CN111476685B - Behavior analysis method, device and equipment - Google Patents

Abstract

Embodiments of the present invention provide a behavior analysis method, device and equipment. The method includes: performing stranger face image recognition on face data collected by at least one image acquisition device within a preset time period, the face data including face images, collection time information and collection location information; The face images of strangers are clustered to obtain face data belonging to the same stranger; a graph database is constructed according to the face data of each stranger; and abnormal behaviors of strangers are identified according to the graph database. The method of the embodiment of the present invention realizes the analysis of the stranger's behavior based on the collected face data, and discovers the abnormal behavior of the stranger in time, thereby improving the security of the community.

Description

Behavior analysis method, device and equipment

technical field

The invention relates to the technical field of community security, in particular to a behavior analysis method, device and equipment.

Background technique

The city is the product of the development of human civilization, and the community is its most basic component. As the carrier of the survival and development of urban residents, the safety index of the community is the core of residents' attention. However, with the continuous improvement of the level of social development, the rise of third-party service industries such as express delivery and food delivery has led to the influx of a large number of strangers into the originally relatively closed community every day. Lawbreakers may mix in, posing a certain threat to the personal safety and property safety of community residents.

As a new concept of community management, smart community has effectively improved the safety index of the community. By installing various sensing devices such as face capture cameras and face access control, collecting face data, combined with artificial intelligence algorithms, the effective screening of resident populations and stranger populations has been realized. However, at present, the behavior analysis of the identified strangers There is no working solution yet. How to analyze the behavior of strangers based on the collected face data and discover abnormal behaviors in time is a problem that needs to be solved urgently.

Contents of the invention

Embodiments of the present invention provide a behavior analysis method, device, and equipment, which can analyze the behavior of strangers based on collected face data, and discover abnormal behaviors of strangers in time.

In a first aspect, an embodiment of the present invention provides a behavior analysis method, including:

Perform face image recognition of strangers on the face data collected by at least one image acquisition device within a preset time period, the face data including face images, collection time information and collection location information;

Clustering the face images of the recognized strangers to obtain face data belonging to the same stranger;

Construct a graph database based on the face data of each stranger;

Abnormal behavior of strangers is identified based on the graph database.

In one embodiment, the face image recognition of strangers is performed on the face data collected by at least one image acquisition device within a preset time period, including:

Match the collected face data with the resident face database;

If the matching fails, the face data is that of a stranger.

In one embodiment, the graph database is constructed according to the face data of each stranger, including:

Each stranger is identified as a first vertex, the first vertex includes identity information; the collection device located at each collection location is identified as a second vertex, the second vertex includes collection location information, and the collection location includes at least The entrance of the area and the exit of the area; an edge between the first vertex and the second vertex corresponds to a piece of face data, and the edge includes collection time information.

In one embodiment, identifying the abnormal behavior of strangers according to the graph database includes:

If the number of edges between a vertex of a stranger in the graph database and the vertex of the collection device at the entrance of the area is greater than the preset frequency threshold, the behavior of the stranger is identified as the first type of abnormal behavior, and the first type of abnormal behavior is used to indicate that the stranger People frequently enter the area.

In one embodiment, identifying the abnormal behavior of strangers according to the graph database includes:

If β2-β1>α, where β1 is the collection time represented by the edge between a stranger vertex in the graph database and the collection device vertex at the area entrance, β2 is the stranger vertex in the graph database and the collection device vertex at the area exit The acquisition time represented by the side between, α is the preset residence time threshold, the behavior of the stranger is identified as the second type of abnormal behavior, and the second type of abnormal behavior is used to indicate that the stranger stays in the area for a long time.

In one embodiment, identifying the abnormal behavior of strangers according to the graph database includes:

If there is an edge between a stranger vertex and the second vertex in the graph database within the preset abnormal time period, the behavior of the stranger is identified as the third type of abnormal behavior, and the third type of abnormal behavior is used to instruct the stranger Enter and exit the corresponding area during the abnormal time period.

