional analysis includes at least one of: basic attribute analysis, archival label analysis, time dimension analysis, location dimension analysis, and affinity dimension analysis. Correspondingly, the group characteristics comprise basic attribute information, archive labels, appearance time characteristics, location characteristics, identity attribute characteristics of persons in the person group (if the persons in the person group are usually shot in an area A at 6: 00-8: 00 and shot in an area B at 17: 00-19: 00; the persons in the person group are usually driven, and the intimacy score between the persons in the person group and the persons with the r business attribute is higher than a threshold value), and the like. Multidimensional analysis is performed on the population of the people, and features or rules which are not obvious in the dimension of the single people can be highlighted to serve as population features. After the group characteristics are obtained, the group characteristics can be used as a new archive label to form a closed loop with the scheme for determining the personnel identity attribute according to the archive label, so that the personnel identity attribute determined subsequently based on the new archive label and the previous archive label is more accurate; and determining a target personnel group matched with the preset group characteristics in the plurality of personnel groups according to the preset group characteristics.

In addition, the basic attribute analysis in the multidimensional analysis is actually the basic attribute of the personnel of the statistical personnel group, and the archival label analysis in the multidimensional analysis is actually the archival label of the personnel of the statistical personnel group.

It should be noted that the portrait archive set with the personnel identity attribute information also supports manual batch addition of portrait archives or single addition of portrait archives (the personnel identity attribute of the added portrait archive matches with the group identity attribute information of the portrait archive set). In addition, along with the change of the corresponding relation between the file label and the personnel identity attribute, the obtained portrait file set and the personnel group are also updated.

The above description introduces the process of determining the identity attribute of the person and the process of dividing the person group, and the screening process of the person group is described in detail below.

In an embodiment of the present invention, after obtaining the portrait archive set, the method further includes: carrying out group identification on the personnel in the target personnel group corresponding to the target portrait archive set based on the group discovery conditions to obtain a personnel group; the target portrait archive set is a subset of the portrait archive set, and the subset is a portrait archive set matched with the preset group identity attribute and/or the preset group characteristic in the portrait archive set.

The preset group identity attribute is a person identity attribute concerned by or interested in the user, and the preset group characteristic is a person group characteristic concerned by or interested in the user.

Specifically, referring to fig. 4, the step of performing group identification on the person in the target person group corresponding to the target portrait archive set based on the group discovery condition includes:

step S401, determining the intimacy between target persons in a target person group; wherein the target personnel are any two personnel in the target personnel group;

step S402, if the intimacy between the target persons is greater than a preset intimacy threshold, determining the target persons as relationship persons;

step S403, constructing a relation chain by taking the relation personnel as nodes;

step S404, determining a target relation chain in the relation chains; wherein, the target relation chain is any relation chain in the relation chains;

step S405, if the number of the nodes of the target relationship chain is larger than a preset threshold value, the related personnel corresponding to the nodes of the target relationship chain are used as personnel in the personnel group, and then the personnel group is obtained.

And determining the intimacy between the target persons according to the times of the same rows of the target persons and the same row occasions. The number of times of the same line is not particularly limited, and may be that the same camera captures the same line once at the same time, or that two persons capture the same line once within a certain time range (for example, within 15 s) by the same camera, or that two persons capture the same line once within a certain distance range (for example, within 10m) at the same time. Two siblings occurring within a certain time frame (e.g., within half an hour) may also be considered as one sibling to avoid double counting. In one example, target persons a and B are traveling 15 times a day, wherein 5 times are separated by more than half an hour, 10 times are separated by less than half an hour, and affinity between a and B is 5 (i.e., affinity score of a and B is 5), and 10 times are not counted separately by less than half an hour from the 5 times. In addition, different weights may be set for different peer occasions, for example, the weight set in the peer of the hotel is w1, the weight set in the peer of the cell is w2, and the like, so when the analysis results that a and B are in the peer of the hotel n times, and the peer in the cell m times, the obtained affinity is determined as: w1 × n + w2 × m. In determining the intimacy degree, various implementation manners may be specifically provided, and the embodiment of the present invention does not limit the implementation manners.

