Campus non-motor vehicle positioning management method and system

Abstract

The invention provides a campus non-motor vehicle positioning management method and system, and relates to the field of campus non-motor vehicle management systems, and the method comprises the steps: collecting student vehicle use related data; according to the student vehicle usage related data, through a clustering algorithm, identifying a student behavior mode; according to the student behavior mode, through a long-short-term memory network, determining a student movement trend; according to the moving trends of the students, through a time sequence prediction model, vehicle demands of all time periods and places in the campus are predicted; and adjusting the distribution position of the vehicles through a resource optimization algorithm according to the predicted vehicle demands of all time periods and places in the campus. According to the invention, the dynamic deployment efficiency and accuracy of vehicles can be improved, the security and privacy of user data are ensured, and more efficient, more economical and safer campus non-motor vehicle management is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of campus non-motor vehicle management systems, and in particular to a campus non-motor vehicle positioning management method and system. Background Art

[0002] Campus non-motor vehicles refer to small vehicles used by students, faculty and staff on campus that do not rely on engine power or use light electric assistance. These vehicles are mainly used for short-distance commuting or daily movement within the campus. They are environmentally friendly, convenient and economical. Campus non-motor vehicle positioning refers to the process of using technical means to obtain real-time location information of non-motor vehicles (such as bicycles, electric vehicles, scooters, etc.) on campus for effective management, scheduling and monitoring.

[0003] With the increase in campus population density and the improvement of environmental sustainability requirements, non-motor vehicles, especially bicycles and electric scooters, have become the main means of transportation for students and faculty on many campuses. However, the management challenges that come with it are also becoming increasingly prominent, mainly including uneven vehicle distribution, low utilization efficiency, safety hazards and vehicle losses. Therefore, the management of campus non-motor vehicles is of great significance to the dynamic allocation efficiency and accuracy of vehicles, the security and privacy of user data, and the safe management of campus non-motor vehicles.

[0004] At present, most campus non-motor vehicle management mainly relies on traditional manual management mode, such as setting fixed parking spots and manually registering vehicle usage. This method is not only labor-intensive, but also inefficient and difficult to cope with vehicle demand during peak hours. In addition, with the development of technology, some campuses have begun to try to use vehicle tracking systems based on RFID or GPS to better monitor vehicle location and usage status. Although these technologies have improved vehicle management to a certain extent, there are still shortcomings such as untimely data processing, high costs and privacy issues. Using the Internet of Things, big data and artificial intelligence technologies, there are still inaccurate demand forecasts, resulting in a mismatch between vehicle distribution and actual demand, and the inability to achieve optimal resource allocation. In addition, many systems do not process data and respond to user needs quickly enough to meet users' immediate use needs. Deploying high-tech vehicle management systems is often costly and involves collecting a large amount of user data, which leads to privacy leaks and other issues. Summary of the invention

[0005] In order to solve the problems existing in the prior art of utilizing the Internet of Things, big data and artificial intelligence technologies, there is still inaccurate demand forecasting, resulting in a mismatch between vehicle distribution and actual demand, and the inability to achieve optimal resource allocation. In addition, many systems are not fast enough to process data and respond to user needs, and cannot meet users' immediate usage needs. The deployment of high-tech vehicle management systems is often costly and involves collecting a large amount of user data, thereby causing technical problems such as privacy leakage. The present invention provides a campus non-motor vehicle positioning management method and system.

[0006] The technical solution provided by the embodiment of the present invention is as follows:

[0007] First aspect

[0008] An embodiment of the present invention provides a campus non-motor vehicle positioning management method, comprising:

[0009] S1: Collect data related to students’ vehicle use;

[0010] S2: Based on the data related to students’ vehicle usage, the clustering algorithm is used to identify students’ behavior patterns;

[0011] S3: Determine the student movement trend based on the student behavior pattern through the long short-term memory network;

[0012] S4: Based on the student mobility trends, the vehicle demand at different time periods and locations on campus is predicted through a time series prediction model;

[0013] S5: According to the predicted vehicle demand at different time periods and locations on campus, the distribution of vehicles is adjusted through resource optimization algorithm.

[0014] Second aspect

[0015] An embodiment of the present invention provides a campus non-motor vehicle positioning management system, comprising:

[0016] processor;

[0017] A memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the campus non-motor vehicle positioning management method as described in the first aspect is implemented.

