Intelligent electronic station board navigation system based on state interaction and dynamic information fusion

Abstract

The invention relates to the technical field of public traffic management, in particular to an intelligent electronic stop board navigation system based on state interaction and dynamic information fusion. The method comprises the steps of obtaining passenger flow data of a target area; analyzing the passenger flow data, and determining the passenger flow distribution characteristics of the target area; generating a dynamic traffic guide including route planning and route smoothness according to the pedestrian flow distribution characteristics; acquiring a travel strategy actively imported by the user; analyzing the travel strategy, and determining travel demand characteristics; and according to the tourism demand characteristics and the dynamic traffic guidance, generating a personalized guide route. And mechanical processing caused by insufficient demand integration is avoided. The travel strategy is analyzed, and the travel demand characteristics are determined, so that the demand characteristics are closer to the actual scene, the fluency of personalized navigation is improved, and route stiffness caused by mechanical mapping is avoided. The personalized guide route is generated, the guide personalization and real-time performance are improved, the user experience is enhanced, and response delay caused by information fusion splitting is solved.

Description

Technical Field

[0001] The present application relates to the technical field of public transportation management, and in particular to a smart electronic bus stop guide system based on state interaction and dynamic information fusion. Background Art

[0002] With the advancement of smart city construction, smart electronic bus stop sign systems are playing an increasingly important role in the field of tourist guidance. Smart electronic bus stop sign systems integrate traffic information and provide real-time guidance services.

[0003] However, existing electronic signboard guides often rely on simple data collection and mechanical calculations, resulting in limited information and a lack of real-time and accuracy, making personalized guides impossible. These issues lead to inefficient guides, an inability to meet the diverse needs of today's passengers, and a negative impact on the tourist experience. Summary of the Invention

[0004] This application provides a smart electronic bus stop guide system based on state interaction and dynamic information fusion to solve the above problems.

[0005] In a first aspect, the present application provides a smart electronic bus stop guide system based on state interaction and dynamic information fusion, the system comprising: Acquire passenger flow data of a target area; analyze the passenger flow data to determine the distribution characteristics of passenger flow in the target area; Generate a dynamic traffic guide including route planning and route smoothness based on the crowd flow distribution characteristics; Obtain travel strategies actively imported by users; analyze the travel strategies and determine travel demand characteristics; Generate a personalized tour route based on the tourism demand characteristics and the dynamic traffic guide.

[0006] This solution captures passenger flow data for the target area, avoiding biased predictions due to incomplete data and supporting the determination of high-precision passenger flow distribution characteristics. Passenger flow data is analyzed to determine the distribution characteristics of passenger flow in the target area, ensuring real-time reflection of gathering areas and evacuation routes. This provides reliable input for dynamic traffic guide generation and reduces the risk of recommending congested routes. Based on the passenger flow distribution characteristics, a dynamic traffic guide is generated that includes route planning and route accessibility, enhancing the guide's credibility and providing a foundation for optimizing personalized guided tours. Travel guides proactively submitted by users are captured to ensure that user needs are captured directly, avoiding mechanical processing caused by insufficient demand integration. Travel guides are analyzed to identify travel demand characteristics, making them more relevant to actual scenarios. This improves the fluidity of personalized guided tours and avoids rigid routes caused by mechanical mapping. Based on travel demand characteristics and the dynamic traffic guide, personalized guided tours are generated, enhancing the personalization and real-time nature of guided tours, enhancing the user experience, and addressing response delays caused by fragmented information integration.

[0007] Optionally, obtaining passenger flow data of the target area includes: Obtain basic passenger flow data within the target area through the interface of a third-party platform; Analyze the basic passenger flow data to determine the data type; Comparing the data type with a preset data item type to determine whether there is a missing data item; If it exists, determine the associated data source based on the missing data item; Estimating customer data based on the associated data source to generate predicted data for the missing data items; The predicted data and the basic passenger flow data are used as the passenger flow data of the target area.

[0008] Through this solution, basic passenger flow data in the target area is obtained through the interface of the third-party platform to ensure the reliability and timeliness of the data source. The basic passenger flow data is parsed to determine the data type, clarify the data structure, eliminate data ambiguity, and ensure the accuracy of the comparison. The data type is compared with the preset data item type to determine whether there are missing data items and reveal the incompleteness of the data. If so, the associated data source is determined based on the missing data items to achieve targeted processing of the missing items, avoid blind data queries, and ensure efficient use of estimated resources. Passenger data is estimated based on the associated data source, and predicted data for missing data items is generated to ensure the overall availability of passenger flow data and provide seamless input for the final data integration. The predicted data and basic passenger flow data are used as the passenger flow data for the target area to ensure the overall consistency and direct availability of passenger flow data.

[0009] Optionally, analyzing the passenger flow data to determine the passenger flow distribution characteristics of the target area includes: Analyze the passenger flow data based on the time series to determine the number of passengers and the number of passengers getting off the bus; Obtaining traffic information within a target area, determining a number of available transportation modes within the target area and an operating period for each available transportation mode; Analyze the operating period, determine the period characteristics, and perform time-attenuation weighted calculation on the passenger data and the number of passengers getting off the bus based on the period characteristics to obtain a calculation result; Performing spatial gridding processing on the target area to obtain a unit grid, and establishing a crowd density prediction model based on the unit grid; Determine the crowd flow distribution characteristics of the target area according to the crowd flow density prediction model and the calculation result.