After the intimacy between the target persons is obtained, whether the intimacy between the target persons is larger than a preset intimacy threshold value or not is further judged, if the intimacy between the target persons is larger than the preset intimacy threshold value, the target persons are determined to be relatives, and relationship chains are constructed by taking the relatives as nodes.

Therefore, a plurality of relation chains can be constructed, each target relation chain in the plurality of relation chains is traversed, and if the number of nodes of the target relation chain is greater than a preset threshold value, the relation personnel corresponding to the nodes of the target relation chain are used as personnel in the personnel group, so that the personnel group is obtained. The embodiment of the present invention does not specifically limit the process of determining the group of people, and may have other implementation manners.

In the practical application process, along with the increase of the portrait snapshot, the degree of intimacy in front of the target person in the target person group can also change in real time. The group discovery conditions may be used to periodically perform group recognition on target persons in the target person group.

Due to the continuous update and increase of the personnel in the personnel group, the intimacy between the target personnel in the target personnel group can be continuously updated, and the member composition and the relationship network of the personnel group determined in the way can continuously approach the real world.

In addition, after the personnel group is obtained, the group personnel can be manually added in the personnel group, so that the personnel group is closer to the real physical world.

In this embodiment, after obtaining the group of people, the method further includes the following processes (i) and (ii):

(i) determining the intimacy between the personnel in the personnel group and the personnel outside the personnel group based on the portrait archive of the personnel in the personnel group and the portrait archive of the personnel outside the personnel group;

(ii) and determining marginal persons of the person group according to the intimacy.

The edge personnel can be personnel in the personnel group or not, the personnel are determined to be the edge personnel of the personnel group as long as the intimacy between the edge personnel and the personnel in the personnel group is greater than a preset threshold value, and the process can dig out the personnel which are not in the group but have close relationship with the group in the group, so that the deep digging and line expansion of the personnel group are realized.

In this embodiment, after obtaining the group of people, the method further includes the following processes 1) and 2):

1) carrying out multi-dimensional analysis on portrait files corresponding to the personnel groups to obtain group characteristics of the personnel groups; wherein the multidimensional analysis comprises at least one of: basic attribute analysis, archive label analysis, time dimension analysis, place dimension analysis and affinity dimension analysis;

2) and determining a target group of people in the group of people according to the preset group characteristics.

The multi-dimensional analysis includes at least one of: basic attribute analysis, archival label analysis, time dimension analysis, location dimension analysis, and affinity dimension analysis. Correspondingly, the group characteristics comprise basic attribute information, profile labels, appearance time characteristics, location characteristics, identity attribute characteristics of persons in the person group (if the persons in the person group are usually shot in a C area at 7: 00-9: 00, 18: 00-20: 00 in a D area, and the persons in the person group are usually in a motor vehicle, and the intimacy score of the persons in the person group and the person with the r identity attribute is higher than a threshold value), and the like.

After the group characteristics are obtained, a target person group matched with the preset group characteristics can be determined in the plurality of person groups according to the preset group characteristics. The preset community characteristics may be community characteristics of persons concerned or interested by the user.

The method for determining the personnel identity attribute of the embodiment of the invention divides the personnel into different groups based on the identified personnel identity attribute on the basis of determining the personnel identity attribute, then carries out research and judgment analysis on the groups formed by the same type of personnel, determines the target personnel group (namely suspected s group) from the personnel groups, discovers the closely-connected personnel group (such as a group in the s group) in the target personnel group based on the group discovery condition, and provides a plurality of means for researching and judgment analysis of the personnel group, thereby greatly improving the efficiency of discovering the personnel group by related departments and realizing the automatic research and judgment analysis of big data.

