A method for constructing a multi-dimensional social group activity monitoring model

Abstract

The present invention discloses a method for constructing a multi-dimensional social group activity monitoring model. This method relates to the field of electronic data processing technology and includes the following steps: collecting and processing data for constructing the social group activity monitoring model; analyzing the data for constructing the social group activity monitoring model; constructing a basic social group activity monitoring model; and optimizing and adjusting the accuracy of the activity monitoring model construction method based on the basic social group activity monitoring model. This method improves the reliability of the method for constructing the social group activity monitoring model and addresses the problem of insufficient reliability of the method for constructing the social group activity monitoring model in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic data processing, and in particular to a method for constructing a multi-dimensional social group activity monitoring model. Background Art

[0002] With the rapid development of the internet and information technology, the speed and scope of information dissemination regarding social group activities have greatly increased. To better manage and supervise these activities, building effective monitoring models has become increasingly important. With the increasing number of universities and social groups, community management faces increasing challenges, such as member recruitment, event organization, and financial management. However, existing social group activity monitoring models suffer from numerous technical issues, resulting in insufficient reliability assessments and difficulty meeting practical needs.

[0003] The existing method of constructing a group activity monitoring model uses positioning technology and the Beidou satellite navigation system for real-time positioning to obtain the precise location information of tour group members; and uses big data processing technology to process and analyze massive positioning data and extract useful information.

[0004] For example, the invention patent application with publication number CN115577052A discloses a method for constructing a real-time population integral model based on activity trajectory data, including: obtaining population data and corresponding activity trajectory data, and preprocessing them to form a basic database; using the data in the basic database to construct a knowledge graph with community buildings, portals, and ID cards as entities and portal relationships as edges, marking target personnel, and forming a knowledge graph of portals and household personnel; based on the activity trajectory data, analyzing the activities and frequency of the population, using multiple venue features of the activity trajectory data to construct a clustering model that can distinguish the residence types of personnel, extracting the venue and frequency features of entry and exit and importing them into the clustering model to obtain the residence types of personnel; and constructing a population integral model based on the results obtained from the personnel activity trajectory data and the clustering model.

[0005] For example, the invention patent announcement with announcement number: CN114066431B discloses a method for realizing a personnel activity map based on a four-dimensional travel model, comprising: constructing a four-dimensional travel model; inputting facial image data of traveling personnel into the four-dimensional travel model; determining the travel trajectory of target personnel and identifying abnormal personnel among the target personnel; mining close contacts A who have contact with abnormal personnel; mining high-frequency travel places A of abnormal personnel; mining high-frequency visitors to high-frequency travel places A; mining personnel who appear in the same frame with abnormal personnel based on high-frequency travel places A; mining high-frequency travel places B of high-frequency visitors; mining high-frequency travel places C of personnel who appear in the same frame; mining close contacts B of personnel who appear in the same frame; mining close contacts C of close contacts A; mining high-frequency travel places D of close contacts A; and generating a personnel activity map.

[0006] However, in the process of implementing the technical solutions of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0007] The method for constructing a social group activity monitoring model is used in real-time tracking the location of tour group members entering a cave to ensure that they travel along a preset safe route. However, there is a problem of insufficient reliability assessment of the method for constructing a group activity monitoring model. When the Beidou signal encounters reflective surfaces such as buildings, ground, and water during propagation, reflection will occur. The reflected signal and the direct signal arrive at the receiver of the Beidou satellite navigation system at the same time, but due to the different path lengths, differences in signal phase and amplitude will occur. At the same time, accurate extraction of abnormal behavior features such as sudden deviation from the route and abnormal stay from massive data increases the difficulty and computational complexity of feature extraction, resulting in insufficient reliability of the method for constructing a social group activity monitoring model. Summary of the Invention

[0008] The embodiments of the present application solve the problem of insufficient reliability of the construction method of the social group activity monitoring model in the prior art by providing a construction method of the social group activity monitoring model based on multiple dimensions, thereby improving the reliability of the construction method of the social group activity monitoring model.

[0009] An embodiment of the present application provides a method for constructing a social group activity monitoring model based on multiple dimensions, comprising the following steps: collecting and processing social group activity monitoring model construction data; analyzing the social group activity monitoring model construction data to obtain a multi-path effect impact evaluation value and an abnormal behavior dynamic analysis evaluation value; obtaining an activity monitoring model construction accuracy evaluation value through comprehensive analysis of the multi-path effect impact evaluation value and the abnormal behavior dynamic analysis evaluation value; constructing a social group activity monitoring basic model, and optimizing and adjusting the activity monitoring model construction accuracy method of the social group activity monitoring basic model according to the multi-path effect impact evaluation value, the abnormal behavior dynamic analysis evaluation value and the activity monitoring model construction accuracy evaluation value.

[0010] Furthermore, the specific steps of collecting and processing the data for constructing the social group activity monitoring model are: collecting the original data for constructing the social group activity monitoring model by receiving GPS satellite signals through a handheld GPS locator; cleaning and denoising the original data for constructing the social group activity monitoring model to obtain the data for constructing the social group activity monitoring model, wherein the data for constructing the social group activity monitoring model includes multi-path effect impact data and abnormal behavior dynamic analysis data.

[0011] Furthermore, the specific steps of obtaining the multipath effect impact evaluation value are as follows: the multipath effect impact data include the number of reflected signals, time delay, reflected signal power, direct signal power and the phase difference between the reflected signal and the direct signal; obtaining the reflected signal number threshold, the time difference threshold for the reflected signal and the direct signal to reach the receiver, the standard phase difference between the reflected signal and the direct signal, the weight factor of the reflected signal number, the weight factor of the time delay, the weight factor of the reflected signal strength and the weight factor of the phase difference between the reflected signal and the direct signal from the group activity monitoring database; summing and averaging the ratio of the number of reflected signals to the number of reflected signals threshold in different multipath effect impact detection sections as the first component of the multipath effect impact; and recording the time of the multipath effect impact detection point as the weight factor of the multipath effect impact detection point. The ratio of the delay to the time difference threshold between the reflected signal and the direct signal arriving at the receiver is recorded as the second component of the multipath effect impact; the ratio of the reflected signal power at the multipath effect impact detection point to the direct signal power at the multipath effect impact detection point is recorded as the third component of the multipath effect impact; the ratio of the absolute value of the phase difference between the reflected signal and the direct signal at the multipath effect impact detection point and the standard phase difference between the reflected signal and the direct signal to the standard phase difference between the reflected signal and the direct signal is recorded as the fourth component of the multipath effect impact; the multipath effect impact evaluation value represents the quantitative data of the degree of influence of the multipath effect first component, the multipath effect second component, the multipath effect third component and the multipath effect fourth component on the reflected signal during the propagation process.