[0010] This solution analyzes passenger flow data based on time series, determining passenger and alighting data and preserving the temporal characteristics of the data. Traffic information within the target area is obtained, identifying several available transportation modes and the operating hours for each mode. This ensures that weighted calculations are integrated with the actual dynamics of transportation operations and avoid being divorced from real-world scenarios. The operating hours are analyzed to determine their characteristics. Based on these characteristics, a time-attenuated weighted calculation is performed on passenger and alighting data to generate results. This enhances the timeliness of the data, reduces the interference of historical data on current predictions, and provides more accurate input data for the crowd density prediction model. The target area is spatially gridded to obtain a unit grid. Based on this unit grid, a crowd density prediction model is established, achieving spatial discretization of the passenger flow data and providing a quantifiable grid foundation for analyzing crowd distribution. Based on the crowd density prediction model and the calculation results, crowd distribution characteristics within the target area are determined, providing a real-time crowd distribution basis for dynamic traffic guidance.

[0011] Optionally, establishing a crowd density prediction model based on the unit grid includes: Obtaining historical passenger flow data; analyzing the historical passenger flow data to determine passenger flow conduction patterns among several available transportation modes; Acquiring meteorological data, analyzing the meteorological data and the available transportation modes, and determining weather interference factors; A crowd density prediction model is established based on the crowd conduction law and the weather interference factors.

[0012] This solution captures historical pedestrian flow data, eliminating static issues caused by missing third-party data. It analyzes historical pedestrian flow data to identify patterns in pedestrian flow between several available transportation modes, providing transfer logic support for dynamic predictions. It also captures meteorological data and analyzes it alongside several available transportation modes to identify weather interference factors, eliminating the impact of weather on pedestrian movement speeds and improving adaptability to dynamic interference. Based on these patterns and weather interference factors, a pedestrian density prediction model is established, eliminating the inability to adaptively process dynamically coupled data and enabling the generation of highly accurate pedestrian distribution features.

[0013] Optionally, generating a dynamic traffic guide including route planning and route accessibility based on the crowd flow distribution characteristics includes: Get the user's current location and initial target coordinates; Generating several candidate routes according to a path planning algorithm based on the user's current location and the initial target coordinates; Calculating a travel time correction coefficient for each candidate route based on the passenger flow distribution characteristics; According to the travel time correction coefficient, the route and time of each candidate route are adjusted to obtain a dynamic traffic guide.

[0014] This solution obtains the user's current location and initial target coordinates, providing a baseline for navigation calculations, including the starting and destination points. Based on the user's current location and initial target coordinates, a path planning algorithm generates several candidate routes, providing a baseline set of routes for crowd flow impact assessment. Based on crowd flow distribution characteristics, a travel time correction factor is calculated for each candidate route, reflecting the proportion of congestion levels affecting the base travel time, providing data for route adjustments. Based on the travel time correction factor, the route and travel time of each candidate route are adjusted to generate dynamic traffic guidance, avoid high-congestion areas, and provide real-time, reliable navigation suggestions.

[0015] Optionally, generating a personalized guided tour route based on the tourism demand characteristics and the dynamic traffic guide includes: Determine the preferred length of stay at each target tourist spot based on the tourism demand characteristics; Dynamically adjust the order of visiting scenic spots according to the crowd density and the preferred duration of stay; Generate a personalized guided tour route based on the order of visiting attractions and the stated operating hours.

[0016] This solution determines the preferred duration of stay at each target attraction based on tourism demand characteristics, quantifying users' individual needs and avoiding the mechanical use of fixed duration values, thereby improving route personalization and user satisfaction. Based on visitor density and preferred durations, the order of scenic spot visits is dynamically adjusted to avoid peak hours, reduce user wait times, avoid congestion and delays, and maximize overall tour efficiency. Based on the order of scenic spot visits and operating hours, personalized guided tours are generated, ensuring the time-based execution of the route and facilitating direct user use, resulting in personalized and efficient guided tour services.

[0017] Optionally, generating a personalized guided tour route based on the order of visiting scenic spots and the operating hours includes: predicting dining spots based on the order of visiting the attractions and the preferred duration of stay; Acquiring dining data within a preset range of the dining attraction; Analyzing the catering data to determine catering characteristics; Generate a recommendation list based on the restaurant characteristics and receive recommendation feedback; Determine target dining locations based on the recommendation feedback; Predicting the expected queuing time at the target dining spot based on the crowd density; Generate a personalized guided tour route based on the order of visiting the attractions, the operating hours and the expected waiting time.

[0018] This solution predicts dining spots based on the order of scenic spot visits and preferred duration of stay, ensuring seamless integration of dining planning and tour sequence, and avoiding itinerary interruptions or time conflicts caused by improper dining arrangements. It also captures restaurant data within a preset range of dining spots, providing the foundation for analyzing and recommending restaurant characteristics, ensuring the generated recommendation list is geographically relevant and practical. It analyzes the restaurant data to identify restaurant characteristics, making recommendations more precise and improving the applicability of dining options. Based on these characteristics, it generates a recommendation list and receives feedback, enabling dynamic interaction between user preferences and recommendations, ensuring personalized recommendations and providing input for further targeting of target dining spots. Based on the feedback, it identifies target dining spots, providing precise input for queue length prediction and route generation, avoiding redundant recommendations. Based on crowd density, it predicts expected queue times at target dining spots, quantifies the impact of crowd congestion on meal times, and provides time parameters for route optimization, reducing the risk of actual wait times for users. It generates personalized guided routes based on the order of scenic spot visits, operating hours, and expected queue times, improving overall practicality and real-time performance.

[0019] Optionally, determining the associated data source based on the missing data item includes: Parsing the missing data items to determine missing monitoring time of the missing attributes; Determine the associated transportation mode according to the missing attributes and the pedestrian flow conduction rule; According to the missing monitoring time, the operation data of the associated transportation mode is obtained as the associated data source.

[0020] This solution parses missing data items, determines the missing monitoring time for the missing attributes, and locates the type and time of the missing data. This provides basic input for identifying associated data sources and ensures a clear starting point for data completion. Based on the missing attributes and passenger flow patterns, associated transportation modes are identified. Dynamic passenger flow shifts are leveraged to narrow the data source range and provide guidance for obtaining alternative data. Based on the missing monitoring time, operational data for the associated transportation mode is obtained as an associated data source, ensuring that alternative operational data is available to support estimation when missing data items occur.

