Public security data digital management system and method based on artificial intelligence

Abstract

The invention discloses a public security data digital management system and method based on artificial intelligence, and relates to the technical field of public security management, and the management method comprises the following steps: carrying out the multi-dimensional data collection of any public security event; based on the processing feedback result, performing anomaly identification on the actual occurrence condition of any public security event; randomly selecting a public security event with a normal judgment result, and identifying a monitoring blind area existing in each dimension; based on the judgment result difference between different public security events, the area range of each monitoring blind area is corrected, and the characteristic value of each dimension is analyzed; based on the characteristic value difference of each dimension, a trigger mechanism is set for the existing evaluation conflict condition; performing multi-dimensional data acquisition on the target area in real time to obtain a characteristic value of each dimension at the current moment; and analyzing the triggering condition between the characteristic value of each dimension and the evaluation conflict mechanism, and judging whether a public security event exists at the current moment.

Description

Technical Field

[0001] The present invention relates to the field of public security management technology, and in particular to a public security data digital management system and method based on artificial intelligence. Background Art

[0002] With the acceleration of urbanization and the complexity of social security situation, public security management is facing more and more challenges. Traditional public security management methods often rely on manual experience and a single data source, resulting in blind spots in the decision-making process, affecting the efficiency and accuracy of public security management; especially when dealing with complex public security incidents, single-dimensional decision-making may lead to judgment errors, which in turn affects the response and handling of the incident;

[0003] In the digital management system of public security data, the diversity and complexity of data make it impossible for single-dimensional data analysis to fully reflect the public security situation; the traditional system relies on a single sensor threshold alarm mechanism, but if it only relies on this data source, other important information may be ignored. For example, when the video analysis module detects abnormal behavior, but the sensors in the corresponding area do not respond, the system often falls into a decision-making deadlock; this decision-making blind spot not only affects the timeliness of public security management, but may also pose a threat to public safety. Summary of the invention

[0004] The purpose of the present invention is to provide a public security data digital management system and method based on artificial intelligence to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solution: a method for digital management of public security data based on artificial intelligence, the management method comprising the following steps:

[0006] Step S100: Preset several monitoring methods to monitor the public security incidents occurring in the target area, and collect multi-dimensional data on any public security incident; based on the processing feedback results of relevant personnel, perform abnormal identification on the actual occurrence of any public security incident;

[0007] Step S200: arbitrarily selecting a public security event with a normal evaluation result, identifying monitoring blind spots in various dimensions; based on the difference in evaluation results between different public security events, correcting the area range of each monitoring blind spot;

[0008] Step S300: Based on the area range of the monitoring blind spots in different dimensions in any public security incident, the characteristic values ​​of each dimension are analyzed; based on the difference in the characteristic values ​​of each dimension, a trigger mechanism is set for the existing assessment conflict situation;

[0009] Step S400: Carry out multi-dimensional data collection on the target area in real time to obtain the characteristic values ​​of each dimension at the current moment; analyze the triggering conditions between the characteristic values ​​of each dimension and the conflict assessment mechanism to determine whether there is a public security incident at the current moment.

[0010] Furthermore, step S100 includes the following steps:

[0011] Step S101: The monitoring data obtained by any monitoring method is set as the dimension data of the corresponding dimension, and the corresponding abnormal identification rules are preset for each dimension. Whenever there is an abnormality in the dimension data of at least one dimension after being identified by the abnormal identification rules, the dimension with abnormal dimension data is set as the abnormal dimension; different monitoring methods include video monitoring, sound sensor monitoring, human flow monitoring and alarm alarm, etc. The corresponding abnormal identification rules are set for different monitoring methods: the user's behavior characteristics are captured through video monitoring and image recognition technology monitoring, and similarity comparison is performed with the behavior characteristics in the preset behavior library to determine whether there is an abnormality; the sound sensor can monitor the intensity and frequency changes of abnormal sounds to determine whether there is an abnormality; the human flow monitoring can determine whether there is an abnormality by the change amplitude of the human flow;

[0012] Step S102: Obtain the monitoring range of each monitoring method in the target area and set it as the dimensional area of ​​the corresponding dimension; extract the dimensional area of ​​any abnormal dimension and set it as the feature area; if there is a common area between the dimensional area of ​​the remaining dimensions and the feature area of ​​the abnormal dimension, then set the dimensional area of ​​the remaining dimensions as the feature area; collect and summarize the dimensional data of any dimension in each feature area to generate a public security event;

[0013] Step S103: Whenever a public security event is generated, relevant personnel are dispatched to handle it, and the processing feedback results of the relevant personnel are collected. If there is an abnormality in the processing feedback result, the corresponding public security event is set as an abnormal public security event; the abnormality in the processing feedback result indicates that the public security event has not actually occurred, so the abnormal public security event indicates a situation that has not occurred, and the regular public security event in the subsequent step indicates the public security event that actually occurred;

[0014] It is inaccurate to directly judge whether a public security incident has actually occurred based on only one monitoring method. For example, video surveillance identifies the user's movements as fighting movements, or someone accidentally triggers the alarm device. Relevant personnel need to process and feedback to know whether it has actually occurred. Therefore, the above steps illustrate the inaccuracy of abnormal identification by a single monitoring method, which can lead to a comprehensive evaluation method for subsequent multi-source monitoring methods.

