Bus station data acquisition system based on AI intelligent analysis

Abstract

The invention discloses a bus station data acquisition system based on AI intelligent analysis. The bus station data acquisition system comprises a multi-dimensional data acquisition module, a data transmission module, an AI intelligent analysis module and a result output and feedback module, the data transmission module is used for transmitting data acquired by the multi-dimensional data acquisition module to the AI intelligent analysis module; the AI intelligent analysis module is used for carrying out preprocessing, feature extraction, correlation analysis and intelligent prediction on the received data; and the result output and feedback module is used for outputting the analysis result of the AI intelligent analysis module in a visual form, and feeding back a related instruction to a bus station operation management system. Through the multi-dimensional data acquisition module, omnibearing acquisition of data of vehicles, personnel, environment, facilities and the like of a bus station is realized, the defect of simplification of traditional data acquisition is overcome, and a complete data basis is provided for comprehensive analysis.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of bus station management, and particularly relates to a bus station data collection system based on AI intelligent analysis. BACKGROUND

[0002] With the rapid development of urban public transportation, the operation efficiency and management level of bus stations as important nodes of bus operation directly affect the quality of bus services. Traditional bus station data collection methods mostly rely on manual recording or single device collection, and have problems such as incomplete data collection, poor real-time performance, weak analysis capability and the like. For example, manual recording of passenger flow data is prone to errors and cannot reflect passenger flow changes in real time; a single vehicle positioning device can only obtain vehicle position information and is difficult to combine with station environment, facility state and other data for comprehensive analysis. These problems lead to a lack of precise data basis for bus operation scheduling, and the bus system cannot respond to sudden situations such as passenger flow fluctuations and vehicle failures in a timely manner, which affects the overall operation efficiency of the bus system. Therefore, the technical personnel in the field provide a bus station data collection system based on AI intelligent analysis to solve the problems in the background technology. SUMMARY

[0003] The purpose of the present application is to provide a bus station data collection system based on AI intelligent analysis to solve the problems in the background technology.

[0004] To achieve the above purpose, the present application provides the following technical scheme:

[0005] The bus station data collection system based on AI intelligent analysis comprises a multi-dimensional data collection module, a data transmission module, an AI intelligent analysis module and a result output and feedback module; the multi-dimensional data collection module is used for collecting vehicle data, personnel data, environment data and facility equipment data of the bus station; the data transmission module is used for transmitting the data collected by the multi-dimensional data collection module to the AI intelligent analysis module; the AI intelligent analysis module is used for pre-processing, feature extraction, correlation analysis and intelligent prediction of the received data; and the result output and feedback module is used for outputting the analysis result of the AI intelligent analysis module in a visual form and feeding back relevant instructions to a bus station operation and management system.

[0006] As a further scheme of the present application: the multi-dimensional data acquisition module includes a vehicle identification unit, a passenger flow statistics unit, an environment monitoring sensor and a facility state monitoring device; the vehicle identification unit collects the entering station time, the leaving station time, the staying time and the vehicle number information of the bus through license plate recognition technology and vehicle positioning information; the passenger flow statistics unit collects the waiting passengers, the boarding and alighting passengers and the personnel flow trajectory information in the station by using infrared induction and video image recognition technology; the environment monitoring sensor is used to collect the temperature, humidity, light intensity and air quality data in the station; the facility state monitoring device is used to collect the running state and fault information of the facilities such as the waiting shelter, the station board and the charging pile in the station.

[0007] As a further scheme of the present application: the data transmission module adopts a transmission mode combining 5G / 4G wireless network and wired network, ensures the real-time and stability of data transmission, and has data encryption function to ensure the safety in the process of data transmission.

