Regional security prevention and control prediction method, device, equipment and storage medium

By obtaining and analyzing the gathering events of personnel in the surveillance video and generating prediction results for public security prevention and control, the problems of high false alarm rate and poor public security management in the existing technology are solved, and more accurate and efficient public security prediction and prevention and control are achieved.

CN117612062BActive Publication Date: 2025-07-01TROY INFORMATION TECHNOLOGY CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202311496756.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-11-10
Publication Date
2025-07-01
Estimated Expiration
2043-11-10

AI Technical Summary

Technical Problem

The existing rural security control methods cannot be prevented before the incident occurs, resulting in a high false alarm rate and poor public security management effect.

Method used

By obtaining the set of personnel conflict events within the region, a map of personnel conflicts is generated, and combining the personnel gathering events in the surveillance video, public security prevention and control predictions are made.

Benefits of technology

It improves the prediction accuracy of rural public security prevention and control, reduces the false alarm rate, and enhances the intensity of public security management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117612062B_ABST
    Figure CN117612062B_ABST
Patent Text Reader

Abstract

The present invention discloses a method, device, equipment and storage medium for predicting public security prevention and control within a region. The method includes: obtaining a set of personnel conflict events within the region; generating a personnel conflict relationship graph within the region based on the set of personnel conflict events; obtaining surveillance videos within the region, extracting face information from the surveillance videos, and generating a personnel gathering event within the region; generating a public security prevention and control prediction result according to the personnel conflict relationship graph and the personnel gathering event. By obtaining the set of personnel conflict events within the region, establishing a personnel conflict relationship graph, and using the personnel conflict relationship graph to filter the personnel gathering events extracted from the surveillance videos and predict public security prevention and control, the present invention can comprehensively consider the influence of personnel conflict events and normal rural gathering activities on the prediction of public security prevention and control, improve the management strength of rural public security prevention and control, and solve the technical problem of high false alarm rate in public security prevention and control prediction.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of public security prevention and control, and particularly to a method, device, equipment and storage medium for predicting public security prevention and control within a regional scope. Background Art

[0002] Existing rural public security prevention and control usually adopts a public security management solution based on video surveillance. By setting video surveillance devices at key positions, when rural public security problems are found, corresponding responsible persons are dispatched to handle relevant problems.

[0003] However, in practice, the existing video surveillance devices and the setting of public security prevention and control responsible persons can only be monitored when or after rural public security incidents occur, and cannot play a preventive role before the incidents occur. The achieved public security maintenance and management effects are not good. If serious public security incidents occur, even if the incidents are monitored, the resulting personal and property losses cannot be recovered. In some solutions, it is proposed to identify incidents such as gatherings and fights by monitoring the gathering of people. However, in the rural scenario, the daily life of residents usually has regular gathering behaviors (such as going to the market, weddings and funerals, and joint labor, etc.), resulting in a high false alarm rate for predicting public security incidents by monitoring the gathering of people. This causes a large workload for public security prevention and control responsible persons or patrol personnel, and further affects the vigilance towards public security management. When real public security incidents occur, the solution plan cannot be triggered quickly and accurately enough.

[0004] Therefore, how to provide a public security prediction and protection method applicable to the rural regional scope, with high detection accuracy and low false alarm rate, is a technical problem that urgently needs to be solved. Summary of the Invention

[0005] The main purpose of the present invention is to provide a method, device, equipment and storage medium for predicting public security prevention and control within a regional scope, aiming to solve the technical problem of high false alarm rate in the current public security prevention and control prediction within a regional scope.

[0006] To achieve the above purpose, the present invention provides a method for predicting public security prevention and control within a regional scope, the method comprising the following steps:

[0007] Obtain a set of personnel conflict events within the regional scope; wherein, the set of personnel conflict events includes a number of personnel conflict events, and each personnel conflict event includes a personnel conflict subject and conflict-related information;

[0008] Generate a personnel conflict relationship graph within the regional scope based on the set of personnel conflict events;

[0009] Obtain the surveillance videos within the regional scope, extract the face information in the surveillance videos, and generate a personnel gathering event within the regional scope;

[0010] Generate a public security prevention and control prediction result based on the personnel conflict relationship diagram and the personnel gathering events.