[0015] Further, step S200 includes the following steps:

[0016] Step S201: setting the public security events without abnormalities in the processing feedback results as regular public security events, arbitrarily selecting a regular public security event, setting each dimension of each feature area monitored in the selected regular public security record as the target dimension, dividing the target dimension according to whether it is an abnormal dimension, and obtaining a normal dimension set and an abnormal dimension set respectively;

[0017] Step S202: arbitrarily select an abnormal dimension from the abnormal dimension set, obtain a feature area corresponding to the selected abnormal dimension, merge the feature areas of all abnormal dimensions to obtain a comprehensive abnormal area; arbitrarily select a normal dimension from the normal dimension set, obtain a common area between the selected normal dimension and the comprehensive abnormal area; set the common area as an expected blind area of ​​the selected normal dimension, and obtain the area range of the expected blind area in the target area;

[0018] Step S203: Set the selected normal dimension as the i-th dimension among all dimensions, and obtain the dimensional area of ​​the i-th dimension from the remaining conventional public security events respectively. When the i-th dimension is a normal dimension, extract the common area between the dimensional area of ​​the i-th dimension and the comprehensive abnormal area of ​​the conventional public security event. If there is an inclusion relationship between the common area of ​​the i-th dimension and the expected blind area, set the expected blind area to a common area with a larger area range. Otherwise, set the common area to another expected blind area of ​​the i-th dimension, and use the set several expected blind areas as the monitoring blind areas of the i-th dimension.

[0019] Step S204: arbitrarily select an abnormal public security event. If the i-th dimension in the selected abnormal public security event is an abnormal dimension, then extract each normal dimension that has a common area with the i-th dimension from the selected abnormal public security event. If the monitoring blind area of ​​the i-th dimension contains a common area with the normal dimension, set the contained common area as the initial area, and then obtain each monitoring blind area of ​​the contained normal dimension, wherein the j-th monitoring blind area in the i-th dimension is set to A1(i,j), and the k-th monitoring blind area in the contained normal dimension is set to A2 k If the monitoring blind area A2 k There is a common area A between the initial area and the pub1 , then the public area A is taken from the initial area pub1 Remove and obtain a correction area;

[0020] Step S205: Compare the correction area with the monitoring blind area A1(i,j). If there is a common area A1 between the two areas, pub2 , then the public area A1(i,j) is removed from the monitoring blind areapub2 Remove it and obtain the corrected j-th monitoring blind area A1 in the i-th dimension ’ (i, j), and perform range correction on each monitoring blind area of ​​the i-th dimension;

[0021] First, by not detecting abnormal data in the selected dimension, but detecting abnormal data in the other dimensions, and when there is actually a public security incident, the monitoring blind spot of the selected dimension can be preliminarily obtained; and if in the monitoring blind spot, if no public security incident actually occurs, abnormal data is detected in the corresponding other dimensions, but abnormal data is not detected in the selected dimension, it means that the public area does not actually belong to the monitoring blind spot, and the monitoring blind spot can be corrected, so that a more accurate monitoring blind spot can be obtained.

[0022] Further, step S300 includes the following steps:

[0023] Step S301: arbitrarily select the i-th dimension to obtain each monitoring blind area after correction in the i-th dimension, wherein the area of ​​the j-th monitoring blind area is set to S (i,j) , according to the formula:

[0024] ;

[0025] Where j is a positive integer and j∈(1,m), m is the number of monitoring blind areas contained in the i-th dimension, S(i) is the monitoring range area of ​​the i-th dimension corresponding to the monitoring method in the target area; the first feature proportion a of the i-th dimension is calculated i ; The first feature ratio represents the area ratio of the monitoring blind area in any dimension, that is, the probability of misjudgment, because abnormal situations occurring in the monitoring blind area are likely to be missed;

[0026] Step S302: All public security events are divided into a first event set and a second event set according to whether the i-th dimension is an abnormal dimension, wherein the i-th dimension of each public security event in the first event set is an abnormal dimension; the number of regular public security events contained in the two event sets is counted respectively, and the number of regular public security events in the first event set is set to p1 i The number of regular public security events in the second event set is p2 i , according to the formula:

[0027] ;

[0028] Among them, n2 i is the number of public security events in the second event set, N is the total number of all public security events; the second feature proportion b of the i-th dimension is calculated i; The second feature ratio represents the accuracy of any dimension in the historical recognition process. The higher the accuracy, the more effective the monitoring method corresponding to the dimension;

[0029] Step S303: Obtain the number of public security events in the first event set as n1 i , the abnormal frequency of the i-th dimension is calculated to be η=n1 i / N; According to the formula:

[0030] ;

[0031] Calculate the confidence Z of the i-th dimension i The confidence of each dimension is based on the historical accuracy rate and the accurate probability of the judgment, which can help to make the confidence more accurate and facilitate the formulation of the subsequent abnormal judgment mechanism;

[0032] Step S304: randomly select a public security event, randomly select the i-th dimension from the selected public security event, if the i-th dimension is an abnormal dimension, obtain the abnormal identification rule preset for the i-th dimension, obtain the normal value range of the i-th dimension, extract the actual value of the i-th dimension in the selected public security event, and obtain the abnormal deviation amplitude under the i-th dimension as F i , set the confidence of the i-th dimension to Z i , the eigenvalue of the i-th dimension is calculated to be T i =Z i ×(1+F i ); if the i-th dimension is a normal dimension, then the eigenvalue T of the i-th dimension is obtained i =Z i ; The characteristic value reflects the degree of abnormality of the monitoring data under the corresponding dimension. On the basis of confidence, if the abnormal deviation amplitude is larger, the probability of the actual occurrence of the abnormality is greater;

