Smart campus security data processing method based on big data

Abstract

The invention discloses an intelligent campus security data processing method based on big data, and relates to the technical field of campus security management, and the method comprises the following steps: collecting original data from campus security check records, intelligent detection equipment and teacher and student report information; storing the original data in a classified manner according to illegal article types, illegal behavior occurrence time, illegal person identities and illegal places, performing duplicate removal on duplicate records, correcting or eliminating wrong and incomplete information, and obtaining a cleaned data set; carrying and using data of historical illegal articles are deeply analyzed by applying time sequence analysis, spatial distribution analysis and personnel feature analysis; according to the analysis result of the historical data, in combination with the actual demand of campus safety management, scientific and reasonable early warning thresholds are set for different types of illegal behaviors, and the problem that the current campus safety risk hidden danger is difficult to find and respond in time is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of campus safety management, and in particular to a smart campus security data processing method based on big data. Background Art

[0002] With the rapid development of information technology, the Internet of Things, and artificial intelligence, smart campus development is becoming an increasingly important means for universities, primary and secondary schools, and colleges to improve management efficiency and ensure campus safety. However, existing campus security systems still rely primarily on traditional video surveillance and manual patrols. These systems suffer from problems such as a single data source, poor real-time performance, weak processing capabilities, and a lack of early warning mechanisms, making them unable to meet the urgent needs of modern campuses for efficient, intelligent, and safe management. On one hand, campus environments are complex, densely populated, and frequently active, leading to a diverse trend in illegal carrying of flammable and explosive items, controlled knives, and hazardous chemicals, making it difficult to promptly identify and respond to potential safety risks. On the other hand, existing systems lack significant capabilities in data integration and mining, resulting in limited capabilities for identifying risk trends, modeling behavioral patterns, and providing proactive early warnings. Furthermore, data fragmentation and the existence of severe information silos severely hinder the sharing and integration of security information and the effectiveness of management decisions. Summary of the Invention

[0003] The purpose of the present invention is to provide a smart campus security data processing method based on big data to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for processing smart campus security data based on big data, comprising the following steps:

[0005] Step S1: Collect raw data from campus safety inspection records, intelligent detection equipment, and teacher and student reporting information;

[0006] Step S2: The raw data is categorized and stored according to the type of illegal item, time of illegal behavior, identity of the illegal person, and location of the illegal behavior, and duplicate records are removed, and erroneous and incomplete information is corrected or eliminated to obtain a cleaned data set;

[0007] Step S3: Conduct in-depth analysis of historical illegal item carrying and use data using time series analysis, spatial distribution analysis, and personnel characteristics analysis;

[0008] Step S4: Based on the analysis results of historical data and the actual needs of campus safety management, scientific and reasonable warning thresholds are set for different types of violations. When the violation reaches the warning threshold, the system automatically generates warning information and releases it to relevant personnel in a timely manner through multiple channels.

[0009] According to the above technical solution, in step S1, collecting raw data includes:

[0010] Security personnel use handheld terminals to record violations discovered during routine inspections, special inspections, or temporary spot checks;

[0011] Deploy intelligent image recognition cameras and odor detection sensors in dormitories, teaching buildings, laboratory buildings, and related key areas to collect images and odor characteristics of illegal items in real time;

[0012] Teachers and students submit suspicious information through the campus security management app, reporting hotline or reporting box, which will be used as one of the data sources after background review.

[0013] According to the above technical solution, in step S3, the specific method of time series analysis is:

[0014] Step S31: Group all events according to the preset time granularity based on the "time of event occurrence" field in the cleaned data set;

[0015] Step S32: Count the number of occurrences of each type of illegal item in each time unit, marked as N type,t Indicates the number of events of type type within time unit t;

[0016] Step S33: Generate a line graph to show N type,t The changing trend of t;

[0017] Step S34: Calculate the growth rate or decline rate of adjacent time units, and the calculation expression is: where t i-1 With t i are adjacent time units, if Then the minimum constant ε is set instead; where, is the time unit t i The number of events of violation type type, GR type (t i ,t i-1 ) is the growth rate between two adjacent time units, and ε is the minimum positive value set to prevent the denominator from being zero.