In one embodiment, the method also includes:

If the abnormal behavior is identified, the abnormal information will be sent to the relevant workers. The abnormal information includes the picture information of the stranger, the time information of the abnormal behavior and the reason for the abnormal behavior.

In a second aspect, an embodiment of the present invention provides a behavior analysis device, including:

A recognition module, configured to perform stranger face image recognition on face data collected by at least one image capture device within a preset time period, the face data including face images, collection time information and collection location information;

The clustering module is used to cluster the face images of the identified strangers to obtain face data belonging to the same stranger;

A building block for constructing a graph database based on face data of each stranger;

An analysis module for identifying abnormal behaviors of strangers based on graph databases.

In a third aspect, an embodiment of the present invention provides a behavior analysis device, including:

at least one processor and memory;

the memory stores computer-executable instructions;

At least one processor executes the computer-implemented instructions stored in the memory, so that the at least one processor executes the behavior analysis method according to any one of the first aspect.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by a processor, they are used to implement any one of the first aspect. The behavioral analysis method described above.

The behavior analysis method, device and equipment provided by the embodiments of the present invention can not only greatly reduce the amount of data processing and improve the efficiency of data processing, but also make the behavior The analysis is more targeted; then cluster the face data of the identified strangers, obtain the face data belonging to the same stranger, and build a graph database based on the face data of each stranger, using the graph database vertices and The edge relationship vividly reflects the relationship between strangers and different acquisition devices at different times; finally, the abnormal behavior of strangers is identified according to the graph database, and the behavior of strangers can be quickly and effectively analyzed based on the graph database, realizing Based on the collected face data, the behavior of strangers is analyzed to detect abnormal behaviors of strangers in time, which can improve the security of the community. .

Description of drawings

Fig. 1 is a flowchart of a behavior analysis method provided by an embodiment of the present invention;

2 is a flowchart of a method for identifying face data of strangers provided by an embodiment of the present invention;

FIG. 3 is a partial schematic diagram of a graph database provided by an embodiment of the present invention;

Fig. 4 is a schematic structural diagram of a behavior analysis device provided by an embodiment of the present invention;

Fig. 5 is a schematic structural diagram of a behavior analysis device provided by an embodiment of the present invention.

Detailed ways

The present invention will be further described in detail below through specific embodiments in conjunction with the accompanying drawings. Wherein, similar elements in different implementations adopt associated similar element numbers. In the following implementation manners, many details are described for better understanding of the present application. However, those skilled in the art can readily recognize that some of the features can be omitted in different situations, or can be replaced by other elements, materials, and methods. In some cases, some operations related to the application are not shown or described in the description, this is to avoid the core part of the application being overwhelmed by too many descriptions, and for those skilled in the art, it is necessary to describe these operations in detail Relevant operations are not necessary, and they can fully understand the relevant operations according to the description in the specification and general technical knowledge in the field.

In addition, the characteristics, operations or characteristics described in the specification can be combined in any appropriate manner to form various embodiments. At the same time, the steps or actions in the method description can also be exchanged or adjusted in a manner obvious to those skilled in the art. Therefore, the various sequences in the specification and drawings are only for clearly describing a certain embodiment, and do not mean a necessary sequence, unless otherwise stated that a certain sequence must be followed.

The serial numbers assigned to components in this document, such as "first", "second", etc., are only used to distinguish the described objects, and do not have any sequence or technical meaning. The "connection" and "connection" mentioned in this application all include direct and indirect connection (connection) unless otherwise specified.

The behavior analysis method provided by the embodiments of the present invention can be used not only in smart communities, but also in smart parks, smart factories, smart campuses and other scenarios where facial data collection devices are installed. In these scenarios, the face data can be collected by the collection device. The following will illustrate how to identify the abnormal behavior of strangers based on the collected face data and issue a timely alarm to improve security through specific embodiments.

FIG. 1 is a flowchart of a behavior analysis method provided by an embodiment of the present invention. As shown in Figure 1, the behavior analysis method provided in this embodiment may include:

S101. Perform face image recognition of strangers on face data collected by at least one image collection device within a preset time period, where the face data includes face images, collection time information, and collection location information.