[0021] Optionally, analyzing the travel strategy to determine travel demand characteristics includes: Performing natural language processing on the travel guide to extract keywords and time descriptions; According to the keywords, matching POI data in the target area to determine candidate tourist spots; Analyze the POI data to determine historical visit patterns; Determine the expected duration of stay at each candidate tourist spot based on the historical tourist patterns and the time description; Obtaining user historical behavior data, and determining user browsing preferences based on the user historical behavior data; A tourism demand feature is generated based on the user's tour preferences and the expected length of stay.

[0022] This solution performs natural language processing on travel guides, extracting keywords and time descriptions to ensure that user intent is accurately captured and represented. Based on keywords, POI data within the target area is matched to identify candidate tourist spots, mapping the points of interest in the user's guide to their actual geographic locations and providing a candidate set for tourist spot selection. POI data is parsed to identify historical visit patterns, providing data support for duration prediction and ensuring that patterns are driven by historical data. Based on historical visit patterns and time descriptions, the expected duration of stay at each candidate tourist spot is determined, ensuring that the duration reflects both historical patterns and user time constraints, providing time parameters for demand profiles. Historical user behavior data is obtained and, based on this data, user travel preferences are determined, personalizing demand profiles and reflecting historical behavior patterns. Based on user travel preferences and expected duration of stay, travel demand profiles are generated to ensure complete representation of demand information.

[0023] Optionally, predicting the expected queuing time at the target dining spot based on the crowd density includes: Analyze the target dining spot and determine the characteristics of the food; The expected queuing time at the target dining spot is predicted based on the food consumption characteristics and the crowd density.

[0024] This solution analyzes target dining spots and identifies food characteristics, ensuring accurate identification of these characteristics and establishing a typology for predicting queue times. Based on these characteristics and customer density, we predict the expected queue times at target dining spots, reflecting the impact of customer density on actual queues and providing time parameters for route optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0026] Figure 1 A schematic diagram of an application scenario provided in one embodiment of the present application; Figure 2 This is a flowchart of a smart electronic bus stop guide system based on state interaction and dynamic information fusion provided in one embodiment of the present application. DETAILED DESCRIPTION

[0027] To make the purpose, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0028] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document, unless otherwise specified, generally indicates an "or" relationship between the related objects.

[0029] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0030] Existing electronic signage guides often rely on simple data collection and mechanical calculations, resulting in limited information and a lack of real-time and accuracy, making personalized guidance impossible. These issues lead to inefficient guidance, an inability to meet the diverse needs of today's passengers, and a negative impact on the visitor experience.

[0031] Based on this, the present application provides a smart electronic bus stop guide system based on stateful interaction and dynamic information fusion. This system captures passenger flow data for target areas, avoiding biased passenger flow predictions due to incomplete data, and thus supports the determination of high-precision passenger flow distribution characteristics. Passenger flow data is analyzed to determine passenger flow distribution characteristics for target areas, ensuring real-time reflection of gathering areas and evacuation routes. This provides reliable input for dynamic traffic guide generation and reduces the risk of recommending congested routes. Based on passenger flow distribution characteristics, a dynamic traffic guide is generated that includes route planning and route accessibility, enhancing the guide's credibility and providing a foundation for optimizing personalized guided tours. Travel guides proactively generated by users are captured to ensure that user needs are directly captured, avoiding mechanical processing caused by insufficient demand integration. Travel guides are analyzed to determine travel demand characteristics, making them more relevant to actual scenarios, improving the fluidity of personalized guided tours, and avoiding route rigidity caused by mechanical mapping. Based on travel demand characteristics and the dynamic traffic guide, personalized guided tours are generated, improving the personalization and real-time nature of guided tours, enhancing the user experience, and addressing response delays caused by fragmented information fusion.

[0032] Figure 1 This is a schematic diagram of an application scenario provided by this application. The method provided by this application is applied when conducting smart electronic bus stop guidance.

[0033] Specifically, the method provided in the present application is applied to any server, and the server interacts with a third-party platform to obtain the passenger flow data of the target area of ​​the third-party platform in real time. Analyze the passenger flow data to determine the distribution characteristics of the flow of people in the target area. Based on the distribution characteristics of the flow of people, generate a dynamic traffic guide that includes route planning and route smoothness. Obtain travel guides actively imported by users to ensure that user needs are directly captured and avoid mechanical processing caused by insufficient demand integration. Analyze travel guides, determine travel demand characteristics, make the demand characteristics more in line with actual scenarios, improve the smoothness of personalized navigation, and avoid route rigidity caused by mechanical mapping. Generate personalized guided tours based on travel demand characteristics and dynamic traffic guides, improve the personalization and real-time nature of navigation, enhance user experience, and solve the response delay caused by information fusion fragmentation. For specific implementation methods, please refer to the following embodiments.

[0034] Figure 2 This is a flow chart of a smart electronic bus stop guide system based on state interaction and dynamic information fusion provided by an embodiment of this application. The method of this embodiment can be applied to the server in the above scenario. Figure 2As shown, the system includes: S201, obtaining passenger flow data of a target area; analyzing the passenger flow data to determine the distribution characteristics of passenger flow in the target area; The target area may be a designated spatial area for city tourism guide services.

[0035] Passenger flow data can be raw crowd movement information.

[0036] The crowd flow distribution characteristics can be a quantitative representation of the spatial distribution of the crowd in the target area.

[0037] Specifically, the system uses a third-party platform's API to obtain real-time passenger flow data for the target area. This data is then fed into a dynamic information fusion module for cleaning. This cleaned data is then fed into a crowd density prediction model based on an LSTM neural network to determine a spatial grid heat map of the target area. Finally, features from the spatial grid heat map are extracted to generate crowd distribution characteristics.

