Intelligent police affair big data analysis system

Abstract

The invention discloses an intelligent police service big data analysis system, and belongs to the technical field of data analysis. The method is used for solving the technical problem that in an existing scheme, the depth and breadth of active processing and analysis of police service data in different position areas are not good. The police service data of different position areas subjected to gridding processing are supervised, data processing analysis of abnormal influence is carried out on the different position areas, dynamic marking is carried out on the different position areas according to an analysis result, and data expansion analysis of overall influence is carried out on all dynamic marking data; and according to an analysis result, dynamically associating overall influence abnormal labels for different position areas, and carrying out integrated analysis on the obtained labels and the overall influence abnormal labels in different aspects in the early stage so as to dynamically implement intelligent police service optimization prompts for different position areas. According to the invention, targeted and differentiated optimization prompts are implemented for different position areas by multiple technical means.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a smart policing big data analysis system. Background Art

[0002] Smart policing refers to the use of modern information technology, such as big data, cloud computing, the Internet of Things, artificial intelligence and other technical means, combined with advanced management concepts and methods, to achieve intelligent work, information-based work and efficient services; smart policing big data includes but is not limited to criminal record data, video surveillance data, social media and network data, Internet of Things (IoT) sensor data, public service request data, traffic flow data and biometric data.

[0003] When implementing existing smart police big data analysis solutions, it is impossible to conduct grid-based supervision and analysis of police big data in different location areas, obtain the usage effects of police data in different location areas in different aspects, and implement targeted police processing prompts based on the usage anomalies of police data in different location areas in different aspects. As a result, the depth and breadth of active processing and analysis of police data in different location areas are poor. Summary of the Invention

[0004] The purpose of the present invention is to provide a smart police big data analysis system to solve the technical problem that the depth and breadth of active processing and analysis of police data in different location areas in existing solutions are poor.

[0005] The purpose of the present invention can be achieved through the following technical solutions: A smart police big data analysis system, comprising: The police grid supervision processing module is used to perform grid processing on different location areas, supervise the police data of different location areas, and analyze the impact of faults, and obtain the fault impact value and fault impact degree corresponding to the different location areas processed by the grid processing; The police grid supervision analysis module is used to process and analyze data on abnormal impacts in different location areas of grid processing, dynamically mark different location areas based on the analysis results, and conduct data expansion analysis on the overall impact of all dynamically marked data, and dynamically associate overall impact abnormal labels with different location areas based on the analysis results; The police grid analysis and prompt module is used to dynamically implement smart police optimization prompts for different location areas based on the labels of different location areas and the associated overall impact anomaly labels.

[0006] Preferably, different location areas are gridded and numbered, and police data of different location areas processed in the grid are periodically supervised and counted according to the numbers. When analyzing the impact of faults on police data of different location areas processed in the grid, fault statistics in the police data are obtained and analyzed. If the fault statistics are empty, the location area is associated with the fault normal label and the corresponding fault impact value is set to 0; If the fault statistics data is not empty and the fault types are all actively discovered, the first fault impact label is associated with the location area, and the corresponding fault impact value is set to N, where N is a positive integer.

[0007] Preferably, if the fault statistics data is not empty and the fault type is a passive discovery type, the second fault impact label is associated with the location area, and the corresponding fault impact value is set to N, and the formula is used. Calculated; where n and m are the total number of active discovery types and the total number of passive discovery types in the fault statistics of the location area, respectively; α is the discovery influence coefficient, and its value is greater than 1; The fault impact value of the location area is compared with a preset fault impact threshold value according to the first fault impact label or the second fault impact label.

[0008] Preferably, if the fault impact value is less than or equal to the fault impact threshold, the fault impact of the corresponding location area is determined to be slightly abnormal, and the total number of slightly abnormal fault impacts is increased by one; Otherwise, the fault impact of the location area is determined to be severely abnormal, and the total number of severe abnormal fault impacts is increased by one.

[0009] Preferably, the total number of minor anomalies C and the total number of major anomalies D corresponding to several monitoring periods of the location area are obtained, and the total number of minor anomalies C and the total number of major anomalies D are calculated by the formula Calculate the abnormal impact value BY corresponding to the location area; where β is the mark influence coefficient, and its value is greater than 1; M is the total number of monitoring cycles; A is the first mark influence threshold.