[0018] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0019] In the present invention, the method collects data related to vehicle use, analyzes students' behavior patterns based on clustering algorithms and long short-term memory networks (LSTM), thereby predicting students' mobility trends, and then predicts vehicle demand at various time periods and locations on campus through the time series prediction model ARIMA, and then combines the resource optimization algorithm to adjust the distribution location and vehicle demand of vehicles, provide decision support for vehicle scheduling, ensure that vehicle distribution is highly matched with student demand, optimize resource utilization, and reduce vehicle idle time. The present invention optimizes prediction and scheduling algorithms by integrating machine learning and data analysis technology, improves the efficiency and accuracy of dynamic vehicle allocation, achieves the optimal configuration of resources, meets users' immediate use needs, and reduces system deployment and maintenance costs, improves system scalability and flexibility, and improves user experience and data security. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 A schematic diagram of a flow chart of a campus non-motor vehicle positioning management method provided by an embodiment of the present invention;

[0022] Figure 2 A schematic diagram of the structure of a campus non-motor vehicle positioning management method provided by an embodiment of the present invention;

[0023] Figure 3 A schematic diagram of the structure of a campus non-motor vehicle positioning management system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0025] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0026] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0027] Reference Manual Attached Figure 1 , showing a flow chart of a campus non-motor vehicle positioning management method provided by an embodiment of the present invention.

[0028] The embodiment of the present invention provides a campus non-motor vehicle positioning management method, which can be implemented by a campus non-motor vehicle positioning management device, and the campus non-motor vehicle positioning management device can be a terminal or a server. The processing flow of the campus non-motor vehicle positioning management method may include the following steps:

[0029] S1: Collect data related to students’ vehicle usage.

[0030] Among them, student vehicle usage data includes various information about students’ use of non-motor vehicles on campus. By comprehensively collecting student vehicle usage data, high-quality input is provided for subsequent behavior modeling and demand forecasting. The diversity of these data (such as time, location, behavior, etc.) can accurately reflect students’ actual usage habits and demand trends, thereby improving the accuracy of the forecast.

[0031] In a possible implementation, the student vehicle usage related data includes: student class schedules, historical location data, vehicle usage records, weather conditions, and special campus events.

[0032] Reference Manual Attached Figure 2 , showing a structural schematic diagram of a campus non-motor vehicle positioning management method provided by an embodiment of the present invention.

[0033] Figure 2 In the process of building a model, collecting data is the first step in building a model, including students' class schedules, historical location data, vehicle usage records and other relevant information (such as weather conditions, special campus events, etc.). These data provide the necessary input for the model to help it more accurately capture the dynamic characteristics of student behavior.

[0034] Establishing a student behavior model is a basic step that provides core data support for the entire system. This model predicts students' mobility trends and vehicle needs by analyzing their class schedules, historical location data, and vehicle usage habits. The output of the model directly affects the second step - dynamically adjusting vehicle distribution, because the optimization of vehicle allocation needs to be based on students' predicted behavior and needs. In addition, the data from the student behavior model can also assist the third step, the real-time feedback and early warning system, by predicting and warning of possible abnormal or irregular behaviors through pattern recognition.

[0035] Dynamically adjusting vehicle distribution as a direct action in response to the student behavior model requires optimizing the geographical distribution of vehicles based on predicted data. The implementation effect of this step will directly affect the effectiveness of the fourth step interactive intelligent interface, because the interface needs to display the latest and most accurate vehicle distribution information to users. At the same time, dynamic adjustment also relies on the real-time feedback and early warning system in the third step to adjust its strategy, such as quickly adjusting the vehicle position according to real-time data to respond to emergencies.

[0036] The real-time feedback and early warning system monitors the behavior patterns derived from the student behavior model in the first step and uses this information to monitor abnormal situations in real time. The output of this system helps to dynamically adjust the vehicle distribution in the second step, especially when dealing with emergencies and immediate needs. In addition, the feedback from the early warning system can also be provided to the behavior correction and incentive mechanism in the fifth step to adjust the incentives and ensure that the incentives can solve the problem in a targeted manner. The interactive intelligent interface is the front end that users directly contact. It not only displays the results of the dynamic adjustment of the vehicle distribution in the second step, but also provides user feedback and behavior data to the system. These user data are critical for refining the student behavior model in the first step. In addition, user interaction and feedback on the interface can be used as input to the behavior correction and incentive mechanism in the fifth step to help the system better understand which incentives are most effective. Behavior correction and incentive mechanisms directly affect students' behavior. This influence is fed back to the system through user activities on the interactive intelligent interface. Successful behavior correction will optimize the accuracy of the student behavior model and improve the efficiency of dynamic vehicle distribution. At the same time, the results of behavior correction will also be monitored through the real-time feedback and early warning system to ensure that incentives can be adjusted and optimized in real time.