Example 3:

in accordance with an embodiment of the present invention, there is provided an embodiment of a community screening method, it should be noted that the steps illustrated in the flowchart of the figure may be performed in a computer system such as a set of computer executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.

Fig. 5 is a flowchart of a community screening method according to an embodiment of the present invention, as shown in fig. 5, the method includes the following steps:

step S501, acquiring a portrait file of a person to be identified; the portrait archive at least includes: the method comprises the following steps that a portrait snapshot image, snapshot time of the portrait snapshot image and information of an image acquisition device for snapshot of the portrait snapshot image are obtained, and each portrait file corresponds to a person to be identified;

step S502, determining archive labels and/or basic attribute information according to the portrait archive;

step S503, determining the personnel identity attribute of the personnel to be identified corresponding to the portrait archive according to the corresponding relation between the archive label and/or the basic attribute information and the personnel identity attribute;

step S504, a plurality of portrait files with determined personnel identity attributes are divided to obtain a portrait file set with personnel identity attribute information;

step S505, carrying out group identification on the personnel in the target personnel group corresponding to the target portrait archive set based on the group discovery conditions to obtain a personnel group; the target portrait archive set is a subset of the portrait archive set, and the subset is a portrait archive set matched with the preset group identity attribute and/or the preset group characteristic in the portrait archive set.

It should be noted that, in the steps involved in the group screening method in embodiment 3, the steps involved in the method for determining the personnel identity attribute in embodiment 2 are the same, and are not described again, and the contents described in embodiment 2 above can be used in this embodiment 3.

Example 4:

the embodiment of the present invention further provides a device for determining a person identity attribute, where the device for determining a person identity attribute is mainly used to execute the method for determining a person identity attribute provided in the foregoing content of the embodiment of the present invention, and the device for determining a person identity attribute provided in the embodiment of the present invention is described in detail below.

Fig. 6 is a schematic diagram of a device for determining a personal identity attribute according to an embodiment of the present invention, and as shown in fig. 6, the device for determining a personal identity attribute mainly includes: an acquisition unit 10, a first determination unit 20 and a second determination unit 30, wherein:

the acquisition unit is used for acquiring a portrait file of a person to be identified; the portrait archive at least includes: the method comprises the following steps that a portrait snapshot image, snapshot time of the portrait snapshot image and information of an image acquisition device for snapshot of the portrait snapshot image are obtained, and each portrait file corresponds to a person to be identified;

the first determining unit is used for determining the file label and/or the basic attribute information according to the portrait file;

and the second determining unit is used for determining the personnel identity attribute of the personnel to be identified corresponding to the portrait archive according to the corresponding relation between the archive label and/or the basic attribute information and the personnel identity attribute.

In the embodiment of the invention, a portrait file of a person to be identified is obtained; then, determining archive labels and/or basic attribute information according to the portrait archive; and finally, determining the personnel identity attribute of the personnel to be identified corresponding to the portrait archive according to the corresponding relation between the archive label and/or the basic attribute information and the personnel identity attribute. According to the description, the method can determine the personnel identity attribute of the personnel to be identified corresponding to the portrait archive based on the corresponding relation between the portrait archive, the archive label and/or the basic attribute information and the personnel identity attribute, and the identity attribute of the personnel in the anonymous photo library can be determined in the process; in addition, the process can also obtain the identity information of the personnel to be identified and the service attribute information of the personnel to be identified according to the information of the personnel identity attribute in the corresponding relationship, and the technical problem that the identity attribute of the personnel is difficult to be effectively determined in the prior art is solved.

Optionally, the profile tag comprises: at least one of an abnormal behavior type archive label, a personnel state type archive label, a presence condition type archive label and an affinity type archive label; the profile label of the abnormal behavior category comprises: a daytime and nighttime outgoing label, a frequent outgoing label, a personnel gathering label and a regional residence label; the profile tags for the personnel status categories include: a standing personnel tag, a district leaving tag and a frequent visit area tag; the profile tags for the presence category include: in a preset time, tags which are not present for a preset number of times in the same image acquisition device or the same area are generated; the profile label for the affinity category includes: tags of number of lines with persons of known person identity attributes; the first determining unit is further configured to perform statistical analysis on the portrait archive to obtain an archive label and/or basic attribute information.