[0038] S202: Generate a dynamic traffic guide including route planning and route accessibility based on the characteristics of passenger flow distribution; Route planning can be a sequence of recommended travel routes.

[0039] Route accessibility can be an evaluation indicator of how smooth a path is.

[0040] Dynamic traffic guidance can be a navigation solution that includes route planning and route accessibility.

[0041] Specifically, the system uses map data of the target area obtained from OpenStreetMap, combined with parameters such as crowd density and gathering areas in crowd distribution characteristics; then, a path planning algorithm is used to calculate the shortest path, and the smoothness is evaluated in combination with the gathering areas; further, combined with real-time traffic data called by a third-party traffic API, a dynamic traffic guide is generated that includes route planning and route smoothness.

[0042] S203, obtaining travel strategies actively imported by users; analyzing the travel strategies and determining travel demand characteristics; A travel guide can be an unstructured description of preferences and plans input in the form of text or documents.

[0043] Tourism demand characteristics can be structured demand data such as attraction lists and length of stay.

[0044] Specifically, the user-initiated travel guides are captured through the interactive interface of the smart electronic bus stop. Natural language processing technology is used to segment the guides and extract different entities. Points of interest are then identified by matching them against a POI database. Dynamic adjustments are then made based on historical user behavior data to determine travel demand characteristics.

[0045] S204: Generate a personalized tour route based on tourism demand characteristics and dynamic traffic guidelines.

[0046] A personalized guided tour route can be a customized tour sequence generated by combining tourism demand characteristics and dynamic transportation guidelines.

[0047] Specifically, it integrates tourism demand characteristics with dynamic traffic guides, applies optimization algorithms to adjust route sequence and duration, and integrates derived demands based on POI data matching to generate personalized guided routes with text and map visualization.

[0048] This solution captures passenger flow data for the target area, avoiding biased predictions due to incomplete data and supporting the determination of high-precision passenger flow distribution characteristics. Passenger flow data is analyzed to determine the distribution characteristics of passenger flow in the target area, ensuring real-time reflection of gathering areas and evacuation routes. This provides reliable input for dynamic traffic guide generation and reduces the risk of recommending congested routes. Based on the passenger flow distribution characteristics, a dynamic traffic guide is generated that includes route planning and route accessibility, enhancing the guide's credibility and providing a foundation for optimizing personalized guided tours. Travel guides proactively submitted by users are captured to ensure that user needs are captured directly, avoiding mechanical processing caused by insufficient demand integration. Travel guides are analyzed to identify travel demand characteristics, making them more relevant to actual scenarios. This improves the fluidity of personalized guided tours and avoids rigid routes caused by mechanical mapping. Based on travel demand characteristics and the dynamic traffic guide, personalized guided tours are generated, enhancing the personalization and real-time nature of guided tours, enhancing the user experience, and addressing response delays caused by fragmented information integration.

[0049] In some embodiments, basic passenger flow data in the target area is obtained through an interface of a third-party platform; the basic passenger flow data is parsed to determine the data type; the data type is compared with the preset data item type to determine whether there are missing data items; if so, the associated data source is determined based on the missing data items; passenger data is estimated based on the associated data source to generate predicted data for the missing data items; the predicted data and the basic passenger flow data are used as the passenger flow data for the target area.

[0050] A third-party platform can be an external data source that provides basic passenger flow data.

[0051] The interface can be a communication protocol or access channel for obtaining basic passenger flow data from a third-party platform.

[0052] The basic passenger flow data may be a set of original passenger flow information.

[0053] The data type may be the attribute category of each field in the basic passenger flow data.

[0054] The preset data item type may be a set of necessary data items that a complete passenger flow data set should contain, which is pre-stored in the server and called when used.

[0055] Missing data items may be preset data item types that are not included in the basic passenger flow data.

[0056] The associated data source may be a supplementary data provider corresponding to the missing data item.

[0057] Predicted data can be the values ​​of missing data items estimated by linking data sources.

[0058] Specifically, by calling the API interface provided by the third-party platform, the target area is input and a data request is sent; then, after the interface responds, the basic passenger flow data is received. Subsequently, the basic passenger flow data is formatted and the data fields are extracted; then, the data processing library is used to identify the data type of each field. Next, the data item types preset by the statistical characteristics of the historical passenger flow data and the industry's general data standards are read; the data types are compared item by item with the preset data item types to determine whether there are any missing data items. If so, based on the missing data items, the association mapping table constructed based on the empirical association rules between different data items in the domain knowledge and the external data source is queried to determine the associated data source. The interface of the associated data source is accessed, and the raw data provided by the associated data source is processed using a simple estimation model to generate predicted data for the missing data items. Finally, the basic passenger flow data and the predicted data are merged to form a complete passenger flow dataset; this is stored in a structured format as the passenger flow data for the target area.

[0059] Through this solution, basic passenger flow data in the target area is obtained through the interface of the third-party platform to ensure the reliability and timeliness of the data source. The basic passenger flow data is parsed to determine the data type, clarify the data structure, eliminate data ambiguity, and ensure the accuracy of the comparison. The data type is compared with the preset data item type to determine whether there are missing data items and reveal the incompleteness of the data. If so, the associated data source is determined based on the missing data items to achieve targeted processing of the missing items, avoid blind data queries, and ensure efficient use of estimated resources. Passenger data is estimated based on the associated data source, and predicted data for missing data items is generated to ensure the overall availability of passenger flow data and provide seamless input for the final data integration. The predicted data and basic passenger flow data are used as the passenger flow data for the target area to ensure the overall consistency and direct availability of passenger flow data.