[0037] It should be noted that by collecting students' class schedules, historical location data and vehicle usage habits, a personalized student behavior model is established. The model uses clustering algorithms and long short-term memory networks (LSTM) to analyze students' behavior patterns, predict students' mobility trends and vehicle needs, and provide decision support for vehicle scheduling. Secondly, according to the output of the behavior model, the system dynamically adjusts the distribution of vehicles to meet real-time and predicted needs. The adjustment of vehicle distribution depends on time series prediction and resource optimization algorithms to ensure efficient use of vehicles. Furthermore, the real-time feedback and early warning system monitors vehicle usage status and student behavior through anomaly detection algorithms, identifies and handles abnormal situations in a timely manner, and improves the response speed and safety of the system. The interactive intelligent interface allows students to view nearby available vehicles, make reservations for vehicles, and view recommended routes, enhancing user experience and interactivity. Finally, the behavior correction and incentive mechanism encourages students to abide by vehicle usage rules, such as correct parking, through reward systems such as point rewards and coupons, thereby optimizing students' behavior patterns. These measures, combined with social functions and gamification design, effectively stimulate students' enthusiasm for participation, improve usage habits, and effectively solve the problems of vehicle resource waste and insufficient management.

[0038] S2: Based on the data related to students’ vehicle usage, identify students’ behavior patterns through clustering algorithm.

[0039] Among them, clustering algorithm is a data analysis method used to group data points with similar characteristics. Here, it means dividing student behavior data into different pattern categories through the weighted K-means algorithm. Student behavior patterns refer to the activity patterns and vehicle usage habits of students on campus, such as commuting in fixed time periods, high-frequency vehicle borrowing and returning, and usage preferences in specific activity areas.

[0040] It should be noted that the use of clustering algorithms can quickly and accurately identify students' behavior patterns, providing an important basis for subsequent mobility trend prediction and vehicle demand analysis. Through clustering algorithms, complex behavioral data can be simplified into clear pattern categories, thereby helping the system understand students' usage habits and travel patterns. This classification can capture the characteristics of different groups (such as morning and evening commuting peaks, special area demand), and improve the system's demand forecasting capabilities.

[0041] In a possible implementation manner, S2 is specifically:

[0042] Identify student behavior patterns using the weighted K-means clustering algorithm:

[0043]

[0044] Among them, S represents the objective function value, k represents the total number of categories of behavior patterns, and C i represents the i-th behavior pattern category, wi represents the weight associated with the data point x contained in the ith behavior pattern category, x represents the data point in the ith behavior pattern category, μ i represents the weighted average position of all points in the i-th behavior pattern category, and || || represents the norm operation.

[0045] S3: Based on the students’ behavior patterns, determine the students’ movement trends through the long short-term memory network.

[0046] Among them, the long short-term memory network is a special recurrent neural network that solves the long-term dependency problem through gating mechanisms (such as forget gate, input gate, and output gate) and is used for the prediction of time series data. The student mobility trend is the potential movement pattern of students' non-motor vehicles on campus and possible travel needs in the future, such as the frequency of vehicle use on common routes or activity locations during a certain period of time.

[0047] Specifically, this network learns students' behavior patterns through historical data, can consider long-term dependencies in time series, and predict students' future locations and vehicle usage needs. Each unit of the long short-term memory network contains multiple gating mechanisms (forget gate, input gate, output gate), which determine what information the network retains, discards, and outputs at each time step. In this way, the long short-term memory network can effectively extract features from complex input sequences and make accurate time series predictions.

[0048] It should be noted that through the long short-term memory network, the long-term and short-term characteristics of time series data can be fully utilized to accurately predict students' future mobility trends. Compared with traditional prediction methods, the long short-term memory network can effectively capture the long-term dependencies in students' behaviors, such as regular travel patterns, and the impact of short-term emergencies (such as temporary activities). By combining multiple input data (class schedule, location, weather, etc.), this method not only improves the prediction accuracy, but also can dynamically adapt to changes in students' behavior, providing a scientific basis for subsequent vehicle distribution adjustments and resource scheduling.

[0049] In a possible implementation, S3 is specifically:

[0050] According to different behavior patterns, the student movement trend is determined through the long short-term memory network:

[0051] X t =[C t ;P t-1 ; E t-1 ]

[0052] f t =σ(W f [h t-1 ,X t]+b f )(Forget Gate)

[0053] i t =σ(W i [h t-1 ,X t ]+b i )(Input gate)

[0054] (Candidate unit status)

[0055] o t =σ(W o [h t-1 ,X t ]+b o )(Output gate)

[0056] (Unit status update)

[0057] h t =o t ⊙tanh(c t )(Output Status)

[0058] Among them, X t represents the input at time t, C t represents the course schedule data input at time t, P t-1 represents the position data input at time t-1, E t-1 represents the additional features input at time t-1 that affect students’ behavior and location selection, f t represents the forget gate, σ represents the sigmoid activation function, h t-1 represents the hidden state at time t-1, i t represents the input gate, represents the possible new state at time t, tanh represents the hyperbolic tangent function, o t represents the output gate, c t represents the cell state that is retained after considering the past state and the current candidate state, C t-1 represents the course schedule data input at time t-1, h t represents the output of the LSTM network at time t, which is used to predict the student movement trend. It represents the dot product operation, W f , W i , W o and W c Both represent the weight matrices used to control the input of each gate and the influence of the past state on the current state, and b f 、b i 、b o and b c Both represent bias terms used to adjust the gating and activation levels of candidate states.

