An attendance information generation method and device, a storage medium and an electronic device

Abstract

This application discloses a method, apparatus, storage medium, and electronic device for generating attendance information, relating to the field of educational technology. The method includes: acquiring a set of movement routes of a target student attending classes in multiple classrooms; filtering the effective movement routes of the target student; constructing a personalized path map for the target student; analyzing the target student's first movement intention based on the current movement route and the target movement route corresponding to the target classroom; analyzing the target student's second movement intention based on the current movement direction and the target movement direction corresponding to the target classroom; generating attendance information for the target student's movement to the target classroom based on the first and second movement intentions; and issuing campus security warnings for abnormal students who have not arrived at the target classroom within the target arrival time. This application can improve the accuracy of attendance information generation and realize campus security monitoring and early warning.

Description

Technical Field

[0001] This application relates to the field of educational technology, and in particular to a method, apparatus, storage medium and electronic device for generating attendance information. Background Technology

[0002] The flexible class system is the mainstream teaching model in high school, where students need to complete their courses in different classrooms and on different floors based on their course selection results.

[0003] Currently, attendance tracking in the flexible class scheduling system involves methods such as students checking in via facial recognition in the classroom, locating students through the wireless signals of their smart devices, and determining students' locations through video surveillance.

[0004] However, students' facial recognition check-in in the classroom can be affected by congestion during breaks, leading to missed check-ins; the wireless signal positioning of students' smart devices can be affected by environmental interference and signal drift, resulting in inaccurate positioning; determining students' location through video surveillance has blind spots and cannot achieve full-scene coverage; using the above methods can lead to misjudgments of attendance, resulting in low accuracy of attendance information generation. Summary of the Invention

[0005] In view of this, this application provides a method, apparatus, storage medium, and electronic device for generating attendance information. The main purpose is to improve the technical problems of the existing technology, which are that students' face recognition attendance in the classroom is affected by the congestion of people during breaks, resulting in missed attendance; the wireless signal positioning of students' smart devices is affected by environmental interference and signal drift, resulting in inaccurate positioning; and the determination of students' location through video surveillance has blind spots and cannot achieve full scene coverage. The use of the above methods will lead to attendance misjudgment and low accuracy of attendance information generation.

[0006] Firstly, this application provides a method for generating attendance information, including: Obtain the set of movement routes of the target student in multiple classrooms, and filter the effective movement routes of the target student based on the multi-dimensional movement data of the target student to obtain the effective route set; Based on the analysis of the effective route set, the movement trajectory and movement habits of the target students are analyzed to obtain personalized movement information of the target students attending classes in multiple classrooms, and a personalized path map of the target students attending classes in multiple classrooms is constructed based on the personalized movement information. Based on the network access point accessed by the target student in the personalized path map and the connection edge of the network access point in physical space, the target classroom where the target student needs to attend class is determined from the personalized path map. Based on the target student's current movement route and the target movement route corresponding to the target student moving to the target classroom, the first movement intention of the target student under the current movement route is analyzed. Based on the target student's current movement direction and the target movement direction corresponding to the target student moving to the target classroom, the second movement intention of the target student under the current movement direction is analyzed. Based on the first movement intention and the second movement intention, the credibility of the target student moving to the target classroom is analyzed. If the credibility of the target student meets the credibility condition, the attendance information of the target student moving to the target classroom is generated, and the target arrival time of the target student to the target classroom is determined. Based on the abnormal students who have not arrived at the target classroom within the target arrival time, campus security warnings are issued.

[0007] Optionally, the step of determining the target classroom where the target student needs to attend class from the personalized path map based on the network access point accessed by the target student and the physical connection edges of the network access point in the personalized path map, and analyzing the target student's first movement intention under the current movement route based on the target student's current movement route and the target movement route corresponding to the target student moving to the target classroom, includes: Based on the static mapping of the campus plane, the node connections of adjacent network access points in the physical space are extracted to construct an initialized undirected static adjacency topology graph. Based on the undirected static adjacency topology graph and the personalized path map, taking the current location of the target student as the starting point and the location of the target classroom as the ending point, the shortest time data from the current location to the target classroom is predicted, and the target movement route corresponding to the shortest time data is determined. Based on the current movement route of the target student and the distribution of the target movement route in the personalized path map, the current network access point sequence corresponding to the current movement route and the target network access point sequence corresponding to the target movement route are extracted. Based on the access order information and access quantity information corresponding to the current network access point in the current network access point sequence and the target network access point in the target network access point sequence, the access point overlap information of the current network access point and the target network access point is analyzed to evaluate the overlap between the current mobile route and the target mobile route. Based on the overlap information of the current network access point and the target network access point, the length of the longest common subsequence that overlaps with the target network access point in the current network access point is determined, and the difference information between the current network access point and the target network access point is determined based on the length of the longest common subsequence. Based on the difference information, the first movement intention of the target student under the current movement route is analyzed.

[0008] Optionally, based on the target student's current movement direction and the target movement direction corresponding to the target student moving to the target classroom, the second movement intention of the target student under the current movement direction is analyzed, including: The personalized path map is divided into path grids. Target path grids containing the movement trajectory of the target student are extracted from the multiple divided path grids. A path grid sequence corresponding to the target path grid is generated based on the movement order of the target student. Based on the number of times the target student moves in the target path grid and the path grid sequence, the personalized movement information of the target student moving in the target path grid is analyzed, and based on the personalized movement information, the first probability information of the target student moving to the target classroom based on the target movement direction is evaluated; Based on the undirected static adjacency topology graph and the personalized path map, determine the first physical space vector of the target student from the current location to the target classroom based on the target movement route, and the second physical space vector of the target student from the current location to the target classroom based on the current movement route; Based on the orientation comparison information between the target movement direction corresponding to the first physical space vector and the current movement direction corresponding to the second physical space vector, the first probability information is updated to obtain the second probability information of the target student moving to the target classroom based on the current movement direction, and the second movement intention of the target student under the current movement direction is analyzed based on the second probability information.

[0009] Optionally, updating the first probability information based on the orientation comparison information between the target movement direction corresponding to the first physical space vector and the current movement direction corresponding to the second physical space vector to obtain second probability information of the target student moving to the target classroom based on the current movement direction, and analyzing the second movement intention of the target student under the current movement direction based on the second probability information, includes: The direction similarity between the target movement direction and the current movement direction is compared, and the azimuth alignment data between the current movement direction and the target movement direction of the target student is analyzed based on the azimuth comparison information obtained from the similarity. Based on the first probability information, a target probability matrix is ​​constructed for the target student to move to the target classroom based on the target movement direction. The probability matrix represents the relationship between the movement direction and the movement probability of the target student moving in the multiple path grids. Based on the orientation alignment data, the correlation between the movement orientation and movement probability of the target student moving to the target classroom based on the target movement direction in the target probability matrix is ​​updated to obtain the current probability matrix of the target student moving to the target classroom based on the current movement direction; Based on the multiple path grids, the target path grid containing the movement trajectory of the target student is extracted. According to the grid state transition information of the target student from the current position to the target classroom, the target probability data corresponding to the target path grid in the current probability matrix is ​​fused to obtain the second probability information of the target student moving to the target classroom based on the current movement direction. Based on the second probability information, the second movement intention of the target student under the current movement direction is analyzed.

[0010] Optionally, a target arrival time for the target student to arrive at the target classroom is determined, and a campus security alert is issued based on abnormal students who have not arrived at the target classroom within the target arrival time, including: Based on the personalized path map, the movement speed of the target student in the current movement route is analyzed to obtain the effective average time data corresponding to multiple movement segments of the target student in the current movement route; The effective average time data corresponding to the multiple movement segments are fused to obtain the total time data of the target student moving on the current movement route. Based on the total time data and the elastic time window corresponding to the current movement route, the time for the target student to arrive at the target classroom is predicted to obtain the target arrival time of the target student to arrive at the target classroom. If the target student does not arrive at the target classroom within the target arrival time, based on the actual arrival time of the target student, determine whether there is student information for other students besides the target student who did not arrive at the target classroom within the actual arrival time; If the student information does not exist, update the attendance information of the target student to abnormal attendance information; If the student information exists, the system analyzes the movement routes of the students who have not yet arrived based on the personalized path map corresponding to the student information, and issues campus safety warnings based on the route analysis results.