[0060] In some embodiments, based on time series, passenger flow data is analyzed to determine passenger data and disembarkation data; traffic information in the target area is obtained to determine several available transportation modes in the target area and the operating hours of each available transportation mode; the operating hours are analyzed to determine the characteristics of the hours, and based on the characteristics of the hours, time-attenuated weighted calculations are performed on the passenger data and disembarkation data to obtain calculation results; spatial gridding is performed on the target area to obtain unit grids, and based on the unit grids, a crowd density prediction model is established; based on the crowd density prediction model and the calculation results, the crowd distribution characteristics of the target area are determined.

[0061] Time series can be the characteristic of data being arranged in order of time.

[0062] Passenger data can be structured information of the number of people on the bus.

[0063] The passenger disembarkation data may be structured information of the number of people disembarking.

[0064] Traffic information may include a list of transportation modes and operating hours within the target area.

[0065] The available transportation modes may be a list of transportation types available in the target area.

[0066] The operating period can be the start time, end time and frequency interval information of each available transportation mode.

[0067] The time period characteristics can be the time periods divided based on the operating period and the average passenger flow density characteristics.

[0068] The calculation result can be a weighted passenger data and passenger drop-off data set.

[0069] The unit grid may be a geographic grid unit of regular size into which the target area is divided through a spatial gridding process.

[0070] The crowd density prediction model may be a machine learning regression model used to predict the crowd density value of each unit grid.

[0071] Specifically, time series information is extracted from passenger flow data. A data processing library is then used to parse the data format, separate the timestamp column, and sort by timestamp. The "number of boardings" field is identified and extracted as passenger data, while the "number of disembarkings" field is identified and extracted as disembarkation data. A query request is then sent to the traffic information device in the target area and traffic information is received. The traffic information is then parsed to determine a list of available transportation modes within the target area, along with the operating hours for each mode. The operating hours are then analyzed, dividing the entire day into multiple time periods. The average passenger flow density for each time period is calculated based on historical data statistics as a time period feature. A time-decay weighting function is then applied to each data point in the passenger and disembarkation data. The difference between the timestamp of each data point and the current reference time is calculated and substituted into the decay function to obtain the weighted value. Based on the weighted values, weighted passenger and disembarkation data are generated. All weighted data is then aggregated to form the calculation result. Next, based on the target area's boundary coordinates, geospatial processing tools were used to spatially grid the target area, generating a regularly sized grid. A crowd density prediction model was then constructed based on this grid. The calculated results were then fed into the crowd density prediction model to generate a predicted crowd density value for each grid cell. Finally, based on the predicted results, the crowd distribution characteristics of the target area were determined.

[0072] This solution analyzes passenger flow data based on time series, determining passenger and alighting data and preserving the temporal characteristics of the data. Traffic information within the target area is obtained, identifying several available transportation modes and the operating hours for each mode. This ensures that weighted calculations are integrated with the actual dynamics of transportation operations and avoid being divorced from real-world scenarios. The operating hours are analyzed to determine their characteristics. Based on these characteristics, a time-attenuated weighted calculation is performed on passenger and alighting data to generate results. This enhances the timeliness of the data, reduces the interference of historical data on current predictions, and provides more accurate input data for the crowd density prediction model. The target area is spatially gridded to obtain a unit grid. Based on this unit grid, a crowd density prediction model is established, achieving spatial discretization of the passenger flow data and providing a quantifiable grid foundation for analyzing crowd distribution. Based on the crowd density prediction model and the calculation results, crowd distribution characteristics within the target area are determined, providing a real-time crowd distribution basis for dynamic traffic guidance.

[0073] In some embodiments, historical pedestrian flow data is obtained; the historical pedestrian flow data is analyzed to determine the pedestrian flow conduction patterns among several available transportation modes; meteorological data is obtained, and the meteorological data and several available transportation modes are analyzed to determine weather interference factors; and a pedestrian flow density prediction model is established based on the pedestrian flow conduction patterns and weather interference factors.

[0074] The historical passenger flow data may be historical passenger flow records of the target area.

[0075] The passenger flow conduction law can be the passenger flow transfer ratio between several available transportation modes.

[0076] Meteorological data can be weather-related temperature, precipitation, and wind data information.

[0077] The weather interference factor can be a quantitative parameter that represents the impact of weather on the passenger flow of a transportation mode.

[0078] Specifically, historical passenger flow data for the target area is retrieved from a historical data storage device. The transportation mode field in the historical passenger flow data is then extracted. The change in passenger flow for each available transportation mode within adjacent time periods is then statistically analyzed. Based on these statistical results, the passenger flow transfer relationships between transportation modes are derived, and the patterns of passenger flow transmission between the available transportation modes are determined. Subsequently, a query request is sent to an external meteorological service interface to receive meteorological data for the target area. The timestamps of the meteorological data are then matched with the timestamps of the historical passenger flow data. Passenger flow deviation values ​​for each available transportation mode under different weather conditions are then calculated. Based on these passenger flow deviation values, a parameter representing the intensity of weather impact is generated and determined as a weather interference factor. Subsequently, based on the spatial division of the unit grids, the historical passenger flow data for each unit grid is correlated. Finally, a regression algorithm is used to train a model based on the patterns of passenger flow transmission and the weather interference factor, outputting a predicted passenger flow density value for each unit grid, thereby constructing a passenger flow density prediction model.

[0079] This solution captures historical pedestrian flow data, eliminating static issues caused by missing third-party data. It analyzes historical pedestrian flow data to identify patterns in pedestrian flow between several available transportation modes, providing transfer logic support for dynamic predictions. It also captures meteorological data and analyzes it alongside several available transportation modes to identify weather interference factors, eliminating the impact of weather on pedestrian movement speeds and improving adaptability to dynamic interference. Based on these patterns and weather interference factors, a pedestrian density prediction model is established, eliminating the inability to adaptively process dynamically coupled data and enabling the generation of highly accurate pedestrian distribution features.