[0008] As a further scheme of the present application: the AI intelligent analysis module includes a data preprocessing submodule, a feature extraction submodule, a correlation analysis submodule and an intelligent prediction submodule; the data preprocessing submodule is used to clean, deduplicate, complete and format convert the collected original data, and remove noise data and abnormal values; the feature extraction submodule extracts key features from the preprocessed data by using deep learning algorithm, including vehicle operation features, passenger flow change features, environmental influence features and facility operation features; the correlation analysis submodule analyzes the internal correlation between different types of data by constructing a data correlation model, such as the correlation between passenger flow change and vehicle arrival frequency, the correlation between environmental factors and facility failure rate, etc.; the intelligent prediction submodule predicts the passenger flow size, the vehicle arrival punctuality rate, the facility equipment failure probability and the like in a certain period of time in the future based on historical data and real-time data by using time series prediction algorithm and machine learning classification algorithm.

[0009] As a further scheme of the present application: the result output and feedback module includes a visual display unit and an instruction generation unit; the visual display unit visually displays the analysis results to the management personnel in the form of charts, curves, heat maps, etc.; the instruction generation unit generates operation scheduling suggestion instructions according to the analysis results, such as adjusting the departure frequency and optimizing the station stopping time, and feeds back to the bus operation scheduling system.

[0010] As a further scheme of the present application: the multi-dimensional data acquisition module is further provided with an event monitoring unit, which uses image recognition and sound monitoring technology to monitor and warn the sudden events in the bus station in real time, such as passenger conflict and vehicle collision, and once an abnormal event is detected, the relevant information is immediately transmitted to the AI intelligent analysis module and the result output and feedback module.

[0011] As a further scheme of the present application: the AI intelligent analysis module is embedded with an energy consumption analysis submodule, which accounts and analyzes the energy consumption of the bus station based on the collected vehicle operation data, facility equipment operation parameters, and environmental data, and predicts the energy consumption trend at different times to provide data support for station energy-saving management. As a further scheme of the present application: the result output and feedback module adds a passenger feedback collection unit to collect passenger feedback information such as evaluation and suggestions on public transportation services through channels such as electronic display screens and mobile applications of the bus station, and transmit the information to the AI intelligent analysis module for sentiment analysis and demand mining to help optimize public transportation operation management services. As a further scheme of the present application: the data transmission module has a data caching function, which can temporarily store untransmitted data when the network transmission is temporarily interrupted or congested, and automatically transmit the cached data to the AI intelligent analysis module in order after the network recovers to normal, ensuring the integrity of data transmission. As a further scheme of the present application: the system is also equipped with a device self-diagnosis module that can regularly self-test various sensors in the multi-dimensional data acquisition module, network devices of the data transmission module, and computing devices of the AI intelligent analysis module, etc., to timely discover potential equipment faults and hidden dangers, and transmit the diagnosis results to the result output and feedback module for the maintenance personnel to arrange equipment maintenance in advance.

[0012] Compared with the prior art, the present application has the following advantages:

[0013] 1. Comprehensive data collection: Through the multi-dimensional data acquisition module, comprehensive data collection of vehicles, personnel, environment, facilities, etc. in the bus station is realized, overcoming the single data collection defect of traditional data collection and providing a complete data basis for comprehensive analysis.

[0014] 2. Intelligent analysis: The introduction of AI intelligent analysis algorithm enables deep mining and correlation analysis of massive data, realizes intelligent prediction of passenger flow changes, vehicle operation status, facility failures, etc., and greatly improves analysis efficiency and accuracy compared with traditional manual analysis.

[0015] 3. Precise operation decision: The result output and feedback module converts the analysis results into specific operation scheduling instructions, providing scientific and precise decision-making basis for public transportation operation management, which helps to optimize the departure frequency, reasonably allocate resources, and improve the operation efficiency and service quality of the bus station.