[0059] It should be noted that this network structure allows the model to use past information (such as previous location and additional environmental factors) to predict students' future locations on campus, which is crucial for understanding students' mobility patterns, predicting high-demand locations, and optimizing the distribution of non-motorized vehicles. By learning patterns extracted from historical behavior, this model can dynamically adapt to changes in student behavior and effectively predict future behavioral trends, thereby achieving more precise and effective campus management.

[0060] S4: Based on the student mobility trends, the vehicle demand at different time periods and locations on campus is predicted through a time series prediction model.

[0061] Among them, the time series prediction model is a mathematical model used to process and predict time series data. The main model used here is ARIMA (AutoRegressive Integrated Moving Average), which is used to predict future vehicle demand based on historical data. Vehicle demand refers to the demand for non-motor vehicles at various locations and time periods on campus, which involves predicting how many non-motor vehicles will be needed at a specific time and location to meet the students' usage needs.

[0062] It should be noted that time series forecasting models (such as ARIMA) can be used to transform complex historical data and student mobility trends into specific vehicle demand forecasts, thereby effectively planning vehicle resources. Compared with relying solely on experience or simple statistical analysis, time series models can take into account seasonal and trend changes in data and generate more accurate demand forecasts. This ARIMA model combines the trends and random fluctuations of historical demand data to predict future demand by integrating historical data. The parameters of the model are usually obtained through statistical analysis of historical data to ensure the accuracy of the prediction.

[0063] In a possible implementation manner, S4 is specifically:

[0064] By integrating the ARIMA model, the vehicle demand at different time periods and locations on campus is predicted:

[0065] Y t =α+φ1Y t-1 +φ2Y t-2 +…+φ p Y t-p +θ1∈ t-1 +θ2∈ t-2 +…+θ q ∈ t-q +∈ t

[0066] Among them, Y trepresents the predicted vehicle demand at time t, Y t-1 represents the predicted vehicle demand at time t-1, Y t-2 represents the predicted vehicle demand at time t-2, α represents the constant term of the integrated ARIMA model, φ1,…,φ p denotes the autoregressive parameters, θ1,…,θ p represents the moving average parameter, ∈ t-1 ,…,∈ t-q represents the error term of the first q time points, ∈ t Represents the prediction error at the current time t.

[0067] Specifically, by using the integrated ARIMA model, the system can accurately predict vehicle demand in various time periods and locations in the future. This prediction takes into account the trend of historical demand, seasonal factors and random fluctuations, providing a scientific basis for vehicle scheduling. Through the autoregressive and moving average parameters obtained through historical data analysis, the model can effectively capture the dynamic changes in demand and predict future demand peaks and troughs.

[0068] S5: According to the predicted vehicle demand at different time periods and locations on campus, the distribution of vehicles is adjusted through resource optimization algorithm.

[0069] Among them, resource optimization algorithm refers to the algorithm used to adjust and optimize resource allocation. Here it specifically refers to the algorithm for adjusting the distribution position of vehicles in the management of non-motor vehicles on campus, such as linear programming or nonlinear programming, to ensure that the vehicle distribution matches the actual needs. The distribution position of the vehicle refers to the specific placement location of each non-motor vehicle on campus.

[0070] It should be noted that in this way, the method of dynamically adjusting vehicle distribution not only responds quickly based on real-time data, but also adjusts resources in a predictable manner, thereby increasing vehicle supply during peak demand and recovering and maintaining vehicles during low demand. This strategy significantly improves the overall operational efficiency of non-motor vehicles on campus and student satisfaction.

[0071] In a possible implementation, S5 is specifically:

[0072] According to the prediction results, the distribution of vehicles is dynamically adjusted through nonlinear programming algorithm:

[0073]

[0074] Among them, c ij represents the dispatching cost from the i-th vehicle to the j-th demand point, i = 1, ..., n, n represents the total number of vehicles, j = 1, ..., m, m represents the total number of demand points, x ij The decision variable representing whether to dispatch the i-th vehicle to the j-th demand point, x ij=0 means no scheduling, x ij =1 means scheduling, Indicates that the demand constraints are met. represents the supply restriction constraint, b j represents the vehicle demand of the jth demand point in the forecast period, d i Represents the number of available vehicles at the current time point.

[0075] Specifically, a nonlinear programming method is used to optimize the distribution of vehicles. This optimization process not only considers cost minimization, but also ensures that the supply of vehicles can meet the predicted demand. By setting specific constraints, such as vehicle supply restrictions and demand satisfaction standards, the optimization algorithm can ensure that all demand points are met while reducing the scheduling cost as much as possible.