Optionally, the second determining unit is further configured to: determining a target portrait file in a plurality of portrait files according to preset basic attribute information; and matching the file label of the target portrait file with the file label corresponding to the preset basic attribute information in the corresponding relation, and determining the personnel identity attribute of the personnel to be identified corresponding to the target portrait file according to the matching result.

Optionally, the apparatus is further configured to: dividing a plurality of portrait files with determined personnel identity attributes to obtain a portrait file set with personnel identity attribute information; taking the personnel identity attribute information of the portrait archive set as the group identity attribute of the personnel group corresponding to the portrait archive set; and/or carrying out multi-dimensional analysis on the portrait archives in the portrait archive set to obtain population characteristics of the personnel population; the multi-dimensional analysis includes at least one of: basic attribute analysis, archival label analysis, time dimension analysis, location dimension analysis, and affinity dimension analysis.

Optionally, the apparatus is further configured to: carrying out group identification on the personnel in the target personnel group corresponding to the target portrait archive set based on the group discovery conditions to obtain a personnel group; the set of target portrait profiles is a subset of the set of portrait profiles.

Optionally, the subset is a portrait archive set matched with the preset group identity attribute and/or the preset group characteristic in the portrait archive set.

Optionally, the apparatus is further configured to: determining the intimacy between the target persons in the target person group; the target person is any two persons in the target person group; if the intimacy between the target persons is greater than a preset intimacy threshold, determining the target persons as the related persons; constructing a relation chain by taking the relation personnel as nodes; determining a target relationship chain in the relationship chain; the target relation chain is any relation chain in the relation chains; and if the number of the nodes of the target relationship chain is greater than the preset threshold value, taking the related personnel corresponding to the nodes of the target relationship chain as personnel in the personnel group, and further obtaining the personnel group.

Optionally, the apparatus is further configured to: determining the intimacy between the personnel in the personnel group and the personnel outside the personnel group based on the portrait archive of the personnel in the personnel group and the portrait archive of the personnel outside the personnel group; and determining marginal persons of the person group according to the intimacy.

Optionally, the apparatus is further configured to: carrying out multi-dimensional analysis on portrait files corresponding to the personnel groups to obtain group characteristics of the personnel groups; the multi-dimensional analysis includes at least one of: basic attribute analysis, archive label analysis, time dimension analysis, place dimension analysis and affinity dimension analysis; and determining a target group of people in the group of people according to the preset group characteristics.

The device provided by the embodiment of the present invention has the same implementation principle and technical effect as the method embodiments, and for the sake of brief description, reference may be made to the corresponding contents in the method embodiments without reference to the device embodiments.

In another implementation of the present invention, there is further provided a computer storage medium having a computer program stored thereon, the computer program, when executed by a computer, performing the steps of the method of any one of the above method embodiments 2.

In addition, in the description of the embodiments of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.

In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for determining personnel identity attribute is applied to a personnel analysis system and comprises the following steps:

acquiring a portrait file of a person to be identified; the portrait archive at least comprises: the system comprises a portrait snapshot, snapshot time of the portrait snapshot and information of an image acquisition device for snapshot of the portrait snapshot, wherein each portrait file corresponds to a person to be identified;

determining archive labels and/or basic attribute information according to the portrait archive;

and determining the personnel identity attribute of the personnel to be identified corresponding to the portrait archive according to the corresponding relation between the archive label and/or the basic attribute information and the personnel identity attribute.