[0012] Furthermore, the specific steps for obtaining the abnormal behavior dynamic analysis evaluation value are as follows: the abnormal behavior dynamic analysis data includes the phase difference, time delay, adjusted threshold, threshold before adjustment and time difference between the reflected signal and the direct signal; obtaining the standard phase difference between the reflected signal and the direct signal, the time difference threshold for the reflected signal and the direct signal to reach the receiver, the weight factor of the dynamic threshold adaptability coefficient, the weight factor of the phase difference between the reflected signal and the direct signal and the weight factor of the time delay from the group activity monitoring database; calculating the ratio of the absolute value of the difference between the adjusted threshold under the dynamic threshold adaptive time window detection section and the threshold before adjustment under the dynamic threshold adaptive time window detection section to obtain the dynamic threshold adaptability coefficient; The dynamic threshold adaptability coefficient is summed and averaged in different dynamic threshold adaptability time window detection segments, and recorded as the first component of abnormal behavior dynamic analysis; the ratio of the absolute value of the phase difference between the reflected signal and the direct signal at the abnormal behavior dynamic analysis detection point minus the standard phase difference between the reflected signal and the direct signal to the standard phase difference between the reflected signal and the direct signal is recorded as the second component of abnormal behavior dynamic analysis; the ratio of the time delay at the abnormal behavior dynamic analysis detection point to the time difference threshold between the reflected signal and the direct signal arriving at the receiver is recorded as the third component of abnormal behavior dynamic analysis; the abnormal behavior dynamic analysis evaluation value represents the quantitative data of the dynamic analysis capabilities of the first component of abnormal behavior dynamic analysis, the second component of abnormal behavior dynamic analysis, and the third component of abnormal behavior dynamic analysis on abnormal behavior characteristics.

[0013] Furthermore, the specific steps of the comprehensive analysis to obtain the construction accuracy evaluation value of the activity monitoring model are: obtaining the data update frequency threshold, the weight factor of the abnormal behavior dynamic analysis evaluation value, the weight factor of the data update frequency and the weight factor of the multi-path effect impact evaluation value from the group activity monitoring database; summing and averaging the abnormal behavior dynamic analysis evaluation value at different abnormal behavior dynamic analysis detection points, and recording it as the first component of the construction accuracy of the activity monitoring model; summing and averaging the data update frequency and the data update frequency threshold at the construction accuracy detection point of the activity monitoring model, and recording it as the second component of the construction accuracy of the activity monitoring model; summing and averaging the multi-path effect impact evaluation value at different multi-path effect impact detection points, and recording it as the third component of the construction accuracy of the activity monitoring model; the construction accuracy evaluation value of the activity monitoring model represents quantitative data on the degree of influence of the first component of the construction accuracy of the activity monitoring model, the second component of the construction accuracy of the activity monitoring model and the third component of the construction accuracy of the activity monitoring model on the overall construction accuracy of the activity monitoring model in multiple dimensions.

[0014] Furthermore, the specific steps of constructing the basic model for monitoring social group activities are: initializing the basic model for monitoring social group activities according to the data for constructing the model; setting the parameters of the basic model for monitoring social group activities, wherein the parameters of the basic model for monitoring social group activities include a multi-path effect impact evaluation value, an abnormal behavior dynamic analysis evaluation value, and an activity monitoring model construction accuracy evaluation value; inputting the data for constructing the model for monitoring social group activities as training data into the basic model for monitoring social group activities for training, and continuously adjusting the parameters of the basic model for monitoring social group activities to obtain the social group activity monitoring model.

[0015] Furthermore, the specific steps of optimizing and adjusting the construction accuracy method of the social group activity monitoring basic model are as follows: importing the first judgment value of the multi-path effect impact evaluation value, the second judgment value of the abnormal behavior dynamic analysis evaluation value and the third judgment value of the construction accuracy evaluation value of the activity monitoring model in the group activity monitoring database into the social group activity monitoring model, and adjusting the output of the social group activity monitoring model through the social group activity monitoring model output adjustment method, which includes optimizing the multi-path effect impact method, optimizing the abnormal behavior dynamic analysis method and optimizing the construction accuracy method of the activity monitoring model.

[0016] Furthermore, the specific steps of the method for optimizing the impact of multipath effect are: if the multipath effect impact evaluation value is less than or equal to the first judgment value of the multipath effect impact evaluation value, the method for optimizing the impact of multipath effect is not performed; if the multipath effect impact evaluation value is greater than the first judgment value of the multipath effect impact evaluation value, the collected signal is filtered by applying a filter, and the filtering parameters are automatically adjusted according to the real-time signal characteristics, and the filtering parameters include signal frequency and amplitude.

[0017] Furthermore, the specific steps of optimizing the abnormal behavior dynamic analysis method are as follows: if the abnormal behavior dynamic analysis evaluation value is greater than or equal to the second abnormal behavior dynamic analysis evaluation value, then there is no need to optimize the abnormal behavior dynamic analysis method; if the abnormal behavior dynamic analysis evaluation value is less than the second abnormal behavior dynamic analysis evaluation value, then formulate selective transmission, and give priority to transmitting key data, the key data including location and abnormal behavior; with the distributed computing cluster, the massive data is divided into pieces for processing and distributed to different computing nodes for parallel processing.

[0018] Furthermore, the specific steps of the method for optimizing the construction accuracy of the activity monitoring model are as follows: if the construction accuracy evaluation value of the activity monitoring model is greater than or equal to the third judgment value of the construction accuracy evaluation value of the activity monitoring model, there is no need to optimize the construction accuracy method of the activity monitoring model; if the construction accuracy evaluation value of the activity monitoring model is less than the third judgment value of the construction accuracy evaluation value of the activity monitoring model, the passenger behavior system is monitored in real time by a camera to identify abnormal behavior, and the abnormal behavior information is converted into intuitive visual elements, the intuitive visual elements include color changes and flashing icons, and a light signal transmission device composed of LED lights is used to transmit visual warning information. Personnel in specific areas are equipped with handheld devices with photoelectric sensors, and the receiving devices decode the light signals and display visual warning information. Personnel locate abnormal passengers based on the warning information; establish an early warning confirmation mechanism to allow operators to confirm or reject the warning information to reduce false alarms, and establish a linkage mechanism between the early warning information and the emergency response system. Once an early warning is issued, the corresponding emergency response measures are immediately initiated.

[0019] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0020] 1. By collecting and processing the data for constructing the social group activity monitoring model; analyzing the data for constructing the social group activity monitoring model, constructing the social group activity monitoring basic model, and optimizing and adjusting the accuracy method of constructing the activity monitoring model of the social group activity monitoring basic model, the reliability of the construction method of the social group activity monitoring model is improved, and the problem of insufficient reliability of the construction method of the social group activity monitoring model in the existing technology is solved.

