Electronic stop board information dynamic updating method based on real-time traffic data
By constructing a spatiotemporal feature matrix and a hybrid prediction model, combined with real-time traffic data, the problems of information lag and prediction deviation on electronic bus stops are solved, high-precision arrival time prediction and personalized information release are achieved, and the real-time and accuracy of electronic bus stop information are improved.
Patent Information
- Application Number
- CN202510870084.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-26
- Publication Date
- 2025-09-23
AI Technical Summary
Traditional electronic bus stop information updates rely on static timetables and simple GPS positioning, which makes it difficult to cope with changes in complex traffic environments, resulting in information lags and prediction biases, and a lack of personalized information release strategies.
Build a spatiotemporal feature matrix, combine it with real-time traffic data, and use a hybrid prediction model (GBDT+classifier) to perform dynamic arrival time prediction and scenario-based information release, including the integration of real-time bus location, speed, road conditions, weather, user behavior and other data.
It achieves high-precision arrival time prediction and personalized information release, improves the real-time and accuracy of electronic bus stop information, and meets the needs of modern smart transportation.
Smart Images
Figure CN120690048A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of intelligent transportation technology, and in particular relates to a method for dynamically updating electronic bus stop information based on real-time traffic data. Background Art
[0002] With the acceleration of urbanization, public transportation systems are facing growing travel demand. As a key vehicle for distributing public transportation information, the real-time and accurate updates of electronic bus stop signs directly impact the passenger experience. Traditional electronic bus stop signs rely primarily on static timetables or simple GPS positioning data, making them difficult to adapt to complex traffic conditions. This leads to information lags and significant prediction errors, making them unable to meet the demands of modern smart transportation.
[0003] In existing technologies, some studies have attempted to use big data and machine learning to optimize traffic forecasts, but they are still limited to historical data analysis and fail to combine dynamic road condition coefficients (such as traffic density and sudden accidents) in real time for dynamic correction, resulting in a lack of personalization in the information release strategy of electronic bus stops. Summary of the Invention
[0004] In view of the above-mentioned shortcomings of the existing technology, the present invention proposes a method for dynamically updating electronic bus stop information based on real-time traffic data. By constructing a spatiotemporal feature matrix and a hybrid prediction model, high-precision arrival time prediction and scenario-based information release are achieved. The technical solution designed by the present invention includes the following steps: S1: Obtain real-time traffic data of buses; S2: Constructing a spatiotemporal feature matrix based on real-time traffic data; S3: Input the spatiotemporal feature matrix into the hybrid prediction model and output the predicted traffic data; S4: Based on the predicted traffic data, trigger the update of the electronic bus stop display content.
[0005] Preferably, the real-time traffic data in S1 includes: Dynamic driving data, historical traffic database, real-time data of urban traffic systems, and user travel scenario data in areas covered by electronic bus stops; The dynamic driving data includes the real-time location of the bus , instantaneous speed and carriage passenger capacity ; The historical traffic database includes the average travel time of each road section and historical congestion event records; The real-time data of the urban traffic system includes weather index , real-time traffic density , emergency accident signs and traffic light status; The user travel scenario data includes the diversion ratio of each mode of transportation within the preset radius of the station and user history waiting time tolerance threshold .
[0006] Preferably, the S2 includes: Search for the shortest path from the bus to the electronic bus stop based on real-time traffic data and dynamic road condition coefficient , construct the spatiotemporal feature matrix , the formula is as follows: .
[0007] Preferably, the dynamic road condition coefficient , the formula is as follows:
[0008] Where, 、 、 and is the weight, satisfying , This is the initial expected time.
[0009] Preferably, the S3 includes: The spatiotemporal feature matrix Input to the hybrid prediction model and output dynamic arrival time , entry distance valuation and scenario suitability rating ; The dynamic arrival time , the formula is as follows:
[0010] Where, is the normalized instantaneous speed of the bus; The estimated pit distance , the formula is as follows:
[0011] Applicability rating for the scenario described , the formula is as follows: .