[0011] Optionally, when the student information exists, the step of performing route analysis on the movement routes of the unreached students based on the personalized route map corresponding to the student information, and issuing campus safety warnings based on the route analysis results, includes: If the student information exists, the unreached movement routes corresponding to the unreached students are determined based on the personalized path map corresponding to the unreached students. Based on the number of students accessing the network access points corresponding to the unreached mobile routes and the standard number of students accessing the network access points corresponding to the unreached mobile routes, the degree of student aggregation corresponding to the unreached mobile routes is analyzed. Based on the number of students accessing and leaving the network access points corresponding to the non-reached movement routes within the target time window, analyze the student mobility level corresponding to the non-reached movement routes. Based on the degree of student gathering and the degree of student mobility corresponding to the unreached routes, the congestion of the routes corresponding to the unreached routes is evaluated, and in the case of abnormal congestion of the unreached routes, campus safety warnings are issued based on the unreached routes.

[0012] Optionally, the step of obtaining a set of movement routes of the target student in multiple classrooms, and filtering the effective movement routes of the target student based on the multi-dimensional movement data of the target student to obtain a set of effective routes, includes: Obtain a set of movement routes of the target student in multiple classrooms, and perform route analysis on the movement routes in the set to obtain multiple network access points corresponding to the target student, as well as time data and step data of movement between the multiple network access points; Based on the time data, the access time and departure time of the target student between adjacent access points are analyzed, and the situation is analyzed based on the time difference between the access time and the departure time. Based on the signal timing logs and pedometer timing logs of the multiple network access points, the signal changes and movement steps between adjacent access points are analyzed to obtain movement time data, signal change data, and movement step data between adjacent access points. From the set of movement routes, select movement routes whose movement time data meets the time span condition, whose signal change data meets the slope gradient condition, and whose movement step data meets the continuous physical kinetic energy output condition, and determine the selected movement routes as valid routes. The effective movement routes are mapped in the physical space to obtain multiple network access points included in the effective routes, and the effective routes are combined into the effective route set based on the physical space connection relationships between the multiple network access points.

[0013] Optionally, the step of analyzing the target student's movement trajectory and habits based on the set of effective routes to obtain personalized movement information of the target student attending classes in multiple classrooms, and constructing a personalized path map of the target student attending classes in multiple classrooms based on the personalized movement information, includes: Based on the set of effective routes, the movement trajectory and movement time habits of the target student when moving between the multiple network access points are analyzed to obtain the personalized movement information of the target student when attending classes in multiple classrooms. Based on the personalized movement information and the physical spatial connection relationship between the network access points, the movement sequence of the target student at the multiple network access points is analyzed to obtain multiple effective movement paths between adjacent network access points. Based on the personalized mobility information, the movement time of the target student at the multiple network access points is analyzed to determine the time consumption data of the target student moving based on multiple effective movement paths, and the time data of the multiple effective movement paths is generated based on the time consumption data. By using the multiple network access points as nodes and the multiple valid movement paths as edges, a basic path map for the target student to attend classes in the multiple classrooms is generated. The time weight is added to the basic path map as an attribute parameter of the edges in the basic path map to obtain a personalized path map for the target student to attend classes in the multiple classrooms.

[0014] Secondly, this application provides an attendance information generation device, comprising: The acquisition module is configured to acquire a set of movement routes of the target student in multiple classrooms, and filter the effective movement routes of the target student based on the multi-dimensional movement data of the target student to obtain a set of effective routes. The construction module is configured to analyze the movement trajectory and movement habits of the target student based on the set of effective routes, obtain personalized movement information of the target student attending classes in multiple classrooms, and construct a personalized path map of the target student attending classes in multiple classrooms based on the personalized movement information. The analysis module is configured to determine the target classroom where the target student needs to attend class based on the network access point accessed by the target student in the personalized path map and the connection edge of the network access point in physical space; analyze the first movement intention of the target student under the current movement route based on the target student's current movement route and the target movement route corresponding to the target student moving to the target classroom; and analyze the second movement intention of the target student under the current movement direction based on the target student's current movement direction and the target movement direction corresponding to the target student moving to the target classroom. The generation module is configured to analyze the target credibility of the target student moving to the target classroom based on the first movement intention and the second movement intention, and generate attendance information of the target student moving to the target classroom when the target credibility meets the credibility condition, and determine the target arrival time of the target student to the target classroom, and issue a campus security warning based on abnormal students who have not arrived at the target classroom within the target arrival time.

[0015] Thirdly, this application provides an electronic device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the computer program to implement the attendance information generation method described in the first aspect.

[0016] By means of the above technical solution, this application provides a method, apparatus, storage medium, and electronic device for generating attendance information, comprising: acquiring a set of movement routes of a target student attending classes in multiple classrooms, and filtering the effective movement routes of the target student based on the multi-dimensional movement data of the target student to obtain a set of effective routes; analyzing the movement trajectory and movement habits of the target student based on the set of effective routes to obtain personalized movement information of the target student attending classes in multiple classrooms, and constructing a personalized path map of the target student attending classes in multiple classrooms based on the personalized movement information; determining the current attendance of the target student based on the network access point accessed by the target student and the connection edges of the network access point in physical space in the personalized path map. The target classroom for the lesson is determined by analyzing the target student's first movement intention based on the current movement route and the target movement route corresponding to the target classroom. The second movement intention is also analyzed based on the current movement direction and the target movement direction corresponding to the target classroom. Based on the first and second movement intentions, the credibility of the target student's movement to the target classroom is analyzed. If the credibility meets the credibility criteria, attendance information for the target student's movement to the target classroom is generated, and the target arrival time is determined. For students who fail to arrive at the target classroom within the target arrival time, a campus safety warning is issued. Compared with existing technologies, this application achieves effective filtering of movement routes by acquiring a set of movement routes of target students and filtering effective movement routes based on multi-dimensional movement data; it provides a personalized data foundation for predicting the route and probability of target students reaching the target classroom by analyzing movement trajectories and habits and constructing personalized path maps; it improves the reliability of movement intention recognition by determining the target classroom based on the personalized path map and analyzing the first and second movement intentions; it achieves automatic attendance for target students by analyzing the credibility of the target based on dual movement intentions and generating attendance information, thereby improving the accuracy of attendance information generation; and it provides campus security warnings based on abnormal students who have not arrived at the target classroom within the target arrival time, enabling real-time monitoring and early warning of campus security. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating an attendance information generation method provided in an embodiment of this application is shown. Figure 2 A flowchart illustrating an attendance information generation method provided in an embodiment of this application is shown. Figure 3 This illustration shows a schematic diagram of an attendance information generation device provided in an embodiment of this application; Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0020] The embodiments of this application will now be described in more detail with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0021] To address the technical issues of existing technologies that hinder student attendance tracking, such as the impact of congestion during breaks on classroom facial recognition, leading to missed attendance records; the inaccuracy of using wireless signals from student-worn smart devices for location tracking due to environmental interference; and the limitations of video surveillance in determining student location due to blind spots and incomplete coverage; these methods result in misjudgments and low accuracy in attendance information generation. This embodiment provides a method for generating attendance information, such as... Figure 1 As shown, the method includes: Step 101: Obtain the set of movement routes of the target student in multiple classrooms, and filter the effective movement routes of the target student based on the multi-dimensional movement data of the target student to obtain the effective route set.

[0022] In this embodiment of the application, the target student can be a student who needs to attend classes across classrooms, floors, or buildings in a flexible class scheduling scenario. For example, the target student in this embodiment of the application can specifically be a student wearing wearable devices such as IoT wristbands or name badges. These wearable devices can collect and report information such as the student's wireless network access point connection logs, signal strength data, step count data, and azimuth data.

[0023] In this embodiment of the application, the set of movement routes can be the set of all movement paths formed by the target student moving between different classrooms on campus. For example, multiple movement routes in the set of movement routes can be represented as a sequence of handover between different network access points.

[0024] In the embodiments of this application, multi-dimensional mobility data can be data used to characterize the student's actual physical movement state, and can be used to effectively distinguish between actual physical displacement and abnormal states such as signal drift and roaming in place. For example, multi-dimensional mobility data may include movement time data, signal change data, and movement step count data between adjacent network access points.

[0025] In this embodiment, an effective movement route can be a movement route that conforms to the laws of real physical motion after eliminating abnormal interference such as signal drift and non-purposeful wandering. It can be used to construct personalized paths and determine attendance intentions.