[0011] Optionally, the step of obtaining the personnel conflict event set within the area range specifically includes:

[0012] Obtain the personnel conflict event information uploaded by the resident side, extract the personnel conflict subjects and conflict-related information in the personnel conflict event information, and generate a personnel conflict event.

[0013] Transmit the personnel conflict event to the review side, and when receiving the confirmation information feedback from the review side, write the personnel conflict event into the personnel conflict event set according to the confirmation information.

[0014] Optionally, the conflict-related information includes the occurrence time of the conflict event and the content of the conflict event; the step of transmitting the personnel conflict event to the review side and writing the personnel conflict event into the personnel conflict event set according to the confirmation information when receiving the confirmation information feedback from the review side specifically includes:

[0015] Transmit the personnel conflict event to the review side so that the staff of the review side can verify the conflict event according to the personnel conflict subject, the occurrence time of the conflict event, and the content of the conflict event, and feedback the confirmation information according to the verification result; wherein, the confirmation information includes the conflict event level.

[0016] When receiving the confirmation information feedback from the review side, write the personnel conflict event into the personnel conflict event set according to the conflict event level in the confirmation information.

[0017] Optionally, the conflict event levels include non-conflict event levels and several factual conflict event levels from low to high; the step of writing the personnel conflict event into the personnel conflict event set according to the conflict event level in the confirmation information specifically includes:

[0018] When the conflict event level is a non-conflict event level, ignore the personnel conflict event corresponding to the received confirmation information.

[0019] When the conflict event level is a factual conflict event level, add the conflict event level to the personnel conflict event and write the personnel conflict event into the personnel conflict event set.

[0020] Optionally, the step of generating a personnel conflict relationship diagram within the area range based on the personnel conflict event set specifically includes:

[0021] Extract the person contradiction subjects of each person contradiction event in the person contradiction event set, and based on the person contradiction subjects, establish an initial person contradiction relationship graph; wherein, the person contradiction relationship graph includes several person contradiction subjects as nodes and connection lines connecting the person contradiction subjects;

[0022] According to the contradiction event level of each person contradiction event, assign a contradiction event level to the connection lines connecting the person contradiction subjects in the initial person contradiction relationship graph to generate the final person contradiction relationship graph within the region range.

[0023] Optionally, obtaining the surveillance videos within the region range, extracting the face information in the surveillance videos, and generating the steps of the person gathering event within the region range specifically include:

[0024] Obtain the surveillance videos within the region range, extract the face information in the surveillance videos, and record the activity trajectories and current moving speeds of each person in the person trajectory database according to the position information and time information of the face information;

[0025] Based on the activity trajectories and current moving speeds of each person, determine whether a person gathering event occurs within the region range; wherein, the person gathering event is: at the current moving speed, the activity trajectories of at least a preset number of gathering persons satisfy that the time difference for reaching the target position point is less than the preset time.

[0026] Optionally, the steps of generating a public security prevention and control prediction result according to the person contradiction relationship graph and the person gathering event specifically include:

[0027] Obtain the normal gathering events uploaded by the resident side; wherein, the normal gathering events include the normal gathering location and the normal gathering time;

[0028] Based on the normal gathering location and the normal gathering time, perform a normal gathering event elimination action from the person gathering events; wherein, the normal gathering event elimination action is to eliminate the person gathering events with the same gathering location and gathering time within the error range;

[0029] Extract all the gathering persons in each of the person gathering events after elimination, and use the gathering persons to match the contradiction event levels of each group of two person contradiction subjects with connection lines in the person contradiction relationship graph;

[0030] Based on the contradiction event levels, query the corresponding public security event contribution scores in the contradiction event level and public security event contribution score comparison table, and calculate the sum of the public security event contribution scores of each person gathering event according to the public security event contribution scores of each group of two person contradiction subjects with connection lines;

[0031] When the sum of the public security incident contribution scores exceeds a preset public security incident contribution score threshold, a public security prevention and control warning signal is generated; wherein, the public security prevention and control warning signal records the gathering location and gathering time of the personnel gathering event.