[0018] According to the above technical solution, in step S3, the specific method of spatial distribution analysis is:

[0019] Step S3a: Based on the “location” field in the cleaned dataset, the campus is divided into several functional zones {1, R2, …, R};

[0020] Step S3b: Receive the “time filter T” from the time series analysis filter ”, extract the event set E within the time range filtered;

[0021] Step S3c: E filtered By partition R j With type type statistics, we get

[0022] Step S3d: Using the campus floor plan, construct the heat map data {(x j ,y j ,W j )}:(x j ,y j ) is R j The plane coordinates of For this area in T filter Total number of violations during the time period;

[0023] Step S3e: Generate heat map, with W j The larger it is, the darker the heat map color;

[0024] Step S3f: When When the type dimension or R j dimension, marked as "high-risk area", where β type The regional threshold for type type calculated based on historical statistics.

[0025] According to the above technical solution, in step S3, the specific method of personnel feature analysis is:

[0026] Step S3U: Based on the "personnel identity" field in the cleaned dataset, all violation data are divided into several sets according to the identity categories of the participants, including but not limited to students, teachers, visitors, logistics personnel, and external staff, and further refined to grade, major, or department;

[0027] Step S3V: For each group of people, count their filter The number of various types of violations involved in the report is used to generate statistical indicators Indicates the number of type violations committed by a specific group within a specific time period;

[0028] Step S3W: Construct a personnel violation ratio map, calculate the ratio of each group of personnel in different violations, thereby determining the proportion of each group of people in specific violations and mining the behavior patterns of key groups;

[0029] Step S3X: Further introduce behavioral risk assessment indicator R group , defined as the average violation frequency of the group divided by the total number of people in the group, is used to measure the violation risk intensity of a specific group of people. High-risk groups will be given higher weights in subsequent warnings;

[0030] Step S3Y: Combine historical violation behavior trends and conduct a multi-dimensional cross-analysis of high-risk groups, high-incidence areas, and key time periods.

[0031] According to the above technical solution, step S4 further includes:

[0032] Step S41: Calculate the historical average μ and standard deviation σ of each type of violation using historical statistics for the same period, and set the dynamic threshold y u , its calculation expression is: u =μ+k·σ, when the number of a certain type of violation in a certain period of time exceeds the threshold y u When , an early warning is triggered, where k is the dynamic control parameter corresponding to different types of violations, which is a constant greater than 0;

[0033] Step S42: When the real-time statistical data reaches the warning threshold y u When a violation occurs, an early warning report is automatically generated containing the type of violation, the area where it occurred, the time range, the current number of violations compared with the threshold, etc., and released to security personnel, dormitory managers and relevant persons in charge through campus broadcasts, SMS / APP push, and electronic bulletin boards;

[0034] Step S43: Based on the early warning information, dynamically adjust the security personnel patrol plan and increase the patrol frequency in high-risk areas and time periods; carry out targeted safety publicity and education; focus on rectifying any violations found, including confiscating items, giving educational talks, or handing over to law enforcement agencies for handling.

[0035] A smart campus security data processing system based on big data, the smart campus security data processing system includes a data acquisition module, a data sorting module, a trend analysis module and an early warning mechanism establishment module, the data acquisition module, the data sorting module, the trend analysis module and the early warning mechanism establishment module are interconnected; wherein,

[0036] The data acquisition module is used to collect campus safety inspection records, intelligent detection equipment data and teacher and student reporting information, and forward the above raw data to the data sorting module;

[0037] The data sorting module is used to classify and sort the original data and clean the data, and output the cleaned data set;

[0038] The trend analysis module is used to analyze the trends and patterns of historical illegal behaviors by analyzing the data of carrying and using historical illegal items;

[0039] The early warning mechanism establishment module is used to set dynamically adjustable early warning thresholds for various types of illegal carrying or use behaviors based on historical data analysis results and combined with the security characteristics of various areas on campus in different time periods. The thresholds are used to trigger the security response mechanism.

