Methods, Systems, Electronic Devices, and Storage Media for Illegal Personnel Mining

Abstract

The present application provides a method, a system, an electronic device and a storage medium for identifying lawbreakers, including: obtaining a first set of suspects associated with existing lawbreakers through a lawbreaking information database; screening the first set of suspects according to the social behavior data of each suspect in the first set of suspects and the existing lawbreakers to obtain a second set of suspects; comparing the movement trajectories of the existing lawbreakers with each suspect in the second set of suspects, and setting the suspects with a movement trajectory similarity greater than a preset similarity threshold as a third set of suspects; obtaining the aggregation information of the existing lawbreakers and the suspects in the third set of suspects; obtaining a fourth set of suspects that meet the aggregation information from the lawbreaking information database; and setting the suspects with a movement trajectory similarity greater than the preset similarity threshold as lawbreakers.

Description

Technical Field

[0001] This application belongs to the field of data, and in particular to methods, systems, electronic devices, and storage media for identifying illegal persons. Background Art

[0002] The organized and premeditated illegal acts of illegal groups often cause great harm to society. The longer an illegal group exists, the more tightly organized it is, and the more members it has, the greater the harm it causes and the more difficult it is to crack down on. For organized and disciplined illegal groups, low-level members often only know the upper-line personnel they contact and are only responsible for completing the illegal tasks assigned by the upper-line personnel, and know nothing about senior illegal members or the overall profile of the organization. This makes it difficult to obtain sufficient information from the police situation data of grass-roots members. If the upper-line personnel are directly arrested, it will inevitably tip off the enemy and cause difficulties in further arresting other core members. Therefore, quickly and accurately identifying the core members of illegal groups and uncovering the complete core illegal groups are the top priorities for the police to arrest illegal groups.

[0003] Within illegal groups, to ensure the orderly progress of illegal acts, illegal gangs either gather together to collaborate on illegal activities or, based on various communication methods and social means, achieve the purpose of maintaining close contact. Therefore, by fully mining the communication and social data of known illegal members, considering the proximity of key personnel as a probability of communication or illegal conspiracy, the closer the distance at which key personnel appear, the less time they appear, and the more similar their staying patterns are, the more similar their illegal intentions are, and the higher the likelihood that they are part of an illegal group.

[0004] Of course, in real life, the group behaviors of those with similar living frequencies and staying patterns are not necessarily illegal groups. For example, illegal persons and their relatives, friends, colleagues, etc. will all exhibit similar living rhythms and travel patterns. This requires further screening. Generally speaking, the illegal groups we need to uncover are often hidden within a certain subgroup of the social group of the illegal person. Summary of the Invention

[0005] The main purpose of the embodiments of the present invention is to provide methods, systems, electronic devices, and storage media for identifying illegal persons, which consider the time and location of illegal acts committed by known illegal persons when identifying illegal persons, ensuring the effectiveness and accuracy of identifying illegal persons.

[0006] In a first aspect, a method for identifying illegal persons is provided, the method comprising:

[0007] Obtaining a first set of suspects having an associated relationship with known illegal persons through an illegal information database;

[0008] Screen the first suspect set according to the social behavior data of the convicted person and each suspect in the first suspect set, and obtain a second suspect set;

[0009] Compare the movement trajectories of the convicted person with each suspect in the second suspect set, and set the suspects with a movement trajectory similarity greater than a preset similarity threshold as the third suspect set;

[0010] Obtain the aggregation information of the convicted person and the suspects in the third suspect set, where the aggregation information includes: aggregation location information and time information;

[0011] Obtain a fourth suspect set that meets the aggregation information from the illegal information database;

[0012] Compare the movement trajectories of the convicted person with each suspect in the fourth suspect set, and set the suspects with a movement trajectory similarity greater than a preset similarity threshold as convicted persons.

[0013] In a possible implementation, the suspects in the fourth suspect set also meet one or more of the following conditions:

[0014] Being photographed alone by a monitoring device multiple times, being photographed by a monitoring device walking with the convicted person, having a criminal record.