[0032] In addition, to achieve the above object, the present invention also provides a public security prevention and control prediction device within a regional scope, including:

[0033] An acquisition module, configured to acquire a set of personnel contradiction events within a regional scope; wherein, the set of personnel contradiction events includes a number of personnel contradiction events, and each personnel contradiction event includes a personnel contradiction subject and contradiction-related information;

[0034] A generation module, configured to generate a personnel contradiction relationship graph within a regional scope based on the set of personnel contradiction events;

[0035] An extraction module, configured to acquire surveillance videos within a regional scope, extract face information from the surveillance videos, and generate a personnel gathering event within a regional scope;

[0036] A prediction module, configured to generate a public security prevention and control prediction result according to the personnel contradiction relationship graph and the personnel gathering event.

[0037] In addition, to achieve the above object, the present invention also provides a public security prevention and control prediction device within a regional scope. The public security prevention and control prediction device within a regional scope includes: a memory, a processor, and a public security prevention and control prediction program stored on the memory and executable on the processor. When the public security prevention and control prediction program within a regional scope is executed by the processor, the steps of the public security prevention and control prediction method within a regional scope as described above are implemented.

[0038] In addition, to achieve the above object, the present invention also provides a storage medium. A public security prevention and control prediction program within a regional scope is stored on the storage medium. When the public security prevention and control prediction program within a regional scope is executed by a processor, the steps of the public security prevention and control prediction method within a regional scope as described above are implemented.

[0039] The beneficial effects of the present invention are as follows: A public security prevention and control prediction method, device, device, and storage medium within a regional scope are proposed. By acquiring a set of personnel contradiction events within a regional scope, a personnel contradiction relationship graph is established, and the personnel contradiction relationship graph is used to filter and perform public security prevention and control prediction on the personnel gathering event extracted from the surveillance video, which can comprehensively consider the prediction impact of personnel contradiction events and normal rural gathering activities on public security prevention and control, improve the management strength of rural public security prevention and control, and solve the technical problem of high false alarm rate in the current public security prevention and control prediction within a regional scope. Description of the Drawings

[0040] Figure 1 Schematic diagram of the device structure of the hardware operating environment involved in the embodiment solution of the present invention;

[0041] Figure 2 Schematic flow chart of the embodiment of the public security prevention and control prediction method within the scope of the present invention;

[0042] Figure 3 Block diagram of the structure of a public security prevention and control prediction device within a certain area in the embodiment of the present invention.

[0043] The realization of the object of the present invention, functional characteristics and advantages will be further described with reference to the embodiments and the accompanying drawings. Detailed implementation manners

[0044] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0045] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0046] As Figure 1 shown, Figure 1 is the schematic diagram of the device structure of the hardware operating environment involved in the embodiment solution of the present invention.

[0047] As Figure 1 shown, the device may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0048] Those skilled in the art can understand that Figure 1 the structure of the device shown in

[0049] does not constitute a limitation to the device, and may include more or fewer components than shown in the figure, or combine some components, or arrange different components. Figure 1As shown, in the memory 1005 which is a computer storage medium, an operating system, a network communication module, a user interface module, and a public security prevention and control prediction program within a region can be included.

[0050] In Figure 1 the terminal shown, the network interface 1004 is mainly used to connect to the background server and communicate with the background server for data; the user interface 1003 is mainly used to connect to the client (user side) and communicate with the client for data; and the processor 1001 can be used to call the public security prevention and control prediction program stored in the memory 1005 and perform the following operations:

[0051] Obtain a set of personnel conflict events within a region; wherein, the set of personnel conflict events includes several personnel conflict events, and each personnel conflict event includes a personnel conflict subject and conflict-related information;

[0052] Based on the set of personnel conflict events, generate a personnel conflict relationship graph within the region;

[0053] Obtain surveillance videos within the region, extract face information from the surveillance videos, and generate a personnel gathering event within the region;

[0054] Generate a public security prevention and control prediction result according to the personnel conflict relationship graph and the personnel gathering event.

[0055] The specific embodiments of the present invention applied to the device are basically the same as the embodiments of the following public security prevention and control prediction method within a region, and will not be elaborated here.