[0021] 2. By analyzing the data of the social group activity monitoring model, we can obtain the multipath effect impact assessment value and abnormal behavior dynamic analysis assessment value, which helps to correct the positioning error caused by signal reflection, refraction, etc., and helps to distinguish normal activities from potential risk activities, thereby improving the accuracy of monitoring data.

[0022] 3. The construction accuracy evaluation value of the activity monitoring model obtained through comprehensive analysis helps to discover and correct errors in the model, reduce false positives and false negatives, and provide quantitative indicators for model performance, which is convenient for comparison and evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A flowchart of a method for constructing a multi-dimensional social group activity monitoring model provided in an embodiment of the present application;

[0024] Figure 2 A schematic diagram of a construction accuracy evaluation value function for an activity monitoring model provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The embodiments of the present application solve the problem of insufficient reliability of the methods for constructing social group activity monitoring models in the prior art by providing a method for constructing a social group activity monitoring model based on multiple dimensions. The method collects and processes data for constructing the social group activity monitoring model; analyzes the data for constructing the social group activity monitoring model, constructs a basic social group activity monitoring model, and optimizes and adjusts the accuracy of the method for constructing the activity monitoring model of the basic social group activity monitoring model, thereby improving the reliability of the method for constructing the social group activity monitoring model.

[0026] The technical solution in the embodiments of the present application is to solve the above-mentioned problem of insufficient reliability of the construction method of the social group activity monitoring model. The overall idea is as follows:

[0027] By collecting and processing data for building a social group activity monitoring model; analyzing the data for building a social group activity monitoring model, building a basic model for social group activity monitoring, and optimizing and adjusting the accuracy of the construction method of the basic model for social group activity monitoring, the reliability of the construction method of the social group activity monitoring model is improved.

[0028] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0029] like Figure 1 As shown, it is a flow chart of a method for constructing a multi-dimensional social group activity monitoring model provided in an embodiment of the present application, the method comprising the following steps: collecting and processing social group activity monitoring model construction data; analyzing the social group activity monitoring model construction data to obtain a multi-path effect impact evaluation value and an abnormal behavior dynamic analysis evaluation value; obtaining an activity monitoring model construction accuracy evaluation value through comprehensive analysis of the multi-path effect impact evaluation value and the abnormal behavior dynamic analysis evaluation value; constructing a social group activity monitoring basic model, and optimizing and adjusting the activity monitoring model construction accuracy method of the social group activity monitoring basic model according to the multi-path effect impact evaluation value, the abnormal behavior dynamic analysis evaluation value and the activity monitoring model construction accuracy evaluation value.

[0030] Furthermore, the specific steps of collecting and processing the data for constructing the social group activity monitoring model are: collecting the original data for constructing the social group activity monitoring model by receiving GPS satellite signals through a handheld GPS locator; cleaning and denoising the original data for constructing the social group activity monitoring model to obtain the data for constructing the social group activity monitoring model, wherein the data for constructing the social group activity monitoring model includes multi-path effect impact data and abnormal behavior dynamic analysis data.

[0031] Furthermore, the specific steps for obtaining the multipath effect impact evaluation value are as follows: the multipath effect impact data include the number of reflected signals, time delay, reflected signal power, direct signal power and the phase difference between the reflected signal and the direct signal; obtaining the reflected signal number threshold, the time difference threshold for the reflected signal and the direct signal to reach the receiver, the standard phase difference between the reflected signal and the direct signal, the weight factor of the reflected signal number, the weight factor of the time delay, the weight factor of the reflected signal strength and the weight factor of the phase difference between the reflected signal and the direct signal from the group activity monitoring database; summing and averaging the ratio of the number of reflected signals to the number of reflected signals threshold in different multipath effect impact detection sections as the first component of the multipath effect impact; and taking the time delay of the multipath effect impact detection point as the weight factor of the multipath effect impact detection point. The ratio of the delay to the time difference threshold between the reflected signal and the direct signal arriving at the receiver is recorded as the second component of the multipath effect impact; the ratio of the reflected signal power at the multipath effect impact detection point to the direct signal power at the multipath effect impact detection point is recorded as the third component of the multipath effect impact; the ratio of the absolute value of the phase difference between the reflected signal and the direct signal at the multipath effect impact detection point and the standard phase difference between the reflected signal and the direct signal to the standard phase difference between the reflected signal and the direct signal is recorded as the fourth component of the multipath effect impact; the multipath effect impact evaluation value represents the quantitative data of the degree of influence of the multipath effect first component, the multipath effect second component, the multipath effect third component and the multipath effect fourth component on the reflected signal during the propagation process.

[0032] In this embodiment, the specific method for obtaining the multipath effect impact assessment value through analysis is as follows:

[0033] ;

[0034] ;

[0035] The preset multipath effect detection points are numbered in sequence. Indicates the The number of the multipath effect detection point under each multipath effect detection segment, , Indicates the total number of detection points affected by the multipath effect.

[0036] Divide the preset multipath effect impact time into multipath effect impact detection segments of equal length. Indicates the number of the detection segment affected by the multipath effect. , Indicates the total number of segments affected by multipath effects.

[0037] Indicates the The multipath effect impact evaluation value of each multipath effect detection point.

[0038] Indicates the The multipath effect affects the number of reflected signals in the detection section, and the number of reflected signals is obtained by a high-precision GPS receiver.

[0039] It represents the reflection signal quantity threshold, which is a preset reflection signal quantity threshold obtained from the group activity monitoring database, and can be the average value of the reflection signal quantity in the preset multipath effect detection section from the historical database.

[0040] Indicates the The time delay at the detection point affected by the multipath effect is the time difference between the reflected signal and the direct signal reaching the receiver. It refers to the time difference between the direct signal reaching the receiver directly from the transmitter and the reflected signal reaching the receiver after one reflection during the same signal transmission process. There are two main ways of signal propagation: direct and reflected. The direct signal refers to the signal that reaches the receiver directly from the transmitter, while the reflected signal reaches the receiver after one or more reflections. In the actual signal transmission process, various objects in the environment such as buildings and the ground will reflect the signal. Therefore, the receiver usually receives both the direct signal and the reflected signal at the same time, and the time delay is obtained by a high-precision GPS receiver.

[0041] The threshold value representing the time difference between the reflected signal and the direct signal arriving at the receiver is a preset threshold value for the time difference between the reflected signal and the direct signal arriving at the receiver obtained from the group activity monitoring database, or can be the average value of the time difference between the reflected signal and the direct signal arriving at the receiver at a preset multipath effect detection point obtained from the historical database.

[0042] Indicates the The multipath effect affects the reflected signal power at the detection point, and the reflected signal power is obtained through a high-precision GPS receiver.