[0076] In this optimization model, the goal is to achieve the optimal allocation of vehicle demand and supply by minimizing the total cost of vehicle scheduling. This model takes into account the cost of each vehicle to the demand point and the availability of the vehicle, ensuring that the scheduling cost is reduced as much as possible while meeting the needs of all demand points. During the optimization process, factors such as vehicle maintenance time and battery charge status may also be considered, which will affect the actual availability of the vehicle. The key to the resource optimization algorithm is its ability to dynamically adjust the distribution of vehicles and respond to immediate changes in demand. For example, if a certain area predicts that there will be a large demand for vehicles, the system will dispatch enough vehicles to the area in advance, while considering recycling and charging plans. This intelligent scheduling not only reduces the idle time of vehicles, but also improves the utilization rate of vehicles.

[0077] In a possible implementation, it further includes:

[0078] S6: Anomaly detection and early warning are performed through the isolation forest algorithm.

[0079] Among them, the isolation forest algorithm is particularly suitable for processing high-dimensional data and large-scale data sets, and can efficiently identify abnormal data points. The isolation forest "isolates" each observation point by constructing multiple random decision trees. Abnormal points are usually isolated earlier in the tree due to their different attributes, so their path length is shorter than that of normal points. This path length is used to calculate the anomaly score of each point. The higher the score, the more likely the point is to be an anomaly.

[0080] It should be noted that the isolation forest algorithm can be used to detect and warn of anomalies, and can quickly and accurately identify anomalies in vehicle use and distribution, such as abnormal vehicle movement, abuse, or excessive concentration. The isolation forest algorithm is particularly suitable for processing high-dimensional data and large-scale data sets. It is highly efficient and does not require supervised learning. It can analyze vehicle status in real time and trigger warnings.

[0081] In a possible implementation, S6 specifically includes:

[0082] S601: Determine the abnormal score of each data point using the isolation forest algorithm:

[0083]

[0084] Among them, score(x) represents the anomaly score of data point x, E[h(x)] represents the average path length of data point x in the isolation forest. The shorter the path length, the more likely the data point is an anomaly. c(n) represents the average path length of normal data when the sample size is n.

[0085] S602: Determine whether the abnormal score of each data point is greater than the dynamic threshold; if so, determine it as abnormal data and trigger an alarm; otherwise, continue monitoring.

[0086] Among them, data points refer to specific information records obtained by collecting various types of data (such as location, vehicle usage behavior, etc.). Each data point represents specific information at a specific time and state. The anomaly score is a value calculated by the isolation forest algorithm, which is used to measure the degree of abnormality of a data point. The higher the score, the greater the difference between the behavioral characteristics of the data point and other data, which may be an abnormal situation. The dynamic threshold is a real-time adjusted standard used to determine whether a data point is abnormal.

[0087] It should be noted that by comparing the anomaly score with the dynamic threshold, it is possible to flexibly and accurately determine which data points are abnormal, ensuring that abnormal situations are discovered and responded to in a timely manner. Unlike fixed thresholds, dynamic thresholds can be automatically adjusted according to historical data and changes in the current environment, significantly reducing the chances of false alarms and missed alarms, thereby improving the robustness and practicality of the system. The mechanism that triggers the alarm can promptly notify managers to take measures to prevent the problem from expanding, such as theft of non-motor vehicles, improper parking or system failures.

[0088] In a possible implementation manner, the dynamic threshold is specifically:

[0089]

[0090] Among them, θ(t) represents the dynamic threshold at time t, θ0 represents the standard threshold determined based on historical data when the system is initially set, that is, the baseline threshold, α represents the adjustment coefficient used to control the impact of historical abnormal changes on the current threshold, and δ i Represents the abnormal change at time i, i=1,…,t, t represents the total number of time.

[0091] Among them, the warning threshold is adjusted dynamically and can be appropriately adjusted according to the recent abnormal activities and the current state of the system to avoid excessive false positives or negative negatives.

[0092] It should be noted that in real-time feedback and early warning systems, dynamic adjustment of thresholds is key. This mechanism enables the system to adaptively adjust the warning threshold based on recent abnormal activities to reflect changes in the current environment or system status. For example, if a gradual increase in the anomaly score is observed at several consecutive time points, the system will automatically increase the threshold to reduce the possibility of false alarms. On the contrary, if the environment is stable, the system may lower the threshold to increase sensitivity to anomalies.