The face data collected in this embodiment may come from different collection devices. Taking a smart community as an example, multiple cameras are usually installed in multiple locations to collect face data at different locations. The face data collected in this embodiment Face data may include face data collected by all collection devices. Face data may include face image information, collection time information, and collection location information. Wherein, the face image information can be a color picture or a grayscale picture, and can also be video information, which is not limited in this embodiment; the collection time information is used to record the collection time of the face image information; the collection location information is used to identify the person The collection position of the face image information can be represented by, for example, the serial number of the collection device.

In order to be able to perform early warning, in this embodiment, face data can be recognized in real time. The so-called strangers are relative to the resident population. For a smart community, the residents in the community are the resident population; for a smart campus, the students and teachers in the campus are the resident population; for a smart factory, the workers in the factory are the resident population. For the collected face data, a face recognition method can be used to identify the stranger face data therein.

Please refer to Fig. 2, in an optional implementation manner, identifying stranger face data from collected face data may include:

S1011. Determine whether the collected face data matches the resident face database. If the matching fails, execute S1012; otherwise, execute S1013.

In this embodiment, a resident face database needs to be created in advance, and the resident face database includes face images of the resident population. The resident face database can be created according to specific application scenarios. For a smart community, the face images of residents in the community are collected to create a resident face database; for a smart campus, the face images of students and teachers in the campus are collected. Face images are used to create a resident face database; for smart factories, face images of workers in the factory are collected to create a resident face database. And the resident face database needs to be updated in time according to the changes of the resident population, so as not to identify the resident population as strangers. In this embodiment, methods such as template matching and machine learning may be used to match the collected face data with the face data in the resident face database.

S1012. Determine that the face data is face data of a stranger.

S1013. Determine that the face data is the face data of the resident population.

It is understandable that there are far more resident face data in the collected face data than stranger face data. By identifying the collected face data, the data is divided into resident face data and stranger face data. Follow-up only conducts further behavioral analysis on the face data of strangers to identify abnormal behaviors of strangers, which can not only greatly reduce the amount of data processing, improve data processing efficiency, but also make behavioral analysis more targeted.

S102. Clustering the recognized face data of strangers to obtain face data belonging to the same stranger.

The stranger face data identified from the collected face data may come from different strangers, and it is meaningless to analyze it directly. The face data of strangers are clustered to obtain the face data belonging to the same stranger. An existing clustering method may be used to cluster stranger face data, which is not limited in this embodiment.

By clustering the recognized face data of strangers, multiple clusters can be obtained, for example, it can be determined that the face data belonging to one cluster belong to the same stranger. To further improve the accuracy, face data far away from the cluster center can be filtered out. The face data collected by different collection devices at different times belonging to the same stranger reflects the stranger's trajectory. Optionally, for multiple face data of the same stranger, a unique virtual ID can be used to identify the identity information.

S103. Construct a graph database according to the face data of each stranger.

In an optional implementation manner, constructing a graph database according to face data of each stranger may include:

Each stranger is identified as a first vertex, the first vertex includes identity information; the collection device located at each collection location is identified as a second vertex, the second vertex includes collection location information, and the collection location includes at least The entrance of the area and the exit of the area; an edge between the first vertex and the second vertex corresponds to a piece of face data, and the edge includes collection time information. In practical applications, the collection locations may include, for example, community entrances, community exits, building unit door entrances, building unit door exits, key road intersections, and the like.

Please refer to FIG. 3 , which shows a graph database constructed based on face data of a stranger whose ID is 320321. As shown in Figure 3, the thick solid line circle in the center represents the first vertex corresponding to the stranger whose ID is 320321; the thin solid line circles marked 0-4 on the periphery respectively represent the collection equipment (labeled 0) at the entrance of the community, The collection equipment at the exit of the community (labeled 1), the collection equipment at the entrance of the building unit door (labeled 2), the collection equipment at the exit of the building unit door (labeled 3) and the collection equipment at the key road intersection ( Labeled 4) corresponds to the second vertex, each edge between the first vertex and the second vertex corresponds to a face data of a stranger whose ID is 320321, and records the time when the face data is collected. Taking the graph database neo4j as an example, the storage statement is as follows:

Match(p:Persion{id:320321}),(c:Camera{type:0})

Create(p)-[r:Cross{time:20191217080059}]->(c)return p,b

The edge shown by the dotted line will be generated in Figure 3, which is used to indicate that the stranger with ID 320321 walked through the community entrance at 08:00:59 on December 17, 2019.