[0043] Indicates the The multipath effect affects the direct signal power at the detection point, and the direct signal power is obtained through a high-precision GPS receiver.

[0044] Indicates the The multipath effect affects the phase difference between the reflected signal and the direct signal at the detection point, and the phase difference between the reflected signal and the direct signal is obtained by the power meter.

[0045] The standard phase difference between the reflected signal and the direct signal is obtained from the group activity monitoring database and is the preset standard phase difference between the reflected signal and the direct signal, indicating the expected phase difference between the reflected signal and the direct signal.

[0046] is the preset reflection signal quantity weighting factor obtained from the group activity monitoring database.

[0047] is the preset time delay weight factor obtained from the group activity monitoring database.

[0048] is the preset reflected signal strength weighting factor obtained from the group activity monitoring database.

[0049] is the phase difference weight factor between the preset reflected signal and the direct signal obtained from the group activity monitoring database.

[0050] The preset reflection signal quantity weight factor, the preset time delay weight factor, the preset reflection signal strength weight factor and the preset phase difference weight factor between the reflection signal and the direct signal are obtained through a mapping relationship. For example, a mapping set of the reflection signal quantity, time delay, reflection signal strength and the phase difference between the reflection signal and the direct signal and their corresponding weights is established respectively through the relationship between the reflection signal quantity, time delay, reflection signal strength and the phase difference between the reflection signal and the direct signal in the historical data. The corresponding preset reflection signal quantity weight factor, preset time delay weight factor, preset reflection signal strength weight factor and preset phase difference weight factor between the reflection signal and the direct signal in the mapping set are obtained by inputting the real-time reflection signal quantity, time delay, reflection signal strength and the phase difference between the reflection signal and the direct signal.

[0051] A greater number of reflected signals indicates that the signal encountered multiple reflectors during propagation, resulting in different reflection paths. Each reflection path has a time delay due to the different distances and speeds of signal propagation. Therefore, an increase in the number of reflected signals is usually accompanied by multiple reflection signals with different time delays. A greater number of reflection signals indicates a longer time delay. Direct signal power is the power of the signal directly from the transmitter to the receiver, while reflected signal power is the power of the signal after reflection. The greater the reflected power, the smaller the direct power. Time delay causes a change in signal phase. The direct signal power and the phase difference between the reflected and direct signals are the phase difference between the reflected and direct signals. The longer the time delay, the greater the direct signal power and the phase difference between the reflected and direct signals.

[0052] There is a positive correlation between the number of reflected signals and the multipath effect impact evaluation value. The more reflected signals there are, the more obvious the multipath effect is, and the more reflected signals there are, the greater the multipath effect impact evaluation value; there is a positive correlation between time delay and the multipath effect impact evaluation value. The difference in time delay will cause the signal to expand in the time domain. The longer the time delay, the greater the multipath effect impact evaluation value; there is a positive correlation between the ratio of reflected signal power to direct signal power and the multipath effect impact evaluation value. The greater the ratio of reflected signal power to direct signal power, the more it affects the intensity of multipath interference. The greater the ratio of reflected signal power to direct signal power, the greater the multipath effect impact evaluation value; there is a positive correlation between the phase difference between the reflected signal and the direct signal and the multipath effect impact evaluation value. The greater the phase difference between the reflected signal and the direct signal, the more it affects the overall strength and stability of the signal. The greater the phase difference between the reflected signal and the direct signal, the greater the multipath effect impact evaluation value.

[0053] Furthermore, the specific steps for obtaining the abnormal behavior dynamic analysis evaluation value are as follows: the abnormal behavior dynamic analysis data include the phase difference, time delay, adjusted threshold, threshold before adjustment and time difference between the reflected signal and the direct signal; the standard phase difference between the reflected signal and the direct signal, the time difference threshold for the reflected signal and the direct signal to reach the receiver, the weight factor of the dynamic threshold adaptability coefficient, the weight factor of the phase difference between the reflected signal and the direct signal and the weight factor of the time delay are obtained from the group activity monitoring database; the dynamic threshold adaptability coefficient is obtained by calculating the ratio of the absolute value of the difference between the adjusted threshold under the dynamic threshold adaptive time window detection section and the threshold before adjustment under the dynamic threshold adaptive time window detection section; the dynamic threshold adaptability coefficient is obtained by dividing the dynamic threshold adaptive time window detection section by the absolute value of the difference between the adjusted threshold under the dynamic threshold adaptive time window detection section and the threshold before adjustment under the dynamic threshold adaptive time window detection section; the dynamic threshold adaptive ... coefficient by the absolute value of the difference between the adjusted threshold under the dynamic threshold adaptive time window detection section and the threshold before adjustment under the dynamic threshold adaptive time window detection section. The dynamic threshold adaptability coefficient is summed and averaged in different dynamic threshold adaptability time window detection segments, which is recorded as the first component of abnormal behavior dynamic analysis; the ratio of the absolute value of the phase difference between the reflected signal and the direct signal at the abnormal behavior dynamic analysis detection point minus the standard phase difference between the reflected signal and the direct signal to the standard phase difference between the reflected signal and the direct signal is recorded as the second component of abnormal behavior dynamic analysis; the ratio of the time delay at the abnormal behavior dynamic analysis detection point to the time difference threshold between the reflected signal and the direct signal arriving at the receiver is recorded as the third component of abnormal behavior dynamic analysis; the abnormal behavior dynamic analysis evaluation value represents the quantitative data of the dynamic analysis capabilities of the first component, the second component and the third component of the abnormal behavior dynamic analysis on abnormal behavior characteristics.

[0054] In this embodiment, the specific method for obtaining the abnormal behavior dynamic analysis evaluation value through analysis is as follows:

[0055] ;

[0056] ; ;

[0057] Number the preset abnormal behavior dynamic analysis detection points in sequence. Indicates the number of the abnormal behavior dynamic analysis detection point, , Indicates the total number of abnormal behavior dynamic analysis detection points.

[0058] The preset dynamic threshold adaptive time window detection segments are numbered in sequence. Indicates the number of the dynamic threshold adaptive time window detection segment, , Indicates the total number of detection segments in the dynamic threshold adaptive time window.

[0059] Indicates the The abnormal behavior dynamic analysis evaluation value of each abnormal behavior dynamic analysis detection point.

[0060] Indicates the The dynamic threshold adaptability coefficient under the dynamic threshold adaptability time window detection segment represents the rate of change of the threshold within the dynamic threshold adaptability time window.

[0061] Indicates the The phase difference between the reflected signal and the direct signal at each abnormal behavior dynamic analysis detection point is obtained through a high-precision GPS receiver.

[0062] represents the standard phase difference between the reflected signal and the direct signal, which is the preset standard phase difference between the reflected signal and the direct signal obtained from the group activity monitoring database.