[0040] According to the above technical solution, the data acquisition module includes a manual inspection terminal module, an intelligent detection equipment module and a reporting information module; wherein,

[0041] The manual inspection terminal module is deployed on the handheld terminal of the security personnel and is used to enter relevant information of the violation incident during the inspection process;

[0042] The intelligent detection equipment module includes an intelligent image recognition camera and an odor detection sensor for collecting images and odor characteristics of illegal items in real time;

[0043] The reporting information module is used to receive suspicious information submitted by teachers and students through the campus safety management APP, hotline or reporting box.

[0044] According to the above technical solution, the data sorting module includes a classification and sorting module and a data cleaning module; wherein,

[0045] The classification and arranging module is used to classify the collected data according to the type of illegal items, the time when the illegal behavior occurred, the identity of the illegal person, and the location of the illegal behavior;

[0046] The data cleaning module is used to remove duplicate, erroneous and incomplete data to ensure the accuracy and reliability of the data.

[0047] According to the above technical solution, the trend analysis module includes a time series analysis module, a spatial distribution analysis module and a personnel feature analysis module; wherein,

[0048] The time series analysis module is used to count the number of various types of violations by time unit based on the cleaned data set, generate a line chart, and calculate the growth rate or decline rate. The time series analysis module also includes a trend anomaly detection function at multiple time granularities to identify sudden changes occurring at the weekly and monthly levels, and automatically assess the event intensity and evolution risk level based on the threshold change curve;

[0049] The spatial distribution analysis module is used to divide the campus into several functional zones, count the number of violations in each zone and generate a heat map;

[0050] The personnel feature analysis module is used to classify and count violation incidents according to identity, grade and major and generate the violation ratio of each group of people.

[0051] According to the above technical solution, the warning mechanism establishment module includes a warning threshold setting module and a warning information generation module; wherein,

[0052] The warning threshold setting module is used to set warning thresholds for different types of violations based on the analysis results of historical data and the actual needs of campus safety management;

[0053] The warning information generation module is used to monitor the comparison between real-time violation statistics and warning thresholds, and automatically generate a warning report once the threshold is reached.

[0054] Compared with the existing technology, the beneficial effects achieved by the present invention are as follows: the present invention, by constructing a multidimensional analysis model including time series, spatial distribution and personnel characteristics, accurately identifies the occurrence trend and spatial aggregation pattern of illegal behaviors, and establishes a dynamically adjusted early warning mechanism based on historical behavior patterns, thereby significantly improving the scientific nature and foresight of campus security management. Compared with the existing technology, the present invention not only improves the monitoring coverage and response speed of illegal carrying and use of dangerous goods, but also effectively promotes the transformation of security management from "passive response after the event" to "active early warning before the event". It has significant advantages such as intelligent data processing, flexible early warning triggering, and precise management and control decision-making. It can play an important role in protecting the life and property safety of campus personnel, optimizing security resource allocation, and improving the overall management level. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0056] In the attached figure:

[0057] Figure 1 A schematic diagram of the overall process of the smart campus security data processing method provided in Example 1 of the present invention;

[0058] Figure 2 This is a schematic diagram of the module composition of the smart campus security data processing system provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0059] 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.

[0060] Example 1

[0061] Figure 1 A schematic diagram of the overall process of the smart campus security data processing method provided in Example 1 of the present invention;

[0062] In this embodiment, the method includes the following steps:

[0063] Step S1: Collect raw data from campus safety inspection records, intelligent detection equipment, and teacher and student reporting information.

[0064] Specifically, security personnel use handheld terminals to record violations discovered during routine inspections, special inspections, or temporary spot checks;

[0065] Deploy intelligent image recognition cameras and odor detection sensors in dormitories, teaching buildings, laboratory buildings, and related key areas to collect images and odor characteristics of illegal items in real time;

[0066] Teachers and students submit suspicious information through the campus security management app, reporting hotline or reporting box, which will be used as one of the data sources after background review.

[0067] Step S2: The raw data is classified and stored according to the type of illegal item, the time of illegal behavior, the identity of the illegal person, and the location of the illegal behavior. Duplicate records are removed, and erroneous and incomplete information is corrected or eliminated to obtain a cleaned data set.