[0093] In the present invention, by real-time monitoring of data streams and using isolation forests for anomaly detection, the system can quickly identify unconventional vehicle usage patterns or student behaviors, such as unauthorized use of vehicles or parking in unexpected locations. Once these anomalies are detected, the system dynamically adjusts through the early warning mechanism and promptly issues alarms to management personnel, allowing them to respond quickly to resolve potential problems. In addition, the implementation of this system makes important contributions to maintaining campus safety, optimizing vehicle utilization, and improving student satisfaction. By reducing vehicle loss and abuse, schools can manage their resources more effectively while also protecting students from potential safety risks. In short, the real-time feedback and early warning system provides a powerful tool to enhance the efficiency and safety of campus non-motor vehicle management through advanced data analysis technology and intelligent threshold adjustment strategies.

[0094] In actual application, in the campus non-motor vehicle positioning management system, the interactive intelligent interface plays a vital role. It provides a user-friendly platform that enables students and administrators to view and manage vehicles in real time. This interface not only needs to display real-time data, but also needs to support interaction with users, such as booking vehicles, reporting problems and other functions.

[0095] Specifically, the interactive intelligent interface design includes:

[0096] Use React as the front-end framework and use Redux for state management:

[0097] state t = reducer(state t-1 ,action t )

[0098] Among them, state t Represents the application state at time t, reducer represents the core function in the Redux architecture, action t Represents an action generated by the user or the system at time t.

[0099] It should be noted that using React as the front-end framework makes it possible to develop complex single-page applications (SPA) due to its efficient update mechanism and componentized architecture. React allows developers to control component rendering through state management so that the interface responds to user interactions. Redux, as a state management library, helps manage the state in the application so that multiple components can share data while maintaining consistency and predictability of the state. WebSocket is used for real-time communication to maintain a continuous connection between the client and the server, allowing the application to receive and send data in real time, such as vehicle location updates, reservation status, etc.

[0100] Get vehicle location and status information from the server via WebSocket.

[0101] Specifically, the WebSocket connection is used to obtain vehicle location and status information from the server in real time, such as the number of available vehicles, current loan status, etc., and the map and vehicle information list are dynamically updated to display the real-time location and available status of the vehicle.

[0102] Design the user interaction interface based on the vehicle location and status information.

[0103] It should be noted that an intuitive user interface is provided, allowing users to easily reserve and manage vehicles. Responsive design is used to ensure that users have a good experience on various devices. Modern UI elements such as modal windows and sliding menus are used to enhance the user's interactive experience, such as making a reservation directly by clicking on the vehicle icon on the map. At the same time, the system design takes into account data security and privacy protection, ensuring that all communications are transmitted through encrypted transmission. The interface design allows new features to be added in the future, such as vehicle fault reporting, user rating systems, etc., to adapt to changing management needs and user expectations.

[0104] In short, the interactive intelligent interface not only improves the user's operational convenience and satisfaction, but also greatly improves the efficiency and effectiveness of the campus non-motor vehicle management system through real-time data processing and advanced user interaction technology. Through such a system, the school can better serve the campus community, optimize vehicle utilization, and reduce management costs and time.

[0105] In the present invention, in the campus non-motor vehicle positioning management system, behavior modification and incentive mechanisms play a key role, and their goal is to promote students to comply with vehicle use rules through rewards and incentives, thereby improving the overall efficiency of vehicle use and the sustainability of the system. This mechanism aims to change students' behavioral habits through positive incentives and encourage them to use vehicle resources more responsibly.

[0106] Specifically, the incentive mechanism is as follows:

[0107] Rewardt =Reward t-1 +f(actions,compliance)

[0108] Among them, Reward t Represents the total reward score of the student at time t, Reward t-1 represents the total reward score of the student at time t-1, and f(actions, compliance) represents the reward function that determines the reward based on the student’s specific actions and compliance with the rules.

[0109] It should be noted that this reward function is the core of the incentive system. It determines the reward score based on the user's specific behavior (such as returning the vehicle on time, parking the vehicle correctly, etc.) and compliance with the rules (such as complying with vehicle usage time and area restrictions). In this way, the system not only encourages positive behavior, but also provides specific rewards through point accumulation, such as discounts, priority, etc. The reward mechanism dynamically calculates the reward score generated by each behavior and updates the student's total reward in real time.

[0110] In the present invention, the system monitors students' vehicle usage in real time through integrated sensors and data tracking technology. These data are used to evaluate each student's behavior pattern, including the frequency of vehicle usage, the accuracy of parking locations, and compliance with vehicle usage rules. The system regularly provides users with feedback on their behavior scores and reward points status, encouraging them to self-adjust by reviewing their own behavior performance. This feedback can be provided through in-app notifications, emails, or other communication channels. In addition, the system also increases user participation and incentive effects through gamification elements (such as leaderboards, badges, achievement systems, etc.), making compliance with rules and good behavior more attractive and competitive. By establishing a community function, users are allowed to share their experiences and achievements, which not only enhances interaction between users, but also encourages more students to comply with the rules through community pressure and positive incentives. Community interaction can include sharing stories about vehicle usage, exchanging tips on best practices, and praising those who comply with the rules.