[0063] Indicates the The time delay at each abnormal behavior dynamic analysis detection point represents the time difference between the reflected signal and the direct signal reaching the receiver. It refers to the time difference between the direct signal reaching the receiver directly from the transmitter and the reflected signal reaching the receiver after one reflection during the same signal transmission process. The time delay is obtained using a high-precision GPS receiver.

[0064] The threshold for the time difference between the reflected signal and the direct signal arriving at the receiver is obtained from the group activity monitoring database. It is used to determine whether the time difference between the reflected signal and the direct signal is within a normal range.

[0065] Indicates the The adjusted threshold value under the dynamic threshold adaptive time window detection segment, ie, the new threshold value, is obtained through the dynamic threshold adaptive detection system.

[0066] Indicates the The threshold value before adjustment under the dynamic threshold adaptive time window detection segment, ie, the old threshold value, is obtained through the dynamic threshold adaptive detection system.

[0067] Indicates the The time difference under the dynamic threshold adaptive time window detection segment is the time interval between two adjacent threshold adjustments. If no threshold adjustment occurs within a time window, the time difference can be marked as infinity or a specific value. At this time, the dynamic threshold adaptability coefficient should be zero or close to zero, indicating that there is no adjustment. The time difference is obtained through data processing software.

[0068] is the preset dynamic threshold adaptability coefficient weight factor obtained from the group activity monitoring database.

[0069] is the phase difference weight factor between the preset reflected signal and the direct signal obtained from the group activity monitoring database.

[0070] is the preset time delay weight factor obtained from the group activity monitoring database.

[0071] The preset dynamic threshold adaptability coefficient weight factor, the preset phase difference weight factor of the reflected signal and the direct signal, and the preset time delay weight factor are obtained through a mapping relationship. For example, a mapping set of the dynamic threshold adaptability coefficient, the phase difference and time delay of the reflected signal and the direct signal and their corresponding weights are established respectively through the relationship between the dynamic threshold adaptability coefficient, the phase difference and time delay of the reflected signal and the direct signal and the number of reflected signals in the historical data. The corresponding preset dynamic threshold adaptability coefficient weight factor, the preset phase difference weight factor of the reflected signal and the direct signal, and the preset time delay weight factor in the mapping set are obtained by inputting the real-time number of reflected signals, time delay, reflected signal strength, and the phase difference between the reflected signal and the direct signal.

[0072] Time delay refers to the difference in arrival time of a signal due to different path lengths during transmission. The phase difference between the reflected signal and the direct signal is caused by the different path lengths. The longer the time delay, the greater the phase difference between the reflected signal and the direct signal. The threshold before and after adjustment are used for signal detection or judgment. The threshold adjustment is to adapt to changes in signal strength, improve detection performance, or reduce false positives. The greater the phase difference between the reflected signal and the direct signal, the more the threshold needs to be adjusted to correctly distinguish the two signals. The time difference generally refers to the difference in arrival time between two signals. The greater the time difference, the greater the phase difference between the reflected signal and the direct signal.

[0073] There is a negative correlation between time delay and the evaluation value of dynamic analysis of abnormal behavior. The longer the time delay, the more abnormal the signal transmission process, such as path changes. The larger the time delay, the smaller the evaluation value of dynamic analysis of abnormal behavior. There is a negative correlation between the phase difference between the reflected signal and the direct signal and the evaluation value of dynamic analysis of abnormal behavior. The larger the phase difference between the reflected signal and the direct signal, the more unexpected the reflector or path changes are. The larger the phase difference between the reflected signal and the direct signal, the smaller the evaluation value of dynamic analysis of abnormal behavior. There is a positive correlation between the product of the absolute value of the difference between the adjusted threshold and the threshold before adjustment and the time difference and the evaluation value of dynamic analysis of abnormal behavior. The larger the product of the absolute value of the difference between the adjusted threshold and the threshold before adjustment and the time difference, the faster the system can adapt to sudden changes in the environment. The larger the product of the absolute value of the difference between the adjusted threshold and the threshold before adjustment and the time difference, the larger the evaluation value of dynamic analysis of abnormal behavior.

[0074] Furthermore, the specific steps for comprehensively analyzing and obtaining the construction accuracy evaluation value of the activity monitoring model are as follows: obtaining the data update frequency threshold, the weight factor of the abnormal behavior dynamic analysis evaluation value, the weight factor of the data update frequency and the weight factor of the multi-path effect impact evaluation value from the group activity monitoring database; summing and averaging the abnormal behavior dynamic analysis evaluation value at different abnormal behavior dynamic analysis detection points, and recording it as the first component of the construction accuracy of the activity monitoring model; summing and averaging the data update frequency and the data update frequency threshold at the construction accuracy detection point of the activity monitoring model, and recording it as the second component of the construction accuracy of the activity monitoring model; summing and averaging the multi-path effect impact evaluation value at different multi-path effect impact detection points, and recording it as the third component of the construction accuracy of the activity monitoring model; the construction accuracy evaluation value of the activity monitoring model represents quantitative data on the degree of influence of the first component of the construction accuracy of the activity monitoring model, the second component of the construction accuracy of the activity monitoring model and the third component of the construction accuracy of the activity monitoring model on the overall construction accuracy of the activity monitoring model in multiple dimensions.

[0075] In this embodiment, the specific method for obtaining the construction accuracy evaluation value of the activity monitoring model through analysis is as follows:

[0076] ;

[0077] ;

[0078] Number the construction accuracy detection points of the preset activity monitoring model in sequence, Indicates the number of the active monitoring model construction accuracy checkpoint under the active monitoring model construction accuracy checkpoint, , The total number of checkpoints indicating the build accuracy of the active monitoring model.

[0079] Represents an assessment of the building accuracy of the activity monitoring model.

[0080] Indicates the The abnormal behavior dynamic analysis evaluation value of each abnormal behavior dynamic analysis detection point.

[0081] Indicates the The data update frequency at each detection point is used to build an activity monitoring model with accuracy, and the data update frequency is obtained through fiber optic sensing technology.

[0082] Indicates the data update frequency threshold, which is the preset data update frequency threshold obtained from the group activity monitoring database.

[0083] Indicates the The multipath effect impact evaluation value of each multipath effect detection point.

[0084] The weight factor is the dynamic analysis evaluation value of the preset abnormal behavior obtained from the group activity monitoring database.

[0085] Updates frequency weighting factors for preset data obtained from the group activity monitoring database.

[0086] is the preset multipath effect impact assessment value weight factor obtained from the group activity monitoring database.