[0068] Step S3: Use time series analysis, spatial distribution analysis, and personnel characteristics analysis to conduct an in-depth analysis of historical data on the carrying and use of illegal items. Time series analysis can draw a line graph showing the number of violations over time, calculate the growth or decline rate in different time periods, and discover the cyclical patterns of violations. Spatial distribution analysis uses heat maps to visually display the density of violation locations and analyze the characteristics of violation types in different areas. Personnel characteristics analysis counts the proportion of violations by different identities and studies the differences in violations by identity on different campuses.

[0069] Multi-dimensional data analysis can proactively identify trends and patterns in violations. For example, if an increase in the illegal bringing of flammable and explosive items into dormitories is detected at the end of a semester, early warnings can be issued to strengthen inspections and management during that period. Based on these predictions, campus security management departments can rationally deploy security resources, increase patrol frequency, and conduct targeted safety awareness and education campaigns to nip potential safety hazards in the bud, shifting campus safety management from reactive response to proactive prevention.

[0070] In the embodiment of the present invention, the specific method of time series analysis is:

[0071] Step S31: Group all events according to the preset time granularity (such as semester, month, week or day) based on the "time of event occurrence" field in the cleaned data set;

[0072] Step S32: Count the number of occurrences of each type of illegal item in each time unit, marked as N type,t Indicates the number of events of type type within time unit t;

[0073] Step S33: Generate a line graph to show N type,t The changing trend of t;

[0074] Step S34: Calculate the growth rate or decline rate of adjacent time units, and the calculation expression is: where t i-1 With t i are adjacent time units, if Then the minimum constant ε is set instead; where, is the time unit t i The number of events of violation type type, GR type (t i ,t i-1 ) is the growth rate between two adjacent time units, and ε is the minimum positive value set to prevent the denominator from being zero.

[0075] The specific methods of spatial distribution analysis are:

[0076] Step S3a: Based on the “location” field in the cleaned dataset, the campus is divided into several functional zones {R1, R2, …, R R Such as dormitory area, teaching area, laboratory area, canteen area, library area, sports field area, etc.

[0077] Step S3b: Receive the “time filter T” from the time series analysis filter ”, extract the event set E within the time range filtered ;

[0078]

[0079] Step S3d: Using the campus floor plan, construct the heat map data {(x j ,y j ,W j )}:(x j ,y j ) is R j The plane coordinates of For this area in T filter Total number of violations during the time period;

[0080] Step S3e: Generate heat map, with Wj The larger it is, the darker the heat map color;

[0081] Step S3f: When When the type dimension or R j dimension, marked as "high-risk area", where β type The regional threshold for type type calculated based on historical statistics.

[0082] The specific methods of personnel characteristics analysis are:

[0083] Step S3U: Based on the "personnel identity" field in the cleaned dataset, all violation data are divided into several sets according to the identity categories of the participants, including but not limited to students, teachers, visitors, logistics personnel, and external staff, and further refined into grade (such as freshman to senior year), major (such as chemistry, biology, machinery, electrical engineering, etc.) or department (such as laboratory management office, logistics support department);

[0084] Step S3V: For each group of people, count their filter The number of various types of violations involved in the report is used to generate statistical indicators Indicates the number of violations of type type committed by a specific group within a specific time period; for example, count the total number of violations of carrying flammable items by sophomores majoring in chemistry in the fall semester of 2024;

[0085] Step S3W: Construct a personnel violation ratio map, calculate the ratio of each group of personnel in different violations, and thus determine the proportion of each group of people in specific violations and mine the behavior patterns of key groups. For example, if the analysis shows that "logistics external personnel account for 28% of violations in the teaching building area," key control targets can be set;

[0086] Step S3X: Further introduce behavioral risk assessment indicator R group , defined as the average violation frequency of the group divided by the total number of people in the group, is used to measure the violation risk intensity of a specific group of people. High-risk groups will be given higher weights in subsequent warnings;

[0087] Step S3Y: Combined with historical violation behavior trends, conduct a multi-dimensional cross-analysis of high-risk groups, high-incidence areas, and key time periods. For example, after discovering the pattern of "junior students of a certain major frequently violated the rules by using prohibited electronic devices in the dormitory area during the final exams", the risk behavior labels of this type of group are recorded through a behavioral labeling mechanism to achieve traceable and predictable behavioral modeling; through the above-mentioned personnel feature analysis method, an in-depth portrayal of the characteristics of the people behind the violations can be achieved, providing decision-making support based on group portraits for campus security management departments, and providing data support and basis for subsequent precise early warning, targeted intervention, and behavior correction, significantly improving the intelligence, differentiation, and foresight of the smart campus security system.