[0111] Through behavior modification and incentive mechanisms, the management system can effectively improve students' compliance with vehicle management rules, reduce vehicle damage and management costs. In the long run, this mechanism helps to cultivate students' sense of responsibility and awareness of public resource sharing, thereby improving the overall utilization efficiency and sustainability of campus vehicle resources. Overall, the behavior modification and incentive mechanisms not only improve the user experience through systematic reward procedures and real-time feedback, but also enhance the long-term effectiveness and influence of the campus non-motor vehicle management system.

[0112] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0113] In the present invention, the method collects data related to vehicle use, analyzes students' behavior patterns based on clustering algorithms and long short-term memory networks (LSTM), thereby predicting students' mobility trends, and then predicts vehicle demand at various time periods and locations on campus through the time series prediction model ARIMA, and then combines the resource optimization algorithm to adjust the distribution location and vehicle demand of vehicles, provide decision support for vehicle scheduling, ensure that vehicle distribution is highly matched with student demand, optimize resource utilization, and reduce vehicle idle time. The present invention optimizes prediction and scheduling algorithms by integrating machine learning and data analysis technology, improves the efficiency and accuracy of dynamic vehicle allocation, achieves the optimal configuration of resources, meets users' immediate use needs, and reduces system deployment and maintenance costs, improves system scalability and flexibility, and improves user experience and data security.

[0114] Reference Manual Attached Figure 3 , showing a schematic structural diagram of a campus non-motor vehicle positioning management system provided by the present invention.

[0115] The present invention also provides a campus non-motor vehicle positioning management system 20, which is applied to the above-mentioned campus non-motor vehicle positioning management method, comprising:

[0116] Processor 201.

[0117] The memory 202 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 201, the campus non-motor vehicle positioning management method as described in the method embodiment is implemented.

[0118] The campus non-motor vehicle positioning management system 20 provided by the present invention can execute the above-mentioned campus non-motor vehicle positioning management method and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0119] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0120] In the present invention, the method collects data related to vehicle use, analyzes students' behavior patterns based on clustering algorithms and long short-term memory networks (LSTM), thereby predicting students' mobility trends, and then predicts vehicle demand at various time periods and locations on campus through the time series prediction model ARIMA, and then combines the resource optimization algorithm to adjust the distribution location and vehicle demand of vehicles, provide decision support for vehicle scheduling, ensure that vehicle distribution is highly matched with student demand, optimize resource utilization, and reduce vehicle idle time. The present invention optimizes prediction and scheduling algorithms by integrating machine learning and data analysis technology, improves the efficiency and accuracy of dynamic vehicle allocation, achieves the optimal configuration of resources, meets users' immediate use needs, and reduces system deployment and maintenance costs, improves system scalability and flexibility, and improves user experience and data security.

[0121] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0122] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0123] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0124] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0125] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0126] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0127] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0128] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0129] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0130] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0131] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0132] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0133] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, a method for locating and managing non-motor vehicles on campus as described in a method embodiment is implemented.

[0134] A computer-readable storage medium provided by the present invention can implement the steps and effects of the campus non-motor vehicle positioning management method of the above method embodiment. To avoid repetition, the present invention will not go into details.

[0135] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0136] In the present invention, the method collects data related to vehicle use, analyzes students' behavior patterns based on clustering algorithms and long short-term memory networks (LSTM), thereby predicting students' mobility trends, and then predicts vehicle demand at various time periods and locations on campus through the time series prediction model ARIMA, and then combines the resource optimization algorithm to adjust the distribution location and vehicle demand of vehicles, provide decision support for vehicle scheduling, ensure that vehicle distribution is highly matched with student demand, optimize resource utilization, and reduce vehicle idle time. The present invention optimizes prediction and scheduling algorithms by integrating machine learning and data analysis technology, improves the efficiency and accuracy of dynamic vehicle allocation, achieves the optimal configuration of resources, meets users' immediate use needs, and reduces system deployment and maintenance costs, improves system scalability and flexibility, and improves user experience and data security.

[0137] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0138] There are a few points to note:

[0139] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention, and other structures may refer to the general design.

[0140] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of the layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0141] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0142] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A campus non-motor vehicle positioning management method, characterized in that: include: S1: Collect data related to students’ vehicle use; S2: identifying student behavior patterns through a clustering algorithm based on the student vehicle usage related data; S3: According to the student behavior pattern, determine the student movement trend through the long short-term memory network; S4: According to the student mobility trend, the vehicle demand at each time period and location on campus is predicted by a time series prediction model; S5: According to the predicted vehicle demand at different time periods and locations on campus, the distribution of vehicles is adjusted through resource optimization algorithm.

2. The campus non-motor vehicle positioning management method according to claim 1 is characterized in that: The student vehicle usage related data includes: student class schedules, historical location data, vehicle usage records, weather conditions and special campus events.