[0056] An embodiment of the present invention provides a public security prevention and control prediction method within a region. Refer to Figure 2 , Figure 2 which is a schematic flowchart of the embodiment of the public security prevention and control prediction method within a region of the present invention.

[0057] In this embodiment, the public security prevention and control prediction method within the region includes the following steps:

[0058] S100: Obtain a set of personnel conflict events within a region; wherein, the set of personnel conflict events includes several personnel conflict events, and each personnel conflict event includes a personnel conflict subject and conflict-related information;

[0059] S200: Based on the set of personnel conflict events, generate a personnel conflict relationship graph within the region;

[0060] S300: Obtain surveillance videos within the region, extract face information from the surveillance videos, and generate a personnel gathering event within the region;

[0061] S400: Generate a public security prevention and control prediction result based on the personnel conflict relationship diagram and the personnel gathering event.

[0062] It should be noted that in the prior art, rural public security prevention and control usually adopts a public security management solution based on video surveillance. By setting video surveillance devices at key locations, when rural public security problems are discovered, the corresponding responsible persons are dispatched to handle relevant problems. However, in practice, the existing video surveillance devices and the setting of public security prevention and control responsible persons can only be monitored when or after rural public security incidents occur, and cannot play a preventive role before the incidents occur. The achieved public security maintenance and management effects are not good. If serious public security incidents occur, even if the incidents are monitored, the resulting personal and property losses cannot be recovered. In some solutions, it is proposed to identify incidents such as gathering and fighting by monitoring personnel gatherings. However, in the rural scenario, the daily lives of residents usually have regular gathering behaviors (such as going to the market, weddings and funerals, and joint labor, etc.), resulting in a high false alarm rate in predicting public security incidents through personnel gatherings, causing a large workload for public security prevention and control responsible persons or patrol personnel, and further affecting the vigilance in the face of public security management. When a real public security incident occurs, the solution plan cannot be triggered quickly and accurately enough.

[0063] To solve the above problems, in this embodiment, by obtaining the personnel conflict event set within the regional scope, a personnel conflict relationship diagram is established based on this, and the personnel gathering events extracted from the surveillance video are filtered and public security prevention and control predicted using this personnel conflict relationship diagram. It can comprehensively consider the influence of personnel conflict events and normal rural gathering activities on public security prevention and control prediction, improve the management intensity of rural public security prevention and control, and solve the technical problem of high false alarm rate in the current public security prevention and control prediction within the regional scope.

[0064] In a preferred embodiment, the step of obtaining the personnel conflict event set within the regional scope specifically includes: obtaining the personnel conflict event information uploaded by the resident side, extracting the personnel conflict subjects and conflict correlation information in the personnel conflict event information to generate personnel conflict events; transmitting the personnel conflict events to the audit side, and when receiving the confirmation information feedback from the audit side, writing the personnel conflict events into the personnel conflict event set according to the confirmation information.

[0065] Among them, the contradictory correlation information includes the occurrence event of the contradictory event and the content of the contradictory event; the step of transmitting the personnel contradictory event to the audit end and writing the personnel contradictory event into the personnel contradictory event set according to the confirmation information when receiving the confirmation information feedback from the audit end specifically includes: transmitting the personnel contradictory event to the audit end, so that the staff of the audit end verifies the contradictory event according to the personnel contradictory subject, the occurrence event of the contradictory event and the content of the contradictory event, and feeds back the confirmation information according to the verification result; among them, the confirmation information includes the contradictory event level; when receiving the confirmation information feedback from the audit end, write the personnel contradictory event into the personnel contradictory event set according to the contradictory event level in the confirmation information.

[0066] Furthermore, the contradictory event level includes a non-contradictory event level and several fact contradictory event levels from low to high; the step of writing the personnel contradictory event into the personnel contradictory event set according to the contradictory event level in the confirmation information specifically includes: when the contradictory event level is the non-contradictory event level, ignore the personnel contradictory event corresponding to the received confirmation information; when the contradictory event level is the fact contradictory event level, add the contradictory event level to the personnel contradictory event and write the personnel contradictory event into the personnel contradictory event set.