[0088] Step S4: Based on the analysis results of historical data and the actual needs of campus safety management, scientific and reasonable warning thresholds are set for different types of violations. When the violation reaches the warning threshold, the system automatically generates warning information and releases it to relevant personnel in a timely manner through multiple channels.

[0089] Through the above steps, it is possible to accurately identify violations on campus, predict trends and issue timely warnings, thereby effectively improving the initiative and scientific nature of campus security response.

[0090] In this embodiment of the present invention, step S4 further includes:

[0091] Step S41: Calculate the historical average μ and standard deviation σ of each type of violation using historical statistics for the same period, and set the dynamic threshold y u , its calculation expression is: u =μ+k·σ, when the number of a certain type of violation in a certain period of time exceeds the threshold y u When , an early warning is triggered, where k is the dynamic control parameter corresponding to different types of violations, which is a constant greater than 0;

[0092] Step S42: When the real-time statistical data reaches the warning threshold y u When a violation occurs, an early warning report is automatically generated containing the type of violation, the area where it occurred, the time range, the current number of violations compared with the threshold, etc., and released to security personnel, dormitory managers and relevant persons in charge through campus broadcasts, SMS / APP push, and electronic bulletin boards;

[0093] Step S43: Based on the early warning information, the security personnel patrol plan is dynamically adjusted to increase the patrol frequency in high-risk areas and time periods; targeted safety publicity and education (safety knowledge lectures, popular science short video push, etc.) are carried out; and any violations found are dealt with in a focused manner, including confiscation of items, educational talks, or transfer to law enforcement agencies for handling;

[0094] Furthermore, in an embodiment of the present invention, based on the multi-dimensional data analysis results of the present invention, it is convenient to analyze the characteristics of the personnel who violate the rules and the characteristics of the violation types, and the campus safety management department can formulate a more targeted safety publicity and education program. For example, in response to the problem that there are many cases of students illegally carrying flammable and explosive items into the dormitory, a publicity and education activity with the theme of dormitory safety is carried out. By holding safety knowledge lectures, distributing publicity materials, organizing emergency drills, etc., students are informed of the dangers of illegally carrying flammable and explosive items and the correct dormitory safety management methods; for the possible illegal use of hazardous chemicals by teachers, professional safety training is carried out to improve teachers' safety awareness and operational skills, and to achieve precise publicity based on personnel characteristics and violation types;

[0095] At the same time, precise safety education and publicity can enhance the safety awareness and self-discipline of teachers and students, enabling them to better understand the dangers and consequences of violations and consciously abide by campus safety regulations. Regular evaluation of education and publicity results, and continuous adjustment and optimization of education and publicity programs based on the evaluation results, can further improve the pertinence and effectiveness of education and publicity, and create a safe and harmonious campus environment.

[0096] Example 2

[0097] Figure 2 A schematic diagram of the module composition of the smart campus security data processing system provided in the second embodiment of the present invention;

[0098] In this embodiment, the system includes:

[0099] The data collection module, data sorting module, trend analysis module and early warning mechanism establishment module are interconnected and communicated with each other; wherein,

[0100] The data collection module is used to collect campus safety inspection records, intelligent detection equipment data, and teacher and student reporting information, and forward the above raw data to the data sorting module;

[0101] The data sorting module is used to classify and clean the original data and output the cleaned data set;

[0102] The trend analysis module is used to analyze the trends and patterns of historical violations by analyzing the data on the carrying and use of historical illegal items;

[0103] The early warning mechanism establishment module is used to set dynamically adjustable early warning thresholds for various illegal carrying or use behaviors based on historical data analysis results and combined with the security characteristics of various areas on campus in different time periods. The thresholds are used to trigger the security response mechanism.