[0033] Step S305: Extract the eigenvalues ​​of each dimension in the selected public security event, and extract a minimum eigenvalue T from all abnormal dimensions min , extract a maximum eigenvalue T from all normal dimensions max ; If the public security event is selected as a regular public security event, then the number of dimensions v whose eigenvalues ​​are greater than or equal to the minimum eigenvalue in the selected public security event is counted; if the public security event is selected as an abnormal public security event, then the number of dimensions w whose eigenvalues ​​are less than or equal to the maximum eigenvalue is counted;

[0034] Step S306: Obtain the number of dimensions v whose eigenvalues ​​are greater than or equal to the minimum eigenvalue or the number of dimensions w whose eigenvalues ​​are less than or equal to the maximum eigenvalue in each public security event, and calculate the average value of the number of dimensions whose eigenvalues ​​are greater than or equal to the minimum eigenvalue to obtain the expected number of abnormal dimensions vax The expected normal dimension number w is calculated by averaging the number of dimensions whose eigenvalues ​​are less than or equal to the maximum eigenvalue ax , the expected trigger mechanism for judging and evaluating conflict results is Max(v ax ,w ax ), where Max() is the maximum value function; the significance of the expected trigger mechanism is to divide the abnormal judgment methods into two types, one is that the number of abnormal dimensions at the same time exceeds the expected trigger mechanism, which indicates that a public security incident has occurred, and the other is that the number of normal dimensions at the same time exceeds the expected trigger mechanism, which indicates that no public security incident has occurred. However, whether it is the judgment of the number of abnormal dimensions or the number of normal dimensions should be dynamically adjusted according to the judgment of historical public security incidents. The purpose of dividing the two judgment methods is to make the judgment result more accurate.

[0035] Furthermore, step S400 includes the following steps:

[0036] Step S401: Obtain monitoring data of each monitoring mode of the monitoring target area at the current moment, obtain dimension data of any dimension, and extract the abnormal dimension existing at the current moment; set the i-th dimension at the current moment as the abnormal dimension, and obtain the abnormal offset amplitude of the i-th dimension as (F i ) now and the confidence value is Z i , the eigenvalue of the i-th dimension is calculated as (T i ) now =(F i ) now ×Z i ;

[0037] Step S402: Obtain the feature values ​​of each dimension at the current moment. If the expected trigger mechanism Max(v ax ,w ax )=v ax , then obtain the minimum eigenvalue of each abnormal dimension, and count the number of dimensions whose eigenvalues ​​are greater than or equal to the minimum eigenvalue as v now , if v now ≥v ax , then it is judged that there is a public security incident at the current moment; if the expected trigger mechanism Max(v ax ,w ax )=w ax , then obtain the maximum eigenvalue of each normal dimension, and count the number of dimensions whose eigenvalues ​​are less than or equal to the maximum eigenvalue as w now , if w now ≤v ax , it is judged that there is a public security incident at the current moment.

[0038] In order to better implement the above method, a digital management system for public security data is also proposed. The management system includes a historical public security analysis module, a dimensional anomaly analysis module, a confidence conflict analysis module and a real-time public security analysis module;

[0039] The historical public security analysis module is used to preset several monitoring methods to monitor public security incidents occurring in the target area, and to collect multi-dimensional data on any public security incident; based on the processing feedback results of relevant personnel, it can identify the actual occurrence of any public security incident;

[0040] The dimension anomaly analysis module is used to arbitrarily select public security events with normal evaluation results and identify the monitoring blind spots in each dimension; based on the differences in evaluation results between different public security events, the regional scope of each monitoring blind spot is corrected;

[0041] The confidence conflict analysis module is used to analyze the characteristic values ​​of each dimension based on the regional scope of the monitoring blind spots in different dimensions in any public security incident; based on the difference in the characteristic values ​​of each dimension, a trigger mechanism is set for the existing assessment conflict situation;

[0042] The real-time public security analysis module is used to collect multi-dimensional data in the target area in real time to obtain the characteristic values ​​of each dimension at the current moment; analyze the triggering situation between the characteristic values ​​of each dimension and the conflict assessment mechanism to determine whether there is a public security incident at the current moment.

[0043] Furthermore, the historical security analysis module includes a historical data collection unit and a difference judgment and identification unit;

[0044] The historical data collection unit is used to preset several monitoring methods to monitor public security incidents occurring in the target area and to carry out multi-dimensional data collection for any public security incident; the difference judgment and identification unit is used to identify anomalies in the actual occurrence of any public security incident based on the processing feedback results of relevant personnel.

[0045] Further, the dimensional anomaly analysis module includes a dimensional blind spot identification unit and a blind spot range correction unit;

[0046] The dimensional blind spot identification unit is used to arbitrarily select public security events with normal evaluation results and identify the monitoring blind spots in each dimension; the blind spot range correction unit is used to correct the area range of each monitoring blind spot based on the differences in evaluation results between different public security events.