2. The method of claim 1, wherein the profile tag comprises: at least one of an abnormal behavior type archive label, a personnel state type archive label, a presence condition type archive label and an affinity type archive label;

the profile label of the personnel status category comprises: a standing personnel tag, a district leaving tag and a frequent visit area tag;

the profile label of the presence category includes: in a preset time, tags which are not present for a preset number of times in the same image acquisition device or the same area are generated;

the profile label of the affinity category includes: tags of number of lines with persons of known person identity attributes;

the step of determining profile label and/or base attribute information from the portrait profile comprises:

and carrying out statistical analysis on the portrait archive to obtain the archive label and/or basic attribute information.

3. The method according to claim 1 or 2, wherein the step of determining the personnel identity attribute of the person to be identified corresponding to the portrait archive according to the correspondence between the archive label and/or the basic attribute information and the personnel identity attribute comprises:

determining a target portrait file in the plurality of portrait files according to preset basic attribute information;

and matching the file label of the target portrait file with the file label corresponding to the preset basic attribute information in the corresponding relation, and determining the personnel identity attribute of the personnel to be identified corresponding to the target portrait file according to the matching result.

4. The method according to any one of claims 1-3, wherein after obtaining the person identity attribute of the person to be identified corresponding to the portrait archive, the method further comprises:

dividing a plurality of portrait files with determined personnel identity attributes to obtain a portrait file set with personnel identity attribute information;

taking the personnel identity attribute information of the portrait archive set as the group identity attribute of the personnel group corresponding to the portrait archive set; and/or carrying out multi-dimensional analysis on the portrait archives in the portrait archive set to obtain population characteristics of the personnel population;

the multi-dimensional analysis includes at least one of: basic attribute analysis, archival label analysis, time dimension analysis, location dimension analysis, and affinity dimension analysis.

5. The method of claim 4, further comprising:

carrying out group identification on the personnel in the target personnel group corresponding to the target portrait archive set based on the group discovery conditions to obtain a personnel group; the target portrait archive set is a subset of the portrait archive set.

6. The method of claim 5, wherein the subset is a set of portrait profiles of the set of portrait profiles that match a predetermined group identity attribute and/or a predetermined group characteristic.

7. The method of claim 5, wherein the step of performing group recognition on the persons in the target person group corresponding to the target portrait archive set based on the group discovery condition comprises:

determining an affinity between target persons in the target person population; the target person is any two persons in the target person group;

if the intimacy between the target persons is greater than a preset intimacy threshold value, determining that the target persons are related persons;

constructing a relation chain by taking the relation personnel as nodes;

determining a target relationship chain among the relationship chains; the target relation chain is any one of the relation chains;

and if the number of the nodes of the target relationship chain is greater than a preset threshold value, taking the related personnel corresponding to the nodes of the target relationship chain as personnel in a personnel group, and further obtaining the personnel group.

8. The method of claim 7, further comprising:

determining an intimacy between a person in the group of people and a person outside the group of people based on the portrait archive of the person in the group of people and the portrait archive of the person outside the group of people;

and determining marginal personnel of the personnel group according to the intimacy.

9. The method of claim 7, further comprising:

carrying out multi-dimensional analysis on the portrait archives corresponding to the personnel groups to obtain group characteristics of the personnel groups; the multi-dimensional analysis includes at least one of: basic attribute analysis, archive label analysis, time dimension analysis, place dimension analysis and affinity dimension analysis;

and determining a target personnel group in the personnel groups according to preset group characteristics.

10. A personnel identity attribute determination device is applied to a personnel analysis system and comprises:

the acquisition unit is used for acquiring a portrait file of a person to be identified; the portrait archive at least comprises: the system comprises a portrait snapshot, snapshot time of the portrait snapshot and information of an image acquisition device for snapshot of the portrait snapshot, wherein each portrait file corresponds to a person to be identified;

the first determining unit is used for determining the file label and/or basic attribute information according to the portrait file;

11. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of the preceding claims 1 to 9 when executing the computer program.

12. A computer storage medium, having a computer program stored thereon, which, when executed by a computer, performs the steps of the method of any of claims 1 to 9.