[0080] In some embodiments, the user's current location and initial target coordinates are obtained; based on the user's current location and initial target coordinates, several candidate routes are generated according to a path planning algorithm; based on the crowd distribution characteristics, the travel time correction coefficient of each candidate route is calculated; based on the travel time correction coefficient, the route and time of each candidate route are adjusted to obtain a dynamic traffic guide.

[0081] The user's current location may be the user's geographic location coordinates.

[0082] The initial target coordinates may be the geographic coordinates of the target destination.

[0083] A path planning algorithm may be an algorithm for calculating a feasible path from a current location to a target location.

[0084] A candidate route can be multiple feasible path options.

[0085] The travel time correction factor may be a numerical factor used to correct the estimated basic time of a candidate route.

[0086] A route can be a sequence of paths or a traffic route.

[0087] The time taken may be the estimated travel time.

[0088] Specifically, the user's current location is collected in real time through the mobile device's GPS. Initial target coordinates are obtained by parsing the destination information in the user's imported travel guide. The user's current location coordinates and initial target coordinates are input into the path planning algorithm. An initial path search is then performed, generating several candidate routes based on the shortest distance or time priority principle. Furthermore, a sequence of unit grids through which these candidate routes pass is extracted. The pedestrian flow distribution characteristics of each unit grid are then mapped to a speed attenuation factor. A travel time correction factor is then calculated for each candidate route, taking into account the route length and available transportation modes. Based on the travel time correction factor, if the travel time correction factor indicates that the candidate route is highly congested, the route is replanned. The estimated base travel time for each candidate route is multiplied by the travel time correction factor to obtain the corrected travel time. These adjustments to each candidate route are then integrated to generate a dynamic traffic guide.

[0089] This solution obtains the user's current location and initial target coordinates, providing a baseline for navigation calculations, including the starting and destination points. Based on the user's current location and initial target coordinates, a path planning algorithm generates several candidate routes, providing a baseline set of routes for crowd flow impact assessment. Based on crowd flow distribution characteristics, a travel time correction factor is calculated for each candidate route, reflecting the proportion of congestion levels affecting the base travel time, providing data for route adjustments. Based on the travel time correction factor, the route and travel time of each candidate route are adjusted to generate dynamic traffic guidance, avoid high-congestion areas, and provide real-time, reliable navigation suggestions.

[0090] In some embodiments, the preferred duration of stay at each target tourist spot is determined based on tourism demand characteristics; the order of sightseeing spots is dynamically adjusted based on crowd density and preferred duration of stay; and a personalized guided tour route is generated based on the order of sightseeing spots and operating hours.

[0091] The target tourist spots may be specific scenic spots or points of interest parsed from the travel guides imported by the user.

[0092] The length of stay preference may be a numerical preference value assigned to each target tourist spot based on tourism demand characteristics.

[0093] The crowd density may be a cell grid density value representing the degree of crowd congestion in different areas.

[0094] The scenic spot tour sequence can be a target tour point sequence.

[0095] Specifically, based on tourism demand characteristics, natural language processing technology is used to analyze travel guide text, identify keywords related to duration of stay, and map these keywords to target attractions. Based on the mapping results, the preferred duration of stay for each target attraction is determined. Furthermore, based on crowd density, the potential waiting time for each target attraction is calculated, and combined with the preferred duration of stay, a new attraction sequence is generated. If the target attraction has a high crowd density, the attraction sequence is dynamically adjusted. Finally, the planned arrival times in the attraction sequence are checked to ensure they are within the operating hours. If a conflict occurs, the sequence is fine-tuned to generate a personalized tour itinerary.

[0096] This solution determines the preferred duration of stay at each target attraction based on tourism demand characteristics, quantifying users' individual needs and avoiding the mechanical use of fixed duration values, thereby improving route personalization and user satisfaction. Based on visitor density and preferred durations, the order of scenic spot visits is dynamically adjusted to avoid peak hours, reduce user wait times, avoid congestion and delays, and maximize overall tour efficiency. Based on the order of scenic spot visits and operating hours, personalized guided tours are generated, ensuring the time-based execution of the route and facilitating direct user use, resulting in personalized and efficient guided tour services.

[0097] In some embodiments, dining attractions are predicted based on the order of sightseeing and the preferred duration of stay; dining data within a preset range of dining attractions is obtained; the dining data is analyzed to determine the characteristics of the dining; based on the dining characteristics, a recommendation list is generated and recommendation feedback is received; based on the recommendation feedback, the target dining spot is determined; based on the crowd density, the expected waiting time at the target dining spot is predicted; and based on the order of sightseeing, operating hours and expected waiting time, a personalized guided route is generated.

[0098] A dining attraction may be a candidate dining location.

[0099] The preset range may be a preset geographical distance range, which is pre-stored in the server and called when used.

[0100] The catering data may be basic information of catering spots within a preset range.

[0101] The catering characteristics may be classification features determined by analyzing the catering data.

[0102] The recommendation list may be a sorted list of dining spots.

[0103] Recommendation feedback may be input data provided by a user to a recommendation list through an interactive interface.

[0104] The target dining point may be the final dining point location determined based on the recommendation feedback.

[0105] The expected queue time may be a predicted numerical queue waiting time.

[0106] Specifically, based on dwell time preferences, the system calculates the estimated end time of each target destination and identifies time gaps within the scenic spot tour sequence to predict candidate destinations suitable for dining. Next, based on the geographic coordinates of the dining destination, it queries restaurant data within a preset range. It then analyzes descriptive information such as menus and service descriptions within the restaurant data to identify and determine the restaurant's characteristics. It then categorizes and sorts the restaurants based on these characteristics, presenting a recommended list through a user interface. Simultaneously, user feedback is received from the recommended list. Furthermore, user feedback is analyzed and mapped to the corresponding items in the recommended list to determine the target dining destination. A density-duration mapping table is then created based on the corresponding traffic density at the target dining destination, and a queuing model algorithm is applied to predict the expected queue time at the target dining destination. The arrival time for each target destination in the scenic spot tour sequence is then verified and adjusted to ensure it falls within operating hours. The expected queue time is then input into the dwell time at the target dining destination, resulting in the final personalized guided route.