[0047] Further, the confidence conflict analysis module includes a dimension confidence evaluation unit and an evaluation conflict determination unit;

[0048] The dimensional confidence assessment unit is used to analyze the characteristic values ​​of each dimension based on the regional scope of the monitoring blind spots in different dimensions in any public security incident; the assessment conflict determination unit is used to set a trigger mechanism for the existing assessment conflict situation based on the difference in the characteristic values ​​of each dimension.

[0049] Furthermore, the real-time public security analysis module includes a real-time data acquisition unit and an abnormality judgment and identification unit;

[0050] The real-time data collection unit is used to collect multi-dimensional data of the target area in real time to obtain the characteristic values ​​of each dimension at the current moment; the abnormal judgment and identification unit is used to analyze the triggering situation between the characteristic values ​​of each dimension and the assessment conflict mechanism to determine whether there is a public security incident at the current moment.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] 1. The present invention comprehensively analyzes the data of various dimensions and comprehensively reflects the abnormal occurrence of the target area, which can more accurately and effectively analyze whether a public security incident has occurred. On the premise of ensuring the timeliness of public security management, it can also eliminate some misjudgments and avoid waste of resources;

[0053] 2. The present invention analyzes the monitoring blind areas of each dimension, can accurately obtain the actual effective monitoring area of ​​each dimension, and has a recognition of the accuracy of the monitoring conditions of each dimension in the monitoring blind areas, helps relevant personnel to make a judgment on the effectiveness of abnormal data, and improves the effectiveness of decision-making;

[0054] 3. The present invention sets corresponding characteristic values ​​by analyzing different dimensions, evaluates the effectiveness and accuracy of different monitoring methods, and then judges the occurrence of actual public security incidents based on the quantitative relationship between abnormal data and normal data. When there are differences in the judgment of abnormal situations by different monitoring methods, it can make decisions accurately and quickly, thereby improving the timeliness of public security management. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A schematic diagram of the steps of a method for digital management of public security data based on artificial intelligence;

[0056] Figure 2 This is a structural diagram of a digital management system for public security data based on artificial intelligence. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0058] Example: Figure 1 to Figure 2 As shown, the present invention provides a method for digital management of public security data based on artificial intelligence, and the management method comprises the following steps:

[0059] Step S100: Preset several monitoring methods to monitor the public security incidents occurring in the target area, and collect multi-dimensional data on any public security incident; based on the processing feedback results of relevant personnel, perform abnormal identification on the actual occurrence of any public security incident;

[0060] Wherein, step S100 includes the following steps:

[0061] Step S101: The monitoring data obtained by any monitoring method is set as the dimension data of the corresponding dimension, and a corresponding abnormality identification rule is preset for each dimension. Whenever at least one dimension of the dimension data is abnormal after being identified by the abnormality identification rule, the dimension with abnormal dimension data is set as the abnormal dimension;

[0062] Step S102: Obtain the monitoring range of each monitoring method in the target area and set it as the dimensional area of ​​the corresponding dimension; extract the dimensional area of ​​any abnormal dimension and set it as the feature area; if there is a common area between the dimensional area of ​​the remaining dimensions and the feature area of ​​the abnormal dimension, then set the dimensional area of ​​the remaining dimensions as the feature area; collect and summarize the dimensional data of any dimension in each feature area to generate a public security event;

[0063] Step S103: Whenever a public security event is generated, relevant personnel are dispatched to handle it, and the processing feedback results of the relevant personnel are collected. If there is an abnormality in the processing feedback results, the corresponding public security event is set as an abnormal public security event.

[0064] Step S200: arbitrarily selecting a public security event with a normal evaluation result, identifying monitoring blind spots in various dimensions; based on the difference in evaluation results between different public security events, correcting the area range of each monitoring blind spot;

[0065] Wherein, step S200 includes the following steps:

[0066] Step S201: setting the public security events without abnormalities in the processing feedback results as regular public security events, arbitrarily selecting a regular public security event, setting each dimension of each feature area monitored in the selected regular public security record as the target dimension, dividing the target dimension according to whether it is an abnormal dimension, and obtaining a normal dimension set and an abnormal dimension set respectively;

[0067] Step S202: arbitrarily select an abnormal dimension from the abnormal dimension set, obtain a feature area corresponding to the selected abnormal dimension, merge the feature areas of all abnormal dimensions to obtain a comprehensive abnormal area; arbitrarily select a normal dimension from the normal dimension set, obtain a common area between the selected normal dimension and the comprehensive abnormal area; set the common area as an expected blind area of ​​the selected normal dimension, and obtain the area range of the expected blind area in the target area;

[0068] Step S203: Set the selected normal dimension as the i-th dimension among all dimensions, and obtain the dimensional area of ​​the i-th dimension from the remaining conventional public security events respectively. When the i-th dimension is a normal dimension, extract the common area between the dimensional area of ​​the i-th dimension and the comprehensive abnormal area of ​​the conventional public security event. If there is an inclusion relationship between the common area of ​​the i-th dimension and the expected blind area, set the expected blind area to a common area with a larger area range. Otherwise, set the common area to another expected blind area of ​​the i-th dimension, and use the set several expected blind areas as the monitoring blind areas of the i-th dimension.