[0087] The preset abnormal behavior dynamic analysis evaluation value weight factor, the preset data update frequency weight factor and the preset multipath effect impact evaluation value weight factor are obtained through mapping relationships. For example, a mapping set of abnormal behavior dynamic analysis evaluation value, data update frequency and multipath effect impact evaluation value and their corresponding weights is established respectively through the relationship between the abnormal behavior dynamic analysis evaluation value, data update frequency and multipath effect impact evaluation value in historical data and the data transmission rate. By inputting the real-time abnormal behavior dynamic analysis evaluation value, data update frequency and multipath effect impact evaluation value, the corresponding preset abnormal behavior dynamic analysis evaluation value weight factor, preset data update frequency weight factor and preset multipath effect impact evaluation value weight factor in the mapping set are obtained.

[0088] Table 1 is an example table of construction accuracy evaluation values of the activity monitoring model. The example parameters in Table 1 only take the parameters under the construction accuracy detection point of the activity monitoring model for example. The weight factor Set to 0.4, the weight factor Set to 0.3, the weight factor Set to 0.3, The data update frequency threshold is 2, as shown in Table 1.

[0089] Table 1 Example of evaluation values for the construction accuracy of the activity monitoring model

[0090] Abnormal behavior dynamic analysis evaluation value Data update frequency Multipath effect impact assessment value Activity monitoring model construction accuracy assessment value 4 5 3 5.51872090775 4 3 2 4.85493819144 5 4 3 7.08617791316 6 2 7 4.79991345964 3 2 4 2.03713139561

[0091] The evaluation value of the dynamic analysis of abnormal behavior depends on the frequency of data updates. The faster the data is updated, the more real-time behavior information can be provided, and the larger the evaluation value of the dynamic analysis of abnormal behavior is. The data update frequency affects the real-time nature of the evaluation value of the dynamic analysis of abnormal behavior. The faster the data update frequency, the faster the abnormal behavior of tourists can be captured, and the larger the evaluation value of the dynamic analysis of abnormal behavior is. The multipath effect affects the accuracy of the evaluation value of the dynamic analysis of abnormal behavior. The greater the multipath effect affects the evaluation value, the accuracy of the abnormal behavior analysis will be affected, and the smaller the evaluation value of the dynamic analysis of abnormal behavior is.

[0092] As shown in Table 1, there is a positive correlation between the abnormal behavior dynamic analysis evaluation value and the activity monitoring model construction accuracy evaluation value. The higher the abnormal behavior dynamic analysis evaluation value, the more accurately the abnormal behavior of tourists can be identified and predicted. The larger the abnormal behavior dynamic analysis evaluation value, the greater the activity monitoring model construction accuracy evaluation value. There is a positive correlation between the data update frequency and the activity monitoring model construction accuracy evaluation value. The higher the data update frequency, the faster the latest location and behavior information of tourists can be obtained, so that the activity monitoring model can respond and judge more in real time. The higher the data update frequency, the greater the activity monitoring model construction accuracy evaluation value. There is a negative correlation between the multipath effect impact evaluation value and the activity monitoring model construction accuracy evaluation value. The higher the multipath effect impact evaluation value, the greater the positioning error. The larger the multipath effect impact evaluation value, the smaller the activity monitoring model construction accuracy evaluation value.

[0093] Depend on Figure 2 As shown, it is a schematic diagram of the construction accuracy evaluation value function of the activity monitoring model provided in the embodiment of the present application; x is the positive semi-axis of the horizontal coordinate, y is the positive semi-axis of the vertical coordinate, and the weight factor Set to 0.4, the weight factor Set to 0.3, the weight factor Set to 0.3, The data update frequency threshold is 2.

[0094] Curve a indicates that if the data update frequency is fixed at 1, the multipath effect impact assessment value is fixed at 1, the abnormal behavior dynamic analysis assessment value is x, and the activity monitoring model construction accuracy assessment value is y, the activity monitoring model construction accuracy assessment value increases as the abnormal behavior dynamic analysis assessment value increases.

[0095] Furthermore, the specific steps of constructing a basic model for monitoring social group activities are as follows: initializing the basic model for monitoring social group activities according to the data for constructing the model; setting parameters of the basic model for monitoring social group activities, wherein the parameters of the basic model for monitoring social group activities include a multi-path effect impact evaluation value, an abnormal behavior dynamic analysis evaluation value, and an activity monitoring model construction accuracy evaluation value; inputting the data for constructing the model for monitoring social group activities as training data into the basic model for monitoring social group activities for training, and continuously adjusting the parameters of the basic model for monitoring social group activities to obtain the social group activity monitoring model.

[0096] Furthermore, the specific steps for optimizing and adjusting the construction accuracy method of the activity monitoring model of the social group activity monitoring basic model are as follows: importing the first judgment value of the multi-path effect impact evaluation value, the second judgment value of the abnormal behavior dynamic analysis evaluation value and the third judgment value of the activity monitoring model construction accuracy evaluation value in the group activity monitoring database into the social group activity monitoring model, and outputting the social group activity monitoring model through the social group activity monitoring model output adjustment method, which includes optimizing the multi-path effect impact method, optimizing the abnormal behavior dynamic analysis method and optimizing the activity monitoring model construction accuracy method.

[0097] Furthermore, the specific steps of optimizing the multipath effect impact method are as follows: if the multipath effect impact evaluation value is less than or equal to the first judgment value of the multipath effect impact evaluation value, the multipath effect impact method is not optimized; if the multipath effect impact evaluation value is greater than the first judgment value of the multipath effect impact evaluation value, the collected signal is filtered by applying a filter, and the filtering parameters are automatically adjusted according to the real-time signal characteristics, and the filtering parameters include signal frequency and amplitude.

[0098] In this embodiment, a first judgment value of a multipath effect impact evaluation value is pre-set to 1, a multipath effect impact evaluation value is 1.5, and if the multipath effect impact evaluation value is greater than the first judgment value of the multipath effect impact evaluation value, optimization adjustment is performed; first, a suitable filter, such as a Kalman filter, is selected to filter the collected signal, and the characteristics of the real-time signal are analyzed, including changes in parameters such as signal frequency and amplitude. According to the real-time signal characteristics, the parameters of the filter are automatically adjusted to adapt to the changes in the signal and reduce the impact of the multipath effect. For example, in a cave environment, a handheld GPS locator is used to monitor social group activities. Due to the complex environment in the cave and the obvious multipath effect, the GPS signal is interfered with. An adaptive filter is applied to filter the GPS signal, and the real-time GPS signal is analyzed. It is found that the signal frequency fluctuates greatly and the amplitude is unstable, and the filter parameters are automatically adjusted: according to the changes in the signal frequency and amplitude, the parameters of the adaptive filter are automatically adjusted. For example, when the signal frequency increases, the bandwidth of the filter is increased; when the signal amplitude decreases, the gain of the filter is adjusted.

