Visitor travel path management system based on Internet of Things

Abstract

The invention discloses a visitor travel path management system based on Internet of Things, which belongs to the technical field of travel path management and comprises a regional travel path verification module, a target visitor verification module, a travel path planning module, an abnormity judgment module and an edge sensing equipment adjustment module. Through cooperative work of the regional travel path verification module, the target visitor verification module, the travel path planning module and the abnormity judgment module, behaviors of visitors are monitored and analyzed in real time, and then real-time travel path detection of target visitors is achieved. The problem that the real-time performance is poor in the travel path management monitoring process of the target visitor in the prior art is effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of behavior management, and in particular to a visitor behavior management system based on the Internet of Things. Background Art

[0002] With the acceleration of urbanization and the development of smart grid technology, the needs and purposes of visitors are becoming increasingly diversified. The different needs and purposes of various visitors make effective resource allocation more difficult. Therefore, the management of visitor behavior faces huge challenges. Visitors refer to individuals who visit specific places.

[0003] The existing behavior management system obtains the visit purpose of the visitor to determine the destination of the visit and then pushes it using a preset map, but it cannot analyze the real-time traffic conditions, and there is a problem of poor real-time behavior management of target visitors.

[0004] For example, the invention patent announcement with announcement number: CN116433196B discloses a library data management method and system, including: obtaining the purpose of a visitor entering the library; generating a visit guide map based on the purpose of the visit, a preset online database corresponding to the library, and a preset map within the library; and pushing the visit guide map to the visitor.

[0005] For example, the digital integrated management method for funeral services announced in the invention patent with announcement number: CN118171796B includes: determining the relevant route through the determined initial point and the end point, and then combining the relevant routes of other mourners to identify whether there is any intersection or congestion, and based on the identified relevant situations, the final moment when the route reaches the end point, that is, the relevant evaluation value, and then based on the relevant evaluation value, the best route can be selected, and the corresponding mourners can choose the best route based on the selected route.

[0006] However, in the process of implementing the technical solution 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: In the prior art, the behavior monitoring and management of visitors is a crucial link. However, the prior art usually performs complex and cumbersome visit registration outside the visit area, and cannot make real-time path adjustments according to the real-time situation of the visitor, resulting in a poor visit experience for the visitor. There is a problem of poor real-time performance in the process of behavior management and monitoring of target visitors. Summary of the invention

[0007] The embodiment of the present application solves the problem of poor real-time performance in the process of behavior management and monitoring of target visitors in the prior art by providing a visitor behavior management system based on the Internet of Things, and realizes real-time behavior detection of target visitors.

[0008] The embodiment of the present application provides a visitor behavior management system based on the Internet of Things, including: a regional behavior verification module, a target visitor verification module, a behavior planning module, and an abnormality judgment module; the regional behavior verification module is used to set a verification collection period, and collect behavior data of regional visitors during the verification collection period, thereby integrating regional behavior verification data; the target visitor verification module is used to sense the target visitor's request access signal and verify the target visitor's information. If the information authentication is successful, access is allowed, and the target visit location and access business type of the target visitor are collected. If the information verification fails, the information of the target visitor is uploaded to the data management center for secondary authentication; the behavior planning module is used to plan a path according to the target visit location of the target visitor, and recommend a real-time route guidance through the mobile receiving port of the target visitor; the abnormality judgment module is used to obtain the behavior data of the target visitor in real time, and simultaneously analyze it according to the regional behavior verification data, judge the abnormal behavior evaluation result of the target visitor, and perform corresponding management and control based on the abnormal behavior evaluation result.

[0009] Furthermore, the step of obtaining the regional behavior verification data includes: collecting behavior data of regional visitors within the verification and collection period, wherein the behavior data include the total stay time in the region, movement speed, walking step frequency, total movement trajectory route length and pause frequency of each visitor corresponding to each visit business type, and obtaining the regional behavior verification data through mean processing, wherein the regional behavior verification data includes the behavior reference data of the visitors corresponding to each visit business type, specifically including: regional control stay time, control movement speed, control walking step frequency, control total movement trajectory route length and control pause frequency.

[0010] Furthermore, the path planning is performed according to the target visit location of the target visitor, and the specific process is as follows: according to the target visit location of the target visitor, several reachable paths between the target visit location of the target visitor and the current location of the target visitor are extracted, and marked as each guidance path to be planned; the current moment is taken as the starting time point, and the expected traffic time period is obtained by dividing it with a preset time length, thereby counting the historical impact data corresponding to each guidance path to be planned within the expected traffic time period, and obtaining the length of each guidance path to be planned and the sensitive average distribution interval distance, thereby processing to obtain the traffic adaptation value of each guidance path to be planned; based on the traffic adaptation value of each guidance path to be planned, the guidance path to be planned corresponding to the maximum traffic adaptation value is selected as the recommended path for the target visitor; the historical impact data includes: historical pedestrian density and historical vehicle flow rate.

[0011] Furthermore, the specific method for obtaining the traffic adaptation value of each guidance path to be planned is as follows: ; represents the traffic adaptation value of the i-th guidance path to be planned, i represents the number of the guidance path to be planned, , I represents the total number of guidance paths to be planned, e represents a natural constant, represents the historical passenger flow density corresponding to the i-th guided path to be planned during the expected travel period, represents the historical traffic flow rate corresponding to the i-th guidance path to be planned during the expected travel period, represents the length of the i-th guidance path to be planned, It represents the average distribution distance between the i-th guidance path to be planned and the sensitive area. represents the weight of historical traffic flow, Indicates the influence weight of the length of the guidance path to be planned, Indicates that the weight of the interval distance is sensitively evenly distributed.