[0069] Step S204: arbitrarily select an abnormal public security event. If the i-th dimension in the selected abnormal public security event is an abnormal dimension, then extract each normal dimension that has a common area with the i-th dimension from the selected abnormal public security event. If the monitoring blind area of ​​the i-th dimension contains a common area with the normal dimension, set the contained common area as the initial area, and then obtain each monitoring blind area of ​​the contained normal dimension, wherein the j-th monitoring blind area in the i-th dimension is set to A1(i,j), and the k-th monitoring blind area in the contained normal dimension is set to A2 k If the monitoring blind area A2 k There is a common area A between the initial area and the pub1 , then the public area A is taken from the initial area pub1 Remove and obtain a correction area;

[0070] Step S205: Compare the correction area with the monitoring blind area A1(i,j). If there is a common area A1 between the two areas, pub2 , then the public area A1(i,j) is removed from the monitoring blind area pub2Remove it and obtain the corrected j-th monitoring blind area A1 in the i-th dimension ’ (i, j), and perform range correction on each monitoring blind area in the i-th dimension.

[0071] Step S300: Based on the area range of the monitoring blind spots in different dimensions in any public security incident, the characteristic values ​​of each dimension are analyzed; based on the difference in the characteristic values ​​of each dimension, a trigger mechanism is set for the existing assessment conflict situation;

[0072] Wherein, step S300 includes the following steps:

[0073] Step S301: arbitrarily select the i-th dimension to obtain each monitoring blind area after correction in the i-th dimension, wherein the area of ​​the j-th monitoring blind area is set to S (i,j) , according to the formula:

[0074] ;

[0075] Where j is a positive integer and j∈(1,m), m is the number of monitoring blind areas contained in the i-th dimension, S(i) is the monitoring range area of ​​the i-th dimension corresponding to the monitoring method in the target area; the first feature proportion a of the i-th dimension is calculated i ;

[0076] Example 1: Assume that there are two monitoring blind areas in the i-th dimension after correction, and the area of ​​the two monitoring blind areas is 5m 2 and 3m 2 , set the total area of ​​the target area to 50m 2 , calculate the first feature proportion a of the i-th dimension i =(5+3) / 50=16%;

[0077] Step S302: All public security events are divided into a first event set and a second event set according to whether the i-th dimension is an abnormal dimension, wherein the i-th dimension of each public security event in the first event set is an abnormal dimension; the number of regular public security events contained in the two event sets is counted respectively, and the number of regular public security events in the first event set is set to p1 i The number of regular public security events in the second event set is p2 i , according to the formula:

[0078] ;

[0079] Among them, n2 i is the number of public security events in the second event set, N is the total number of all public security events; the second feature proportion b of the i-th dimension is calculated i ;

[0080] Example 2: Under the premise that the i-th dimension is an abnormal dimension, the number of regular public security events is set to 10, and under the premise that the i-th dimension is a normal dimension, the number of regular public security events is set to 20; at the same time, the number of public security events when the i-th dimension is a normal dimension is set to 50, and the total number of all public security events is 100, and the second feature proportion b is obtained. i =(10+50-20) / 100=40%;

[0081] Step S303: Obtain the number of public security events in the first event set as n1 i , the abnormal frequency of the i-th dimension is calculated to be η=n1 i / N; According to the formula:

[0082] ;

[0083] Calculate the confidence Z of the i-th dimension i ;

[0084] Example 3: The number of public security events under the premise that the i-th dimension is set as an abnormal dimension is 50, and the total number of all public security events is 100. The abnormal frequency of the i-th dimension is 50%. According to Example 1 and Example 2, the first feature accounts for 16% and the second feature accounts for 40%. The confidence Z of the i-th dimension is calculated. i =50%×16%+50%×40%=28%;

[0085] Step S304: randomly select a public security event, randomly select the i-th dimension from the selected public security event, if the i-th dimension is an abnormal dimension, obtain the abnormal identification rule preset for the i-th dimension, obtain the normal value range of the i-th dimension, extract the actual value of the i-th dimension in the selected public security event, and obtain the abnormal deviation amplitude under the i-th dimension as F i , set the confidence of the i-th dimension to Z i , the eigenvalue of the i-th dimension is calculated to be T i =Z i ×(1+F i ); if the i-th dimension is a normal dimension, then the eigenvalue T of the i-th dimension is obtained i =Z i ;

[0086] Step S305: Extract the eigenvalues ​​of each dimension in the selected public security event, and extract a minimum eigenvalue T from all abnormal dimensions min , extract a maximum eigenvalue T from all normal dimensions max; If the public security event is selected as a regular public security event, then the number of dimensions v whose eigenvalues ​​are greater than or equal to the minimum eigenvalue in the selected public security event is counted; if the public security event is selected as an abnormal public security event, then the number of dimensions w whose eigenvalues ​​are less than or equal to the maximum eigenvalue is counted;

[0087] Step S306: Obtain the number of dimensions v whose eigenvalues ​​are greater than or equal to the minimum eigenvalue or the number of dimensions w whose eigenvalues ​​are less than or equal to the maximum eigenvalue in each public security event, and calculate the average value of the number of dimensions whose eigenvalues ​​are greater than or equal to the minimum eigenvalue to obtain the expected number of abnormal dimensions v ax The expected normal dimension number w is calculated by averaging the number of dimensions whose eigenvalues ​​are less than or equal to the maximum eigenvalue ax , the expected trigger mechanism for judging and evaluating conflict results is Max(v ax ,w ax ), where Max() is the maximum value function.