[0104] The data collection module includes a manual inspection terminal module, an intelligent detection equipment module and a reporting information module; among them,

[0105] The manual inspection terminal module is deployed on the security personnel's handheld terminal to input relevant information of violation incidents during the inspection process;

[0106] The intelligent detection equipment module includes an intelligent image recognition camera and an odor detection sensor, which are used to collect images and odor characteristics of illegal items in real time;

[0107] The reporting information module is used to receive suspicious information submitted by teachers and students through the campus safety management app, hotline or reporting box.

[0108] The data sorting module includes a classification and sorting module and a data cleaning module;

[0109] The classification and sorting module is used to classify the collected data according to the type of illegal items (such as flammable and explosive items, controlled knives, dangerous chemicals, etc.), the time when the violation occurred (specifically to the year, month, day, and time period), the identity of the violator (student, teacher, visitor, etc.), and the location of the violation (dormitory, teaching building, laboratory, etc.);

[0110] The data cleaning module is used to remove duplicate, erroneous, and incomplete data to ensure data accuracy and reliability. For example, it can correct or remove obviously incorrect time records or unclear descriptions of illegal items.

[0111] The trend analysis module includes time series analysis module, spatial distribution analysis module and personnel characteristics analysis module; among them,

[0112] The time series analysis module is used to count the number of various violations by time unit based on the cleaned data set, generate a line graph, and calculate the growth rate or decline rate. The time series analysis module also includes trend anomaly detection at multiple time granularities to identify sudden changes occurring at the weekly and monthly levels, and automatically assess the intensity of events and the level of evolutionary risk by combining threshold change curves. For example, the number of violations in the same month of two consecutive semesters can be compared to calculate the growth rate. If the number of violations of bringing flammable and explosive items into dormitories in December of a semester increases by 30% compared to December of the previous semester, it indicates that this behavior has an upward trend in that time period.

[0113] The spatial distribution analysis module is used to divide the campus into several functional zones, count the number of violations in each zone, and generate a heat map. The campus is divided into different areas (such as dormitory areas, teaching areas, and laboratory areas), and the number of violations in each area is counted, with different colors representing the intensity of violations. The heat map can intuitively identify areas with high incidence of violations, for example, finding that the number of illegal carrying of items is higher in the dormitory area during a specific time period.

[0114] The Personnel Profile Analysis module categorizes and compiles statistics based on identity, grade, and major, generating the percentage of violations by each group. For example, it calculates the proportion of students, faculty, and non-campus personnel in all violations, analyzing which groups are more likely to engage in illegal carrying and use of items. It also studies the differences in violations among students of different grades and majors. By comparing violation data for students of different grades and majors, it is found that students in certain majors or grades may be more prone to specific types of violations due to course requirements or personal habits.

[0115] The early warning mechanism establishment module includes an early warning threshold setting module and an early warning information generation module;

[0116] The warning threshold setting module is used to set warning thresholds for different types of violations based on the analysis results of historical data and the actual needs of campus safety management. According to the analysis results of historical data and the actual needs of campus safety management, scientific and reasonable warning thresholds are set for different types of violations. At the same time, different warning thresholds are set considering the characteristics of different areas and time periods, thereby improving the accuracy of warnings. For example, for the illegal behavior of bringing flammable and explosive items into the dormitory at the end of the semester, the warning is triggered when the number of occurrences of this behavior in a certain month exceeds 1.5 times the historical average number of times in that month, avoiding false alarms or missed alarms caused by unreasonable warning threshold settings.

[0117] Different warning thresholds can be set based on the characteristics of different areas and time periods. For example, the warning threshold for dormitories at the end of the semester can be appropriately increased because there are likely to be more violations during this period; while the warning threshold for teaching areas during normal teaching hours should be relatively low.

[0118] The early warning information generation module is used to monitor the comparison between real-time violation statistics and the early warning threshold. Once the threshold is reached, an early warning report is automatically generated and released through channels such as campus broadcasts, SMS / APP push, and electronic bulletin boards.