[0012] Furthermore, the target visitor's behavior data is acquired in real time, and is simultaneously analyzed according to the regional behavior verification data. The specific method is: the target visitor's behavior data is acquired in real time, and the target visitor's behavior data includes: the target visitor's regional stay time, movement speed, walking frequency, total movement trajectory route length and pause frequency; the regional behavior verification data is screened based on the target visitor's visit business type to obtain the behavior reference data corresponding to the target visitor's visit business type, and use it as the target visitor's behavior reference data; the target visitor's behavior data acquired in real time and the target visitor's behavior reference data are comprehensively analyzed to obtain the target visitor's behavior abnormality score; the target visitor's behavior abnormality score is used to characterize the degree of abnormal behavior of the target visitor.

[0013] Furthermore, the specific method for determining the target visitor's behavior abnormality assessment result is: obtaining a behavior abnormality threshold preset in a database, and comparing it with the target visitor's behavior abnormality score; if the target visitor's behavior abnormality score is above the behavior abnormality threshold, then the target visitor's behavior abnormality assessment result is abnormal behavior; if the target visitor's behavior abnormality score is less than the behavior abnormality threshold, then the target visitor's behavior abnormality assessment result is normal behavior.

[0014] Furthermore, the corresponding control is carried out based on the behavior abnormality assessment result. The specific method is: if the behavior abnormality assessment result of the target visitor is normal, no corresponding control will be carried out; if the behavior abnormality assessment result of the target visitor is abnormal, the monitoring device around the target visitor will be called up for high-performance mode monitoring, and the detailed behavior data of the target visitor will be uploaded to the data management center for supervision.

[0015] Furthermore, it also includes an edge sensor device adjustment module, which is used to set a sensor adjustment period and obtain comprehensive visit data in the area during the sensor adjustment period, thereby analyzing the comprehensive visit characteristic value in the area, and adjusting and managing the edge sensor devices in the area based on the comprehensive visit characteristic value, specifically including: obtaining the comprehensive visit data in the area during the sensor adjustment period, the comprehensive visit data including: the total number of target visitors, the average stay time of target visitors, the current pedestrian density in each traffic path, and the current vehicle density in each traffic path; obtaining the dynamic control reference parameters preset in the database, and comparing them with the comprehensive visit data to obtain the comprehensive visit characteristic value in the area, and adjusting and managing the edge sensor devices in the area based on the comprehensive visit characteristic value; the comprehensive visit characteristic value in the area is used to characterize the overall visit situation of the area during the sensor adjustment period and monitor the pressure load.

[0016] Furthermore, the edge sensing device in the area is adjusted and managed based on the comprehensive visiting characteristic value, and the specific steps include: obtaining the comprehensive visiting characteristic threshold in the area, and comparing it with the comprehensive visiting characteristic value in the area; if the comprehensive visiting characteristic value in the area is greater than the comprehensive visiting characteristic threshold in the area, the edge sensing device is adjusted; if the comprehensive visiting characteristic value in the area is below the comprehensive visiting characteristic threshold in the area, the edge sensing device is not adjusted.

[0017] Furthermore, the edge sensor device adjustment comprises the following specific steps: if the comprehensive visit characteristic value in the area is greater than the comprehensive visit characteristic threshold in the area, then obtaining the difference between the comprehensive visit characteristic value in the area and the comprehensive visit characteristic threshold in the area, and recording it as the edge sensor adjustment index of the area; statistically analyzing the performance of each edge sub-sensor device in the area, and obtaining the operating performance value of each edge sub-sensor device in the area; based on the operating adjustment execution parameters of the edge sub-sensor devices preset in the database corresponding to different operating performance value ranges under each edge sensor adjustment index interval, and according to the edge sensor adjustment index of the area and the operating performance value of each edge sub-sensor device in the area, mapping and extracting the operating adjustment execution parameters of each edge sub-sensor device in the area; and adjusting the corresponding edge sub-sensor devices based on the execution network adjustment parameters.

[0018] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. The present invention provides a visitor behavior management system based on the Internet of Things, which monitors and analyzes the visitor behavior in real time through the collaborative work of the regional behavior verification module, the target visitor verification module, the behavior planning module and the abnormal judgment module, thereby realizing real-time behavior detection of the target visitor, and effectively solving the problem of poor real-time performance in the process of behavior management and monitoring of the target visitor in the prior art.

[0019] 2. The present invention verifies information and plans the target visit location and visit business type of the target visitor, thereby realizing real-time recommendation and guidance of the access path, thereby improving the visit efficiency of the visitor and solving the problem of inaccurate path planning in complex environments in the prior art.

[0020] 3. By acquiring and analyzing the behavior data of target visitors in real time, timely assessment and control of abnormal behavior can be achieved, thereby ensuring the safety and management effectiveness in the area. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A schematic diagram of the structure of a visitor behavior management system based on the Internet of Things provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The embodiment of the present application provides a visitor behavior management system based on the Internet of Things, which solves the problem of poor real-time performance in the process of behavior management and monitoring of target visitors in the prior art. It includes a regional behavior verification module, a target visitor verification module, a behavior planning module, and an abnormality judgment module; the regional behavior verification module is used to set a verification collection cycle, and collect behavior data of regional visitors within the verification collection cycle, thereby integrating regional behavior verification data; the target visitor verification module is used to sense the target visitor's request access signal and verify the target visitor's information. If the information authentication is successful, the target visitor is allowed to enter the visitor's area. The target visitor's target location and visit business type are collected. If the information verification fails, the target visitor's information is uploaded to the data management center for secondary authentication; the behavior planning module is used to plan the path according to the target visit location of the target visitor, and to recommend real-time route guidance through the mobile receiving port of the target visitor; the abnormality judgment module is used to obtain the behavior data of the target visitor in real time, and simultaneously analyze it according to the regional behavior verification data, judge the abnormal behavior evaluation result of the target visitor, and perform corresponding management and control based on the abnormal behavior evaluation result, thereby realizing real-time behavior detection of the target visitor.