[0067] In this embodiment, through the personnel contradictory event information uploaded from the resident side, the resident side can be a reporting channel for personnel contradictory events provided by the government or the responsible unit to the public. When residents see or learn about personnel contradictory events in the village during their daily lives, they can report the personnel contradictory event information through this channel. After being confirmed by the audit end, the personnel contradictory event is written into the personnel contradictory event set for calling relevant information about personnel relationships during public security prevention and control prediction. It should be noted that when the audit end conducts the audit of contradictory events, it is necessary to classify them by level (for example, for the contradiction of ordinary quarrels between villagers, its level is classified as level one; for the contradiction involving finances, its level is classified as level two; for the contradiction involving physical pushing and shoving, its level is classified as level three, and so on, covering all possible behavioral characteristics of contradictions). Thus, by quantifying contradictions, quantitative contradiction data can be provided during public security prevention and control prediction, improving the accuracy of public security prevention and control prediction and reducing the false alarm rate.

[0068] In a preferred embodiment, the steps of generating a personnel conflict relationship diagram within a region based on the set of personnel conflict events specifically include: extracting the personnel conflict subjects of each personnel conflict event in the set of personnel conflict events, and establishing an initial personnel conflict relationship diagram based on the personnel conflict subjects; wherein, the personnel conflict relationship diagram includes a number of personnel conflict subjects as nodes and connection lines connecting the personnel conflict subjects; according to the conflict event level of each personnel conflict event, assigning a conflict event level to the connection lines connecting the personnel conflict subjects in the initial personnel conflict relationship diagram to generate the final personnel conflict relationship diagram within the region.

[0069] Among them, the steps of obtaining a surveillance video within a region, extracting the face information in the surveillance video, and generating a personnel gathering event within the region specifically include: obtaining a surveillance video within the region, extracting the face information in the surveillance video, recording the activity trajectory and current moving speed of each person in the personnel trajectory database according to the position information and time information of the face information; judging whether a personnel gathering event occurs within the region based on the activity trajectory and current moving speed of each person; wherein, the personnel gathering event is: with the current moving speed, at least a preset number of gathering personnel's activity trajectories satisfy that the time difference for reaching the target position point is less than a preset time.

[0070] On this basis, the steps of generating a public security prevention and control prediction result according to the personnel conflict relationship diagram and the personnel gathering event specifically include: obtaining a normal gathering event uploaded by the resident side; wherein, the normal gathering event includes a normal gathering location and a normal gathering time; based on the normal gathering location and the normal gathering time, performing a normal gathering event elimination action on the personnel gathering events; wherein, the normal gathering event elimination action is to eliminate the personnel gathering events with the same gathering location and gathering time within the error range; extracting all the gathering personnel in each of the personnel gathering events after elimination, and using the gathering personnel to match the conflict event levels of each group of two personnel conflict subjects with connection lines in the personnel conflict relationship diagram; based on the conflict event levels, querying the corresponding public security event contribution scores in the conflict event level and public security event contribution score comparison table, and calculating the sum of the public security event contribution scores of each personnel gathering event according to the public security event contribution scores of each group of two personnel conflict subjects with connection lines; when the sum of the public security event contribution scores exceeds a preset public security event contribution score threshold, generating a public security prevention and control warning signal; wherein, the public security prevention and control warning signal records the gathering location and gathering time of the personnel gathering event.

[0071] In this embodiment, first, a personnel conflict relationship graph is generated using the personnel conflict event set, with personnel as nodes and the conflicts between personnel as connection lines. After that, based on the personnel activity trajectories obtained through video surveillance, all personnel gathering events within the area range are extracted according to the activity trajectories. Finally, for the personnel in all personnel gathering events, the conflict event levels between them are searched in the personnel conflict relationship graph, and the corresponding public security event contribution scores are matched using the conflict event levels. Thus, by statistically comparing the sum of the public security event contribution scores between all personnel in each personnel gathering event with a preset public security event contribution score threshold, when the sum of the public security event contribution scores exceeds the preset public security event contribution score threshold, it is determined that there may be a public security event. At this time, a public security prevention and control warning signal is generated, enabling patrol personnel or responsible persons to carry out corresponding public security management according to the gathering location and gathering time in the public security prevention and control warning signal.