[0016] 4. Strong real-time performance: Efficient data transmission methods and real-time analysis algorithms are used to ensure that the whole process from data collection to analysis and feedback can be completed in a short time, enabling management personnel to timely grasp the station dynamics and quickly respond to various emergencies. BRIEF DESCRIPTION OF DRAWINGS

[0017] Fig. 1 Structure diagram of a bus station data collection system based on AI intelligent analysis;

[0018] Fig. 2 Framework diagram of a multi-dimensional data collection module in a bus station data collection system based on AI intelligent analysis;

[0019] Fig. 3 Framework diagram of an AI intelligent analysis module in a bus station data collection system based on AI intelligent analysis;

[0020] Fig. 4 Framework diagram of a result output and feedback module in a bus station data collection system based on AI intelligent analysis;

[0021] Fig. 5 Framework diagram of a data transmission module in a bus station data collection system based on AI intelligent analysis. DETAILED DESCRIPTION

[0022] Referring to Figs. 1-5 In an embodiment of the present application, a bus station data collection system based on AI intelligent analysis includes a multi-dimensional data collection module, a data transmission module, an AI intelligent analysis module, and a result output and feedback module.

[0023] The multi-dimensional data collection module is the core of the system's data source, and captures all-around data of the bus station through various high-precision collection devices.

[0024] The vehicle recognition unit uses a high-definition camera with a resolution of 20 million pixels, and is equipped with an advanced license plate recognition algorithm. The algorithm has a recognition accuracy of up to 99.5% for various types of license plates, and can accurately identify the license plate information of the bus vehicle. Combined with the vehicle GPS positioning data with an error of no more than 5 meters, the vehicle's entry time, exit time, and in-station stay duration can be recorded in real time, and the vehicle number can be accurately associated, thereby establishing a complete and detailed vehicle operation trajectory file, and providing a reliable basis for subsequent vehicle scheduling and operation analysis.

[0025] The passenger flow statistics unit uses a combination of binocular cameras and infrared sensors. The binocular camera has depth perception capability and can effectively distinguish between human bodies and other objects. Combined with the precise detection of infrared sensors in low-light environments, advanced video image recognition technology is used to dynamically monitor the waiting crowd in the station. This unit can accurately count the number of waiting passengers, boarding and alighting passengers at different time periods, with an error rate of less than 3%, and can also clearly track the flow trajectory of personnel in the station, providing solid data support for in-depth analysis of passenger flow distribution patterns.

[0026] The environmental monitoring sensors are distributed in various key areas of the station yard, which can collect air quality parameters such as temperature (measurement range -40℃ to 85℃, accuracy ±0.5℃), humidity (measurement range 0 to 100%RH, accuracy ±2%RH), light intensity (measurement range 0 to 100000 lux) and PM2.5 (measurement range 0 to 500μg / m³, accuracy ±5μg / m³) in real time, so that the management personnel can timely grasp the environmental state of the station yard and ensure that the station yard environment is in a suitable state.

[0027] The facility state monitoring device monitors the running parameters of facilities such as shelters, station boards and charging piles by installing sensors on them. For example, the charging current (measurement range 0 to 50A, accuracy ±0.1A) and voltage (measurement range 0 to 500V, accuracy ±0.5V) of the charging pile, and the display state of the station board. Once abnormal data is found, the system will immediately mark it as fault information and upload it for timely maintenance.

[0028] The data transmission module is responsible for safely and efficiently transmitting the massive data collected by the multi-dimensional data acquisition module to the AI intelligent analysis module. Considering the real-time and reliability requirements of data, this module uses a hybrid transmission method combining 5G / 4G wireless network and wired Ethernet.

[0029] The 5G network has a transmission rate of up to 10Gbps and a transmission delay of as low as 10 milliseconds, which can meet the high-speed transmission requirements of vehicle dynamic data, peak passenger flow data and other data with high real-time requirements, ensuring that these key data can be delivered to the analysis module in a timely manner. The wired Ethernet has a bandwidth of 1000Mbps, which can stably transmit non-real-time data such as environmental data and facility state, effectively reducing the risk of network congestion.