Through the relationship between the vertices and edges of the graph database, the relationship between strangers and different collection devices at different times can be recorded vividly.

S104. Identify the abnormal behavior of the stranger according to the graph database.

Since the relationship between the vertices and edges of the graph database records the associations between strangers and different collection devices at different times, the abnormal behavior of strangers can be identified by retrieving the relationship between the vertices and edges of the graph database.

Specifically, if the number of edges between a vertex of a stranger in the graph database and the vertex of the collection device at the entrance of the area is greater than the preset frequency threshold, the behavior of the stranger is identified as the first type of abnormal behavior, and the first type of abnormal behavior is used to instruct strangers to frequently enter the area. For example, the preset frequency threshold can be set to N, where N is a positive integer, and the specific value of N can be determined according to statistics, and a larger N means a higher entry frequency. The graph database can be retrieved in batches to obtain the number n of edges between the stranger vertex and the collection device vertex at the community entrance within the preset time period in the graph database, which represents the number of times strangers enter the community within the preset time period; if n>N, it means that the stranger frequently enters the community, and the higher the value, the higher the suspicious behavior index.

If β2-β1>α, where β1 is the collection time represented by the edge between a stranger vertex in the graph database and the collection device vertex at the area entrance, β2 is the stranger vertex in the graph database and the collection device vertex at the area exit The acquisition time represented by the side between, α is the preset residence time threshold, the behavior of the stranger is identified as the second type of abnormal behavior, and the second type of abnormal behavior is used to indicate that the stranger stays in the area for a long time. Wherein, the unit of the set preset residence time threshold α may be seconds. For example, retrieve the edge between the stranger vertex and the collection device vertex at the community entrance within the specified time, which indicates the time β1 when the stranger entered the community; retrieve the edge between the stranger vertex and the collection device vertex at the community exit within the specified time , which indicates the time β2 when the stranger left the community; if β2-β1>α, where β2-β1 represents the time the stranger stays in the community, it is determined that the stranger has been in and out for a long time, and the longer the stay time is suspicious The higher the degree index.

If there is an edge between a stranger vertex and the second vertex in the graph database within the preset abnormal time period, the behavior of the stranger is identified as the third type of abnormal behavior, and the third type of abnormal behavior is used to instruct the stranger Enter and exit the corresponding area during the abnormal time period. For example, the preset abnormal time period can be set to 23:00-5:00. During this time period, the number S of edges between each stranger vertex in the graph database and all collection device vertices can be batch retrieved. If S>0 , it means that the stranger is active in the community during the abnormal time period, and the larger the S value, the higher the suspicious index.

The behavior analysis method provided in this embodiment first identifies the face data of strangers from the collected face data, which can not only greatly reduce the amount of data processing, improve the efficiency of data processing, but also make the behavior analysis more targeted; Then cluster the face data of the identified strangers to obtain the face data belonging to the same stranger, and construct a graph database based on the face data of each stranger, and use the relationship between the vertices and edges of the graph database to vividly reflect The relationship between strangers and different collection devices at different times; Finally, the abnormal behavior of strangers is identified according to the graph database. The data analyzes the behavior of strangers to detect abnormal behaviors of strangers in time, which can improve the safety of the community.

On the basis of the previous embodiment, in order to deal with the abnormal situation in time, if the abnormal behavior is identified, the abnormal information will be sent to relevant workers for early warning. For example, abnormal information can be sent to community security managers through short messages, WeChat, or platform messages. The abnormal information may include the picture information of the stranger, the time information of the abnormal behavior, and the reason for the abnormal behavior.