[0023] The technical solution in the embodiment of the present application is to solve the problem of poor real-time performance in the process of behavior management and monitoring of target visitors. The overall idea is as follows: through the regional behavior verification module, the target visitor verification module, the behavior planning module, and the abnormal judgment module; the regional behavior verification module is used to set the verification collection cycle, and collect the behavior data of the regional visitors during the verification collection cycle, thereby integrating the regional behavior verification data; the target visitor verification module is used to sense the target visitor's request access signal and verify the target visitor's information. If the information authentication is successful, access is allowed, and the target visitor's information is collected. The target visit location and visit business type of the target visitor are determined by the information verification. If the information verification fails, the information of the target visitor is uploaded to the data management center for secondary authentication; the behavior planning module is used to plan the path according to the target visit location of the target visitor, and to provide real-time recommended route guidance through the mobile receiving port of the target visitor; the abnormality judgment module is used to obtain the behavior data of the target visitor in real time, and simultaneously analyze it according to the regional behavior verification data, judge the abnormal behavior evaluation result of the target visitor, and perform corresponding management and control based on the abnormal behavior evaluation result, so as to achieve real-time behavior detection of the target visitor.

[0024] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0025] like Figure 1 As shown, it is a structural schematic diagram of a visitor behavior management system based on the Internet of Things provided by an embodiment of the present application. The visitor behavior management system based on the Internet of Things provided by an embodiment of the present application includes: a regional behavior verification module, a target visitor verification module, a behavior planning module, and an abnormality judgment module; the regional behavior verification module is used to set a verification collection cycle, and collect behavior data of regional visitors within the verification collection cycle, thereby integrating to obtain regional behavior verification data; the target visitor verification module is used to sense the target visitor's request access signal and verify the target visitor's information. If the signal is received, the target visitor verification module is used to verify the target visitor's information. If the information authentication is successful, access is allowed, and the target visit location and visit business type of the target visitor are collected. If the information verification fails, the information of the target visitor is uploaded to the data management center for secondary authentication; the behavior planning module is used to plan the path according to the target visit location of the target visitor, and to provide real-time recommended route guidance through the mobile receiving port of the target visitor; the anomaly judgment module is used to obtain the behavior data of the target visitor in real time, and simultaneously analyze it according to the regional behavior verification data, judge the behavior anomaly assessment results of the target visitor, and perform corresponding management and control based on the behavior anomaly assessment results.

[0026] In this embodiment, it should be noted that the specific steps of verifying the information of the target visitor include: sensing the target visitor's request access signal, recording the visit information, and the visit information includes the visitor's identity information (such as name, ID number, etc.), visit time and target visit location, etc. The types of visit services include: business visits (for example: customer talks), technical support (technicians visit to provide equipment maintenance and other services), supply chain management (suppliers visit to carry out material distribution, equipment transportation and other services), etc.

[0027] It should also be noted that if the information verification fails, the information of the target visitor will be uploaded to the data management center for secondary authentication. The specific steps include: uploading the identity information of the visitor who failed the verification (such as name, ID number, access signal, etc.) to the data management center. The access signal contains the reason for the verification failure, such as incomplete information, unable to match, etc. After receiving the uploaded identity information, the data management center automatically performs a secondary comparison. The secondary comparison method uses more detailed data matching, such as combining multiple databases (such as internal corporate databases, historical visitor databases) for more comprehensive identity confirmation. The data management center provides feedback based on the secondary comparison results. If the identity information passes the review, an authorized access signal is sent to the target visitor to allow access. If it still fails to pass the secondary authentication, access is denied and the visit record is stored in the abnormal access log.

[0028] Furthermore, regional behavior verification data is obtained, and the steps include: collecting behavior data of regional visitors within the verification and collection period, wherein the behavior data include the total stay time in the region, movement speed, walking step frequency, total movement trajectory route length and pause frequency of each visitor corresponding to each visit business type, and obtaining the regional behavior verification data through mean processing, the regional behavior verification data includes the behavior reference data of the visitors corresponding to each visit business type, specifically including: regional control stay time, control movement speed, control walking step frequency, control total movement trajectory route length and control pause frequency.

[0029] In this embodiment, it should be noted that the real-time recommended route guidance is provided through the mobile receiving port of the target visitor, specifically including: after the target visitor passes the identity authentication, the target visitor self-scans the QR code to bind the target visitor's mobile device (such as a smart phone, smart wearable device, etc.), and these devices acquire data in real time through the Bluetooth, Wi-Fi or GPS module in the Internet of Things. The target visitor's visit location and business type are obtained from the verification information of the target visitor. The visit location can be a specific room or floor, and the business type will affect the priority and method of the recommended path (such as providing the fastest path for emergency business).

[0030] Furthermore, the path planning is carried out according to the target visit location of the target visitor. The specific process is as follows: according to the target visit location of the target visitor, several reachable paths between the target visit location of the target visitor and the current location of the target visitor are extracted, and marked as each guidance path to be planned; the current moment is taken as the starting time point, and the expected traffic time period is obtained by dividing it with a preset time length, thereby counting the historical impact data corresponding to each guidance path to be planned within the expected traffic time period, and obtaining the length of each guidance path to be planned and the sensitive average distribution interval distance, thereby processing to obtain the traffic adaptation value of each guidance path to be planned; based on the traffic adaptation value of each guidance path to be planned, the guidance path to be planned corresponding to the maximum traffic adaptation value is selected as the recommended path for the target visitor; the historical impact data include: historical pedestrian density and historical vehicle flow rate.