[0015] In a second aspect, a system for mining convicted persons is provided, and the system includes:

[0016] A first suspect set acquisition module, configured to obtain a first suspect set having an associated relationship with a convicted person through an illegal information database;

[0017] A second suspect set acquisition module, configured to screen the first suspect set according to the social behavior data of the convicted person and each suspect in the first suspect set, and obtain a second suspect set;

[0018] A third suspect set acquisition module, configured to compare the movement trajectories of the convicted person with each suspect in the second suspect set, and set the suspects with a movement trajectory similarity greater than a preset similarity threshold as the third suspect set;

[0019] An aggregation information acquisition module, configured to obtain the aggregation information of the convicted person and the suspects in the third suspect set, where the aggregation information includes: aggregation location information and time information;

[0020] The fourth suspect set obtaining module is used to obtain the fourth suspect set that meets the aggregation information from the illegal information database;

[0021] The illegal personnel setting module is used to compare the trajectories of the illegal personnel with each suspect in the fourth suspect set, and set the suspect whose trajectory similarity is greater than a preset similarity threshold as an illegal personnel.

[0022] In a possible implementation, the suspects in the fourth suspect set also meet one or more of the following conditions:

[0023] Being photographed alone by the monitoring device multiple times, being photographed by the monitoring device walking with the illegal personnel, and having a record of previous convictions.

[0024] In a third aspect, an electronic device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the method for mining illegal personnel provided in the first aspect is implemented.

[0025] In a fourth aspect, a non-transitory computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for mining illegal personnel provided in the first aspect is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for describing the embodiments of the present application will be briefly introduced below.

[0027] Figure 1 It is a flowchart of the method for mining illegal personnel provided by an embodiment of the present invention;

[0028] Figure 2 It is a structural diagram of the system for mining illegal personnel provided by an embodiment of the present invention;

[0029] Figure 3 It is a schematic physical structure diagram of an electronic device of the present invention.

[0030] DETAILED IMPLEMENTATION MANNER

[0031] The embodiments of the present application will be described in detail below. The examples of the embodiments are shown in the drawings, where the same or similar reference numerals represent the same or similar modules or modules with the same or similar functions from beginning to end. The embodiments described below with reference to the drawings are exemplary and are only used to explain the present application, and cannot be construed as a limitation of the present invention.

[0032] Those skilled in the art can understand that, unless specifically stated otherwise, the singular forms "a", "an", "the" and "said" used herein may also include the plural forms. It should be further understood that the term "including" used in the specification of this application means the presence of the described features, integers, steps, operations, modules and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, modules, components and / or their groups. It should be understood that when we say that a module is "connected" or "coupled" to another module, it can be directly connected or coupled to other modules, or there may also be intermediate modules. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any module and all combinations of one or more related listed items.

[0033] To make the objectives, technical solutions and advantages of this application more clear, the implementation manners of this application will be further described in detail below in conjunction with the accompanying drawings.

[0034] The technical solutions of this application and how this application solves the above technical problems will be described in detail below with specific embodiments. These several specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this application will be described below in conjunction with the accompanying drawings.

[0035] As Figure 1 shown is a flowchart of a method for mining lawbreakers provided by an embodiment of the present invention. The method includes:

[0036] Step 101, obtaining a first suspect set associated with lawbreakers who have already violated the law through a lawbreaking information database;

[0037] Step 102, screening the first suspect set according to the social behavior data of the lawbreakers who have already violated the law and each suspect in the first suspect set to obtain a second suspect set;

[0038] Step 103, comparing the movement trajectories of the lawbreakers who have already violated the law with each suspect in the second suspect set, and setting the suspects with a movement trajectory similarity greater than a preset similarity threshold as a third suspect set;

[0039] Step 104, obtaining the aggregation information of the lawbreakers who have already violated the law and the suspects in the third suspect set. The aggregation information includes: aggregated location information and time information;

[0040] Step 105, obtaining a fourth suspect set that meets the aggregation information from the lawbreaking information database;

[0041] Step 106: Compare the movement trajectories of the identified lawbreakers with each suspect in the fourth suspect set, and set as lawbreakers those suspects whose movement trajectory similarity is greater than a preset similarity threshold.