Fig. 4 is a schematic structural diagram of a behavior analysis device provided by an embodiment of the present invention. As shown in FIG. 4 , the behavior analysis device 40 provided in this embodiment may include: an identification module 401 , a clustering module 402 , a construction module 403 and an analysis module 404 .

The recognition module 401 is configured to perform stranger face image recognition on face data collected by at least one image capture device within a preset time period, the face data including face images, collection time information and collection location information;

A clustering module 402, configured to cluster the recognized face images of strangers to obtain face data belonging to the same stranger;

Construction module 403, for constructing graph database according to the face data of each stranger;

The analysis module 404 is configured to identify abnormal behaviors of strangers according to the graph database.

The behavior analysis device provided in this embodiment can be used to implement the technical solution of the method embodiment corresponding to FIG. 1 , and its implementation principle and technical effect are similar, and will not be repeated here.

In one embodiment, the identification module 401 is used to perform face image recognition of strangers on face data collected by at least one image acquisition device within a preset time period, which may specifically include:

Match the collected face data with the resident face database;

If the matching fails, the face data is that of a stranger.

In one embodiment, the construction module 403 is used to construct a graph database according to the face data of each stranger, which may specifically include:

Each stranger is identified as a first vertex, the first vertex includes identity information; the collection device located at each collection location is identified as a second vertex, the second vertex includes collection location information, and the collection location includes at least The entrance of the area and the exit of the area; an edge between the first vertex and the second vertex corresponds to a piece of face data, and the edge includes collection time information.

In one embodiment, the analysis module 404 is used to identify abnormal behaviors of strangers according to the graph database, which may specifically include:

If the number of edges between a vertex of a stranger in the graph database and the vertex of the collection device at the entrance of the area is greater than the preset frequency threshold, the behavior of the stranger is identified as the first type of abnormal behavior, and the first type of abnormal behavior is used to indicate that the stranger People frequently enter the area.

In one embodiment, the analysis module 404 is used to identify abnormal behaviors of strangers according to the graph database, which may specifically include:

If β2-β1>α, where β1 is the collection time represented by the edge between a stranger vertex in the graph database and the collection device vertex at the area entrance, β2 is the stranger vertex in the graph database and the collection device vertex at the area exit The acquisition time represented by the side between, α is the preset residence time threshold, the behavior of the stranger is identified as the second type of abnormal behavior, and the second type of abnormal behavior is used to indicate that the stranger stays in the area for a long time.

In one embodiment, the analysis module 404 is used to identify abnormal behaviors of strangers according to the graph database, which may specifically include:

If there is an edge between a stranger vertex and the second vertex in the graph database within the preset abnormal time period, the behavior of the stranger is identified as the third type of abnormal behavior, and the third type of abnormal behavior is used to instruct the stranger Enter and exit the corresponding area during the abnormal time period.

In one embodiment, the behavior analysis device 40 may also include an early warning module (not shown in the figure), which is used to send abnormal information to relevant workers if an abnormal behavior is identified. The abnormal information includes picture information of strangers, Information about the time when the abnormal behavior occurred and the reason for the abnormal behavior.

The embodiment of the present invention also provides a behavior analysis device, as shown in FIG. 5 . The embodiment of the present invention is only described by taking FIG. 5 as an example, which does not mean that the present invention is limited thereto. Fig. 5 is a schematic structural diagram of a behavior analysis device provided by an embodiment of the present invention. As shown in FIG. 5 , the behavior analysis device 50 provided in this embodiment may include: a memory 501 , a processor 502 and a bus 503 . Among them, the bus 503 is used to realize the connection between various components.

A computer program is stored in the memory 501 , and when the computer program is executed by the processor 502 , the technical solution of the behavior analysis method provided by any one of the above method embodiments can be realized.

Wherein, the memory 501 and the processor 502 are electrically connected directly or indirectly to realize data transmission or interaction. For example, these components may be electrically connected to each other through one or more communication buses or signal lines, for example, they may be connected through a bus 503 . Stored in the memory 501 is a computer program that implements the behavior analysis method, including at least one software function module that can be stored in the memory 501 in the form of software or firmware, and the processor 502 executes the software program and the module stored in the memory 501 by running Various functional applications and data processing.