[0031] In this embodiment, by extracting the accessible paths between the target visit location and the current location, and combining the historical pedestrian density and vehicle flow rate data during the expected travel period, the traffic adaptation value of the path is dynamically evaluated, so as to select the path with the highest traffic efficiency for recommendation. This process comprehensively considers factors such as path length and sensitive land distribution, and can effectively avoid congested areas, ensure smooth travel for visitors, and improve travel efficiency and safety.

[0032] Furthermore, the traffic adaptation value of each guidance path to be planned is obtained, and the specific method is as follows: ; represents the traffic adaptation value of the i-th guidance path to be planned, i represents the number of the guidance path to be planned, , I represents the total number of guidance paths to be planned, e represents a natural constant, represents the historical passenger flow density corresponding to the i-th guided path to be planned during the expected travel period, represents the historical traffic flow rate corresponding to the i-th guidance path to be planned during the expected travel period, represents the length of the i-th guidance path to be planned, It represents the average distribution distance between the i-th guidance path to be planned and the sensitive area. represents the weight of historical traffic flow, Indicates the influence weight of the length of the guidance path to be planned, Indicates that the weight of the interval distance is sensitively evenly distributed.

[0033] In this embodiment, the historical pedestrian density and the historical vehicle flow rate can be obtained through a database, and the length of each guidance path to be planned and the average distribution interval distance of the sensitive land can be obtained by obtaining the position of the sensor of each guidance path to be planned and measuring according to the position relationship, wherein the average distribution interval distance of the sensitive land can be obtained by obtaining the sensitive distribution interval distance and then calculating the average value, and the sensitive distribution interval distance refers to the vertical distance between the center point of the sensitive land and each guidance path to be planned.

[0034] Furthermore, the behavior data of the target visitor is obtained in real time, and is simultaneously analyzed based on the regional behavior verification data. The specific method is: the behavior data of the target visitor is obtained in real time, and the behavior data of the target visitor includes: the target visitor's regional stay time, movement speed, walking frequency, total movement trajectory route length and pause frequency; the regional behavior verification data is screened based on the target visitor's visit business type to obtain the behavior reference data corresponding to the target visitor's visit business type, and used as the target visitor's behavior reference data; the target visitor's behavior data obtained in real time and the target visitor's behavior reference data are comprehensively analyzed to obtain the target visitor's behavior abnormality score; the target visitor's behavior abnormality score is used to characterize the degree of abnormal behavior of the target visitor.

[0035] In this embodiment, the behavior data of the target visitor is acquired in real time and comprehensively analyzed, which can effectively monitor and evaluate the behavior patterns of the visitors. By analyzing key data such as the length of stay in the area, movement speed, walking frequency, total movement trajectory length and pause frequency, and combining regional behavior verification data, potential behavioral anomalies can be accurately identified. The real-time response capability to the behavior of visitors is improved. At the same time, the behavior reference data is screened based on the type of access business, which ensures the pertinence and effectiveness of the analysis and enhances the reliability of data analysis. Finally, by calculating the behavior anomaly score, managers can identify and deal with potential problems in a timely manner, thereby improving the level of regional security management and the experience of visitors, and optimizing overall operational efficiency.

[0036] It should be noted that the reference data of the target visitor's behavior include: reference area stay time, reference moving speed, reference walking step frequency, reference total moving trajectory route length and reference pause frequency.

[0037] Get the abnormal behavior score of the target visitor. The specific method is as follows: ; In the formula, Indicates the abnormal behavior score of the target visitor. Indicates the target visitor's stay time in the area. Indicates the length of stay in the reference area, Indicates the moving speed of the target visitor. represents the reference moving speed, Indicates the walking frequency of the target visitor. Indicates the reference walking frequency, Indicates the total moving trajectory length of the target visitor. Indicates the length of the reference total moving trajectory route, Indicates the pause frequency of the target visitor, Indicates the reference pause frequency, Indicates the influence weight of the length of stay in the area. Indicates that the moving speed affects the weight, Indicates the weight of walking frequency. Indicates the total moving trajectory route length influence weight, Indicates that the pause frequency affects the weight.

[0038] It should be noted that the target visitor's stay time in the area refers to the target visitor's cumulative stay time from the time he or she enters the area. The time is updated in real time by obtaining real-time target visitor behavior data and reverse real-time analysis. The longer the target visitor's stay time in the area, the more abnormal his or her behavior is.

[0039] The moving speed of the target visitor refers to the average moving speed of the target visitor when entering the area. The walking frequency of the target visitor refers to the average walking frequency of the target visitor when entering the area. The total moving trajectory route length of the target visitor refers to the real-time moving trajectory route length of the target visitor, that is, the real-time moving trajectory route length of the target visitor when entering the area. The pause frequency of the target visitor refers to the pause frequency of the target visitor from entering the area to the real-time update time, which needs to be monitored in real time.

[0040] The target visitor's behavior data can be obtained through sensors to obtain the target visitor's walking trajectory and corresponding time nodes, and obtained through background statistics.