[0010] Preferably, the fault impact values ​​corresponding to several monitoring periods of the location area are obtained, and the formula Calculate the abnormal impact value BY corresponding to the location area; where B is the second mark impact threshold.

[0011] Preferably, if the abnormal impact value is less than or equal to 0, the corresponding location area is marked as a normal impact area; Otherwise, the location area will be marked as a special impact area.

[0012] Preferably, all special impact areas marked in all monitoring cycles and the corresponding abnormal impact values ​​are obtained, and the formula Calculate and obtain the overall impact value ZY corresponding to all special impact areas; where i is a different special impact area, i=1, 2, 3, ..., p; p is a positive integer representing the total number of all special impact areas; F is the overall impact threshold; If the overall impact value is less than or equal to 1, all location areas are associated with the overall impact mild abnormality label; Otherwise, the location area will be associated with a label with a severe overall impact anomaly.

[0013] Preferably, when dynamically optimizing prompts for smart policing in different location areas, the corresponding marks and associated abnormal labels of different location areas are synchronously analyzed in sequence; If the location area is marked as a regular impact area and is associated with a slight abnormal overall impact label, the first smart police optimization prompt will be implemented for the location area; If the location area is marked as a special impact area and is associated with an overall impact severe abnormality label, the third smart policing optimization prompt will be implemented for the location area.

[0014] Preferably, if the location area is marked as a regular impact area and is associated with a severe abnormal overall impact label, the second smart police optimization prompt is implemented for the location area; If the location area is marked as a special impact area and is associated with a mild abnormal overall impact label, the second smart policing optimization prompt will be implemented for the location area.

[0015] Compared with the existing solutions, the present invention achieves the following beneficial effects: The present invention performs grid processing on different location areas, and supervises the police data of different location areas and performs processing and analysis of fault impacts. It can not only obtain the fault impact values ​​and fault impact degrees corresponding to the different location areas processed by grid processing, but also provide reliable local supervision and processing data support for subsequent abnormal impact analysis corresponding to different aspects of different location areas.

[0016] The present invention performs data processing and analysis of abnormal impacts on different location areas processed in a grid manner, dynamically marks different location areas based on the analysis results, performs data expansion analysis of the overall impact on all dynamically marked data, and dynamically associates overall impact abnormal labels with different location areas based on the analysis results, thereby realizing diversified expansion analysis of local abnormal supervision data corresponding to different location areas, and improving the depth and breadth of active processing and analysis of police data in different location areas.

[0017] The present invention dynamically implements smart policing optimization prompts for different location areas by integrating and analyzing the marks obtained from different aspects of early processing and the overall impact abnormal labels, and realizes multiple technical means to implement targeted and differentiated optimization prompts for different location areas, further improving the depth and breadth of active processing and analysis of police data in different location areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The present invention will be further described below with reference to the accompanying drawings.

[0019] Figure 1 This is a flowchart of the operation of a smart police big data analysis system of the present invention. DETAILED DESCRIPTION