[0072] In this embodiment, a method for predicting public security prevention and control within a regional scope is provided. By obtaining the personnel conflict event set within the regional scope, a personnel conflict relationship graph is established, and the personnel gathering events extracted from the surveillance video are filtered and public security prevention and control predicted using this personnel conflict relationship graph. It can comprehensively consider the influence of personnel conflict events and normal rural gathering activities on public security prevention and control prediction, improve the management strength of rural public security prevention and control, and solve the technical problem of high false alarm rate in current public security prevention and control prediction within the regional scope.

[0073] Refer to Figure 3 , Figure 3 which is the structural block diagram of the embodiment of the public security prevention and control prediction device within the regional scope of the present invention.

[0074] As Figure 3 shown, the public security prevention and control prediction device proposed in the embodiment of the present invention within the regional scope includes:

[0075] An acquisition module 10, configured to acquire a personnel conflict event set within the regional scope; wherein, the personnel conflict event set includes a number of personnel conflict events, and each personnel conflict event includes a personnel conflict subject and conflict-related information;

[0076] A generation module 20, configured to generate a personnel conflict relationship graph within the regional scope based on the personnel conflict event set;

[0077] An extraction module 30, configured to acquire a surveillance video within the regional scope, extract the face information in the surveillance video, and generate a personnel gathering event within the regional scope;

[0078] A prediction module 40, configured to generate a public security prevention and control prediction result according to the personnel conflict relationship graph and the personnel gathering event.

[0079] Other embodiments or specific implementation manners of the public security prevention and control prediction device within the scope of the present invention may refer to the above method embodiments, and will not be elaborated herein.

[0080] In addition, the present invention also provides a public security prevention and control prediction device within a region. The public security prevention and control prediction device within the region includes: a memory, a processor, and a public security prevention and control prediction program stored on the memory and executable on the processor. When the public security prevention and control prediction program within the region is executed by the processor, the steps of the public security prevention and control prediction method within the region as described above are implemented.

[0081] The specific implementation manner of the public security prevention and control prediction device within the scope of the present application is basically the same as each of the above embodiments of the public security prevention and control prediction method within the region, and will not be elaborated herein.

[0082] In addition, the present invention also provides a readable storage medium. The readable storage medium includes a computer-readable storage medium, on which a public security prevention and control prediction program within a region is stored. The readable storage medium may be Figure 1 the memory 1005 in a terminal, or at least one of ROM (Read-Only Memory), RAM (Random Access Memory), magnetic disk, and optical disk. The readable storage medium includes several instructions for causing a public security prevention and control prediction device with a processor to execute the public security prevention and control prediction method within the region described in each embodiment of the present invention.

[0083] The specific implementation manner of the readable storage medium in the present application is basically the same as each of the above embodiments of the public security prevention and control prediction method within the region, and will not be elaborated herein.

[0084] It can be understood that in the description of this specification, the descriptions referring to terms such as "one embodiment", "another embodiment", "other embodiments", or "the first embodiment to the Nth embodiment" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0085] It should be noted that in this text, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article or system comprising a series of elements not only includes those elements but also other elements not explicitly listed, or elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of additional identical elements in the process, method, article or system comprising such element.

[0086] The serial numbers of the above embodiments of the present invention are only for description and do not represent the superiority or inferiority of the embodiments.