[0041] The influence weight of the length of stay in the area indicates the numerical value of the influence of the length of stay in the area on the abnormal behavior score of the target visitor. When used, the influence weight corresponding to the length of stay in the area can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the length of stay in the area and the influence weight of the length of stay in the area form a mapping set. The real-time length of stay in the area is input into the mapping set to obtain the influence weight corresponding to the length of stay in the area. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. The moving speed influence weight indicates the numerical value of the influence of the moving speed on the abnormal behavior score of the target visitor. When used, the influence weight corresponding to the moving speed can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the moving speed and the moving speed influence weight form a mapping set. The real-time moving speed is input into the mapping set to obtain the influence weight corresponding to the moving speed. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. The walking cadence influence weight represents the numerical value of the degree of influence of the walking cadence on the abnormal behavior score of the target visitor. When used, the influence weight corresponding to the walking cadence can be directly obtained from the database, and the corresponding relationship can be a pre-set mapping relationship. For example, the walking cadence and the walking cadence influence weight form a mapping set, and the real-time walking cadence is input into the mapping set to obtain the influence weight corresponding to the walking cadence. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. The total moving trajectory route length influence weight represents the numerical value of the degree of influence of the total moving trajectory route length on the abnormal behavior score of the target visitor. When used, the influence weight corresponding to the total moving trajectory route length can be directly obtained from the database, and the corresponding relationship can be a pre-set mapping relationship. For example, the total moving trajectory route length and the total moving trajectory route length influence weight form a mapping set, and the real-time total moving trajectory route length is input into the mapping set to obtain the influence weight corresponding to the total moving trajectory route length. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. The pause frequency impact weight represents the numerical value of the impact degree of the pause frequency on the abnormal behavior score of the target visitor. When used, the impact weight corresponding to the pause frequency can be directly obtained from the database, and the corresponding relationship can be a pre-set mapping relationship. For example, the pause frequency and the pause frequency impact weight form a mapping set, and the real-time pause frequency is input into the mapping set to obtain the impact weight corresponding to the pause frequency. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship.

[0042] The behavior abnormality score of the target visitor obtained by analyzing the behavior data of the target visitor takes into account the mutual influence between these parameters. For example, the increase in movement speed and walking frequency usually reflects the normal behavior of the person. The two are positively correlated. The faster the speed and the higher the frequency, the lower the behavior abnormality score. The length of stay and the frequency of pauses are positively correlated with the abnormality score, which means that long stay time and frequent pauses will increase the abnormality score. At the same time, they are negatively correlated with the movement speed and walking frequency. The higher the speed or frequency, the lower the length of stay and the frequency of pauses. The longer the total movement trajectory route length, the more abnormal the behavior of the target visitor. At this time, the target visitor stays longer and may have a higher frequency of pauses.

[0043] The recommended route is displayed to the target visitor through the target visitor's mobile receiving port, and after the target visitor confirms, real-time recommended route guidance is provided, and the real-time location of the target visitor is obtained. If the real-time location of the target visitor deviates from the recommended guidance route, a voice prompt is given.

[0044] Furthermore, the abnormal behavior assessment result of the target visitor is judged. The specific method is: obtain the abnormal behavior threshold preset in the database, and compare it with the abnormal behavior score of the target visitor. If the abnormal behavior score of the target visitor is above the abnormal behavior threshold, the abnormal behavior assessment result of the target visitor is abnormal behavior; if the abnormal behavior score of the target visitor is less than the abnormal behavior threshold, the abnormal behavior assessment result of the target visitor is normal behavior.

[0045] Furthermore, corresponding control is carried out based on the abnormal behavior assessment result. The specific method is: if the abnormal behavior assessment result of the target visitor is normal, no corresponding control will be carried out; if the abnormal behavior assessment result of the target visitor is abnormal, the monitoring device around the target visitor will be called up for high-performance mode monitoring, and the detailed behavior data of the target visitor will be uploaded to the data management center for supervision.

[0046] In this embodiment, performing high-performance mode monitoring refers to increasing the resolution, clarity, and smoothness of monitoring, as well as the maximum monitoring intensity and frequency.

[0047] Furthermore, it also includes an edge sensor device adjustment module, which is used to set a sensor adjustment period and obtain comprehensive visit data in the area during the sensor adjustment period, thereby analyzing the comprehensive visit characteristic value in the area, and adjusting and managing the edge sensor devices in the area based on the comprehensive visit characteristic value, specifically including: obtaining the comprehensive visit data in the area during the sensor adjustment period, the comprehensive visit data including: the total number of target visitors, the average stay time of target visitors, the current pedestrian density in each traffic path, and the current vehicle density in each traffic path; obtaining the dynamic control reference parameters preset in the database, and comparing them with the comprehensive visit data to obtain the comprehensive visit characteristic value in the area, and adjusting and managing the edge sensor devices in the area based on the comprehensive visit characteristic value; the comprehensive visit characteristic value in the area is used to characterize the overall visit situation of the area during the sensor adjustment period and monitor the pressure load.

[0048] In this embodiment, the comprehensive visitor data includes: the total number of target visitors, the average stay time of the target visitors, the current density of people flow in each passage, and the current density of vehicles flow in each passage. The total number of target visitors can be obtained from the reservation information of the target visitors, the average stay time of the target visitors can be obtained by the background manager to obtain the average value of the stay time of each visitor, and the current density of people flow in each passage and the current density of vehicles flow in each passage can be obtained by obtaining the real-time flow of people and real-time flow of vehicles in each passage through sensors and analyzing with the corresponding area of ​​each passage.

[0049] It should be noted that the preset dynamic control reference parameters include: reference total number of visitors, reference visitor stay time, reference pedestrian density and reference vehicle density.

[0050] The comprehensive visit feature value in the area is obtained by: ; In the formula, represents the comprehensive visit feature value in the area, represents a natural constant, Indicates the total number of target visitors. Indicates the total number of reference visitors. Indicates the average stay time of target visitors, Indicates the reference personnel's stay time, represents the current flow density in the jth passage, j represents the number of the passage, , J represents the total number of paths, represents the reference crowd density, represents the current traffic density in the jth traffic path, represents the reference traffic density, Indicates the total number of visitors affecting the weight, Indicates the influence weight of personnel stay time, Indicates the total traffic density impact weight.