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0021] like Figure 1 As shown, the present invention is a smart police big data analysis system, including a police grid supervision processing module, a police grid supervision analysis module and a police grid analysis prompt module; The police grid supervision processing module is used to perform grid processing on different location areas, supervise police data in different location areas, and analyze fault impacts, obtaining fault impact values ​​and fault impact levels corresponding to different location areas processed by the grid; it includes: Performing grid processing on different location areas, numbering the different location areas processed by the grid processing, and periodically supervising and statistically analyzing the police data of the different location areas processed by the grid processing according to the numbers; when performing fault impact processing and analysis on the police data of the different location areas processed by the grid processing, obtaining and analyzing fault statistical data in the police data; It should be noted that the location area can be determined according to the actual application scenario, and the grid processing of different location areas can be determined according to the existing administrative area division rules, or according to the preset division area, or customized by professional and technical personnel in this field according to the application requirements of the actual application scenario. The specific processing steps and processing rules are not limited here; In addition, the numbering rules can be customized according to the requirements of the actual application scenario; Periodic supervision statistics can be achieved through a preset supervision cycle. The unit of the supervision cycle is day. The specific supervision period is not limited and can also be based on the default 30 days. Police data includes fault statistics and the corresponding fault locations and time points; fault statistics include the specific faults recorded and the corresponding fault types; Fault types include active discovery type and passive discovery type; Among them, the active discovery type specifically refers to police officers actively discovering the failure of police equipment, and police equipment can specifically be cameras in public areas; Passive discovery refers to the passive discovery of police equipment failures by police officers, for example, through public feedback or during the police officers' handling of public feedback incidents. If the fault statistics are empty, the location area is associated with the fault normal label and the corresponding fault impact value is set to 0; If the fault statistics data is not empty and the fault type is all active discovery type, the first fault impact label is associated with the location area, and the corresponding fault impact value is set to N; N is a positive integer, and the specific value is the total number of faults corresponding to the active discovery type; If the fault statistics data is not empty and the fault type is a passive discovery type, the second fault impact label is associated with the location area and its corresponding fault impact value is set to N. Calculated; where n and m are the total number of active discovery types and the total number of passive discovery types in the fault statistics of the location area, respectively; α is the discovery impact coefficient, and its value is greater than 1. The discovery impact coefficient is used to digitally represent the calculation impact of the calculation item. The specific value is not limited, and the default value of 1.5 can also be used for calculation; It should be noted that the fault impact value is used to digitally process and represent the impact of faults occurring in a location area during a corresponding regulatory cycle. It serves the following purposes: it can digitally represent all fault impacts in different location areas during a corresponding regulatory cycle, and also provide reliable local regulatory processing data support for subsequent analysis of abnormal impacts in different aspects of different location areas. The fault impact value of the location area is compared with a preset fault impact threshold based on the first fault impact label or the second fault impact label. The value of the fault impact threshold can be determined based on the median value of all fault impact values ​​obtained through historical supervision processing or based on the actual operational design requirements corresponding to the location area. The specific value is not limited in the embodiments of the present invention. If the fault impact value is less than or equal to the fault impact threshold, the fault impact of the corresponding location area is determined to be slightly abnormal, and the total number of its fault impact slightly abnormalities is increased by one; Otherwise, the fault impact of the location area is determined to be severe abnormal, and the total number of severe abnormal fault impact is increased by one; In an embodiment of the present invention, by gridding different location areas and supervising the police data of different location areas and performing processing and analysis of fault impacts, it is possible to obtain the fault impact values ​​and fault impact degrees corresponding to the different location areas processed by the gridding, and provide reliable local supervision and processing data support for subsequent abnormal impact analysis corresponding to different aspects of different location areas.