[0042] In an embodiment of the present invention, the public security business database, the social personnel association information database, and the lawbreaker association information database are merged to form a lawbreaking information database. The analytic hierarchy process is used to determine the lawbreaking coefficient of each association in the network, and the lawbreaking coefficient is mapped to the [0, 1] space to complete the quantification process. Among them, the different priorities should be adjusted according to different cases and different associated objects, and the priorities should be able to correctly reflect the impact of the personnel relationship on specific types of cases. Set the value of this association degree as S. If an associated person has two or more association relationships with the identified lawbreakers, such as: this associated person is both an accomplice association and a relative association, then the association degree is: The first suspect set can be obtained through the screening of the association relationships.

[0043] For each suspect in the first suspect set, based on social behavior data such as their communication records and transfer records with the identified lawbreakers, the first suspect set is screened to obtain the second suspect set. The screening process also uses the analytic hierarchy process to determine the social frequency T, T ∈ [0, 1]. Let the lawbreaking association degree be M, then M = S * T. This lawbreaking association degree can reflect the possible degree of the identified lawbreakers and the associated persons colluding in illegal acts. The greater the social harmfulness of the associated person, the greater the possibility of lawbreaking, and the greater the value of S. The closer the relationship between the identified lawbreakers and the associated person, and the closer the connection, the greater the value of T.

[0044] For each suspect in the second suspect set, calculate the trajectory similarity between them and the identified lawbreakers, and screen out those suspects whose trajectory similarity is higher than the preset similarity threshold, and set them as the third suspect set.

[0045] Among them, calculating the trajectory similarity with the identified lawbreakers includes:

[0046] Dividing according to the social schedule time into holidays and working days, and dividing a day into 6 - 12 am, 12 pm - 6 pm, 6 pm - 0 am, and 0 - 6 am. Divide the activity area into multiple local areas according to the movement trajectory range of the identified lawbreakers, and use the staying time of the identified lawbreakers and the associated persons in each local area to construct a polynomial distribution.

[0047]

[0048] Among them, W represents the distribution of this event;

[0049] n represents the number of divisions of the activity area;

[0050] Tm represents the total number of time selected for this time semantic segment;

[0051] Ti represents the total time that the target person stays in area i during this time semantic segment;

[0052] The KL divergence is used to measure the trajectory similarity between the known lawbreakers and the suspicious associated persons.

[0053]

[0054] Where N represents the number of divided activity areas;

[0055] Pw1(Xi) represents the residence probability of the known lawbreaker in the i-th area;

[0056] Pw2(Xi) represents the residence probability of the suspicious associated person in the i-th area;

[0057] The smaller the KL divergence value, the higher the trajectory similarity between the two under this time semantic. The higher the KL divergence value, the lower the trajectory similarity. By setting a reasonable threshold, the associated persons with high trajectory similarity can be screened out.

[0058] For the third suspect set, extract the aggregation information between it and the known lawbreakers. Among them, the aggregation information includes but is not limited to: the location information and time information of the aggregation.

[0059] Compare the aggregation information with the illegal information database to obtain the fourth suspect set that meets this aggregation information. The suspects in the fourth suspect set also meet one or more of the following conditions:

[0060] Being photographed alone by the monitoring device multiple times, being photographed by the monitoring device walking with the said known lawbreaker, having a criminal record.

[0061] For the fourth suspect set, compare its trajectory similarity with that of the known lawbreakers. If the similarity is greater than the similarity threshold, mark it as a lawbreaker to complete the excavation of lawbreakers.