[0051] The total number of visitors’ influence weight represents the numerical value of the influence degree of the total number of target visitors on the comprehensive visit characteristic value in the area. When used, the influence weight corresponding to the total number of target visitors can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the total number of target visitors and the total number of visitors’ influence weight form a mapping set. The real-time total number of target visitors is input into the mapping set to obtain the influence weight corresponding to the total number of target visitors. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. The staff stay time influence weight represents the numerical value of the influence degree of the average stay time of the target visitors on the comprehensive visit characteristic value in the area. When used, the influence weight corresponding to the average stay time of the target visitors can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the average stay time of the target visitors and the staff stay time influence weight form a mapping set. The real-time average stay time of the target visitors is input into the mapping set to obtain the influence weight corresponding to the average stay time of the target visitors. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. The total flow density impact weight represents the numerical value of the impact degree of the total flow density on the comprehensive visit characteristic value in the area. When used, the impact weight corresponding to the total flow density can be directly obtained from the database. The corresponding relationship can be a pre-set mapping relationship. For example, the total flow density and the total flow density impact weight form a mapping set. The real-time total flow density is input into the mapping set to obtain the impact weight corresponding to the total flow density. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. The total flow density includes the current pedestrian flow density in each passage path and the current vehicle flow density in the passage path.

[0052] By obtaining the preset dynamic control reference parameters in the database and comparing them with the comprehensive visit data, the comprehensive visit characteristic value in the area is obtained. This takes into account the mutual influence between these parameters. For example, when the total number of visitors increases, it will drive the flow frequency of people and vehicles in the area, thereby increasing the changes in the density of people and vehicles. The length of time people stay in a specific area will affect the distribution of people density. For example, during peak hours, if people stay for a long time, the density of people will increase, while a short stay may cause a rapid flow of people, thus affecting the overall rhythm of visits. Changes in the length of time people stay will also be fed back to the adjustment of vehicle density, and parking demand will increase or decrease.

[0053] Furthermore, the edge sensor devices in the area are adjusted and managed based on the comprehensive visit feature value. The specific steps include: obtaining the comprehensive visit feature threshold in the area, and comparing it with the comprehensive visit feature value in the area; if the comprehensive visit feature value in the area is greater than the comprehensive visit feature threshold in the area, the edge sensor device is adjusted; if the comprehensive visit feature value in the area is below the comprehensive visit feature threshold in the area, the edge sensor device is not adjusted.

[0054] In this embodiment, it should be noted that the performance analysis of each edge sub-sensor device in the statistical area is performed to obtain the operating performance value of each edge sub-sensor device in the area. The specific steps include: obtaining the performance parameters of each edge sub-sensor device in the area, wherein the performance parameters of each edge sub-sensor device in the area include: packet loss rate, network delay, data throughput and signal strength of each edge sub-sensor device in the area. The operating performance value of each edge sub-sensor device in the area is obtained by comprehensively analyzing the performance of each edge sub-sensor device in the area with the preset reference performance parameters, wherein the preset reference performance parameters include: reference packet loss rate, reference network delay, reference data throughput and reference signal strength.

[0055] It should also be noted that the performance parameters of each edge sub-sensor device in the region can be measured and obtained through network traffic monitoring software or network delay test instruments, Ping tools and other tools. By performing performance analysis on each edge sub-sensor device in the region and obtaining the operating performance values ​​of each edge sub-sensor device in the region, the mutual influence between these parameters is taken into account. For example, if the delay is too high, the throughput will decrease accordingly. Signal strength and packet loss rate jointly affect the transmission quality of data. Weak signal strength will increase the packet loss rate, which in turn affects the overall performance of the device. Transmission delay directly affects data throughput. When the delay is low, data can pass through the device faster, thereby increasing throughput; when the delay increases, the speed at which the device processes data slows down, resulting in a decrease in throughput. Secondly, signal strength has an important impact on transmission delay and data throughput. Higher signal strength can keep data transmitted at a lower delay and reduce transmission errors, thereby increasing throughput. Conversely, when the signal strength is weak, the device may need to retransmit more times, further increasing transmission delay and reducing throughput. In addition, packet loss rate is closely related to signal strength and throughput. A decrease in signal strength will lead to an increase in packet loss rate. Lost data packets need to be retransmitted, resulting in a decrease in overall throughput and longer transmission delays. The increase in packet loss rate not only affects stability, but also further aggravates the vicious cycle of transmission delay and throughput decline. Therefore, the combination of these four parameters can comprehensively evaluate the operating status of edge sub-sensing devices.

[0056] The operating performance values ​​of each edge sub-sensor device in the area are obtained by: ; In the formula, represents the operating performance value of the kth edge sub-sensor device in the region, represents the packet loss rate of the kth edge sub-sensor device in the area, k represents the number of the edge sub-sensor device, , represents the total number of edge sub-sensing devices, Indicates the reference packet loss rate. represents the signal strength of the kth edge sub-sensor device in the area, represents the reference signal strength, represents the data throughput of the kth edge sub-sensor device in the region, Indicates the reference data throughput, represents the network delay of the kth edge sub-sensor device in the region, Indicates reference network delay, Indicates that the packet loss rate affects the weight, Indicates the signal strength influence weight, Data throughput affects the weight, Indicates that network delay affects the weight.

[0057] The operation adjustment execution parameters of each edge sub-sensor device in the area include: power and bandwidth. Increasing power can enhance signal strength and improve signal coverage, especially when the signal is blocked or the distance is far. This will help reduce the packet loss rate and transmission delay caused by weak signal during transmission. At the same time, when the power is too low, the signal of the device is easily interfered by other devices. By moderately increasing power, the impact of external interference can be reduced and the communication quality between devices can be enhanced. When the packet loss rate of the device is detected to be high, the signal transmission quality can be improved by increasing power, thereby reducing data loss. By increasing bandwidth, data throughput can be significantly increased, enabling devices to transmit larger amounts of data, thereby improving data transmission efficiency and reducing transmission delay. When the device faces high data traffic or needs to perform real-time transmission (such as high-definition video monitoring, sensor data aggregation), the bandwidth can be appropriately increased to ensure smooth data transmission. When the transmission delay of the device is detected to be too high, the bandwidth can be increased to accelerate data processing and transmission and reduce delay. When multiple devices share the same network resources and there is data congestion, increasing bandwidth can reduce competition between devices, thereby improving the transmission performance of the overall network environment.