3. The campus non-motor vehicle positioning management method according to claim 1 is characterized in that: The S2 is specifically: Identify student behavior patterns using the weighted K-means clustering algorithm: Among them, S represents the objective function value, k represents the total number of categories of behavior patterns, and C i represents the i-th behavior pattern category, w i represents the weight associated with the data point x contained in the ith behavior pattern category, x represents the data point in the ith behavior pattern category, μ i represents the weighted average position of all points in the i-th behavior pattern category and represents the norm operation.

4. The campus non-motor vehicle positioning management method according to claim 1 is characterized in that: The S3 is specifically: According to different behavior patterns, the student movement trend is determined through the long short-term memory network: X t =[C t ;P t-1 ;E t-1 ] f t =σ(W f [h t-1 ,X t ]+b f )(Forget Gate) i t =σ(W i [h t-1 , X t ]+b i )(Input gate) o t =σ(W o [h t-1 , X t ]+b o )(Output gate) h t =o t ⊙tanh(c t )(Output Status) Among them, X t represents the input at time t, C t represents the course schedule data input at time t, P t-1 represents the position data input at time t-1, E t-1 represents the additional features input at time t-1 that affect students’ behavior and location selection, f t represents the forget gate, σ represents the sigmoid activation function, h t-1 represents the hidden state at time t-1, i t represents the input gate, represents the possible new state at time t, tanh represents the hyperbolic tangent function, o t represents the output gate, c t represents the cell state that is retained after considering the past state and the current candidate state, C t-1 represents the course schedule data input at time t-1, h t represents the output of the LSTM network at time t, which is used to predict the student movement trend. ⊙ represents the dot product operation. W f , W i , W o and W c Both represent the weight matrices used to control the input of each gate and the influence of the past state on the current state, and b f , b i , b o and b c Both represent bias terms used to adjust the gating and activation levels of candidate states.

5. The campus non-motor vehicle positioning management method according to claim 1 is characterized in that: The S4 is specifically: By integrating the ARIMA model, the vehicle demand at different time periods and locations on campus is predicted: Y t =α+φ1Y t-1 +φ2Y t-2 +…+φ p Y t-p +θ1∈ t-1 +θ2∈ t-2 +…+θ q ∈ t-q +∈ t Among them, Y t represents the predicted vehicle demand at time t, Y t-1 represents the predicted vehicle demand at time t-1, Y t-2 represents the predicted vehicle demand at time t-2, α represents the constant term of the integrated ARIMA model, φ1,…,φ p denotes the autoregressive parameters, θ1,…,θ p represents the moving average parameter, ∈ t-1 ,…,∈ t-q represents the error term of the first q time points, ∈ t Represents the prediction error at the current time t.

6. The campus non-motor vehicle positioning management method according to claim 1 is characterized in that: The S5 is specifically: According to the prediction results, the distribution of vehicles is dynamically adjusted through a nonlinear programming algorithm: Among them, c ij represents the dispatching cost from the i-th vehicle to the j-th demand point, i = 1,,n, n represents the total number of vehicles, j = 1,,m, m represents the total number of demand points, x ij The decision variable representing whether to dispatch the i-th vehicle to the j-th demand point, x ij =0 means no scheduling, x ij =1 means scheduling, Indicates that the demand constraints are met. represents the supply restriction constraint, b j represents the vehicle demand of the jth demand point in the forecast period, d i represents the number of available vehicles at the current time point.

7. The campus non-motor vehicle positioning management method according to claim 1 is characterized in that: Also includes: S6: Anomaly detection and early warning are performed through the isolation forest algorithm.

8. The campus non-motor vehicle positioning management method according to claim 7 is characterized in that: The S6 specifically includes: S601: Determine the abnormal score of each data point using the isolation forest algorithm: Among them, score(x) represents the anomaly score of data point x, E[h(x)] represents the average path length of data point x in the isolation forest. The shorter the path length, the more likely the data point is an anomaly. c(n) represents the average path length of normal data when the sample size is n. S602: Determine whether the abnormal score of each data point is greater than the dynamic threshold; if so, determine it as abnormal data and trigger an alarm; otherwise, continue monitoring.

9. The campus non-motor vehicle positioning management method according to claim 8 is characterized in that: The dynamic threshold is specifically: Among them, θ(t) represents the dynamic threshold at time t, θ0 represents the standard threshold determined based on historical data when the system is initially set, that is, the baseline threshold, α represents the adjustment coefficient used to control the impact of historical abnormal changes on the current threshold, and δ i Represents the abnormal change at time i, i=1,,t, t represents the total number of time.

10. A campus non-motor vehicle positioning management system, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the campus non-motor vehicle positioning management method as described in any one of claims 1 to 9 is implemented.

Images