[0026] In this embodiment of the application, the system can first obtain the set of all movement routes generated by the target student taking classes in multiple classrooms, perform preliminary analysis on the set of movement routes to obtain the corresponding network access point sequence, time data and step data; the system can filter the routes in the set of movement routes based on multi-dimensional movement data, retain the movement routes that meet the time span condition, slope gradient condition and continuous physical kinetic energy output condition, and summarize the filtered routes to obtain the set of effective routes.

[0027] Step 102: Analyze the movement trajectory and movement habits of the target students based on the effective route set to obtain personalized movement information of the target students attending classes in multiple classrooms, and construct personalized path maps of the target students attending classes in multiple classrooms based on the personalized movement information.

[0028] In this embodiment of the application, the movement trajectory can be the sequence of network access points traversed by the target student on the effective route, the physical spatial connectivity, and the movement order, which can be used to reflect the student's regular paths and spatial preferences when moving between classrooms. For example, the movement trajectory may include the sequence of network access points traversed from the current classroom to the target classroom and the physical spatial connectivity.

[0029] In this embodiment, movement habits can be information such as the target student's historical travel time characteristics, walking speed stability, and path selection preferences on different path segments, which can be used to characterize the student's personalized class-hopping flow pattern. For example, movement habits can include information such as the historical median time, standard deviation of time, and degree of fluctuation of the same effective physical movement connection.

[0030] In the embodiments of this application, personalized mobility information can be student-specific class-hopping feature information formed by integrating mobility trajectory and mobility habits, which can be used to construct a personalized path model that fits the student's real behavioral characteristics.

[0031] In this embodiment, the personalized route map can be a two-dimensional network topology graph with network access points as nodes, effective physical movement paths as edges, and time weights as edge attribute parameters. It can be used as a benchmark model for attendance intent determination, route matching, and arrival time prediction. For example, the personalized route map can be a two-dimensional network access point topology graph with time weights, where the edge weights can represent the time a student typically spends traversing that route.

[0032] In this embodiment of the application, the historical travel trajectory and time consumption characteristics of the target student can be statistically analyzed based on the effective route set to extract personalized movement information; a basic path map is generated by using multiple network access points as nodes and multiple effective physical movement paths as edges, and time weights are injected into the basic path map as attribute parameters of the edges to obtain a personalized path map of the target student attending classes in multiple classrooms.

[0033] Step 103: Based on the network access point accessed by the target student in the personalized path map and the connection edge of the network access point in physical space, determine the target classroom where the target student needs to attend class. Based on the target student's current movement route and the target movement route corresponding to the target student moving to the target classroom, analyze the target student's first movement intention under the current movement route, and based on the target student's current movement direction and the target movement direction corresponding to the target student moving to the target classroom, analyze the target student's second movement intention under the current movement direction.

[0034] In this embodiment of the application, the network access point can be a wireless access point (AP) deployed on campus. The network access point can be used to collect connection signals and signal strength timing logs of wearable devices, and to achieve physical space anchoring and area mapping. For example, the network access point can be bound to physical space areas such as classrooms, corridors, stairwells, and restrooms.

[0035] In this embodiment, the connecting edges in the physical space can be the physical connectivity between adjacent network access points obtained from static mapping of the campus plane, which can be used to construct the basic spatial topology.

[0036] In the embodiments of this application, the target classroom can be the classroom area corresponding to the current class schedule of the target student, and can be used as the endpoint area for attendance confirmation, trajectory prediction and arrival time calculation.

[0037] In this embodiment of the application, the current movement route can be the actual travel route represented by the network access point switching sequence generated in real time by the target student.

[0038] In the embodiments of this application, the target movement route can be the shortest time-consuming route from the current location to the target classroom obtained from the personalized path map, which can be used as a reference route for route matching and intent judgment.

[0039] In the embodiments of this application, the first movement intention can be a path-level intention obtained based on the overlap and matching results of the current movement route and the target movement route, which can be used to characterize the credibility of a student going to the target classroom on the route.

[0040] In the embodiments of this application, the current direction of movement can be real-time azimuth data collected by the electronic compass of the wearable device, which can be used to characterize the student's actual physical orientation.

[0041] In this embodiment of the application, the target movement direction can be the theoretical physical spatial direction from the current position to the target classroom.

[0042] In the embodiments of this application, the second movement intention can be a location-level intention obtained based on directional similarity and grid probability prediction, which can be used to characterize the credibility of a student heading to the target classroom in a certain direction.

[0043] In this embodiment of the application, the target classroom that the target student should arrive at can be determined based on the distribution of network access points and physical space connection edges in the personalized path map; the overlap degree analysis between the current movement route and the target movement route can be performed to obtain the first movement intention; at the same time, the orientation comparison and probability correction between the current movement direction and the target movement direction can be performed to obtain the second movement intention.

[0044] Step 104: Based on the first and second movement intentions, analyze the credibility of the target student moving to the target classroom. If the credibility of the target student meets the credibility conditions, generate the attendance information of the target student moving to the target classroom and determine the target arrival time of the target student. Based on the abnormal students who have not arrived at the target classroom within the target arrival time, issue a campus security warning.

[0045] In the embodiments of this application, the target credibility can be the overall confidence level of the student going to the target classroom obtained by combining the first movement intention and the second movement intention, which can be used as the basis for determining automatic attendance triggering.

[0046] In this embodiment, the confidence condition can be a preset path matching degree threshold and an arrival probability threshold, which can be used to determine whether the attendance confirmation standard is met.

[0047] In this embodiment of the application, the attendance information can be automatically generated, contactless attendance confirmation information, which can be used to record the status of students arriving at the target classroom normally.

[0048] In this embodiment of the application, the target arrival time can be the estimated arrival time dynamically predicted based on a personalized route map, real-time traffic damping coefficient, and preceding student passage data, which can be used as a time benchmark for judging abnormal attendance.

[0049] In the embodiments of this application, an abnormal student can be a student who has not arrived at the target classroom after the target arrival time plus the flexible fault tolerance time window, and can be used as an object for individual anomaly marking and group anomaly analysis.

[0050] In this application embodiment, the campus security early warning can be a security event notification based on the characteristics of Estimated Time of Arrival (ETA) offset clustering, clustering degree and turnover rate, which can be used to achieve full-scene security monitoring without blind spots.

[0051] In this embodiment, the system can fuse the first and second movement intentions to determine the target's credibility. If the target's credibility meets the credibility criteria, attendance information is generated, and the target's arrival time is calculated simultaneously. For students who have not arrived by the target arrival time, the system can first mark their individual attendance as abnormal. When the number of abnormal students reaches a clustering threshold, the system can perform group analysis on the movement routes of the absent students, evaluate route congestion based on student clustering and mobility, and issue a campus security warning when abnormal congestion is detected, thus achieving data association between attendance data and campus security.

[0052] Compared with existing technologies, this embodiment acquires a set of target students' movement routes and filters effective movement routes based on multi-dimensional movement data, achieving effective route filtering; by analyzing movement trajectories and habits and constructing personalized path maps, it provides a personalized data foundation for predicting the route and probability of target students reaching the target classroom; by determining the target classroom based on the personalized path map and analyzing the first and second movement intentions, it improves the reliability of movement intention recognition; by analyzing the credibility of the target based on dual movement intentions and generating attendance information, it achieves automatic attendance for target students, improving the accuracy of attendance information generation; and by issuing campus safety warnings based on abnormal students who have not arrived at the target classroom within the target arrival time, it enables real-time monitoring and early warning of campus safety.

[0053] As an optional approach, when performing the task of "determining the target classroom for the target student's current class based on the network access point accessed by the target student in the personalized path map and the physical connection edges of the network access points, and analyzing the target student's first movement intention under the current movement route based on the target student's current movement route and the target movement route corresponding to the target student's movement to the target classroom," the following methods can be used, but are not limited to: Figure 2 As shown, the method includes: Step 201: Based on the static mapping of the campus plane, extract the node connections of adjacent network access points in the physical space and construct an initialized undirected static adjacency topology graph.

[0054] In the embodiments of this application, static mapping of the campus can be a standardized drawing and coordinate calibration of physical spaces such as campus floors, classrooms, corridors, stairs, and stairwells, which can be used to determine the spatial layout, adjacency relationship and connectivity of network access points.

[0055] In this embodiment, the undirected static adjacency topology graph can be an initial topology structure with network access points as nodes and physical adjacency relationships as edges, which can be used as the basic framework for path planning, route search, and shortest time calculation. For example, the undirected static adjacency topology graph can be represented as G0=(V,E0), where V can be the set of network access points across the entire campus, and E0 can be the set of static adjacent edges.