[0088] Step S400: collect multi-dimensional data in real time on the target area to obtain the characteristic values ​​of each dimension at the current moment; analyze the triggering conditions between the characteristic values ​​of each dimension and the conflict assessment mechanism to determine whether there is a public security incident at the current moment;

[0089] Wherein, step S400 includes the following steps:

[0090] Step S401: Obtain monitoring data of each monitoring mode of the monitoring target area at the current moment, obtain dimension data of any dimension, and extract the abnormal dimension existing at the current moment; set the i-th dimension at the current moment as the abnormal dimension, and obtain the abnormal offset amplitude of the i-th dimension as (F i ) now and the confidence value is Z i , the eigenvalue of the i-th dimension is calculated as (T i ) now =(F i ) now ×Z i ;

[0091] Step S402: Obtain the feature values ​​of each dimension at the current moment. If the expected trigger mechanism Max(v ax ,w ax )=v ax , then obtain the minimum eigenvalue of each abnormal dimension, and count the number of dimensions whose eigenvalues ​​are greater than or equal to the minimum eigenvalue as v now , if v now ≥v ax , then it is judged that there is a public security incident at the current moment; if the expected trigger mechanism Max(v ax ,wax )=w ax , then obtain the maximum eigenvalue of each normal dimension, and count the number of dimensions whose eigenvalues ​​are less than or equal to the maximum eigenvalue as w now , if w now ≤v ax , it is judged that there is a public security incident at the current moment.

[0092] A public security data digital management system, the management system includes a historical public security analysis module, a dimensional anomaly analysis module, a confidence conflict analysis module and a real-time public security analysis module;

[0093] The historical public security analysis module is used to preset several monitoring methods to monitor public security incidents occurring in the target area, and to collect multi-dimensional data on any public security incident; based on the processing feedback results of relevant personnel, it can identify the actual occurrence of any public security incident;

[0094] The dimension anomaly analysis module is used to arbitrarily select public security events with normal evaluation results and identify the monitoring blind spots in each dimension; based on the differences in evaluation results between different public security events, the regional scope of each monitoring blind spot is corrected;

[0095] The confidence conflict analysis module is used to analyze the characteristic values ​​of each dimension based on the regional scope of the monitoring blind spots in different dimensions in any public security incident; based on the difference in the characteristic values ​​of each dimension, a trigger mechanism is set for the existing assessment conflict situation;

[0096] The real-time public security analysis module is used to collect multi-dimensional data in the target area in real time to obtain the characteristic values ​​of each dimension at the current moment; analyze the triggering situation between the characteristic values ​​of each dimension and the conflict assessment mechanism to determine whether there is a public security incident at the current moment.

[0097] Among them, the historical security analysis module includes a historical data collection unit and a difference judgment and identification unit;

[0098] The historical data collection unit is used to preset several monitoring methods to monitor public security incidents occurring in the target area and to carry out multi-dimensional data collection for any public security incident; the difference judgment and identification unit is used to identify anomalies in the actual occurrence of any public security incident based on the processing feedback results of relevant personnel.

[0099] Among them, the dimensional anomaly analysis module includes a dimensional blind spot identification unit and a blind spot range correction unit;

[0100] The dimensional blind spot identification unit is used to arbitrarily select public security events with normal evaluation results and identify the monitoring blind spots in each dimension; the blind spot range correction unit is used to correct the area range of each monitoring blind spot based on the differences in evaluation results between different public security events.

[0101] Among them, the confidence conflict analysis module includes a dimension confidence evaluation unit and an evaluation conflict determination unit;

[0102] The dimensional confidence assessment unit is used to analyze the characteristic values ​​of each dimension based on the regional scope of the monitoring blind spots in different dimensions in any public security incident; the assessment conflict determination unit is used to set a trigger mechanism for the existing assessment conflict situation based on the difference in the characteristic values ​​of each dimension.

[0103] Among them, the real-time public security analysis module includes a real-time data acquisition unit and an abnormality judgment and identification unit;

[0104] The real-time data collection unit is used to collect multi-dimensional data of the target area in real time to obtain the characteristic values ​​of each dimension at the current moment; the abnormal judgment and identification unit is used to analyze the triggering situation between the characteristic values ​​of each dimension and the assessment conflict mechanism to determine whether there is a public security incident at the current moment.

[0105] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A method for digital management of public security data based on artificial intelligence, characterized by: The management method comprises the following steps: Step S100: Preset several monitoring methods to monitor the public security incidents occurring in the target area, and collect multi-dimensional data on any public security incident; based on the processing feedback results of relevant personnel, perform abnormal identification on the actual occurrence of any public security incident; Step S200: arbitrarily selecting a public security event with a normal evaluation result, identifying monitoring blind spots in various dimensions; based on the difference in evaluation results between different public security events, correcting the area range of each monitoring blind spot; Step S300: Based on the area range of the monitoring blind spots in different dimensions in any public security incident, the characteristic values ​​of each dimension are analyzed; based on the difference in the characteristic values ​​of each dimension, a trigger mechanism is set for the existing assessment conflict situation; Step S400: Carry out multi-dimensional data collection on the target area in real time to obtain the characteristic values ​​of each dimension at the current moment; analyze the triggering conditions between the characteristic values ​​of each dimension and the conflict assessment mechanism to determine whether there is a public security incident at the current moment.