[0062] In an embodiment of the present invention, a first suspect set associated with law-breaking persons is obtained through a law-breaking information database; the first suspect set is filtered according to the social behavior data of each suspect in the first suspect set and the law-breaking persons to obtain a second suspect set; the movement trajectories of the law-breaking persons and each suspect in the second suspect set are compared, and the suspects with a movement trajectory similarity greater than a preset similarity threshold are set as a third suspect set; the aggregation information of the law-breaking persons and the suspects in the third suspect set is obtained, and the aggregation information includes: aggregation location information and time information; a fourth suspect set that meets the aggregation information is obtained from the law-breaking information database; the movement trajectories of the law-breaking persons and each suspect in the fourth suspect set are compared, and the suspects with a movement trajectory similarity greater than a preset similarity threshold are set as law-breaking persons. When mining law-breaking persons, the time and location of the law-breaking act of the law-breaking persons are considered, ensuring the effectiveness and accuracy of mining law-breaking persons.

[0063] As Figure 2 shown is a structural diagram of a system for mining law-breaking persons provided by an embodiment of the present invention. The system includes:

[0064] A first suspect set obtaining module 201, configured to obtain a first suspect set associated with law-breaking persons through a law-breaking information database;

[0065] A second suspect set obtaining module 202, configured to filter the first suspect set according to the social behavior data of each suspect in the first suspect set and the law-breaking persons to obtain a second suspect set;

[0066] A third suspect set obtaining module 203, configured to compare the movement trajectories of the law-breaking persons and each suspect in the second suspect set, and set the suspects with a movement trajectory similarity greater than a preset similarity threshold as a third suspect set;

[0067] An aggregation information obtaining module 204, configured to obtain the aggregation information of the law-breaking persons and the suspects in the third suspect set, where the aggregation information includes: aggregation location information and time information;

[0068] A fourth suspect set obtaining module 205, configured to obtain a fourth suspect set that meets the aggregation information from the law-breaking information database;

[0069] A law-breaking person setting module 206, configured to compare the movement trajectories of the law-breaking persons and each suspect in the fourth suspect set, and set the suspects with a movement trajectory similarity greater than a preset similarity threshold as law-breaking persons.

[0070] In the embodiments of the present invention, the public security business database, the social personnel association information database, and the illegal personnel association information data are merged to form an illegal information database. The analytic hierarchy process is used to determine the illegal coefficient of each association in the network, and the illegal coefficient is mapped to the [0, 1] space to complete the quantification process. Among them, the different priorities should be adjusted according to different cases and different associated objects, and the priorities should be able to correctly reflect the influence of the personnel relationship on specific types of cases. Set the value of the association degree as S. If an associated person has two or more association relationships with an illegal person, such as: the associated person is both an accomplice association and a relative association, then the association degree is: The first suspect set can be obtained through the screening of the association relationships.

[0071] For each suspect in the first suspect set, based on social behavior data such as communication records and transfer records between the suspect and the illegal person, the first suspect set is screened to obtain the second suspect set. The screening process also uses the analytic hierarchy process to determine the social frequency T, T ∈ [0, 1]. Let the illegal association degree be M, then M = S * T. This illegal association degree can reflect the possible degree of the illegal person and the associated person colluding in illegal acts. The greater the social harmfulness of the associated person, the greater the possibility of illegal behavior, and the greater the S value. The closer the relationship between the illegal person and the associated person and the closer the connection, the greater the T value.

[0072] For each suspect in the second suspect set, calculate the trajectory similarity between the suspect and the illegal person, and screen out the suspects whose trajectory similarity is higher than the preset similarity threshold, and set them as the third suspect set.

[0073] Among them, calculating the trajectory similarity with the illegal person includes:

[0074] According to the social work and rest regular time, it is divided into holidays and working days. One day is divided into 6 - 12 am, 12 pm - 6 pm, 6 pm - 0 am, and 0 - 6 am. According to the trajectory range of the illegal person's activities, the activity area is divided into multiple local areas, and the polynomial distribution is constructed by using the staying time of the illegal person and the associated person in each local area.

[0075]

[0076] Where W represents the distribution of this event;

[0077] n represents the number of divisions of the activity area;

[0078] Tm represents the total time selected for this time semantic segment;

[0079] Ti represents the total time that the target person stays in area i during this time semantic segment;

[0080] The KL divergence is used to measure the trajectory similarity between the law-breaking persons and the suspicious associated persons.