[0056] In this embodiment of the application, the nodes connecting adjacent network access points can be extracted based on the campus plan survey results, and an undirected static adjacency topology graph without time weight information can be constructed. This topology graph can represent the physical connectivity between network access points. For example, classroom A and classroom B can be located on different floors, and classroom A and classroom B can be indirectly connected through the network access point in the stairwell. Based on the node connection relationships in the undirected static adjacency topology graph, an effective movement route through the stairwell can be determined, thereby improving the accuracy of student movement path positioning and route planning.

[0057] Step 202: Based on the undirected static adjacency topology graph and personalized path map, with the current location of the target student as the starting point and the location of the target classroom as the ending point, predict the shortest time data from the current location to the target classroom, and determine the target movement route corresponding to the shortest time data.

[0058] In this embodiment of the application, the shortest travel time data can be the minimum travel time from the origin to the destination calculated based on the time weight in the personalized route map. The calculation formula for the shortest travel time data is shown in Formula 1, where, It can represent the distance from the starting point to the network access point. The shortest time, It can represent the distance from the starting point to the network access point. The shortest time, It can represent a network access point. To network access point Time weighting.

[0059] (Formula 1) In this embodiment of the application, the shortest time-consuming path can be calculated by taking the student's current network access point as the starting point and the network access point corresponding to the target classroom as the ending point, and combining the time weights of the undirected static adjacency topology graph and the personalized path map, and the path can be determined as the target movement route.

[0060] Step 203: Based on the current movement route of the target student and the distribution of the target movement route in the personalized path map, extract the current network access point sequence corresponding to the current movement route and the target network access point sequence corresponding to the target movement route.

[0061] In this embodiment of the application, the network access point sequence can be a set of network access point identifiers arranged in chronological or spatial order, which can be used for sequence matching and overlap calculation. For example, the current network access point sequence can be an AP sequence generated by students switching in real time, and the target network access point sequence can be the AP sequence corresponding to the shortest path.

[0062] In this embodiment of the application, the corresponding network access point sequences can be extracted from the current mobile route and the target mobile route respectively, providing a data foundation for the calculation of the longest common subsequence and path matching degree analysis.

[0063] Step 204: Based on the access order information and access quantity information corresponding to the current network access point in the current network access point sequence and the target network access point in the target network access point sequence, analyze the access point overlap information of the current network access point and the target network access point to evaluate the overlap between the current mobile route and the target mobile route.

[0064] In this embodiment of the application, the access order information may be the order in which the network access point is accessed by the student wearable device.

[0065] In the embodiments of this application, the access quantity information may be the total number of network access points contained in the sequence, which can be used to calculate the overlap ratio.

[0066] In the embodiments of this application, the access point overlap information can be the location, number and order information of the same network access points in two sequences. The access point overlap information can be used to reflect the similarity between the current mobile route and the target mobile route.

[0067] In the embodiments of this application, the system can compare the order and number of the current network access point sequence and the target network access point sequence, count the overlapping node information, and evaluate the overlap between the two routes.

[0068] Step 205: Based on the overlap information of the current network access point and the target network access point, determine the length of the longest common subsequence that overlaps with the target network access point in the current network access point, and determine the difference information between the current network access point and the target network access point based on the length of the longest common subsequence. Analyze the target student's first movement intention under the current movement route based on the difference information.

[0069] For the embodiments of this application, the length of the longest common subsequence can be the number of longest overlapping nodes that maintain the same order between two sequences. The length of the longest common subsequence can be used to calculate the path matching degree. The calculation of the longest common subsequence can be carried out using, but is not limited to, the LCS algorithm. The calculation formula of the longest common subsequence can be as shown in Formula 2, where L(i,j) can represent the length of the longest common subsequence between the first i nodes of the target sequence and the first j nodes of the current sequence. It can represent the i-th network access point in the target sequence; It can represent the j-th network access point in the current sequence.

[0070] (Formula 2) In this embodiment of the application, determining the difference information between the current network access point and the target network access point based on the length of the longest common subsequence can be achieved by calculating the route matching degree between the current mobile route and the target mobile route. The calculation formula for the route matching degree is shown in Formula 3, where M can represent the path matching degree; L(m, n) can represent the length of the longest common subsequence; m can represent the total length of the target network access point sequence; and n can represent the total length of the current network access point sequence.

[0071] (Formula 3) Optionally, when performing the task of "analyzing the target student's second movement intention based on the target student's current movement direction and the target movement direction corresponding to the target classroom," the following method can be used, but is not limited to: dividing the personalized path map into path grids; extracting the target path grid containing the target student's movement trajectory from the divided path grids; generating a path grid sequence corresponding to the target path grid based on the target student's movement order; analyzing the target student's personalized movement information within the target path grid based on the number of times the target student moves and the path grid sequence within the target path grid; and evaluating the personalized movement information based on the personalized movement information. The system calculates the first probability information of a target student moving to the target classroom based on the target movement direction; based on the undirected static adjacency topology graph and the personalized path map, it determines the first physical space vector of the target student moving from the current position to the target classroom based on the target movement route, and the second physical space vector of the target student moving from the current position to the target classroom based on the current movement route; based on the orientation comparison information between the target movement direction corresponding to the first physical space vector and the current movement direction corresponding to the second physical space vector, it updates the first probability information to obtain the second probability information of the target student moving to the target classroom based on the current movement direction, and analyzes the second movement intention of the target student under the current movement direction based on the second probability information.

[0072] In this embodiment, the path grid can be a spatial unit after discretizing the campus map, which can be used to construct the state space of Markov prediction.

[0073] In this embodiment, the path grid sequence can be the order in which students pass through the grids in chronological order, and can be used to construct the state transition probability basis.

[0074] In the embodiments of this application, the first probability information can be the initial arrival probability obtained based on historical movement frequency, which can be used as a baseline probability before direction correction.

[0075] In this embodiment of the application, the physical space vector can be a space vector pointing from the current position to the target position, and can be used to calculate the direction angle and cosine similarity.

[0076] In the embodiments of this application, the orientation comparison information can be a direction alignment coefficient between two spatial vectors, which can be used to correct the transfer probability; the formula for calculating the direction alignment coefficient can be as shown in Formula 4, where... It can represent the orientation alignment coefficient. It can represent the student's real-time intention vector (i.e., the first physical space vector in the embodiments of this application). It can represent the ideal transfer vector between grids (i.e., the second physical space vector in the embodiments of this application).

[0077] (Formula 4) In this embodiment of the application, the second probability information may be the dynamic arrival probability after fusing real-time direction, which can be used to characterize the second movement intention.

[0078] As an optional approach, when performing the following steps: "updating the first probability information based on the orientation comparison information between the target movement direction corresponding to the first physical space vector and the current movement direction corresponding to the second physical space vector, obtaining the second probability information of the target student moving to the target classroom based on the current movement direction, and analyzing the target student's second movement intention under the current movement direction based on the second probability information," the following method can be used, but is not limited to: comparing the orientation similarity between the target movement direction and the current movement direction, and analyzing the orientation alignment data between the target student's current movement direction and the target movement direction based on the orientation comparison information obtained from the similarity; constructing a target probability matrix for the target student moving to the target classroom based on the target movement direction based on the first probability information, wherein the probability matrix represents... The correlation between the movement orientation and movement probability of the target student moving through multiple path grids is established. Based on the orientation alignment data, the correlation between the movement orientation and movement probability of the target student moving to the target classroom based on the target movement direction in the target probability matrix is ​​updated to obtain the current probability matrix of the target student moving to the target classroom based on the current movement direction. Target path grids containing the target student's movement trajectory are extracted from multiple path grids. Based on the grid state transition information of the target student from the current position to the target classroom, the target probability data corresponding to the target path grids in the current probability matrix are fused to obtain the second probability information of the target student moving to the target classroom based on the current movement direction. The second probability information is then used to analyze the target student's second movement intention under the current movement direction.

[0079] In this embodiment of the application, the orientation alignment data can be the value normalized by the direction cosine similarity, which can be used as the exponential weighting coefficient for probability correction. The dynamic transfer probability correction formula can be as shown in Formula 5, where, It can represent the dynamic transition probability matrix (i.e., the current probability matrix in the embodiments of this application). It can represent the initial historical transition probability matrix (i.e., the target probability matrix in the embodiments of this application). It can represent the orientation sensitivity adjustment factor. This can represent the directional alignment coefficient from the current path grid i to the path grid j to which the student will move next, based on the target movement direction. N can represent the total number of path grids. This can represent the directional alignment coefficient of a student from the current path grid i to any path grid k based on the current direction of movement. It can represent the probability of a student transitioning from the current path grid i to any path grid k based on the current movement direction.