[0022] The police grid supervision analysis module is used to process and analyze data on abnormal impacts in different location areas of grid processing, dynamically mark different location areas based on the analysis results, and conduct data expansion analysis on the overall impact of all dynamically marked data. Based on the analysis results, it dynamically associates overall impact abnormal labels with different location areas; including: It should be noted that, in the embodiments of the present invention, processing of abnormal impact data in different location areas of the grid processing can be achieved through different technical solutions; Technical Solution 1: Obtain the total number of minor anomalies C and the total number of major anomalies D corresponding to several monitoring cycles in the location area, and use the formula Calculate and obtain the abnormal impact value BY corresponding to the location area; where β is the marker impact coefficient, and its value is greater than 1. The marker impact coefficient is also used to digitally represent the calculation impact of the corresponding calculation item, and the specific value is not limited; M is the total number of monitoring cycles; A is the first marker impact threshold, and the specific value is not limited. It can be determined based on the design requirements of the abnormal impact corresponding to the location area, or based on the median value of different historical abnormal impact values. Technical Solution 2: Obtain the fault impact value corresponding to several monitoring cycles in the location area, and use the formula Calculate and obtain the abnormal impact value BY corresponding to the location area. Where B is the second mark impact threshold. The specific value is not limited and can be determined based on the design requirements of the abnormal impact corresponding to the location area, or based on the median of different historical abnormal impact values. Technical Solution 3: Obtain the maximum value of the abnormal impact values ​​calculated by Technical Solution 1 and Technical Solution 2, and set it as the abnormal impact value; It should be noted that the abnormal impact value is used to integrate and calculate the supervision processing data corresponding to several monitoring cycles of the location area to digitally represent the corresponding abnormal impact; its role is to achieve the expansion of the fault impact value and fault impact degree corresponding to different location areas in the early stage, further digitally represent the abnormal impact of different location areas corresponding to all monitoring cycles, and improve the depth of active processing and analysis of police data in different location areas; In addition, unlike the existing technical solutions that use a single technical solution to process and analyze data, which has the problem of poor accuracy and reliability of processing and analysis, the embodiments of the present invention use different technical solutions to dynamically process abnormal impacts corresponding to different location areas, which can effectively improve the accuracy and reliability of data expansion analysis in different location areas. If the abnormal impact value is less than or equal to 0, the location area is marked as a regular impact area; Otherwise, the location area will be marked as a special impact area; In the embodiment of the present invention, by performing data analysis on the calculated abnormal impact values ​​and dynamically marking different location areas based on the analysis results, reliable data support can be provided for subsequent overall impact analysis corresponding to all special impact areas; And, obtain all special impact areas marked in all monitoring cycles and the corresponding abnormal impact values, and use the formula Calculate and obtain the overall impact value ZY corresponding to all special impact areas; where i is a different special impact area, i=1, 2, 3, ..., p; p is a positive integer representing the total number of all special impact areas; F is the overall impact threshold, the specific value is not limited and can be determined based on the design requirements of the overall abnormal impact corresponding to all location areas, or can be customized by professionals in this field based on the application requirements of actual application scenarios; It should be noted that the overall impact value is used to process and calculate the abnormal data corresponding to all special impact areas marked in the early stage, so as to digitally represent the corresponding overall impact; The overall impact value further enables the calculation of abnormal data corresponding to all special impact areas obtained in the previous analysis, further improving the breadth of active processing and analysis of police data in different locations; If the overall impact value is less than or equal to 1, all location areas are associated with the overall impact mild abnormality label; Otherwise, the location area will be associated with the overall impact severe abnormality label; In an embodiment of the present invention, by performing data processing and analysis of abnormal impacts on different location areas processed in a grid manner, dynamically marking different location areas based on the analysis results, and performing data expansion analysis of overall impacts on all dynamically marked data, and dynamically associating overall impact abnormal labels with different location areas based on the analysis results, diversified expansion analysis of local abnormal supervision data corresponding to different location areas is achieved, thereby improving the depth and breadth of active processing and analysis of police data in different location areas.

[0023] The police grid analysis and prompt module is used to dynamically implement smart police optimization prompts for different location areas based on the tags of different location areas and the associated overall impact anomaly labels; it includes: When dynamically optimizing smart policing in different locations, the corresponding tags and associated abnormal labels of different locations are analyzed synchronously. If the location area is marked as a regular impact area and is associated with a slight abnormal overall impact label, the first smart police optimization prompt will be implemented for the location area; If the location area is marked as a regular impact area and is associated with a severe abnormal overall impact label, the second smart policing optimization prompt will be implemented for the location area; If the location area is marked as a special impact area and is associated with a label of mild anomaly in overall impact, the second smart policing optimization prompt will be implemented for the location area; If the location area is marked as a special impact area and is associated with a severe abnormal overall impact label, the third smart policing optimization prompt will be implemented for the location area; Among them, the levels corresponding to the first smart police optimization prompt, the second smart police optimization prompt, and the third smart police optimization prompt increase in sequence, and the specific optimization content and rules are not limited, so that the smart policing corresponding to different location areas can carry out targeted and differentiated optimization processing in a timely and efficient manner.

[0024] Different from the existing technical solutions, which can only implement alarm prompts for different location areas through the analysis results of a single technical solution, the reliability and pertinence of the alarm prompts are poor; in the embodiment of the present invention, by integrating and analyzing the marks obtained from different aspects of the early processing and the overall impact abnormal labels, smart policing optimization prompts are dynamically implemented for different location areas, and multiple technical means are used to implement targeted and differentiated optimization prompts for different location areas, further improving the depth and breadth of active processing and analysis of police data in different location areas.

[0025] In the several embodiments provided by the present invention, it should be understood that the disclosed system can be implemented in other ways. For example, the embodiments of the invention described above are merely illustrative. For example, the division of modules is only a logical function division, and other division methods may be used in actual implementation.

[0026] Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, and may be located in one place or distributed across multiple network modules. Some or all of these modules may be selected to achieve the objectives of this embodiment based on actual needs.

[0027] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing module, each module may exist physically separately, or two or more modules may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or hardware plus software functional modules.

[0028] It is obvious to a person skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, but that the present invention can be implemented in other specific forms without departing from the essential characteristics of the present invention.