The memory 501 can be, but not limited to, random access memory (Random Access Memory, referred to as: RAM), read-only memory (Read Only Memory, referred to as: ROM), programmable read-only memory (Programmable Read-Only Memory, referred to as: PROM) ), Erasable Programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM for short), Electric Erasable Programmable Read-Only Memory (EEPROM for short), etc. Wherein, the memory 501 is used to store programs, and the processor 502 executes the programs after receiving execution instructions. Further, the software programs and modules in the memory 501 may also include an operating system, which may include various software components and/or drivers for managing system tasks (such as memory management, storage device control, power management, etc.), and It can communicate with various hardware or software components to provide an operating environment for other software components.

The processor 502 may be an integrated circuit chip and has a signal processing capability. The above-mentioned processor 502 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), and the like. Various methods, steps and logic block diagrams disclosed in the embodiments of the present invention may be implemented or executed. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like. It can be understood that the structure in FIG. 5 is only for illustration, and may include more or less components than those shown in FIG. 5 , or have different configurations from those shown in FIG. 5 . Each component shown in Fig. 5 may be implemented by hardware and/or software.

It should be noted that the behavior analysis device provided in this embodiment includes but is not limited to at least one of the following: a user side device and a network side device. User-side devices include but are not limited to computers, smart phones, tablet computers, digital broadcast terminals, messaging devices, game consoles, personal digital assistants, etc. Network-side devices include but are not limited to a single network server, a server group composed of multiple network servers, or a cloud composed of a large number of computers or network servers based on cloud computing. Cloud computing is a type of distributed computing, consisting of a group of loosely coupled A super virtual computer composed of computers.

This document is described with reference to various exemplary embodiments. However, those skilled in the art will recognize that changes and modifications can be made to the exemplary embodiments without departing from the scope herein. For example, the various operational steps, as well as the components used to perform the operational steps, may be implemented in different ways depending on the particular application or considering any number of cost functions associated with the operation of the system (e.g., one or more steps may be deleted, modified or incorporated into other steps).

In addition, the principles herein may be embodied in a computer program product on a computer-readable storage medium having computer-readable program code preloaded thereon, as understood by those skilled in the art. Any tangible, non-transitory computer-readable storage medium may be used, including magnetic storage devices (hard disks, floppy disks, etc.), optical storage devices (CD-ROMs, DVDs, Blu Ray discs, etc.), flash memory and/or the like . These computer program instructions can be loaded into a general purpose computer, special purpose computer or other programmable data processing apparatus to form a machine, so that these instructions executed on the computer or other programmable data processing apparatus can generate an apparatus for realizing specified functions. These computer program instructions may also be stored in a computer-readable memory which can instruct a computer or other programmable data processing device to operate in a particular manner such that the instructions stored in the computer-readable memory form a Manufactures, including implementing devices for implementing specified functions. Computer program instructions can also be loaded on a computer or other programmable data processing device, thereby performing a series of operational steps on the computer or other programmable device to produce a computer-implemented process, so that the computer or other programmable device Instructions may provide steps for performing specified functions.

While the principles herein have been shown in various embodiments, many modifications in structure, arrangement, proportions, elements, materials and components, particularly suited to particular circumstances and operational requirements may be made without departing from the principles and scope of this disclosure use. The above modifications and other changes or amendments are intended to be included within the scope of this document.

The foregoing detailed description has been described with reference to various embodiments. However, those skilled in the art will recognize that various modifications and changes can be made without departing from the scope of the present disclosure. Accordingly, the disclosure is to be considered in an illustrative rather than a restrictive sense, and all such modifications are intended to be embraced within its scope. Also, advantages, other advantages and solutions to problems have been described above with respect to various embodiments. However, neither benefits, advantages, solutions to problems, nor any elements that lead to these, or make the solutions more definite, should be construed as critical, required, or necessary. As used herein, the term "comprises" and any other variants thereof are non-exclusive, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements, but also elements not expressly listed or not part of the process. , method, system, article or other element of a device. Additionally, the term "coupled" and any other variations thereof, as used herein, refers to a physical connection, an electrical connection, a magnetic connection, an optical connection, a communicative connection, a functional connection, and/or any other connection.