[0080] (Formula 5) In this embodiment of the application, the initial historical transition probability matrix The calculation formula can be shown in Formula Six, where, This can represent the path grid state of the student at time t+1. This can represent the path grid state of the student at time t. It can represent the state corresponding to the target path grid. It can represent the state corresponding to the current path grid. It can represent the state in historical data. to state Number of times, It can represent the state in historical data. to state The number of times, k can represent the index variable when traversing all path grid states, and N can represent the total number of path grids.

[0081] (Formula 6) In the embodiments of this application, grid state transition information can be used for probability fusion calculation, and the initial state probability vector With dynamic transition matrix The probability distribution after k transitions can be shown in Equation 7, where, It can represent the initial state probability vector. It can represent the state probability vector after k-step transitions. It can represent the dynamic transition probability matrix (i.e., the current probability matrix in the embodiments of this application), and k can represent the number of transition steps.

[0082] (Formula 7) As an optional approach, when executing the task of "determining the target arrival time of the target student to the target classroom and issuing a campus safety warning based on abnormal students who have not arrived at the target classroom within the target arrival time," the following methods can be used, but are not limited to: Analyzing the target student's movement speed along the current route using a personalized path map to obtain effective average time data for multiple movement segments along the current route; fusing the effective average time data for multiple movement segments to obtain the total time data for the target student's movement along the current route, and predicting the target student's arrival time at the target classroom based on the total time data and the elastic time window corresponding to the current route; if the target student has not arrived at the target classroom within the target arrival time, determining whether there are other students besides the target student who have not arrived within the actual arrival time based on the target student's actual arrival time; if no student information exists, updating the target student's attendance information to abnormal attendance information; if student information exists, performing route analysis on the movement routes corresponding to the non-arriving students based on the personalized path map corresponding to the non-arriving students, and issuing a campus safety warning based on the route analysis results.

[0083] In this embodiment, the effective average travel time data can be the average travel time of the road segment after removing outliers, which can be used for dynamic ETA calculation; the formula for calculating the road condition damping coefficient can be as shown in Formula 8, where, It can represent the road condition damping coefficient. It can represent the effective average time spent on the current road segment. It can represent the base time weight of the current road segment.

[0084] (Formula 8) For the embodiments of this application, the formula for calculating the total time spent by the target student moving along the current route can be shown in Formula Nine, where, It can represent the total time spent. It can represent the set of remaining paths. It can represent the remaining path. It can represent the road condition damping coefficient. It can represent the base time weight of the current road segment.

[0085] (Formula Nine) In this embodiment, the flexible time window can be a tolerance time reserved for objective situations such as congestion and slow traffic.

[0086] In the embodiments of this application, abnormal attendance information can be a weak tag indicating that an individual did not arrive on time; the tagging time of the weak tag can be phased. If a student with a weak tag subsequently connects to a wireless network access point in a non-teaching area (such as a restroom or medical room), the system can determine that the student is staying legally through spatial semantics and automatically cancel the weak tag; if the student finally arrives at the target classroom within the subsequent flexible time window, the weak tag can also be automatically canceled.

[0087] As an optional approach, when performing the task of "analyzing the movement routes of students who have not yet arrived based on the personalized path maps corresponding to the students' information, and issuing campus safety warnings based on the route analysis results," the following methods can also be used, but are not limited to: determining the missing movement routes for each missing student based on the personalized path maps corresponding to the students' information; analyzing the student concentration level of the missing movement routes based on the number of students accessing the network access points corresponding to the missing movement routes and the standard number of students accessing the network access points corresponding to the missing movement routes; analyzing the student mobility level of the missing movement routes based on the number of students accessing and leaving the network access points corresponding to the missing movement routes within the target time window; evaluating the route congestion situation based on the student concentration level and student mobility level of the missing movement routes, and issuing campus safety warnings based on the missing movement routes if the missing movement routes are abnormally congested.

[0088] In this embodiment of the application, the student gathering degree can be the ratio of the current number of connected users to the space's baseline capacity. The formula for calculating the student gathering degree is shown in Formula 10, where, This can represent the degree of student gathering at time t. It can represent the security baseline capacity of the space corresponding to network access point j (i.e., the standard number of accesses in this application embodiment). This can represent the number of students accessing network access point j at time t.

[0089] (Formula 10) In this embodiment, student mobility can be the ratio of the number of people entering and exiting the device within a time window to the current number of people, i.e., the group turnover rate. The formula for calculating student mobility is shown in Formula 11, where, It can represent the group turnover rate. This can represent the number of newly connected students. It can represent the number of students who left. This can represent the number of online students at the network access point at time t. It can represent the number of online students at the network access point at time t-1.

[0090] (Formula Eleven) For the embodiments of this application, high aggregation and high turnover (i.e., as described in the embodiments of this application) Greater than 1 and Traffic congestion on main roads during normal teaching periods can be identified as congestion exceeding the traffic threshold; high concentration and low flow (i.e., as described in the embodiments of this application) Greater than 1 and If the value approaches 0, it can be identified as an abnormal gathering or a dangerous event, and the system can trigger a campus safety warning.

[0091] As an optional approach, when performing the task of "obtaining a set of movement routes for target students attending classes in multiple classrooms, and filtering the effective movement routes of target students based on their multi-dimensional movement data to obtain a set of effective routes," the following method can also be used, but is not limited to: obtaining a set of movement routes for target students attending classes in multiple classrooms, performing route analysis on the movement routes in the set to obtain multiple network access points corresponding to the target students, as well as time data and step count data of movement between multiple network access points; analyzing the access time and departure time of target students between adjacent access points based on the time data, and analyzing the time difference between access time and departure time. Based on the signal timing logs and pedometer timing logs of multiple network access points, the system analyzes the signal changes and step counts between adjacent access points to obtain movement time data, signal change data, and step count data between adjacent access points. From the set of movement routes, routes whose movement time data meets the time span condition, signal change data meets the slope gradient condition, and step count data meets the continuous physical kinetic energy output condition are selected and defined as valid routes. These valid routes are then mapped in physical space to obtain the multiple network access points included in the valid routes. Based on the physical spatial connections between these multiple network access points, the valid routes are grouped into a set of valid routes.

[0092] In the embodiments of this application, the signal change data can be the signal change data of the new access network access point and the original network access point; for example, the signal change data in the embodiments of this application can specifically be the difference between the signal rise slope of the new access network access point and the signal attenuation slope of the original network access point.

[0093] For the embodiments of this application, the formula for calculating the signal rise slope of the newly accessed network access point can be as shown in Formula Twelve, wherein the difference in signal attenuation slope between the original network access points can be as shown in Formula Thirteen, wherein... It can represent the signal rise slope of a newly accessed network access point. This can represent the received signal strength of a newly connected network access point at time t2. It can represent the signal reception strength of a newly connected network access point at time t1. It can represent the time interval from t1 to t2. It can represent the signal attenuation slope of the original network access point. This can represent the received signal strength of the original network access point at time t2. It can represent the received signal strength of the original network access point at time t1. The calculation of signal change data can be the difference between the signal rise slope of the newly accessed network access point and the signal attenuation slope of the original network access point.

[0094] (Formula 12) (Formula Thirteen) In this embodiment of the application, the signal timing log can be data that records the change of RSSI signal strength over time.

[0095] In the embodiments of this application, the pedometer time log can be data that records the cumulative changes in the number of steps, which can be used to determine whether there is actual physical movement.

[0096] In this embodiment of the application, the continuous physical kinetic energy output condition can be that the step increment is greater than zero and within a reasonable range, which can be used to eliminate signal drift and roaming in place.

[0097] In this embodiment, the DBSCAN density clustering algorithm can be used to remove abnormal clusters from the feature vectors of moving routes where the movement time data between adjacent access points is extremely short, the signal change data shows disordered jumps, and the number of movement steps is approximately equal to 0; abnormal clusters can also be removed from the feature vectors of moving routes where the movement time data between adjacent access points exceeds the normal walking speed time window, the signal change data does not form a unidirectional switching trend, and the number of movement steps deviates significantly from the normal distribution; moving routes that meet the time span condition, the slope gradient condition, and the continuous physical kinetic energy output condition are selected from the set of moving routes, and the selected moving routes are determined as valid routes.