[0119] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0120] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0121] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0122] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which are all protected by the present invention.

Claims

1. A method for processing smart campus security data based on big data, characterized by: The smart campus security data processing method comprises the following steps: Step S1: Collect raw data from campus safety inspection records, intelligent detection equipment, and teacher and student reporting information; Step S2: The raw data is categorized and stored according to the type of illegal item, time of illegal behavior, identity of the illegal person, and location of the illegal behavior, and duplicate records are removed, and erroneous and incomplete information is corrected or eliminated to obtain a cleaned data set; Step S3: Conduct in-depth analysis of historical illegal item carrying and use data using time series analysis, spatial distribution analysis, and personnel characteristics analysis; Step S4: Based on the analysis results of historical data and the actual needs of campus safety management, scientific and reasonable warning thresholds are set for different types of violations. When the violation reaches the warning threshold, the system automatically generates warning information and releases it to relevant personnel in a timely manner through multiple channels.

2. The method for processing smart campus security data based on big data according to claim 1, characterized in that: In step S1, collecting raw data includes: Security personnel use handheld terminals to record violations discovered during routine inspections, special inspections, or temporary spot checks; Deploy intelligent image recognition cameras and odor detection sensors in dormitories, teaching buildings, laboratory buildings, and related key areas to collect images and odor characteristics of illegal items in real time; Teachers and students submit suspicious information through the campus security management app, reporting hotline or reporting box, which will be used as one of the data sources after background review.

3. The method for processing smart campus security data based on big data according to claim 1, characterized in that: In step S3, the specific method of time series analysis is: Step S31: Group all events according to the preset time granularity based on the "time of event occurrence" field in the cleaned data set; Step S32: Count the number of occurrences of each type of illegal item in each time unit, marked as N type,t Indicates the number of events of type type within time unit t; Step S33: Generate a line graph to show N type,t The changing trend of t; Step S34: Calculate the growth rate or decline rate of adjacent time units, and the calculation expression is: where t i-1 With t i are adjacent time units, if Then the minimum constant ε is set instead; where, is the time unit t i The number of events of violation type type, GR type (t i ,t i-1 ) is the growth rate between two adjacent time units, and ε is the minimum positive value set to prevent the denominator from being zero.

4. The method for processing smart campus security data based on big data according to claim 3, characterized in that: In step S3, the specific method of spatial distribution analysis is: Step S3a: Based on the "location" field in the cleaned dataset, the campus is divided into several functional zones {R1, R2, ..., R R }; Step S3b: Receive the "time filter T" from the time series analysis filter ”, extract the event set E within the time range filtered ; Step S3c: E filtered By partition R j With type type statistics, we get Step S3d: Using the campus floor plan, construct the heat map data {(x j ,y j ,W j )}:(x j ,y j ) is R j The plane coordinates of For this area in T fiter Total number of violations during the time period; Step S3e: Generate heat map, with W j The larger it is, the darker the heat map color; Step S3f: When When the type dimension or R j dimension, marked as "high-risk area", where β type The regional threshold for type type calculated based on historical statistics.

5. The method for processing smart campus security data based on big data according to claim 4, characterized in that: In step S3, the specific method of personnel feature analysis is: Step S3U: Based on the "Personnel Identity" field in the cleaned dataset, all violation data are divided into several sets based on the identity of the participants, including but not limited to students, teachers, visitors, logistics personnel, and external staff, and further refined to grade, major, or department; Step S3V: For each group of people, count their filter The number of various types of violations involved in the report is used to generate statistical indicators Indicates the number of type violations committed by a specific group within a specific time period; Step S3W: Construct a personnel violation ratio map, calculate the ratio of each group of personnel in different violations, thereby determining the proportion of each group of people in specific violations and mining the behavior patterns of key groups; Step S3X: Further introduce behavioral risk assessment indicator R group , defined as the average violation frequency of the group divided by the total number of people in the group, is used to measure the violation risk intensity of a specific group of people. High-risk groups will be given higher weights in subsequent warnings; Step S3Y: Combine historical violation behavior trends and conduct a multi-dimensional cross-analysis of high-risk groups, high-incidence areas, and key time periods.