[0107] This solution predicts dining spots based on the order of scenic spot visits and preferred duration of stay, ensuring seamless integration of dining planning and tour sequence, and avoiding itinerary interruptions or time conflicts caused by improper dining arrangements. It also captures restaurant data within a preset range of dining spots, providing the foundation for analyzing and recommending restaurant characteristics, ensuring the generated recommendation list is geographically relevant and practical. It analyzes the restaurant data to identify restaurant characteristics, making recommendations more precise and improving the applicability of dining options. Based on these characteristics, it generates a recommendation list and receives feedback, enabling dynamic interaction between user preferences and recommendations, ensuring personalized recommendations and providing input for further targeting of target dining spots. Based on the feedback, it identifies target dining spots, providing precise input for queue length prediction and route generation, avoiding redundant recommendations. Based on crowd density, it predicts expected queue times at target dining spots, quantifies the impact of crowd congestion on meal times, and provides time parameters for route optimization, reducing the risk of actual wait times for users. It generates personalized guided routes based on the order of scenic spot visits, operating hours, and expected queue times, improving overall practicality and real-time performance.

[0108] In some embodiments, missing data items are parsed to determine the missing monitoring time of the missing attributes; the associated transportation mode is determined based on the missing attributes and the pedestrian flow conduction pattern; and the operating data of the associated transportation mode is obtained as the associated data source based on the missing monitoring time.

[0109] The missing attribute can be a specific attribute of the missing data item.

[0110] The missing monitoring time may be the time point at which the missing data item occurs.

[0111] The associated transportation mode can be a transportation mode related to the missing attribute.

[0112] The operational data may be operational data associated with a transportation mode.

[0113] Specifically, the missing data items are parsed using a log analyzer, the missing attributes are extracted, and the time of occurrence of the missing data items is determined as the missing monitoring time. Then, based on the missing attributes, a preset rule library is queried for pedestrian flow patterns. Based on these patterns, transportation modes associated with the missing attributes are generated as associated transportation modes. Finally, using the missing monitoring time as a query parameter, a data query request is initiated to the associated transportation mode interface to query the operational data of the associated transportation mode, and the operational data is used as the associated data source.

[0114] This solution parses missing data items, determines the missing monitoring time for the missing attributes, and locates the type and time of the missing data. This provides basic input for identifying associated data sources and ensures a clear starting point for data completion. Based on the missing attributes and passenger flow patterns, associated transportation modes are identified. Dynamic passenger flow shifts are leveraged to narrow the data source range and provide guidance for obtaining alternative data. Based on the missing monitoring time, operational data for the associated transportation mode is obtained as an associated data source, ensuring that alternative operational data is available to support estimation when missing data items occur.

[0115] In some embodiments, natural language processing is performed on the travel guide to extract keywords and time descriptions; based on the keywords, POI data in the target area is matched to determine candidate tourist spots; the POI data is parsed to determine historical touring patterns; based on the historical touring patterns and time descriptions, the expected duration of stay at each candidate tourist spot is determined; user historical behavior data is obtained, and based on the user historical behavior data, the user's touring preferences are determined; and based on the user's touring preferences and expected duration of stay, travel demand characteristics are generated.

[0116] Keywords can be vocabulary units extracted from travel guides.

[0117] The time description may be a time expression string recognized from a travel guide.

[0118] The POI data may be a point of interest database entry within the target area.

[0119] The candidate tour points may be a set of potential tour points.

[0120] The historical browsing pattern may be a statistical indicator calculated from historical visit records.

[0121] The expected stay duration may be a stay time value for each candidate tourist spot.

[0122] User historical behavior data can be the user's past browsing records and preference settings.

[0123] User browsing preferences may be preference features analyzed from user historical behavior data.

[0124] Specifically, natural language processing is performed on travel guides to extract keywords and time descriptions. First, word segmentation is performed to segment the text into independent lexical units. Then, part-of-speech tagging techniques are used to identify nouns, verbs, and other parts of speech, and keywords are extracted based on named entity recognition. Furthermore, time descriptions are identified using a temporal expression parsing model. A string matching algorithm is used to match keywords with POI data within the target area. Successfully matched POIs are then screened to identify candidate tourist spots. Subsequently, the POI data is accessed and the historical dataset for each POI is parsed. Statistical indicators of this historical dataset are then calculated to identify historical visit patterns. For each candidate tourist spot, the expected duration of stay is determined by combining historical visit patterns with the time description. If the time description indicates a shorter stay, the duration is reduced; if the time description indicates an extended stay, the duration is increased. This determines the expected duration of stay for each candidate tourist spot. Furthermore, historical user behavior data is retrieved from the user database and analyzed to identify preference characteristics. A rule engine is then used to classify and output user travel preferences. Finally, the user browsing preferences and expected duration assigned to each candidate tourist spot are combined to generate a tourism demand profile.

[0125] This solution performs natural language processing on travel guides, extracting keywords and time descriptions to ensure that user intent is accurately captured and represented. Based on keywords, POI data within the target area is matched to identify candidate tourist spots, mapping the points of interest in the user's guide to their actual geographic locations and providing a candidate set for tourist spot selection. POI data is parsed to identify historical visit patterns, providing data support for duration prediction and ensuring that patterns are driven by historical data. Based on historical visit patterns and time descriptions, the expected duration of stay at each candidate tourist spot is determined, ensuring that the duration reflects both historical patterns and user time constraints, providing time parameters for demand profiles. Historical user behavior data is obtained and, based on this data, user travel preferences are determined, personalizing demand profiles and reflecting historical behavior patterns. Based on user travel preferences and expected duration of stay, travel demand profiles are generated to ensure complete representation of demand information.