[0098] For the embodiments of this application, the formula for calculating the effective set of movement routes can be as shown in Formula Fourteen, wherein, It can represent the set of valid routes after cleaning. It can represent anomaly clusters. can represent the x-th high-density cluster (i.e., the actual movement route), and m can represent the total number of effective clusters.

[0099] (Formula Fourteen) As an optional approach, when performing the task of "analyzing the movement trajectory and habits of target students based on a set of effective routes to obtain personalized movement information of target students attending classes in multiple classrooms, and constructing a personalized path map of target students attending classes in multiple classrooms based on the personalized movement information," the following method can also be used, but is not limited to: analyzing the movement trajectory and movement time habits of target students moving between multiple network access points based on a set of effective routes to obtain personalized movement information of target students attending classes in multiple classrooms; and based on the personalized movement information and the physical spatial connection relationship between network access points, analyzing the movement trajectory and movement time habits of target students attending classes in multiple network access points to obtain personalized movement information of target students attending classes in multiple classrooms. The system analyzes the movement sequence of points to obtain multiple effective movement paths between adjacent network access points. Based on personalized movement information, it analyzes the movement time of the target student across multiple network access points to determine the time consumption data of the target student moving along multiple effective movement paths, and generates time data for multiple effective movement paths based on the time consumption data. Using multiple network access points as nodes and multiple effective movement paths as edges, it generates a basic path map of the target student attending classes in multiple classrooms. The time weight is added to the basic path map as an attribute parameter of the edges, resulting in a personalized path map of the target student attending classes in multiple classrooms.

[0100] In the embodiments of this application, the effective physical movement path can be a real physical connection confirmed after clustering and cleaning, which can be used to construct a reliable topology.

[0101] In this embodiment, the time consumption data can be historical travel time samples, which can be used to calculate the time weight. The time weight calculation formula is as shown in Formula Fifteen, where, It can represent time weight. It can represent the time-consuming sample set The relative median, It can represent the adjustment coefficient. It can represent the standard deviation of a sample set.

[0102] (Formula Fifteen) In the embodiments of this application, the personalized path map can be represented as G=(V, Evalid, W), where V can represent the set of valid movement routes, Evalid can represent the set of physical space edges, and W can represent the time weight.

[0103] Compared with existing technologies, this embodiment provides campus safety warnings based on abnormal students who fail to arrive at the target classroom within the target arrival time, enabling real-time monitoring and early warning of campus safety. It improves the accuracy of route matching and intent determination by constructing a static adjacency topology graph and analyzing the first movement intent based on the longest common subsequence. It enhances the accuracy of target classroom arrival probability calculation and intent determination by updating the probability matrix based on orientation alignment data and fusing grid transfer probabilities. It achieves accurate identification of abnormal attendance by analyzing effective average time consumption and combining it with flexible time windows to predict target arrival time. It enables real-time monitoring of campus path status by analyzing student aggregation and mobility and providing abnormal congestion warnings. Finally, it improves the matching degree between the path map and students' personalized class-hopping habits by constructing a personalized path map based on effective routes and time weights, and by utilizing the switching of target students between different network access points to reflect the movement of target students in various areas.

[0104] Furthermore, as Figure 1 and Figure 2 The specific implementation of the method shown in this embodiment provides an attendance information generation device, such as... Figure 3 As shown, the device includes: an acquisition module 31, a construction module 32, an analysis module 33, and a generation module 34.

[0105] The acquisition module 31 is configured to acquire a set of movement routes of the target student in multiple classrooms, and filter the effective movement routes of the target student based on the multi-dimensional movement data of the target student to obtain a set of effective routes. Module 32 is configured to analyze the movement trajectory and movement habits of target students based on the effective route set, obtain personalized movement information of target students attending classes in multiple classrooms, and construct personalized path maps of target students attending classes in multiple classrooms based on personalized movement information. Analysis module 33 is configured to determine the target classroom where the target student needs to attend class based on the network access point accessed by the target student in the personalized path map and the connection edge of the network access point in the physical space. Based on the target student's current movement route and the target movement route corresponding to the target student moving to the target classroom, it analyzes the target student's first movement intention under the current movement route, and based on the target student's current movement direction and the target movement direction corresponding to the target student moving to the target classroom, it analyzes the target student's second movement intention under the current movement direction. The generation module 34 is configured to analyze the target credibility of the target student moving to the target classroom based on the first movement intention and the second movement intention, and generate the attendance information of the target student moving to the target classroom when the target credibility meets the credibility condition, and determine the target arrival time of the target student to the target classroom, and issue a campus security warning based on abnormal students who have not arrived at the target classroom within the target arrival time.

[0106] In some examples of this embodiment, the analysis module 33 is specifically configured to: extract the node connections between adjacent network access points in the physical space based on static mapping of the campus plane, and construct an initialized undirected static adjacency topology graph; based on the undirected static adjacency topology graph and the personalized path map, predict the shortest time data from the current location to the target classroom, taking the target student's current location as the starting point and the target classroom's location as the ending point, and determine the target movement route corresponding to the shortest time data; based on the target student's current movement route and the distribution of the target movement route in the personalized path map, extract the current network access point sequence corresponding to the current movement route and the target network access point corresponding to the target movement route. The sequence is analyzed based on the access order and access quantity information corresponding to the current network access point in the current network access point sequence and the target network access point in the target network access point sequence, respectively. The overlap information between the current and target network access points is analyzed to evaluate the overlap between the current and target movement routes. Based on the overlap information between the current and target network access points, the length of the longest common subsequence that overlaps with the target network access point in the current network access point is determined. Based on the length of the longest common subsequence, the difference information between the current and target network access points is determined. Based on the difference information, the first movement intention of the target student under the current movement route is analyzed.

[0107] In some examples of this embodiment, the analysis module 33 is further configured to perform path grid division on the personalized path map, extract the target path grid containing the target student's movement trajectory from the divided path grids, and generate a path grid sequence corresponding to the target path grid based on the target student's movement order; analyze the personalized movement information of the target student moving in the target path grid based on the number of times the target student moves in the target path grid and the path grid sequence, and evaluate the first probability information of the target student moving to the target classroom based on the target movement direction based on the personalized movement information; determine the first physical space vector of the target student reaching the target classroom from the current position based on the target movement route and the second physical space vector of the target student reaching the target classroom from the current position based on the current movement route based on the undirected static adjacency topology graph and the personalized path map; update the first probability information based on the orientation comparison information between the target movement direction corresponding to the first physical space vector and the current movement direction corresponding to the second physical space vector to obtain the second probability information of the target student moving to the target classroom based on the current movement direction, and analyze the second movement intention of the target student in the current movement direction based on the second probability information.

[0108] In some examples of this embodiment, the analysis module 33 is further configured to compare the directional similarity between the target movement direction and the current movement direction, and analyze the directional alignment data between the target student's current movement direction and the target movement direction based on the directional comparison information obtained from the similarity; construct a target probability matrix for the target student to move to the target classroom based on the target movement direction based on the first probability information, wherein the probability matrix represents the correlation between the movement direction and the movement probability of the target student moving in multiple path grids; update the correlation between the movement direction and the movement probability of the target student moving to the target classroom based on the directional alignment data in the target probability matrix to obtain the current probability matrix for the target student moving to the target classroom based on the current movement direction; extract the target path grid containing the target student's movement trajectory from multiple path grids, and perform fusion processing on the target probability data corresponding to the target path grid in the current probability matrix based on the grid state transition information of the target student from the current position to the target classroom to obtain the second probability information for the target student moving to the target classroom based on the current movement direction, and analyze the second movement intention of the target student in the current movement direction based on the second probability information.

[0109] In some examples of this embodiment, the generation module 34 is specifically configured to analyze the target student's movement speed on the current route based on the personalized path map, and obtain the effective average time data corresponding to multiple movement segments on the current route; fuse the effective average time data corresponding to multiple movement segments to obtain the total time data of the target student's movement on the current route, and predict the time for the target student to arrive at the target classroom based on the total time data and the elastic time window corresponding to the current route, to obtain the target arrival time of the target student; if the target student does not arrive at the target classroom within the target arrival time, determine whether there is student information for other students besides the target student who did not arrive at the target classroom within the actual arrival time based on the target student's actual arrival time; if there is no student information, update the target student's attendance information to abnormal attendance information; if there is student information, perform route analysis on the movement route corresponding to the student who did not arrive based on the personalized path map corresponding to the student information, and issue a campus safety warning based on the route analysis results.