[0058] The packet loss rate impact weight represents the numerical value of the impact of the packet loss rate on the operating performance of each edge sub-sensor device in the area. When used, the impact weight corresponding to the packet loss rate can be directly obtained from the database, and the corresponding relationship can be a pre-set mapping relationship. For example, the packet loss rate and the packet loss rate impact weight form a mapping set, and the real-time packet loss rate is input into the mapping set to obtain the impact weight corresponding to the packet loss rate. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. The signal strength impact weight represents the numerical value of the impact of the signal strength on the operating performance of each edge sub-sensor device in the area. When used, the impact weight corresponding to the signal strength can be directly obtained from the database, and the corresponding relationship can be a pre-set mapping relationship. For example, the signal strength and the signal strength impact weight form a mapping set, and the real-time signal strength is input into the mapping set to obtain the impact weight corresponding to the signal strength. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. The data throughput impact weight represents the numerical value of the impact of the data throughput on the operating performance value of each edge sub-sensor device in the region. When used, the impact weight corresponding to the data throughput can be directly obtained from the database, and the corresponding relationship can be a pre-set mapping relationship. For example, the data throughput and the data throughput impact weight form a mapping set, and the real-time data throughput is input into the mapping set to obtain the impact weight corresponding to the data throughput. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship. The network delay impact weight represents the numerical value of the impact of the network delay on the operating performance value of each edge sub-sensor device in the region. When used, the impact weight corresponding to the network delay can be directly obtained from the database, and the corresponding relationship can be a pre-set mapping relationship. For example, the network delay and the network delay impact weight form a mapping set, and the real-time network delay is input into the mapping set to obtain the impact weight corresponding to the network delay. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship.

[0059] Furthermore, the edge sensor device is adjusted, and the specific steps include: if the comprehensive visit characteristic value in the area is greater than the comprehensive visit characteristic threshold in the area, then the difference between the comprehensive visit characteristic value in the area and the comprehensive visit characteristic threshold in the area is obtained, and recorded as the edge sensor adjustment index of the area; the performance of each edge sub-sensor device in the area is statistically analyzed to obtain the operation performance value of each edge sub-sensor device in the area; based on the operation adjustment execution parameters of the edge sub-sensor devices preset in the database corresponding to different operation performance value ranges under each edge sensor adjustment index interval, and according to the edge sensor adjustment index of the area and the operation performance value of each edge sub-sensor device in the area, the operation adjustment execution parameters of each edge sub-sensor device in the area are mapped and extracted; and the corresponding edge sub-sensor devices are adjusted based on the execution network adjustment parameters.

[0060] In this embodiment, by implementing edge sensing device adjustments, it is possible to effectively respond to changes in the density of human traffic in the area and improve overall management efficiency. When the comprehensive visitor characteristic value exceeds the threshold, the edge sensing adjustment index is quickly calculated, and the overload condition can be identified and responded to in a timely manner to avoid congestion and potential safety hazards. At the same time, the performance of each edge sub-sensing device is statistically analyzed to ensure the accuracy of the adjustment, thereby optimizing the operation of the equipment and improving its response speed and accuracy. The mapping and extraction process based on the preset database makes the adjustment parameters more targeted, ensuring the effective operation of the equipment, and then realizing the rational allocation and utilization of resources. In the end, this dynamic adjustment mechanism not only improves the level of security management in the area, but also optimizes the visitor experience.

[0061] To sum up, this embodiment realizes real-time monitoring and analysis of visitor behavior through the collaborative work of the regional behavior verification module, the target visitor verification module, the behavior planning module and the abnormal judgment module, thereby realizing real-time behavior detection of the target visitor, and effectively solving the problem of poor real-time performance in the process of behavior management and monitoring of the target visitor in the prior art.

[0062] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. 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 disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0063] The present invention is described with reference to flowcharts and / or block diagrams of systems, 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 flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, 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 flowchart and / or block diagram. 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.

[0064] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate 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 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0065] 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 instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0066] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other 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.

[0067] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A visitor behavior management system based on the Internet of Things, characterized in that: include: Regional behavior verification module, target visitor verification module, behavior planning module, and abnormality judgment module; The regional behavior verification module is used to set a verification collection period and collect behavior data of regional visitors during the verification collection period, thereby integrating and obtaining regional behavior verification data; The target visitor verification module is used to sense the target visitor's request access signal and verify the target visitor's information. If the information verification is successful, the target visitor is allowed to access and the target visit location and visit business type of the target visitor are collected. If the information verification fails, the target visitor's information is uploaded to the data management center for secondary authentication; The route planning module is used to plan the route according to the target visitor's target visit location and provide real-time recommended route guidance through the target visitor's mobile receiving port; The abnormality judgment module is used to obtain the behavior data of the target visitor in real time, and simultaneously analyze it according to the regional behavior verification data, judge the abnormal behavior assessment result of the target visitor, and perform corresponding management and control based on the abnormal behavior assessment result.

2. A visitor behavior management system based on the Internet of Things as claimed in claim 1, characterized in that: The step of obtaining the regional behavior verification data comprises: During the verification and collection period, behavior data of regional visitors are collected, wherein the behavior data include the total stay time in the region, movement speed, walking step frequency, total movement trajectory route length and pause frequency of each visitor corresponding to each visit business type, and regional behavior verification data is obtained by mean processing, wherein the regional behavior verification data includes the behavior reference data of visitors corresponding to each visit business type, specifically including: regional control stay time, control movement speed, control walking step frequency, control total movement trajectory route length and control pause frequency.