[0099] Furthermore, the specific steps for optimizing the abnormal behavior dynamic analysis method are as follows: if the abnormal behavior dynamic analysis evaluation value is greater than or equal to the second determination value of the abnormal behavior dynamic analysis evaluation value, then there is no need to optimize the abnormal behavior dynamic analysis method; if the abnormal behavior dynamic analysis evaluation value is less than the second determination value of the abnormal behavior dynamic analysis evaluation value, then selective transmission is formulated, and key data is transmitted first, and the key data includes location and abnormal behavior; with a distributed computing cluster, massive data is processed in shards and distributed to different computing nodes for parallel processing.

[0100] In this embodiment, a second judgment value of an abnormal behavior dynamic analysis evaluation value is pre-set to 0.7, and the abnormal behavior dynamic analysis evaluation value is 0.5. If the abnormal behavior dynamic analysis evaluation value is less than the second judgment value of the abnormal behavior dynamic analysis evaluation value, optimization adjustment is performed; for example, when the tour group members enter the cave, the monitoring system is used to perform real-time analysis of the tour group members' behavior. Due to the huge amount of data, the abnormal behavior dynamic analysis evaluation value is low and fails to reach the preset 0.7. First, a selective transmission strategy is formulated to identify key data, including location information and abnormal behavior identification, to ensure that these key data are given priority during the transmission process to reduce delays; with a distributed computing cluster, the massive data is sharded for distributed processing, and the data slices are allocated to different computing nodes. Each computing node processes its own data slice at the same time to improve processing efficiency.

[0101] Furthermore, the specific steps of the method for optimizing the construction accuracy of the activity monitoring model are as follows: if the construction accuracy evaluation value of the activity monitoring model is greater than or equal to the third judgment value of the construction accuracy evaluation value of the activity monitoring model, there is no need to optimize the construction accuracy method of the activity monitoring model; if the construction accuracy evaluation value of the activity monitoring model is less than the third judgment value of the construction accuracy evaluation value of the activity monitoring model, the passenger behavior system is monitored in real time by a camera to identify abnormal behavior, and the abnormal behavior information is converted into intuitive visual elements, the intuitive visual elements include color changes and flashing icons, and a light signal transmission device composed of LED lights is used to transmit visual warning information. Personnel in specific areas are equipped with handheld devices with photoelectric sensors, and the receiving devices decode the light signals and display visual warning information. Personnel locate abnormal passengers based on the warning information; establish an early warning confirmation mechanism to allow operators to confirm or reject the warning information to reduce false alarms, and establish a linkage mechanism between the early warning information and the emergency response system. Once an early warning is issued, the corresponding emergency response measures are immediately initiated.

[0102] In this embodiment, a third judgment value of the construction accuracy evaluation value of an activity monitoring model is pre-set to 1.3, the construction accuracy evaluation value of the activity monitoring model is 1, and the construction accuracy evaluation value of the activity monitoring model is less than the third judgment value of the construction accuracy evaluation value of the activity monitoring model, then optimization adjustment is performed; for example, in a large social group activity, the camera monitors the activity venue in real time, and the system identifies abnormal gathering behavior in a certain area. The area is displayed in red on the monitoring screen, and a flashing warning icon appears. The optical signal transmission device composed of LED lights transmits a red flashing light signal to the area. The security personnel in the area receive the light signal with a handheld device, which displays a red warning and specific location information. The security personnel quickly go to the designated location for verification. The security personnel confirms the abnormal behavior on site and confirms the warning through the handheld device. The system records the confirmation information and further analyzes the cause of the abnormality. After the warning is confirmed, the emergency response system is immediately activated, the nearby crowd is evacuated, and the relevant area is blocked. The security personnel and emergency teams are quickly in place to deal with the abnormal situation.

[0103] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0104] 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.

[0105] 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.

[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational 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 A step that specifies a function in one or more boxes.

[0107] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0108] Obviously, those skilled in the art may make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if such modifications and variations fall within the scope of the claims and their equivalents, the present invention is intended to include such modifications and variations.

Claims

1. A method for constructing a multi-dimensional social group activity monitoring model, characterized in that: The following steps are involved: Collect and process data for building social group activity monitoring models; Analyze the data of the social group activity monitoring model to obtain the multi-path effect impact assessment value and the abnormal behavior dynamic analysis assessment value; The construction accuracy evaluation value of the activity monitoring model is obtained through comprehensive analysis of the multi-path effect impact evaluation value and the abnormal behavior dynamic analysis evaluation value; Construct a basic model for monitoring social group activities, and optimize and adjust the accuracy of the activity monitoring model construction method based on the multi-path effect impact assessment value, abnormal behavior dynamic analysis assessment value, and activity monitoring model construction accuracy assessment value; The specific steps of comprehensively analyzing and obtaining the construction accuracy evaluation value of the activity monitoring model are: Obtaining a data update frequency threshold, a weight factor for an abnormal behavior dynamic analysis evaluation value, a weight factor for a data update frequency, and a weight factor for a multipath effect impact evaluation value from a group activity monitoring database; The abnormal behavior dynamic analysis evaluation values at different abnormal behavior dynamic analysis detection points are summed and averaged, and recorded as the first component of the construction accuracy of the activity monitoring model; The data update frequency at the construction accuracy detection point of the activity monitoring model and the data update frequency threshold are summed and averaged, and recorded as the second component of the construction accuracy of the activity monitoring model; The multipath effect impact assessment values at different multipath effect detection points are summed and averaged, and recorded as the third component of the construction accuracy of the activity monitoring model; The construction accuracy evaluation value of the activity monitoring model represents quantitative data on the degree of influence of the first component of the construction accuracy of the activity monitoring model, the second component of the construction accuracy of the activity monitoring model, and the third component of the construction accuracy of the activity monitoring model on the overall construction accuracy of the activity monitoring model in multiple dimensions.

2. The method for constructing a multi-dimensional social group activity monitoring model according to claim 1, characterized in that: The specific steps of collecting and processing data for building a social group activity monitoring model are as follows: The original data of social group activity monitoring model is constructed by receiving GPS satellite signals through handheld GPS locators; The original data for constructing the social group activity monitoring model is cleaned and denoised to obtain data for constructing the social group activity monitoring model. The data for constructing the social group activity monitoring model includes multi-path effect impact data and abnormal behavior dynamic analysis data.