2. According to the method of digital management of public security data based on artificial intelligence in claim 1, it is characterized by: The step S100 includes the following steps: Step S101: The monitoring data obtained by any monitoring method is set as the dimension data of the corresponding dimension, and a corresponding abnormality identification rule is preset for each dimension. Whenever at least one dimension of the dimension data is abnormal after being identified by the abnormality identification rule, the dimension with abnormal dimension data is set as the abnormal dimension; Step S102: Obtain the monitoring range of each monitoring method in the target area and set it as the dimensional area of ​​the corresponding dimension; extract the dimensional area of ​​any abnormal dimension and set it as the feature area; if there is a common area between the dimensional area of ​​the remaining dimensions and the feature area of ​​the abnormal dimension, then set the dimensional area of ​​the remaining dimensions as the feature area; collect and summarize the dimensional data of any dimension in each feature area to generate a public security event; Step S103: Whenever a public security event is generated, relevant personnel are dispatched to handle it, and the processing feedback results of the relevant personnel are collected. If there is an abnormality in the processing feedback results, the corresponding public security event is set as an abnormal public security event.

3. The method for digital management of public security data based on artificial intelligence according to claim 2 is characterized in that: The step S200 includes the following steps: Step S201: setting the public security events without abnormalities in the processing feedback results as regular public security events, arbitrarily selecting a regular public security event, setting each dimension of each feature area monitored in the selected regular public security record as the target dimension, dividing the target dimension according to whether it is an abnormal dimension, and obtaining a normal dimension set and an abnormal dimension set respectively; Step S202: arbitrarily select an abnormal dimension from the abnormal dimension set, obtain a feature area corresponding to the selected abnormal dimension, merge the feature areas of all abnormal dimensions to obtain a comprehensive abnormal area; arbitrarily select a normal dimension from the normal dimension set, obtain a common area between the selected normal dimension and the comprehensive abnormal area; set the common area as an expected blind area of ​​the selected normal dimension, and obtain the area range of the expected blind area in the target area; Step S203: Set the selected normal dimension as the i-th dimension among all dimensions, and obtain the dimensional area of ​​the i-th dimension from the remaining conventional public security events respectively. When the i-th dimension is a normal dimension, extract the common area between the dimensional area of ​​the i-th dimension and the comprehensive abnormal area of ​​the conventional public security event. If there is an inclusion relationship between the common area of ​​the i-th dimension and the expected blind area, set the expected blind area to a common area with a larger area range. Otherwise, set the common area to another expected blind area of ​​the i-th dimension, and use the set several expected blind areas as the monitoring blind areas of the i-th dimension. Step S204: arbitrarily select an abnormal public security event. If the i-th dimension in the selected abnormal public security event is an abnormal dimension, then extract each normal dimension that has a common area with the i-th dimension from the selected abnormal public security event. If the monitoring blind area of ​​the i-th dimension contains a common area with the normal dimension, set the contained common area as the initial area, and then obtain each monitoring blind area of ​​the contained normal dimension, wherein the j-th monitoring blind area in the i-th dimension is set to A1(i,j), and the k-th monitoring blind area in the contained normal dimension is set to A2 k If the monitoring blind area A2 k There is a common area A between the initial area and the pub1 , then the public area A is taken from the initial area pub1 Remove and obtain a correction area; Step S205: Compare the correction area with the monitoring blind area A1(i,j). If there is a common area A1 between the two areas, pub2 , then the public area A1(i,j) is removed from the monitoring blind area pub2 Remove it and obtain the corrected j-th monitoring blind area A1 in the i-th dimension ’ (i, j), and perform range correction on each monitoring blind area in the i-th dimension.

4. The method for digital management of public security data based on artificial intelligence according to claim 3 is characterized in that: The step S300 includes the following steps: Step S301: arbitrarily select the i-th dimension to obtain each monitoring blind area after correction in the i-th dimension, wherein the area of ​​the j-th monitoring blind area is set to S (i,j) , according to the formula: ； Where j is a positive integer and j∈(1,m), m is the number of monitoring blind areas contained in the i-th dimension, S(i) is the monitoring range area of ​​the i-th dimension corresponding to the monitoring method in the target area; the first feature proportion a of the i-th dimension is calculated i ; Step S302: All public security events are divided into a first event set and a second event set according to whether the i-th dimension is an abnormal dimension, wherein the i-th dimension of each public security event in the first event set is an abnormal dimension; the number of regular public security events contained in the two event sets is counted respectively, and the number of regular public security events in the first event set is set to p1 i The number of regular public security events in the second event set is p2 i , according to the formula: ； Among them, n2 i is the number of public security events in the second event set, N is the total number of all public security events; the second feature proportion b of the i-th dimension is calculated i ; Step S303: Obtain the number of public security events in the first event set as n1 i , the abnormal frequency of the i-th dimension is calculated to be η=n1 i / N; According to the formula: ； Calculate the confidence Z of the i-th dimension i ; Step S304: randomly select a public security event, randomly select the i-th dimension from the selected public security event, if the i-th dimension is an abnormal dimension, obtain the abnormal identification rule preset for the i-th dimension, obtain the normal value range of the i-th dimension, extract the actual value of the i-th dimension in the selected public security event, and obtain the abnormal deviation amplitude under the i-th dimension as F i , set the confidence of the i-th dimension to Z i , the eigenvalue of the i-th dimension is calculated to be T i =Z i ×(1+F i ); if the i-th dimension is a normal dimension, then the eigenvalue T of the i-th dimension is obtained i =Z i ; Step S305: Extract the eigenvalues ​​of each dimension in the selected public security event, and extract a minimum eigenvalue T from all abnormal dimensions min , extract a maximum eigenvalue T from all normal dimensions max ; If the public security event is selected as a regular public security event, then the number of dimensions v whose eigenvalues ​​are greater than or equal to the minimum eigenvalue in the selected public security event is counted; if the public security event is selected as an abnormal public security event, then the number of dimensions w whose eigenvalues ​​are less than or equal to the maximum eigenvalue is counted; Step S306: Obtain the number of dimensions v whose eigenvalues ​​are greater than or equal to the minimum eigenvalue or the number of dimensions w whose eigenvalues ​​are less than or equal to the maximum eigenvalue in each public security event, and calculate the average value of the number of dimensions whose eigenvalues ​​are greater than or equal to the minimum eigenvalue to obtain the expected number of abnormal dimensions v ax The expected normal dimension number w is calculated by averaging the number of dimensions whose eigenvalues ​​are less than or equal to the maximum eigenvalue ax , the expected trigger mechanism for judging and evaluating conflict results is Max(v ax ,w ax ), where Max() is the maximum value function.