[0110] In some examples of this embodiment, the generation module 34 is further configured to, when student information exists, determine the non-arrived travel routes corresponding to the non-arrived students based on the personalized path maps corresponding to the non-arrived students; analyze the student aggregation degree corresponding to the non-arrived travel routes based on the number of students accessing the network access points corresponding to the non-arrived travel routes and the standard number of students accessing the network access points corresponding to the non-arrived travel routes; analyze the student mobility degree corresponding to the non-arrived travel routes based on the number of students accessing the network access points corresponding to the non-arrived travel routes and the number of students leaving the network access points corresponding to the non-arrived travel routes within the target time window; evaluate the route congestion situation corresponding to the non-arrived travel routes based on the student aggregation degree and student mobility degree corresponding to the non-arrived travel routes; and, if the non-arrived travel routes are abnormally congested, issue campus safety warnings based on the non-arrived travel routes.

[0111] In some examples of this embodiment, the acquisition module 31 is specifically configured to acquire a set of movement routes of the target student attending classes in multiple classrooms, and perform route analysis on the movement routes in the set to obtain multiple network access points corresponding to the target student, as well as time data and step data of movement between multiple network access points; analyze the access time and departure time of the target student between adjacent access points based on the time data, and analyze the situation based on the time difference between the access time and departure time; analyze the signal change and movement step situation between adjacent access points based on the signal timing logs and pedometer timing logs of multiple network access points to obtain movement time data, signal change data, and movement step data between adjacent access points; filter movement routes from the set of movement routes whose movement time data meets the time span condition, whose signal change data meets the slope gradient condition, and whose movement step data meets the continuous physical kinetic energy output condition, and determine the filtered movement routes as valid routes; map the valid movement routes in physical space to obtain multiple network access points included in the valid routes, and form a set of valid routes based on the physical space connection relationship between multiple network access points.

[0112] In some examples of this embodiment, the construction module 32 is specifically configured to analyze the movement trajectory and movement time habits of the target student moving between multiple network access points based on the set of effective routes, to obtain personalized movement information of the target student attending classes in multiple classrooms; based on the personalized movement information and the physical spatial connection relationship between network access points, analyze the movement order of the target student moving between multiple network access points, to obtain multiple effective movement paths between adjacent network access points; based on the personalized movement information, analyze the movement time of the target student moving between multiple network access points, determine the time consumption data of the target student moving based on multiple effective movement paths, and generate time data of multiple effective movement paths based on the time consumption data; using multiple network access points as nodes and multiple effective movement paths as edges, generate a basic path map of the target student attending classes in multiple classrooms, and add time weights as attribute parameters of the edges in the basic path map to obtain a personalized path map of the target student attending classes in multiple classrooms.

[0113] Based on the above, Figure 1 and Figure 2 Accordingly, this embodiment also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method. Figure 1 and Figure 2 The method shown.

[0114] Based on this understanding, the technical solution of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as CD-ROM, USB flash drive, mobile hard drive, etc.) and includes several instructions to cause a computer device (such as personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of this application.

[0115] like Figure 4 The diagram shown is a hardware structure schematic of an electronic device according to the present invention, comprising: At least one processor 401; and, Memory 402 is communicatively connected to at least one processor 401; wherein, The memory 402 stores instructions that can be executed by at least one processor, which enables the at least one processor to perform the attendance information generation method as described above.

[0116] Figure 4 Take a processor 401 as an example.

[0117] The electronic device may also include an input device 403 and a display device 404.

[0118] The processor 401, memory 402, input device 403, and display device 404 can be connected via a bus or other means. Figure 4 Taking the example of a connection between China and Israel via a bus.

[0119] Memory 402, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the attendance information generation method in the embodiments of this application, for example, Figure 1 and Figure 2 The method flow is shown. The processor 401 executes various functional applications and data processing by running non-volatile software programs, instructions, and modules stored in the memory 402, thereby realizing the attendance information generation method in the above embodiment.

[0120] The memory 402 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created according to the use of the attendance information generation method. Furthermore, the memory 402 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 402 may optionally include memory remotely located relative to the processor 401, and these remote memories may be connected via a network to the apparatus performing the attendance information generation method. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0121] Input device 403 can receive user clicks and generate signal inputs related to user settings and function control of the attendance information generation method. Display device 404 may include display devices such as a display screen.

[0122] One or more modules are stored in memory 402, and when run by one or more processors 401, the attendance information generation method in any of the above method embodiments is executed.

[0123] Optionally, the aforementioned physical devices may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB interfaces, card reader interfaces, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Wi-Fi interfaces), etc.

[0124] Those skilled in the art will understand that the physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0125] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the aforementioned physical device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software in the information processing physical device.

[0126] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms, or it can be implemented by hardware. By applying the solution of this embodiment, compared with the prior art, this embodiment obtains a set of movement routes of the target students and filters effective movement routes based on multi-dimensional movement data, thus achieving effective filtering of movement routes; by analyzing movement trajectories and habits and constructing personalized path maps, it provides a personalized data foundation for predicting the route and probability of the target students reaching the target classroom; by determining the target classroom based on the personalized path map and analyzing the first and second movement intentions, it improves the reliability of movement intention recognition; by analyzing the credibility of the target based on dual movement intentions and generating attendance information, it achieves automatic attendance for the target students, improving the accuracy of attendance information generation; and by issuing campus security warnings based on abnormal students who have not arrived at the target classroom within the target arrival time, it can achieve campus security. Real-time monitoring and early warning; improving the accuracy of route matching and intent determination by constructing a static adjacency topology graph and analyzing the first movement intent based on the longest common subsequence; improving the accuracy of target classroom arrival probability calculation and intent determination by updating the probability matrix based on orientation alignment data and fusing grid transfer probabilities; achieving accurate identification of abnormal attendance by analyzing effective average time consumption and combining it with flexible time windows to predict target arrival time; achieving real-time monitoring of campus path status by analyzing student gathering and mobility and issuing abnormal congestion warnings; and improving the matching degree between path maps and students' personalized class-hopping habits by constructing personalized path maps based on effective routes and time weights and using the switching of target students between different network access points to reflect the movement of target students in various areas.

[0127] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0128] The above are merely specific embodiments of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to these embodiments, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for generating attendance information, characterized in that, include: Obtain the set of movement routes of the target student in multiple classrooms, and filter the effective movement routes of the target student based on the multi-dimensional movement data of the target student to obtain the effective route set; Based on the analysis of the effective route set, the movement trajectory and movement habits of the target students are analyzed to obtain personalized movement information of the target students attending classes in multiple classrooms, and a personalized path map of the target students attending classes in multiple classrooms is constructed based on the personalized movement information. Based on the network access point accessed by the target student in the personalized path map and the connection edge of the network access point in physical space, the target classroom where the target student needs to attend class is determined from the personalized path map. Based on the target student's current movement route and the target movement route corresponding to the target student moving to the target classroom, the first movement intention of the target student under the current movement route is analyzed. Based on the target student's current movement direction and the target movement direction corresponding to the target student moving to the target classroom, the second movement intention of the target student under the current movement direction is analyzed. Based on the first movement intention and the second movement intention, the credibility of the target student moving to the target classroom is analyzed. If the credibility of the target student meets the credibility condition, the attendance information of the target student moving to the target classroom is generated, and the target arrival time of the target student to the target classroom is determined. Based on the abnormal students who have not arrived at the target classroom within the target arrival time, campus security warnings are issued.

2. The method according to claim 1, characterized in that, The step of determining the target classroom where the target student needs to attend class based on the network access point accessed by the target student in the personalized path map and the physical connection edges of the network access point, and analyzing the target student's first movement intention under the current movement route based on the target student's current movement route and the target movement route corresponding to the target student moving to the target classroom, includes: Based on the static mapping of the campus plane, the node connections of adjacent network access points in the physical space are extracted to construct an initialized undirected static adjacency topology graph. Based on the undirected static adjacency topology graph and the personalized path map, taking the current location of the target student as the starting point and the location of the target classroom as the ending point, the shortest time data from the current location to the target classroom is predicted, and the target movement route corresponding to the shortest time data is determined. Based on the current movement route of the target student and the distribution of the target movement route in the personalized path map, the current network access point sequence corresponding to the current movement route and the target network access point sequence corresponding to the target movement route are extracted. Based on the access order information and access quantity information corresponding to the current network access point in the current network access point sequence and the target network access point in the target network access point sequence, the access point overlap information of the current network access point and the target network access point is analyzed to evaluate the overlap between the current mobile route and the target mobile route. Based on the overlap information of the current network access point and the target network access point, the length of the longest common subsequence that overlaps with the target network access point in the current network access point is determined, and the difference information between the current network access point and the target network access point is determined based on the length of the longest common subsequence. Based on the difference information, the first movement intention of the target student under the current movement route is analyzed.