[0081]

[0082] Where N represents the number of divisions of the activity area;

[0083] Pw1(Xi) represents the residence probability of the law-breaking person in the i-th area;

[0084] Pw2(Xi) represents the residence probability of the suspicious associated person in area i;

[0085] The smaller the KL divergence value, the higher the trajectory similarity between the two under this time semantics. The higher the KL divergence value, the lower the trajectory similarity. By setting a reasonable threshold, the associated persons with high trajectory similarity can be screened out.

[0086] For the third suspect set, extract the aggregation information between it and the law-breaking persons. Among them, the aggregation information includes but is not limited to: the location information and time information of the aggregation.

[0087] Compare the aggregation information with the law-breaking information database to obtain the fourth suspect set that meets this aggregation information. The suspects in the fourth suspect set also meet one or more of the following conditions:

[0088] Being photographed alone by the monitoring device multiple times, being photographed by the monitoring device walking with the said law-breaking person, having a criminal record.

[0089] For the fourth suspect set, compare its trajectory with that of the law-breaking persons. If the similarity is greater than the similarity threshold, mark it as a law-breaking person to complete the excavation of law-breaking persons.

[0090] In an embodiment of the present invention, a first suspect set associated with the already-law-violating persons is obtained through a law-violation information database; the first suspect set is screened according to the social behavior data of the already-law-violating persons and each suspect in the first suspect set to obtain a second suspect set; the movement trajectories of the already-law-violating persons and each suspect in the second suspect set are compared, and the suspects with a movement trajectory similarity greater than a preset similarity threshold are set as a third suspect set; the aggregation information of the already-law-violating persons and the suspects in the third suspect set is obtained, and the aggregation information includes: aggregated location information and time information; a fourth suspect set that meets the aggregation information is obtained from the law-violation information database; the movement trajectories of the already-law-violating persons and each suspect in the fourth suspect set are compared, and the suspects with a movement trajectory similarity greater than a preset similarity threshold are set as law-violating persons. When mining law-violating persons, the time and location of the already-law-violating persons' law violations are considered, ensuring the effectiveness and accuracy of law-violating person mining.

[0091] Figure 3 Illustrates a schematic physical structure diagram of an electronic device, such as Figure 3 As shown, the electronic device may include: a processor 301, a communication interface 302, a memory 303, and a communication bus 304. Among them, the processor, the communication interface, and the memory communicate with each other through the communication bus. The processor can call the logical instructions in the memory to execute the method for mining law-violating persons, and the method includes: obtaining a first suspect set associated with the already-law-violating persons through a law-violation information database; screening the first suspect set according to the social behavior data of the already-law-violating persons and each suspect in the first suspect set to obtain a second suspect set; comparing the movement trajectories of the already-law-violating persons and each suspect in the second suspect set, and setting the suspects with a movement trajectory similarity greater than a preset similarity threshold as a third suspect set; obtaining the aggregation information of the already-law-violating persons and the suspects in the third suspect set, and the aggregation information includes: aggregated location information and time information; obtaining a fourth suspect set that meets the aggregation information from the law-violation information database; comparing the movement trajectories of the already-law-violating persons and each suspect in the fourth suspect set, and setting the suspects with a movement trajectory similarity greater than a preset similarity threshold as law-violating persons.

[0092] In addition, when the logical instructions in the above-mentioned memory are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0093] On the other hand, an embodiment of the present invention further provides a computer program product. The computer program product includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the method for mining lawbreakers provided in each of the above method embodiments. The method includes: obtaining a first set of suspects having an associated relationship with the existing lawbreakers through a lawbreaking information database; screening the first set of suspects according to the social behavior data of the existing lawbreakers and each suspect in the first set of suspects to obtain a second set of suspects; comparing the movement trajectories of the existing lawbreakers with each suspect in the second set of suspects, and setting the suspects with a movement trajectory similarity greater than a preset similarity threshold as a third set of suspects; obtaining the aggregation information of the existing lawbreakers and the suspects in the third set of suspects, where the aggregation information includes: aggregation location information and time information; obtaining a fourth set of suspects that meet the aggregation information from the lawbreaking information database; comparing the movement trajectories of the existing lawbreakers with each suspect in the fourth set of suspects, and setting the suspects with a movement trajectory similarity greater than a preset similarity threshold as lawbreakers.