6. The method for processing smart campus security data based on big data according to claim 1, characterized in that: The step S4 further comprises: Step S41: Calculate the historical average μ and standard deviation σ of each type of violation using historical statistics for the same period, and set the dynamic threshold y u , its calculation expression is: u =μ+k·σ, when the number of a certain type of violation in a certain period of time exceeds the threshold y u When , an early warning is triggered, where k is the dynamic control parameter corresponding to different types of violations, which is a constant greater than 0; Step S42: When the real-time statistical data reaches the warning threshold y u When a violation occurs, an early warning report is automatically generated, including the type of violation, the area where it occurred, the time range, and the comparison between the current number of violations and the threshold. The report is then released to security personnel, dormitory managers, and relevant persons in charge through campus broadcasts, SMS / APP push, and electronic bulletin boards. Step S43: Based on the early warning information, dynamically adjust the security personnel patrol plan and increase the patrol frequency in high-risk areas and time periods; carry out targeted safety publicity and education; focus on rectifying any violations found, including confiscating items, giving educational talks, or handing over to law enforcement agencies for handling.

7. A smart campus security data processing system for implementing the method of claim 1, characterized in that: The smart campus security data processing system includes a data acquisition module, a data sorting module, a trend analysis module and an early warning mechanism establishment module, and the data acquisition module, the data sorting module, the trend analysis module and the early warning mechanism establishment module are interconnected; wherein, The data acquisition module is used to collect campus safety inspection records, intelligent detection equipment data and teacher and student reporting information, and forward the above raw data to the data sorting module; The data sorting module is used to classify and sort the original data and clean the data, and output the cleaned data set; The trend analysis module is used to analyze the trends and patterns of historical illegal behaviors by analyzing the data of carrying and using historical illegal items; The early warning mechanism establishment module is used to set dynamically adjustable early warning thresholds for various types of illegal carrying or use behaviors based on historical data analysis results and in combination with the security characteristics of various areas of the campus at different time periods. The thresholds are used to trigger the security response mechanism; The early warning mechanism establishment module includes an early warning threshold setting module and an early warning information generation module; the early warning threshold setting module is used to set early warning thresholds for different types of violations based on the analysis results of historical data and the actual needs of campus safety management; the early warning information generation module is used to monitor the comparison between real-time violation statistics and early warning thresholds, and automatically generate an early warning report once the threshold is reached.

8. The big data-based smart campus security data processing system according to claim 7, characterized in that: The data acquisition module includes a manual inspection terminal module, an intelligent detection equipment module and a reporting information module; wherein, The manual inspection terminal module is deployed on the handheld terminal of the security personnel and is used to enter relevant information of the violation incident during the inspection process; The intelligent detection equipment module includes an intelligent image recognition camera and an odor detection sensor for collecting images and odor characteristics of illegal items in real time; The reporting information module is used to receive suspicious information submitted by teachers and students through the campus safety management APP, hotline or reporting box.

9. The big data-based smart campus security data processing system according to claim 7, characterized in that: The data sorting module includes a classification and sorting module and a data cleaning module; wherein, The classification and arranging module is used to classify the collected data according to the type of illegal items, the time when the illegal behavior occurred, the identity of the illegal person, and the location of the illegal behavior; The data cleaning module is used to remove duplicate, erroneous and incomplete data to ensure the accuracy and reliability of the data.

10. The big data-based smart campus security data processing system according to claim 7, characterized in that: The trend analysis module includes a time series analysis module, a spatial distribution analysis module and a personnel feature analysis module; wherein, The time series analysis module is used to count the number of various types of violations by time unit based on the cleaned data set, generate a line chart, and calculate the growth rate or decline rate. The time series analysis module also includes a trend anomaly detection function at multiple time granularities to identify sudden changes occurring at the weekly and monthly levels, and automatically assess the event intensity and evolution risk level based on the threshold change curve; The spatial distribution analysis module is used to divide the campus into several functional zones, count the number of violations in each zone and generate a heat map; The personnel feature analysis module is used to classify and count violation incidents according to identity, grade and major and generate the violation ratio of each group of people.

Images