[0030] At the same time, the data is encrypted using the AES encryption algorithm during transmission, which has high security and efficiency, ensuring the confidentiality and integrity of the data, preventing data leakage or tampering during transmission.

[0031] The AI intelligent analysis module is the "brain" of the system, which performs deep processing on the received data based on deep learning and big data analysis technology.

[0032] The data preprocessing submodule first cleans the raw data, removes noise data and outliers caused by equipment failure or environmental interference through outlier detection algorithms (such as Z-score method), and improves data quality; then it converts data of different formats to a standard format, laying a solid foundation for subsequent analysis.

[0033] The feature extraction sub-module adopts an algorithm combining convolutional neural network (CNN) and recurrent neural network (RNN). CNN is good at extracting spatial features of data, and RNN can effectively capture time sequence features. The combination of the two can accurately extract key features from pre-processed data, such as extracting peak period features from passenger flow data and extracting punctuality rate features from vehicle data.

[0034] The correlation analysis sub-module builds a data correlation model and uses association rule mining algorithms (such as Apriori algorithm) to mine the internal relationship between different types of data, such as analyzing the correlation between passenger flow peaks and vehicle departure frequency, and the potential relationship between environmental temperature changes and facility failure probability, to provide more dimensional reference for operation decision-making.

[0035] The intelligent prediction sub-module is based on a machine learning model trained on historical data, such as an LSTM time series prediction model. The model has a prediction accuracy of more than 85% for passenger flow size, vehicle arrival punctuality rate, and facility failure probability in the future, which can provide a scientific basis for formulating operation strategies in advance.

[0036] The result output and feedback module is the bridge between the system and the user, presenting the analysis results of the AI intelligent analysis module to the bus station management personnel in an intuitive and easy-to-understand way, and realizing linkage with the operation management system.

[0037] The visual display unit displays the analysis results in the form of line charts, bar charts, heat maps, etc. through large screen displays or management terminal software, with a content update frequency of 1 minute / second. For example, it can display the passenger flow distribution heat map of the current station and the vehicle punctuality rate statistical curve in real time, so that the management personnel can quickly and accurately grasp the station operation status.

[0038] The instruction generation unit automatically generates operation scheduling suggestion instructions according to the analysis results and prediction data, with a response time of no more than 30 seconds. When a passenger flow peak is predicted to occur in a certain time period, an instruction to increase the departure frequency in that time period is generated. When a facility failure is detected, a maintenance scheduling instruction is generated, and these instructions are fed back to the bus operation scheduling system through a data interface, realizing intelligent adjustment of operation management.

[0039] The above is only the preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any skilled person in the art can make equivalent substitutions or changes within the technical scope disclosed by the present application and according to the technical solutions and inventive concepts of the present application, which should be covered within the protection scope of the present application.