[0094] In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is configured to execute the method for mining lawbreakers provided in the above embodiments. The method includes: obtaining a first set of suspects having an associated relationship with lawbreakers from a lawbreaking information database; screening the first set of suspects according to the social behavior data of each suspect in the first set of suspects and the lawbreakers to obtain a second set of suspects; comparing the movement trajectories of the lawbreakers and each suspect in the second set of suspects, and setting the suspects with a movement trajectory similarity greater than a preset similarity threshold as a third set of suspects; obtaining the aggregation information of the lawbreakers and the suspects in the third set of suspects, where the aggregation information includes: aggregation location information and time information; obtaining a fourth set of suspects that meet the aggregation information from the lawbreaking information database; comparing the movement trajectories of the lawbreakers and each suspect in the fourth set of suspects, and setting the suspects with a movement trajectory similarity greater than a preset similarity threshold as lawbreakers.

[0095] It should be understood that although the steps in the flowchart of the accompanying drawings are shown in sequence according to the indication of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. Their execution order is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0096] The above is only a partial implementation manner of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for mining illegal persons, characterized in that, The method includes: Obtaining a first suspect set associated with the law-violating personnel from the law-violation information database; Screening the first suspect set according to the social behavior data of the law-violating personnel and each suspect in the first suspect set to obtain a second suspect set; Comparing the movement trajectories of the law-violating personnel and each suspect in the second suspect set, and setting the suspects with a movement trajectory similarity greater than a preset similarity threshold as a third suspect set; Obtaining the aggregation information of the law-violating personnel and the suspects in the third suspect set, where the aggregation information includes: aggregation location information and time information; Obtaining a fourth suspect set that conforms to the aggregation information from the law-violation information database; Comparing the movement trajectories of the law-violating personnel and each suspect in the fourth suspect set, and setting the suspects with a movement trajectory similarity greater than a preset similarity threshold as law-violating personnel.

2. The method according to claim 1, wherein The suspects in the fourth suspect set also satisfy one or more of the following conditions: Being photographed alone by the monitoring device multiple times, being photographed walking with the law-violating personnel by the monitoring device, having a law-violation record.

3. A system for digging out lawbreakers, characterized in that, The system includes: A first suspect set obtaining module, configured to obtain a first suspect set associated with the law-violating personnel from the law-violation information database; A second suspect set obtaining module, configured to screen the first suspect set according to the social behavior data of the law-violating personnel and each suspect in the first suspect set to obtain a second suspect set; A third suspect set obtaining module, configured to compare the movement trajectories of the law-violating personnel and each suspect in the second suspect set, and set the suspects with a movement trajectory similarity greater than a preset similarity threshold as a third suspect set; An aggregation information obtaining module, configured to obtain the aggregation information of the law-violating personnel and the suspects in the third suspect set, where the aggregation information includes: aggregation location information and time information; A fourth suspect set obtaining module, configured to obtain a fourth suspect set that conforms to the aggregation information from the law-violation information database; A law-violating personnel setting module, configured to compare the movement trajectories of the law-violating personnel and each suspect in the fourth suspect set, and set the suspects with a movement trajectory similarity greater than a preset similarity threshold as law-violating personnel.

4. The system according to claim 3, wherein The suspects in the fourth suspect set also satisfy one or more of the following conditions: Being photographed alone by the monitoring device multiple times, being photographed walking with the law-violating personnel by the monitoring device, having a law-violation record.

5. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method for mining law-violating personnel as described in any one of claims 1-2.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for mining law-violating personnel as described in any one of claims 1-2.

Images