[0029] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A smart police big data analysis system, characterized by: include: The police grid supervision processing module is used to perform grid processing on different location areas, supervise the police data of different location areas, and analyze the impact of faults, and obtain the fault impact value and fault impact degree corresponding to the different location areas processed by the grid processing; The police grid supervision analysis module is used to process and analyze data on abnormal impacts in different location areas of grid processing, dynamically mark different location areas based on the analysis results, and conduct data expansion analysis on the overall impact of all dynamically marked data, and dynamically associate overall impact abnormal labels with different location areas based on the analysis results; The police grid analysis and prompt module is used to dynamically implement smart police optimization prompts for different location areas based on the labels of different location areas and the associated overall impact anomaly labels.

2. The smart police big data analysis system according to claim 1 is characterized in that: Performing grid processing on different location areas, numbering the different location areas processed by the grid processing, and periodically supervising and statistically analyzing the police data of the different location areas processed by the grid processing according to the numbers; when performing fault impact processing and analysis on the police data of the different location areas processed by the grid processing, obtaining and analyzing fault statistical data in the police data; If the fault statistics are empty, the location area is associated with the fault normal label and the corresponding fault impact value is set to 0; If the fault statistics data is not empty and the fault types are all actively discovered, the first fault impact label is associated with the location area, and the corresponding fault impact value is set to N, where N is a positive integer.

3. The smart police big data analysis system according to claim 2 is characterized in that: If the fault statistics data is not empty and the fault type is a passive discovery type, the second fault impact label is associated with the location area, and the corresponding fault impact value is set to N. Calculated; where n and m are the total number of active discovery types and the total number of passive discovery types in the fault statistics of the location area, respectively; α is the discovery influence coefficient, and its value is greater than 1; The fault impact value of the location area is compared with a preset fault impact threshold value according to the first fault impact label or the second fault impact label.

4. The smart police big data analysis system according to claim 3 is characterized in that: If the fault impact value is less than or equal to the fault impact threshold, the fault impact of the corresponding location area is determined to be slightly abnormal, and the total number of its fault impact slightly abnormalities is increased by one; Otherwise, the fault impact of the location area is determined to be severely abnormal, and the total number of severe abnormal fault impacts is increased by one.

5. The smart police big data analysis system according to claim 4 is characterized in that: Obtain the total number of minor anomalies C and the total number of major anomalies D corresponding to several monitoring cycles in the location area, and use the formula Calculate the abnormal impact value BY corresponding to the location area; where β is the mark influence coefficient, and its value is greater than 1; M is the total number of monitoring cycles; A is the first mark influence threshold.

6. The smart police big data analysis system according to claim 4 is characterized in that: Obtain the fault impact value corresponding to several monitoring cycles in the location area, and use the formula Calculate the abnormal impact value BY corresponding to the location area; where B is the second mark impact threshold.

7. The smart police big data analysis system according to claim 5 or 6, characterized in that: If the abnormal impact value is less than or equal to 0, the location area is marked as a regular impact area; Otherwise, the location area will be marked as a special impact area.

8. The smart police big data analysis system according to claim 7 is characterized in that: Obtain all special impact areas marked in all monitoring cycles and the corresponding abnormal impact values, and use the formula Calculate and obtain the overall impact value ZY corresponding to all special impact areas; where i is a different special impact area, i=1, 2, 3, ..., p; p is a positive integer representing the total number of all special impact areas; F is the overall impact threshold; If the overall impact value is less than or equal to 1, all location areas are associated with the overall impact mild abnormality label; Otherwise, the location area will be associated with a label with a severe overall impact anomaly.

9. The smart police big data analysis system according to claim 8, characterized in that: When dynamically optimizing smart policing in different locations, the corresponding tags and associated abnormal labels of different locations are analyzed synchronously. If the location area is marked as a regular impact area and is associated with a slight abnormal overall impact label, the first smart police optimization prompt will be implemented for the location area; If the location area is marked as a special impact area and is associated with an overall impact severe abnormality label, the third smart policing optimization prompt will be implemented for the location area.

10. The smart police big data analysis system according to claim 9, characterized in that: If the location area is marked as a regular impact area and is associated with a severe abnormal overall impact label, the second smart policing optimization prompt will be implemented for the location area; If the location area is marked as a special impact area and is associated with a mild abnormal overall impact label, the second smart policing optimization prompt will be implemented for the location area.

Images