5. The method for digital management of public security data based on artificial intelligence according to claim 4 is characterized in that: The step S400 includes the following steps: Step S401: Obtain monitoring data of each monitoring mode of the monitoring target area at the current moment, obtain dimension data of any dimension, and extract the abnormal dimension existing at the current moment; set the i-th dimension at the current moment as the abnormal dimension, and obtain the abnormal offset amplitude of the i-th dimension as (F i ) now and the confidence value is Z i , the eigenvalue of the i-th dimension is calculated as (T i ) now =(F i ) now ×Z i ; Step S402: Obtain the feature values ​​of each dimension at the current moment. If the expected trigger mechanism Max(v ax ,w ax )=v ax , then obtain the minimum eigenvalue of each abnormal dimension, and count the number of dimensions whose eigenvalues ​​are greater than or equal to the minimum eigenvalue as v now , if v now ≥v ax , then it is judged that there is a public security incident at the current moment; if the expected trigger mechanism Max(v ax ,w ax )=w ax , then obtain the maximum eigenvalue of each normal dimension, and count the number of dimensions whose eigenvalues ​​are less than or equal to the maximum eigenvalue as w now , if w now ≤v ax , it is judged that there is a public security incident at the current moment.

6. A public security data digital management system, used to implement a public security data digital management method based on artificial intelligence as claimed in any one of claims 1 to 5, characterized in that: The management system includes a historical public security analysis module, a dimensional anomaly analysis module, a confidence conflict analysis module and a real-time public security analysis module; The historical public security analysis module is used to preset several monitoring methods to monitor public security incidents occurring in the target area, and to collect multi-dimensional data on any public security incident; based on the processing feedback results of relevant personnel, the actual occurrence of any public security incident is anomaly identified; The dimension anomaly analysis module is used to arbitrarily select public security events with normal evaluation results and identify monitoring blind spots in each dimension; based on the differences in evaluation results between different public security events, the regional scope of each monitoring blind spot is corrected; The confidence conflict analysis module is used to analyze the characteristic values ​​of each dimension based on the regional scope of the monitoring blind spots in different dimensions in any public security incident; based on the difference in the characteristic values ​​of each dimension, a trigger mechanism is set for the existing assessment conflict situation; The real-time public security analysis module is used to collect multi-dimensional data in real time on the target area to obtain the characteristic values ​​of each dimension at the current moment; analyze the triggering situation between the characteristic values ​​of each dimension and the assessment conflict mechanism to determine whether there is a public security incident at the current moment.

7. A digital public security data management system according to claim 6, characterized in that: The historical public security analysis module includes a historical data collection unit and a difference judgment and identification unit; The historical data collection unit is used to preset several monitoring methods to monitor public security incidents occurring in the target area and to carry out multi-dimensional data collection for any public security incident; the difference judgment and identification unit is used to identify anomalies in the actual occurrence of any public security incident based on the processing feedback results of relevant personnel.

8. The digital public security data management system according to claim 6, characterized in that: The dimension anomaly analysis module includes a dimension blind spot identification unit and a blind spot range correction unit; The dimensional blind spot identification unit is used to arbitrarily select public security events with normal evaluation results and identify monitoring blind spots existing in each dimension; the blind spot range correction unit is used to correct the area range of each monitoring blind spot based on the differences in evaluation results between different public security events.

9. A digital public security data management system according to claim 6, characterized in that: The confidence conflict analysis module includes a dimension confidence evaluation unit and an evaluation conflict determination unit; The dimensional confidence assessment unit is used to analyze the characteristic values ​​of each dimension based on the regional scope of the monitoring blind spots in different dimensions in any public security incident; the assessment conflict determination unit is used to set a trigger mechanism for the existing assessment conflict situation based on the difference in the characteristic values ​​of each dimension.

10. A digital public security data management system according to claim 6, characterized in that: The real-time public security analysis module includes a real-time data acquisition unit and an abnormality judgment and identification unit; The real-time data collection unit is used to collect multi-dimensional data of the target area in real time to obtain the characteristic value of each dimension at the current moment; The abnormality judgment and identification unit is used to analyze the triggering situation between the characteristic values ​​of each dimension and the evaluation conflict mechanism, and judge whether there is a public security incident at the current moment.

Images