[0087] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium as described above (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0088] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the description of the present invention and the content of the drawings, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A public security prevention and control prediction method within a region, characterized in that, The method includes the following steps: Obtain a set of personnel conflict events within a region; wherein, the set of personnel conflict events includes a number of personnel conflict events, and each personnel conflict event includes a personnel conflict subject and conflict-related information; Among them, obtaining the set of personnel conflict events within a region specifically includes: Obtain the personnel conflict event information uploaded by the resident side, extract the personnel conflict subject and conflict-related information in the personnel conflict event information, and generate a personnel conflict event; transmit the personnel conflict event to the review side, and when receiving the confirmation information feedback from the review side, write the personnel conflict event into the set of personnel conflict events according to the confirmation information; Among them, the conflict-related information includes the occurrence time and content of the conflict event; the step of transmitting the personnel conflict event to the review side and writing the personnel conflict event into the set of personnel conflict events according to the confirmation information when receiving the confirmation information feedback from the review side specifically includes: Transmit the personnel conflict event to the review side so that the staff of the review side verifies the conflict event based on the personnel conflict subject, the occurrence time of the conflict event, and the content of the conflict event, and feedback the confirmation information according to the verification result; wherein, the confirmation information includes the conflict event level; when receiving the confirmation information feedback from the review side, write the personnel conflict event into the set of personnel conflict events according to the conflict event level in the confirmation information; Generate a personnel conflict relationship diagram within the region based on the set of personnel conflict events; specifically include: extract the personnel conflict subject of each personnel conflict event in the set of personnel conflict events, and establish an initial personnel conflict relationship diagram based on the personnel conflict subject; wherein, the personnel conflict relationship diagram includes a number of personnel conflict subjects as nodes and connection lines connecting the personnel conflict subjects; according to the conflict event level of each personnel conflict event, assign a conflict event level to the connection lines connecting the personnel conflict subjects in the initial personnel conflict relationship diagram to generate the final personnel conflict relationship diagram within the region; Obtain the surveillance videos within the region, extract the face information in the surveillance videos, and generate a personnel gathering event within the region; specifically include: obtain the surveillance videos within the region, extract the face information in the surveillance videos, record the activity trajectory and current moving speed of each person in the personnel trajectory database according to the position information and time information of the face information; based on the activity trajectory and current moving speed of each person, judge whether a personnel gathering event occurs within the region; wherein, the personnel gathering event is: with the current moving speed, at least a preset number of gathering personnel's activity trajectories satisfy that the time difference for reaching the target position point is less than a preset time; Generate a public security prevention and control prediction result based on the personnel contradiction relationship diagram and the personnel gathering events; specifically including: Obtain normal gathering events uploaded by the resident side; wherein, the normal gathering events include normal gathering locations and normal gathering times; Based on the normal gathering locations and the normal gathering times, perform a normal gathering event elimination action on the personnel gathering events; wherein, the normal gathering event elimination action is to eliminate personnel gathering events with the same gathering location and gathering time within the error range; Extract all the gathering personnel in each of the personnel gathering events after elimination, and use the gathering personnel to match the contradiction event levels of each group of two personnel contradiction subjects with connection lines in the personnel contradiction relationship diagram; Based on the contradiction event levels, query the corresponding public security event contribution scores in the contradiction event level and public security event contribution score comparison table, and calculate the sum of the public security event contribution scores of each of the personnel gathering events according to the public security event contribution scores of each group of two personnel contradiction subjects with connection lines; When the sum of the public security event contribution scores exceeds the preset public security event contribution score threshold, generate a public security prevention and control warning signal; wherein, the public security prevention and control warning signal records the gathering location and gathering time of the personnel gathering event.

2. The public security prevention and control prediction method within the scope of the area described in claim 1, characterized in that, The contradiction event levels include a non-contradiction event level and several factual contradiction event levels from low to high. The step of writing the personnel contradiction event into the personnel contradiction event set according to the contradiction event level in the confirmation information specifically includes: When the contradiction event level is the non-contradiction event level, ignore the personnel contradiction event corresponding to the received confirmation information. When the contradiction event level is the factual contradiction event level, add the contradiction event level to the personnel contradiction event and write the personnel contradiction event into the personnel contradiction event set.