3. A visitor behavior management system based on the Internet of Things as claimed in claim 1, characterized in that: The specific process of performing route planning according to the target visitor's target visit location is as follows: According to the target visit location of the target visitor, a number of reachable paths between the target visit location of the target visitor and the current location of the target visitor are extracted and marked as each guidance path to be planned; Taking the current time as the starting time point and dividing it by the preset time length to obtain the expected traffic period, the historical impact data corresponding to each guidance path to be planned in the expected traffic period is counted, and the length of each guidance path to be planned and the sensitive average distribution interval distance are obtained, thereby processing to obtain the traffic adaptation value of each guidance path to be planned; Based on the traffic adaptation values ​​of each guidance path to be planned, the guidance path to be planned corresponding to the maximum traffic adaptation value is selected as the recommended path for the target visitor; The historical impact data include: historical pedestrian density and historical vehicle flow rate.

4. A visitor behavior management system based on the Internet of Things as claimed in claim 3, characterized in that: The specific method for obtaining the traffic adaptation value of each guidance path to be planned is as follows: ； represents the traffic adaptation value of the i-th guidance path to be planned, i represents the number of the guidance path to be planned, , I represents the total number of guidance paths to be planned, e represents a natural constant, represents the historical passenger flow density corresponding to the i-th guided path to be planned during the expected travel period, represents the historical traffic flow rate corresponding to the i-th guidance path to be planned during the expected travel period, represents the length of the i-th guidance path to be planned, It represents the average distribution distance between the i-th guidance path to be planned and the sensitive area. represents the impact weight of historical traffic flow, Indicates the influence weight of the length of the guidance path to be planned, Indicates that the weights are sensitively and evenly distributed.

5. The visitor behavior management system based on the Internet of Things as claimed in claim 1, characterized in that: The method of acquiring the target visitor's behavior data in real time and analyzing it according to the regional behavior verification data is as follows: Acquire the target visitor's behavior data in real time, wherein the target visitor's behavior data includes: the target visitor's regional stay time, movement speed, walking frequency, total movement trajectory route length and pause frequency; Screening the regional behavior verification data based on the target visitor's visit business type, obtaining the behavior reference data corresponding to the target visitor's visit business type, and using it as the behavior reference data of the target visitor; Comprehensively analyzing the behavior data of the target visitor acquired in real time and the behavior reference data of the target visitor to obtain the behavior abnormality score of the target visitor; The target visitor's behavior abnormality score is used to characterize the degree of the target visitor's behavior abnormality.

6. A visitor behavior management system based on the Internet of Things as claimed in claim 5, characterized in that: The specific method for determining the abnormal behavior assessment result of the target visitor is as follows: The behavior abnormality threshold preset in the database is obtained and compared with the behavior abnormality score of the target visitor. If the behavior abnormality score of the target visitor is above the behavior abnormality threshold, the behavior abnormality assessment result of the target visitor is abnormal behavior. If the behavior abnormality score of the target visitor is less than the behavior abnormality threshold, the behavior abnormality assessment result of the target visitor is normal behavior.

7. A visitor behavior management system based on the Internet of Things as claimed in claim 6, characterized in that: The specific method for carrying out corresponding control based on the abnormal behavior assessment result is as follows: If the target visitor's behavior abnormality assessment result is normal, no corresponding control will be carried out. If the target visitor's behavior abnormality assessment result is abnormal, the monitoring device around the target visitor will be called up for high-performance mode monitoring, and the detailed behavior data of the target visitor will be uploaded to the data management center for supervision.

8. The visitor behavior management system based on the Internet of Things as claimed in claim 1, characterized in that: It also includes an edge sensor device adjustment module, which is used to set a sensor adjustment period, and obtain comprehensive visit data in the area during the sensor adjustment period, thereby analyzing the comprehensive visit feature value in the area, and adjusting and managing the edge sensor devices in the area based on the comprehensive visit feature value, specifically including: Acquire comprehensive visitor data in the area during the sensing adjustment period, wherein the comprehensive visitor data includes: the total number of target visitors, the average stay time of the target visitors, the current density of pedestrian flow in each passage path, and the current density of vehicle flow in each passage path; Obtain dynamic control reference parameters preset in the database, and compare them with the comprehensive visit data to obtain the comprehensive visit feature value in the area, and adjust and manage the edge sensor devices in the area based on the comprehensive visit feature value; The comprehensive visit characteristic value in the area is used to characterize the overall visit situation of the area during the sensing adjustment period and monitor the pressure load.

9. A visitor behavior management system based on the Internet of Things as claimed in claim 8, characterized in that: The step of regulating and managing edge sensor devices in the area based on the comprehensive visitor feature value includes: The comprehensive visit feature threshold in the area is obtained and compared with the comprehensive visit feature value in the area. If the comprehensive visit feature value in the area is greater than the comprehensive visit feature threshold in the area, the edge sensor device is adjusted. If the comprehensive visit feature value in the area is below the comprehensive visit feature threshold in the area, the edge sensor device is not adjusted.

10. A visitor behavior management system based on the Internet of Things as claimed in claim 9, characterized in that: The edge sensing device adjustment includes the following specific steps: If the comprehensive visit feature value in the area is greater than the comprehensive visit feature threshold in the area, then the difference between the comprehensive visit feature value in the area and the comprehensive visit feature threshold in the area is obtained and recorded as the edge sensing adjustment index of the area; Analyze the performance of each edge sub-sensor device in the statistical area to obtain the operating performance value of each edge sub-sensor device in the area; Based on the operation adjustment execution parameters of the edge sub-sensing devices preset in the database corresponding to different operation performance value ranges under each edge sensing adjustment index interval, and according to the edge sensing adjustment index of the area and the operation performance value of each edge sub-sensing device in the area, the operation adjustment execution parameters of each edge sub-sensing device in the area are mapped and extracted; Based on the execution network adjustment parameters, the corresponding edge sub-sensing devices are adjusted.

Images