3. The method for constructing a multi-dimensional social group activity monitoring model according to claim 2, characterized in that: The specific steps of obtaining the multipath effect impact assessment value are as follows: The multipath effect impact data includes the number of reflected signals, time delay, reflected signal power, direct signal power and the phase difference between the reflected signal and the direct signal; Obtaining from the group activity monitoring database a threshold value for the number of reflected signals, a threshold value for the time difference between the reflected signal and the direct signal arriving at the receiver, a standard phase difference between the reflected signal and the direct signal, a weighting factor for the number of reflected signals, a weighting factor for the time delay, a weighting factor for the strength of the reflected signal, and a weighting factor for the phase difference between the reflected signal and the direct signal; The ratio of the number of reflected signals to the threshold value of the number of reflected signals is summed and averaged in different multipath effect detection sections and recorded as the first component of the multipath effect; The ratio of the time delay of the detection point affected by the multipath effect to the time difference threshold between the reflected signal and the direct signal arriving at the receiver is recorded as the second component of the multipath effect; The ratio of the reflected signal power at the multipath effect detection point to the direct signal power at the multipath effect detection point is recorded as the third component of the multipath effect; The ratio of the absolute value of the difference between the phase difference between the reflected signal and the direct signal at the multipath effect detection point and the standard phase difference between the reflected signal and the direct signal to the standard phase difference between the reflected signal and the direct signal is recorded as the fourth component of the multipath effect; The multipath effect impact evaluation value represents quantitative data of the degree of influence of the multipath effect first component, the multipath effect second component, the multipath effect third component and the multipath effect fourth component on the reflected signal during the propagation process.

4. The method for constructing a multi-dimensional social group activity monitoring model according to claim 2, characterized in that: The specific steps of obtaining the abnormal behavior dynamic analysis evaluation value are: The abnormal behavior dynamic analysis data includes the phase difference, time delay, threshold value after adjustment, threshold value before adjustment and time difference between the reflected signal and the direct signal; Obtaining from the group activity monitoring database the standard phase difference between the reflected signal and the direct signal, the time difference threshold between the reflected signal and the direct signal arriving at the receiver, the weight factor of the dynamic threshold adaptability coefficient, the weight factor of the phase difference between the reflected signal and the direct signal, and the weight factor of the time delay; Calculate the ratio of the absolute value of the difference between the adjusted threshold value in the dynamic threshold adaptive time window detection section and the threshold value before adjustment in the dynamic threshold adaptive time window detection section to obtain the dynamic threshold adaptability coefficient; The dynamic threshold adaptability coefficient is summed and averaged in different dynamic threshold adaptability time window detection segments, and recorded as the first component of abnormal behavior dynamic analysis; The ratio of the absolute value of the difference between the phase difference between the reflected signal and the direct signal at the abnormal behavior dynamic analysis detection point minus the standard phase difference between the reflected signal and the direct signal to the standard phase difference between the reflected signal and the direct signal is recorded as the second component of the abnormal behavior dynamic analysis; The ratio of the time delay at the abnormal behavior dynamic analysis detection point to the time difference threshold between the reflected signal and the direct signal arriving at the receiver is recorded as the third component of the abnormal behavior dynamic analysis; The abnormal behavior dynamic analysis evaluation value represents quantitative data of the dynamic analysis capability of the abnormal behavior dynamic analysis first component, the abnormal behavior dynamic analysis second component, and the abnormal behavior dynamic analysis third component on abnormal behavior characteristics.

5. The method for constructing a multi-dimensional social group activity monitoring model according to claim 1, characterized in that: The specific steps of constructing the basic model for monitoring social group activities are as follows: Construct data based on the social group activity monitoring model and initialize the basic model for social group activity monitoring; Setting parameters of a basic model for monitoring social group activities, wherein the basic model parameters include a multipath effect impact assessment value, an abnormal behavior dynamic analysis assessment value, and an activity monitoring model construction accuracy assessment value; The social group activity monitoring model construction data is input as training data into the social group activity monitoring basic model for training, and the parameters of the social group activity monitoring basic model are continuously adjusted to obtain the social group activity monitoring model.

6. The method for constructing a multi-dimensional social group activity monitoring model according to claim 1, characterized in that: The specific steps of optimizing and adjusting the accuracy of the construction method of the social group activity monitoring basic model are as follows: The first judgment value of the multi-path effect impact evaluation value, the second judgment value of the abnormal behavior dynamic analysis evaluation value and the third judgment value of the activity monitoring model construction accuracy evaluation value in the group activity monitoring database are imported into the social group activity monitoring model, and the social group activity monitoring model output adjustment method is used. The social group activity monitoring model output adjustment method includes optimizing the multi-path effect impact method, optimizing the abnormal behavior dynamic analysis method and optimizing the activity monitoring model construction accuracy method.

7. The method for constructing a multi-dimensional social group activity monitoring model according to claim 6, characterized in that: The specific steps of the method for optimizing the multipath effect are as follows: If the multipath effect impact assessment value is less than or equal to the first multipath effect impact assessment value, the multipath effect impact method is not optimized; If the multipath effect impact assessment value is greater than the first multipath effect impact assessment value, the collected signal is filtered by applying a filter, and the filtering parameters are automatically adjusted according to the real-time signal characteristics. The filtering parameters include signal frequency and amplitude.

8. The method for constructing a multi-dimensional social group activity monitoring model according to claim 6, characterized in that: The specific steps of the method for optimizing the dynamic analysis of abnormal behavior are as follows: If the abnormal behavior dynamic analysis evaluation value is greater than or equal to the abnormal behavior dynamic analysis evaluation value second determination value, then there is no need to optimize the abnormal behavior dynamic analysis method; If the abnormal behavior dynamic analysis evaluation value is less than the second abnormal behavior dynamic analysis evaluation value, selective transmission is formulated, and key data is transmitted first, wherein the key data includes location and abnormal behavior; Combined with a distributed computing cluster, massive data can be divided into shards and distributed to different computing nodes for parallel processing.

9. The method for constructing a multi-dimensional social group activity monitoring model according to claim 6, characterized in that: The specific steps of the method for optimizing the accuracy of building an activity monitoring model are: If the construction accuracy evaluation value of the activity monitoring model is greater than or equal to the third determination value of the construction accuracy evaluation value of the activity monitoring model, then there is no need to optimize the construction accuracy method of the activity monitoring model; If the construction accuracy assessment value of the activity monitoring model is less than the third determination value of the construction accuracy assessment value of the activity monitoring model, the system will monitor the passenger behavior in real time through cameras to identify abnormal behavior and convert the abnormal behavior information into intuitive visual elements. The intuitive visual elements include color changes and flashing icons. A light signal transmission device composed of LED lights will be used to transmit visual warning information. Personnel in specific areas will be equipped with handheld devices with photoelectric sensors. The receiving devices will decode the light signals and display visual warning information. Personnel will then locate abnormal passengers based on the warning information. Establish an early warning confirmation mechanism to allow operators to confirm or reject early warning information to reduce false alarms, and establish a linkage mechanism between early warning information and emergency response systems. Once an early warning is issued, immediately initiate corresponding emergency response measures.

Images