[0012] Preferably, the S4 includes: when When the electronic station sign updates the arrival time display value; when When the electronic station sign shows the expected Time, when When the electronic station sign shows the delay time; when When the electronic station sign updates the station entry progress display, is the preset total path length; Rating by scenario applicability Classify the types into bus-dominated, subway-competitive and balanced; when When the bus-dominated type is bus-dominated, the electronic bus stop will be updated to show the recommended bus; when When it is a subway competition type, the electronic station board will update and display the subway arrival time; when When it is a balanced type, there are multiple optional ways to update the display of the electronic station sign.
[0013] Beneficial effects: This application proposes a method for dynamically updating electronic bus stop information based on real-time traffic data. By constructing a spatiotemporal feature matrix (integrating data such as vehicle speed, road conditions, weather, and user behavior) and a hybrid prediction model (GBDT+classifier), high-precision arrival time prediction and scenario-based information release are achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] Figure 1 It is a flow chart of a preferred embodiment of the present invention. DETAILED DESCRIPTION
[0015] The embodiments of the present invention are described in detail below. The following embodiments are implemented based on the technical solutions of the present invention, and provide detailed implementation methods and specific operating procedures. However, the protection scope of the present invention is not limited to the following embodiments.
[0016] The present invention designs a method for dynamically updating electronic bus stop information based on real-time traffic data. The technical solution includes the following steps: Figure 1 As shown, specifically including: S1: Obtain real-time traffic data of buses; S2: Constructing a spatiotemporal feature matrix based on real-time traffic data; S3: Input the spatiotemporal feature matrix into the hybrid prediction model and output the predicted traffic data; S4: Based on the predicted traffic data, trigger the update of the electronic bus stop display content.
[0017] Preferably, the real-time traffic data in S1 includes: Dynamic driving data, historical traffic database, real-time data of urban traffic systems, and user travel scenario data in areas covered by electronic bus stops; The dynamic driving data includes the real-time location of the bus , instantaneous speed and carriage passenger capacity ; The historical traffic database includes the average travel time of each road section and historical congestion event records; The real-time data of the urban traffic system includes weather index , real-time traffic density , emergency accident signs and traffic light status; The user travel scenario data includes the diversion ratio of each mode of transportation within the preset radius of the station and user history waiting time tolerance threshold .
[0018] Specifically, for the real-time traffic data in S1, the user's historical waiting time tolerance threshold , which means the average maximum waiting time threshold acceptable to the site user group. It can be obtained through mobile APP questionnaires or statistics on the actual waiting time when users give up waiting at the site, taking the 90th percentile value; for the meteorological index , which means a continuous indicator that quantifies the impact of weather on traffic (the larger the value, the more serious the impact). Real-time weather conditions and visibility can be obtained through the Meteorological Bureau API or based on mapping rules, including sunny = 0, light rain = 3, heavy rain = 6, blizzard = 9, etc.; for accident signs , indicates whether the current path is affected by an accident (0: no accident, 1: accident), which can be obtained through the traffic event API; for the diversion ratio , which is the proportion of users around the site who choose bus / subway / walking for travel. It can be obtained by counting the transportation methods of users starting from the site through base station positioning.
[0019] Preferably, the S2 includes: Search for the shortest path from the bus to the electronic bus stop based on real-time traffic data and dynamic road condition coefficient , construct the spatiotemporal feature matrix , the formula is as follows: .
[0020] Specifically, for the spatiotemporal feature matrix , the matrix dimension needs to be fixed to ensure that it matches the input layer of the prediction model.
[0021] Preferably, the dynamic road condition coefficient , the formula is as follows:
[0022] Where, 、 、 and is the weight, satisfying , This is the initial expected time.
[0023] Specifically, for the initial expected time , which is the benchmark arrival time prediction value based on historical data, can be obtained by querying the historical database and taking the average travel time of the last 30 days under the same period, the same road section and the same weather level; In addition, by integrating the physical road conditions and , quantitative perception of congestion, is closer to user needs than the existing single indicator.
[0024] Preferably, the S3 includes: The spatiotemporal feature matrix Input to the hybrid prediction model and output dynamic arrival time , entry distance valuation and scenario suitability rating ; The dynamic arrival time , the formula is as follows:
[0025] Where, is the normalized instantaneous speed of the bus; The estimated pit distance , the formula is as follows:
[0026] Applicability rating for the scenario described , the formula is as follows: .