3. The method according to claim 1, characterized in that, Based on the target student's current movement direction and the target movement direction corresponding to the target student's movement to the target classroom, the second movement intention of the target student under the current movement direction is analyzed, including: The personalized path map is divided into path grids. Target path grids containing the movement trajectory of the target student are extracted from the multiple divided path grids. A path grid sequence corresponding to the target path grid is generated based on the movement order of the target student. Based on the number of times the target student moves in the target path grid and the path grid sequence, the personalized movement information of the target student moving in the target path grid is analyzed, and based on the personalized movement information, the first probability information of the target student moving to the target classroom based on the target movement direction is evaluated; Based on the undirected static adjacency topology graph and the personalized path map, determine the first physical space vector of the target student from the current location to the target classroom based on the target movement route, and the second physical space vector of the target student from the current location to the target classroom based on the current movement route; Based on the orientation comparison information between the target movement direction corresponding to the first physical space vector and the current movement direction corresponding to the second physical space vector, the first probability information is updated to obtain the second probability information of the target student moving to the target classroom based on the current movement direction, and the second movement intention of the target student under the current movement direction is analyzed based on the second probability information.

4. The method according to claim 3, characterized in that, The step of updating the first probability information based on the orientation comparison information between the target movement direction corresponding to the first physical space vector and the current movement direction corresponding to the second physical space vector, to obtain second probability information of the target student moving to the target classroom based on the current movement direction, and analyzing the second movement intention of the target student under the current movement direction based on the second probability information, includes: The direction similarity between the target movement direction and the current movement direction is compared, and the azimuth alignment data between the current movement direction and the target movement direction of the target student is analyzed based on the azimuth comparison information obtained from the similarity. Based on the first probability information, a target probability matrix is ​​constructed for the target student to move to the target classroom based on the target movement direction. The probability matrix represents the relationship between the movement direction and the movement probability of the target student moving in the multiple path grids. Based on the orientation alignment data, the correlation between the movement orientation and movement probability of the target student moving to the target classroom based on the target movement direction in the target probability matrix is ​​updated to obtain the current probability matrix of the target student moving to the target classroom based on the current movement direction; Based on the multiple path grids, the target path grid containing the movement trajectory of the target student is extracted. According to the grid state transition information of the target student from the current position to the target classroom, the target probability data corresponding to the target path grid in the current probability matrix is ​​fused to obtain the second probability information of the target student moving to the target classroom based on the current movement direction. Based on the second probability information, the second movement intention of the target student under the current movement direction is analyzed.

5. The method according to claim 1, characterized in that, Determine the target arrival time of the target student to the target classroom, and issue campus safety alerts based on abnormal students who have not arrived at the target classroom within the target arrival time, including: Based on the personalized path map, the movement speed of the target student in the current movement route is analyzed to obtain the effective average time data corresponding to multiple movement segments of the target student in the current movement route; The effective average time data corresponding to the multiple movement segments are fused to obtain the total time data of the target student moving on the current movement route. Based on the total time data and the elastic time window corresponding to the current movement route, the time for the target student to arrive at the target classroom is predicted to obtain the target arrival time of the target student to arrive at the target classroom. If the target student does not arrive at the target classroom within the target arrival time, based on the actual arrival time of the target student, determine whether there is student information for other students besides the target student who did not arrive at the target classroom within the actual arrival time; If the student information does not exist, update the attendance information of the target student to abnormal attendance information; If the student information exists, the system analyzes the movement routes of the students who have not yet arrived based on the personalized path map corresponding to the student information, and issues campus safety warnings based on the route analysis results.

6. The method according to claim 5, characterized in that, In the case of the existence of the student information, based on the personalized path map corresponding to the student information for the unreached student, route analysis is performed on the movement route of the unreached student, and campus safety early warning is issued based on the route analysis results, including: If the student information exists, the unreached movement routes corresponding to the unreached students are determined based on the personalized path map corresponding to the unreached students. Based on the number of students accessing the network access points corresponding to the unreached mobile routes and the standard number of students accessing the network access points corresponding to the unreached mobile routes, the degree of student aggregation corresponding to the unreached mobile routes is analyzed. Based on the number of students accessing and leaving the network access points corresponding to the non-reached mobile routes within the target time window, analyze the student mobility corresponding to the non-reached mobile routes. Based on the degree of student gathering and the degree of student mobility corresponding to the unreached routes, the congestion of the routes corresponding to the unreached routes is evaluated, and in the case of abnormal congestion of the unreached routes, campus safety warnings are issued based on the unreached routes.

7. The method according to claim 1, characterized in that, The process involves acquiring a set of movement routes for target students attending classes in multiple classrooms, and then filtering the effective movement routes based on the multi-dimensional movement data of the target students to obtain a set of effective routes, including: Obtain a set of movement routes of the target student in multiple classrooms, and perform route analysis on the movement routes in the set to obtain multiple network access points corresponding to the target student, as well as time data and step data of movement between the multiple network access points; Based on the time data, the access time and departure time of the target student between adjacent access points are analyzed, and the situation is analyzed based on the time difference between the access time and the departure time. Based on the signal timing logs and pedometer timing logs of the multiple network access points, the signal changes and movement steps between adjacent access points are analyzed to obtain movement time data, signal change data, and movement step data between adjacent access points. From the set of movement routes, select movement routes whose movement time data meets the time span condition, whose signal change data meets the slope gradient condition, and whose movement step data meets the continuous physical kinetic energy output condition, and determine the selected movement routes as valid routes. The effective movement routes are mapped in the physical space to obtain multiple network access points included in the effective routes, and the effective routes are combined into the effective route set based on the physical space connection relationships between the multiple network access points.

8. The method according to claim 1, characterized in that, The process involves analyzing the target student's movement trajectory and habits based on the set of effective routes to obtain personalized movement information for the target student attending classes in multiple classrooms. A personalized path map for the target student attending classes in these multiple classrooms is then constructed based on this personalized movement information, including: Based on the set of effective routes, the movement trajectory and movement time habits of the target student when moving between the multiple network access points are analyzed to obtain the personalized movement information of the target student when attending classes in multiple classrooms. Based on the personalized movement information and the physical spatial connection relationship between the network access points, the movement order of the target student at the multiple network access points is analyzed to obtain multiple effective movement paths between adjacent network access points. Based on the personalized mobility information, the movement time of the target student at the multiple network access points is analyzed to determine the time consumption data of the target student moving based on multiple effective movement paths, and the time data of the multiple effective movement paths is generated based on the time consumption data. By using the multiple network access points as nodes and the multiple valid movement paths as edges, a basic path map for the target student to attend classes in the multiple classrooms is generated. Time weights are added to the basic path map as attribute parameters of the edges to obtain a personalized path map for the target student to attend classes in the multiple classrooms.

9. An attendance information generation device, characterized in that, include: The acquisition module is configured to acquire a set of movement routes of the target student in multiple classrooms, and filter the effective movement routes of the target student based on the multi-dimensional movement data of the target student to obtain a set of effective routes. The construction module is configured to analyze the movement trajectory and movement habits of the target student based on the set of effective routes, obtain personalized movement information of the target student attending classes in multiple classrooms, and construct a personalized path map of the target student attending classes in multiple classrooms based on the personalized movement information. The analysis module is configured to determine the target classroom where the target student needs to attend class based on the network access point accessed by the target student in the personalized path map and the connection edge of the network access point in physical space; analyze the first movement intention of the target student under the current movement route based on the target student's current movement route and the target movement route corresponding to the target student moving to the target classroom; and analyze the second movement intention of the target student under the current movement direction based on the target student's current movement direction and the target movement direction corresponding to the target student moving to the target classroom. The generation module is configured to analyze the target credibility of the target student moving to the target classroom based on the first movement intention and the second movement intention, and generate attendance information of the target student moving to the target classroom when the target credibility meets the credibility condition, and determine the target arrival time of the target student to the target classroom, and issue a campus security warning based on abnormal students who have not arrived at the target classroom within the target arrival time.

10. An electronic device comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 8.

Images