The above uses specific examples to illustrate the present invention, which is only used to help understand the present invention, and is not intended to limit the present invention. For those skilled in the technical field to which the present invention belongs, some simple deduction, deformation or replacement can also be made according to the idea of the present invention.

Claims (9)

1. A behavior analysis method, characterized in that, comprising: Perform face image recognition of strangers on the face data collected by at least one image acquisition device within a preset time period, the face data including face images, collection time information and collection location information; Clustering the face images of the recognized strangers to obtain face data belonging to the same stranger; Construct a graph database based on the face data of each stranger; The described constructing graph database according to the face data of each stranger includes: Each stranger is identified as a first vertex, the first vertex includes identity information; the collection device located at each collection location is identified as a second vertex, the second vertex includes collection location information, and the collection location includes at least The entrance of the area and the exit of the area; an edge between the first vertex and the second vertex corresponds to a face data, and the edge includes acquisition time information; Abnormal behavior of strangers is identified based on the graph database. 2. The method according to claim 1, wherein the face image recognition of strangers is performed on the face data collected by at least one image acquisition device within a preset time period, comprising: Match the collected face data with the resident face database; If the matching fails, the face data is that of a stranger. 3. The method according to claim 1, wherein the identifying abnormal behaviors of strangers according to the graph database comprises: If the number of edges between a vertex of a stranger in the graph database and the vertex of the collection device at the entrance of the area is greater than the preset frequency threshold, the behavior of the stranger is identified as the first type of abnormal behavior, and the first type of abnormal behavior is used for Indicates that strangers frequently enter the area. 4. The method according to claim 1, wherein the identifying abnormal behaviors of strangers according to the graph database comprises: If β2-β1>α, where β1 is the collection time represented by the edge between a stranger vertex in the graph database and the collection device vertex at the area entrance, β2 is the stranger vertex in the graph database and the collection device vertex at the area exit The acquisition time represented by the side between, α is the preset residence time threshold, then the behavior of the stranger is identified as the second type of abnormal behavior, and the second type of abnormal behavior is used to indicate that the stranger has been in the area for a long time stranded. 5. The method according to claim 1, wherein the identifying abnormal behaviors of strangers according to the graph database comprises: If there is an edge between a stranger vertex and the second vertex in the graph database within the preset abnormal time period, the behavior of the stranger is identified as the third type of abnormal behavior, and the third type of abnormal behavior is used It is used to instruct strangers to enter and exit the corresponding area during the abnormal time period. 6. The method according to any one of claims 1-5, further comprising: If the abnormal behavior is identified, the abnormal information will be sent to relevant workers, and the abnormal information includes the picture information of the stranger, the time information of the abnormal behavior and the reason of the abnormal behavior. 7. A behavior analysis device, characterized in that, comprising: A recognition module, configured to perform stranger face image recognition on face data collected by at least one image capture device within a preset time period, the face data including face images, collection time information and collection location information; The clustering module is used to cluster the face images of the identified strangers to obtain face data belonging to the same stranger; A building block for constructing a graph database based on face data of each stranger; The described constructing graph database according to the face data of each stranger includes: Each stranger is identified as a first vertex, the first vertex includes identity information; the collection device located at each collection location is identified as a second vertex, the second vertex includes collection location information, and the collection location includes at least The entrance of the area and the exit of the area; an edge between the first vertex and the second vertex corresponds to a face data, and the edge includes acquisition time information; An analysis module is used for identifying abnormal behaviors of strangers according to the graph database. 8. A behavior analysis device, comprising: at least one processor and memory; the memory stores computer-executable instructions; The at least one processor executes the computer-executed instructions stored in the memory, so that the at least one processor executes the behavior analysis method according to any one of claims 1-6. 9. A computer-readable storage medium, characterized in that, computer-executable instructions are stored in the computer-readable storage medium, and the computer-executable instructions are used to implement any one of claims 1-6 when executed by a processor The behavioral analysis method described.

Images