[0027] Preferably, the S4 includes: when When the electronic station sign updates the arrival time display value; when When the electronic station sign shows the expected Time, when When the electronic station sign shows the delay time; when When the electronic station sign updates the station entry progress display, is the preset total path length; Rating by scenario applicability Classify the types into bus-dominated, subway-competitive and balanced; when When the bus-dominated type is bus-dominated, the electronic bus stop will be updated to show the recommended bus; when When it is a subway competition type, the electronic station board will update and display the subway arrival time; when When it is a balanced type, there are multiple optional ways to update the display of the electronic station sign.
[0028] Specifically, for S3, the GBDT+classifier combination is used to take into account both continuous value prediction and discrete scene judgment to improve comprehensive decision-making capabilities; in addition, The classifier is used to analyze the diversion ratio of user travel modes and finally divide the scenarios into three types: bus-dominated, subway-competitive and balanced. The design of the classifier can be directly divided by a preset ratio threshold or based on a machine learning classifier, such as dividing by a preset ratio threshold, including setting bus-dominated as , the subway competition type is The balanced type does not satisfy either the bus-dominated type or the subway-competitive type.
[0029] The above describes in detail the preferred embodiments of the present invention. It should be understood that numerous modifications and variations based on the concepts of the present invention are possible by those skilled in the art without inventive effort. Therefore, any technical solution that can be derived by those skilled in the art through logical analysis, reasoning, or limited experimentation based on the concepts of the present invention and the prior art should be within the scope of protection defined by the claims.
Claims
1. A method for dynamically updating electronic bus stop information based on real-time traffic data, characterized in that: include: S1: Obtain real-time traffic data of buses; S2: Constructing a spatiotemporal feature matrix based on real-time traffic data; S3: Input the spatiotemporal feature matrix into the hybrid prediction model and output the predicted traffic data; S4: Based on the predicted traffic data, trigger the update of the electronic bus stop display content.
2. A method for dynamically updating electronic bus stop information based on real-time traffic data according to claim 1, characterized in that: The real-time traffic data in S1 includes: Dynamic driving data, historical traffic database, real-time data of urban traffic systems, and user travel scenario data in areas covered by electronic bus stops; The dynamic driving data includes the real-time location of the bus , instantaneous speed and carriage passenger capacity ; The historical traffic database includes the average travel time of each road section and historical congestion event records; The real-time data of the urban traffic system includes weather index , real-time traffic density , emergency accident signs and traffic light status; The user travel scenario data includes the diversion ratio of each mode of transportation within the preset radius of the station and user history waiting time tolerance threshold .
3. The method for dynamically updating electronic bus stop information based on real-time traffic data according to claim 2, characterized in that: The S2 includes: Search for the shortest path from the bus to the electronic bus stop based on real-time traffic data and dynamic road condition coefficient , construct the spatiotemporal feature matrix , the formula is as follows: 。 4. A method for dynamically updating electronic bus stop information based on real-time traffic data according to claim 3, characterized in that: The dynamic road condition coefficient , the formula is as follows: Where, 、 、 and is the weight, satisfying , This is the initial expected time.
5. The method for dynamically updating electronic bus stop information based on real-time traffic data according to claim 2, characterized in that: The S3 includes: The spatiotemporal feature matrix Input to the hybrid prediction model and output dynamic arrival time , entry distance valuation and scenario suitability rating ; The dynamic arrival time , the formula is as follows: Where, is the normalized instantaneous speed of the bus; The estimated pit distance , the formula is as follows: Applicability rating for the scenario described , the formula is as follows: 。 6. A method for dynamically updating electronic bus stop information based on real-time traffic data according to claim 5, characterized in that: The S4 includes: when When the electronic station sign updates the arrival time display value; when When the electronic station sign shows the expected Time, when When the electronic station sign shows the delay time; when When the electronic station sign updates the station entry progress display, is the preset total path length; Rating by scenario applicability Classify the types into bus-dominated, subway-competitive and balanced; when When the bus-dominated type is bus-dominated, the electronic bus stop will be updated to show the recommended bus; when When it is a subway competition type, the electronic station board will update and display the subway arrival time; when When it is a balanced type, there are multiple optional ways to update the display of the electronic station sign.