3. A public security prevention and control prediction device within a region, characterized in that, Including: An acquisition module, configured to acquire a personnel contradiction event set within a regional scope; wherein, the personnel contradiction event set includes several personnel contradiction events, and each personnel contradiction event includes personnel contradiction subjects and contradiction correlation information. Among them, acquiring the personnel contradiction event set within a regional scope specifically includes: Obtain the personnel contradiction event information uploaded by the resident side, extract the personnel contradiction subjects and contradiction correlation information in the personnel contradiction event information, and generate a personnel contradiction event; Transmit the personnel contradiction event to the review end, and when receiving the confirmation information feedback from the review end, write the personnel contradiction event into the personnel contradiction event set according to the confirmation information. Among them, the contradiction correlation information includes the contradiction event occurrence time and the contradiction event occurrence content; Transmitting the personnel contradiction event to the review end, and when receiving the confirmation information feedback from the review end, writing the personnel contradiction event into the personnel contradiction event set specifically includes: Transmit the personnel conflict event to the review end, so that the staff at the review end can verify the conflict event according to the personnel conflict subject, the time of the conflict event occurrence, and the content of the conflict event occurrence, and feedback confirmation information according to the verification result; wherein, the confirmation information includes the conflict event level; when receiving the confirmation information feedback from the review end, write the personnel conflict event into the personnel conflict event set according to the conflict event level in the confirmation information; A generation module, configured to generate a personnel conflict relationship diagram within a region based on the personnel conflict event set; specifically including: extracting the personnel conflict subjects of each personnel conflict event in the personnel conflict event set, and establishing an initial personnel conflict relationship diagram based on the personnel conflict subjects; wherein, the personnel conflict relationship diagram includes several personnel conflict subjects as nodes and connection lines connecting the personnel conflict subjects; according to the conflict event level of each personnel conflict event, assign a conflict event level to the connection lines connecting the personnel conflict subjects in the initial personnel conflict relationship diagram to generate the final personnel conflict relationship diagram within the region; An extraction module, configured to obtain surveillance videos within a region, extract face information in the surveillance videos, and generate a personnel gathering event within the region; specifically including: obtaining surveillance videos within the region, extracting face information in the surveillance videos, and recording the activity trajectories and current moving speeds of each person in the personnel trajectory database according to the position information and time information of the face information; based on the activity trajectories and current moving speeds of each person, determine whether a personnel gathering event occurs within the region; wherein, the personnel gathering event is: with the current moving speed, at least a preset number of gathering personnel's activity trajectories satisfy that the time difference for reaching the target position point is less than a preset time; A prediction module, configured to generate a public security prevention and control prediction result according to the personnel conflict relationship diagram and the personnel gathering event; specifically including: obtaining normal gathering events uploaded by the resident side; wherein, the normal gathering events include normal gathering locations and normal gathering times; based on the normal gathering locations and the normal gathering times, perform a normal gathering event elimination operation on the personnel gathering events; wherein, the normal gathering event elimination operation is to eliminate personnel gathering events with the same gathering location and gathering time within an error range; extract all the gathering personnel in each of the personnel gathering events after elimination, and use the gathering personnel to match the conflict event levels of each pair of two personnel conflict subjects with connection lines in the personnel conflict relationship diagram; based on the conflict event levels, query the corresponding public security event contribution scores in the conflict event level and public security event contribution score comparison table, and calculate the sum of the public security event contribution scores of each of the personnel gathering events according to the public security event contribution scores of each pair of two personnel conflict subjects with connection lines; when the sum of the public security event contribution scores exceeds a preset public security event contribution score threshold, generate a public security prevention and control warning signal; wherein, the public security prevention and control warning signal records the gathering location and gathering time of the personnel gathering event.

4. A public security prevention and control prediction device within a region, characterized in that, The public security prevention and control prediction device within the said area range includes: a memory, a processor, and a public security prevention and control prediction program within the said area range that is stored on the memory and can run on the processor. When the public security prevention and control prediction program within the said area range is executed by the processor, it implements the steps of the public security prevention and control prediction method within the said area range as described in any one of claims 1 to 2.

5. A storage medium, characterized in that, A public security prevention and control prediction program within the said area range is stored on the storage medium. When the public security prevention and control prediction program within the said area range is executed by the processor, it implements the steps of the public security prevention and control prediction method within the said area range as described in any one of claims 1 to 2.

Citation Information

Patent Citations

  • Safety monitoring method, device and system and storage medium

    CN108960352A

  • Identification method, identification device and identification system for dispute event

    CN111324740A

  • Crowd gathering prediction method and device, computer equipment and storage medium

    CN113536932A

  • User event tag generation method, equipment, storage medium and device

    CN115438248A