Claims

1. A bus station field data collection system based on AI intelligent analysis, characterized in that, It comprises the following steps: S1: a multi-dimensional data acquisition module is used to acquire vehicle data, personnel data, environmental data and facility equipment data of the bus station; S2: a data transmission module is used to transmit the data acquired by the multi-dimensional data acquisition module to an AI intelligent analysis module; S3: the AI intelligent analysis module is used to preprocess, feature extract, correlation analyze and intelligently predict the received data; S4: a result output and feedback module is used to output the analysis result of the AI intelligent analysis module in a visual form, and feedback relevant instructions to the bus station operation management system. 2.The bus station field data collection system based on AI intelligent analysis according to claim 1, characterized in that, The multi-dimensional data acquisition module comprises a vehicle recognition unit, a passenger flow statistics unit, an environmental monitoring sensor and a facility state monitoring device; the vehicle recognition unit acquires the entering station time, leaving station time, staying time and vehicle number information of the bus vehicle through license plate recognition technology and vehicle-mounted positioning information; the passenger flow statistics unit acquires the waiting passenger number, boarding and alighting passenger number and personnel flow trajectory information in the station by using infrared induction and video image recognition technology; the environmental monitoring sensor is used to acquire temperature, humidity, illumination intensity and air quality data in the station; the facility state monitoring device is used to acquire the running state and fault information of facilities such as waiting shelters, station boards and charging piles in the station. 3.The bus station field data collection system based on AI intelligent analysis according to claim 1, characterized in that, The data transmission module adopts a transmission mode combining 5G / 4G wireless network and wired network, ensures the real-time and stability of data transmission, and has data encryption function to ensure the security in the data transmission process. 4.The bus station field data collection system based on AI intelligent analysis according to claim 1, characterized in that, The AI intelligent analysis module comprises a data preprocessing submodule, a feature extraction submodule, a correlation analysis submodule and an intelligent prediction submodule; the data preprocessing submodule is used to clean, deduplicate, complete and format convert the acquired original data, and remove noise data and outliers; the feature extraction submodule extracts key features from the preprocessed data by using deep learning algorithm, including vehicle operation features, passenger flow change features, environmental influence features and facility operation features; the correlation analysis submodule analyzes the internal correlation between different types of data by constructing a data correlation model, such as the correlation between passenger flow change and vehicle arrival frequency, the correlation between environmental factors and facility failure rate, etc.; the intelligent prediction submodule predicts the passenger flow size, vehicle arrival punctuality rate, facility equipment failure probability, etc. in a certain period of time in the future based on historical data and real-time data by using time series prediction algorithm and machine learning classification algorithm. 5.The bus station field data collection system based on AI intelligent analysis according to claim 1, characterized in that, The result output and feedback module comprises a visual display unit and an instruction generation unit; the visual display unit visually displays the analysis result to the management personnel in the form of charts, curves, heat maps, etc.; the instruction generation unit generates operation scheduling suggestion instructions according to the analysis result, such as adjusting the departure frequency, optimizing the station stop time, etc., and feeds back to the bus operation scheduling system. 6.The bus station field data collection system based on AI intelligent analysis according to claim 1, characterized in that, The multi-dimensional data acquisition module is also provided with an event monitoring unit which uses image recognition and sound monitoring technology to monitor and give early warning of sudden events in the bus station field such as passenger conflicts and vehicle collisions. Once an abnormal event is detected, relevant information is immediately transmitted to the AI intelligent analysis module and the result output and feedback module. 7.The bus station field data collection system based on AI intelligent analysis of claim 1, wherein, The AI intelligent analysis module is embedded with an energy consumption analysis submodule which calculates and analyzes the energy consumption of the bus station field according to the collected vehicle operation data, facility and equipment operation parameters, and environmental data, and predicts the energy consumption trend at different times to provide data support for station energy-saving management. 8.The bus station field data collection system based on AI intelligent analysis of claim 1, wherein, The result output and feedback module adds a passenger feedback collection unit which collects passenger feedback information such as evaluation and suggestions on bus services through channels such as electronic display screens and mobile applications in the bus station field, and transmits the information to the AI intelligent analysis module for sentiment analysis and demand mining to help optimize bus operation management services. 9.The bus station field data collection system based on AI intelligent analysis of claim 1, wherein, The data transmission module has a data caching function. When there is a temporary interruption or congestion in network transmission, it can temporarily store the untransmitted data. When the network returns to normal, the cached data is automatically transmitted to the AI intelligent analysis module in order, ensuring the integrity of data transmission. 10.The bus station field data collection system based on AI intelligent analysis of claim 1, wherein, The system is also equipped with a device self-diagnosis module which can regularly self-test various sensors in the multi-dimensional data acquisition module, network devices in the data transmission module, and computing devices in the AI intelligent analysis module, discover potential equipment faults and hidden dangers in time, and transmit the diagnosis results to the result output and feedback module so that maintenance personnel can arrange equipment maintenance in advance.

Images