[0126] In some embodiments, the target dining spot is analyzed to determine the characteristics of food consumption; based on the food consumption characteristics and crowd density, the expected waiting time at the target dining spot is predicted.

[0127] The food consumption characteristics may be a classification of the characteristics of the food provided at the target dining spot in terms of the way in which it is consumed.

[0128] Specifically, the database query interface inputs the unique identifier of the target dining spot and retrieves the "Food Characteristics" field of the POI data entry to determine the food characteristics. A pre-stored mapping table based on historical third-party review data is then queuing to map the food characteristics to corresponding basic queue times. Based on the crowd density value, an adjustment factor is calculated using a pre-defined adjustment rule based on historical crowd density and queue times. The final expected queue time for the target dining spot is generated based on the basic queue time and the adjustment factor.

[0129] This solution analyzes target dining spots and identifies food characteristics, ensuring accurate identification of these characteristics and establishing a typology for predicting queue times. Based on these characteristics and customer density, we predict the expected queue times at target dining spots, reflecting the impact of customer density on actual queues and providing time parameters for route optimization.

Claims

1. A smart electronic bus stop guide system based on state interaction and dynamic information fusion, characterized by: include: Obtain passenger flow data for the target area; Analyzing the passenger flow data to determine the passenger flow distribution characteristics of the target area; Generate a dynamic traffic guide including route planning and route smoothness based on the crowd flow distribution characteristics; Obtain travel strategies actively imported by users; analyze the travel strategies and determine travel demand characteristics; Generate a personalized tour route based on the tourism demand characteristics and the dynamic traffic guide.

2. The system according to claim 1, wherein: The obtaining of passenger flow data of the target area includes: Obtain basic passenger flow data within the target area through the interface of a third-party platform; Analyze the basic passenger flow data to determine the data type; Comparing the data type with a preset data item type to determine whether there is a missing data item; If it exists, determine the associated data source based on the missing data item; Estimating customer data based on the associated data source to generate predicted data for the missing data items; The predicted data and the basic passenger flow data are used as the passenger flow data of the target area.

3. The system according to claim 1, wherein: The analyzing the passenger flow data to determine the passenger flow distribution characteristics of the target area includes: Analyze the passenger flow data based on the time series to determine the number of passengers and the number of passengers getting off the bus; Obtaining traffic information within a target area, determining a number of available transportation modes within the target area and an operating period for each available transportation mode; Analyze the operating period, determine the period characteristics, and perform time-attenuation weighted calculation on the passenger data and the number of passengers getting off the bus based on the period characteristics to obtain a calculation result; Performing spatial gridding processing on the target area to obtain a unit grid, and establishing a crowd density prediction model based on the unit grid; Determine the crowd flow distribution characteristics of the target area according to the crowd flow density prediction model and the calculation result.

4. The system according to claim 3, characterized in that The establishing of a crowd density prediction model based on the unit grid includes: Obtaining historical passenger flow data; analyzing the historical passenger flow data to determine passenger flow conduction patterns among several available transportation modes; Acquiring meteorological data, analyzing the meteorological data and the available transportation modes, and determining weather interference factors; A crowd density prediction model is established based on the crowd conduction law and the weather interference factors.

5. The system according to claim 1, wherein: Generating a dynamic traffic guide including route planning and route accessibility based on the crowd flow distribution characteristics includes: Get the user's current location and initial target coordinates; Generating several candidate routes according to a path planning algorithm based on the user's current location and the initial target coordinates; Calculating a travel time correction coefficient for each candidate route based on the passenger flow distribution characteristics; According to the travel time correction coefficient, the route and time of each candidate route are adjusted to obtain a dynamic traffic guide.

6. The system according to claim 3, wherein: Generating a personalized guided tour route based on the tourism demand characteristics and the dynamic traffic guide includes: Determine the preferred length of stay at each target tourist spot based on the tourism demand characteristics; Dynamically adjust the order of visiting scenic spots according to the crowd density and the preferred duration of stay; Generate a personalized guided tour route based on the order of visiting attractions and the stated operating hours.

7. The system according to claim 6, characterized in that The generation of a personalized guided tour route based on the order of scenic spot visits and the operating hours includes: predicting dining spots based on the order of visiting the attractions and the preferred duration of stay; Acquiring dining data within a preset range of the dining attraction; Analyzing the catering data to determine catering characteristics; Generate a recommendation list based on the restaurant characteristics and receive recommendation feedback; Determine target dining locations based on the recommendation feedback; Predicting the expected queuing time at the target dining spot based on the crowd density; Generate a personalized guided tour route based on the order of visiting the attractions, the operating hours and the expected waiting time.

8. The system according to claim 2 or 4, characterized in that The determining of the associated data source according to the missing data item includes: Parsing the missing data items to determine missing monitoring time of the missing attributes; Determine the associated transportation mode according to the missing attributes and the pedestrian flow conduction rule; According to the missing monitoring time, the operation data of the associated transportation mode is obtained as the associated data source.

9. The system according to claim 1, wherein: The analyzing the travel strategy and determining travel demand characteristics include: Performing natural language processing on the travel guide to extract keywords and time descriptions; According to the keywords, matching POI data in the target area to determine candidate tourist spots; Analyze the POI data to determine historical visit patterns; Determine the expected duration of stay at each candidate tourist spot based on the historical tourist patterns and the time description; Obtaining user historical behavior data, and determining user browsing preferences based on the user historical behavior data; A tourism demand feature is generated based on the user's tour preferences and the expected length of stay.

10. The system according to claim 7, wherein: The step of predicting the expected queuing time at the target dining spot based on the crowd density includes: Analyze the target dining spot and determine the characteristics of the food; The expected queuing time at the target dining spot is predicted based on the food consumption characteristics and the crowd density.

Images