Logistics vehicle information digital query method and system

Abstract

The invention discloses a logistics vehicle information digital query method and system, and relates to the technical field of vehicle data management, and the method comprises the following steps: obtaining the real-time position data of a logistics vehicle, and transmitting the real-time position data to a cloud platform; processing and judging the data; constructing an intelligent database for classification; providing an intelligent query interface; according to the query condition, dynamically adjusting the priority of the query result, and displaying the query result; generating an analysis report and providing suggestions; and generating a fault early warning, notifying related personnel through a short message and an APP, and adjusting a transportation plan or scheduling a vehicle according to the early warning information. According to the invention, the real-time data of the vehicle is obtained through the intelligent device, and the data is dynamically processed and predicted and analyzed in combination with big data and a deep learning technology, so that the intelligent analysis of the transportation efficiency, the real-time monitoring of the fault risk and the query interface based on the natural language can be realized; therefore, more accurate and more efficient decision support is provided for logistics managers.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle data management, and in particular to a method and system for digitally querying logistics vehicle information. Background Art

[0002] With the rapid development of the logistics industry, improving vehicle transportation efficiency and ensuring transportation safety have become the focus of industry attention. Logistics vehicles are affected by many factors during daily transportation, such as driving behavior, road conditions, vehicle status, etc. These factors often lead to delays, inefficiency and safety hazards in the transportation process.

[0003] Traditional logistics vehicle management methods usually rely on manual records and simple data processing methods, resulting in delayed information updates and a lack of real-time and accuracy. However, with the continuous advancement of Internet of Things technology, more and more logistics companies have begun to use smart devices, such as GPS positioning devices, sensors, and on-board data acquisition terminals, to monitor the operating status of vehicles in real time. However, the real-time data collected by these devices is often single and lacks effective analysis and in-depth mining, resulting in great limitations in optimizing transportation efficiency and predicting faults. To this end, we propose a digital query method and system for logistics vehicle information. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for digitally querying logistics vehicle information to solve the problems raised in the above background technology.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a method for digitally querying logistics vehicle information, comprising the following steps:

[0006] Step 1: Obtain real-time location data of logistics vehicles through smart devices, and transmit the vehicle's driving trajectory, status information, and driver identity data to the cloud platform for aggregation and storage;

[0007] Step 2: Dynamically process the received real-time data and perform predictive analysis on the data based on historical data to determine whether there is a potential fault;

[0008] Step 3: Build an intelligent database to store data obtained through dynamic data processing, classify vehicles according to their real-time status and historical trajectory, and perform data annotation;

[0009] Step 4: Provide an intelligent query interface based on natural language processing technology. Users can enter query conditions through voice and text. The system can understand natural language and automatically parse it into query instructions.

[0010] Step 5: Dynamically adjust the priority of the query results based on the query conditions, and display the query results including real-time location, vehicle status, and historical trajectory information;

[0011] Step 6: Based on the query results, analyze vehicle transportation efficiency through a deep learning model, generate an analysis report, and provide optimization suggestions based on big data analysis;

[0012] Step 7: Based on the comparison of real-time data and historical data, potential failure risks are monitored and predicted in real time, and failure warnings are generated in advance. Relevant personnel are notified via SMS and APP, and transportation plans or vehicle dispatch are adjusted based on the warning information.

[0013] Preferably, the specific steps of step 1 include:

[0014] Step 1.1: Use the vehicle's GPS to obtain the vehicle's real-time location data, including longitude, latitude, speed, driving direction, and location timestamp;

[0015] Step 1.2: Collect vehicle operating status information through onboard sensors, including but not limited to engine status, fuel level, temperature, oil pressure, and tire pressure indicators, and monitor vehicle driving behavior, including but not limited to sudden braking, sudden acceleration, and speeding;

[0016] Step 1.3: Use the vehicle-mounted RFID reader to obtain the driver's identity information, including the driver's ID number, boarding time, and disembarkation time;

[0017] Step 1.4: The collected real-time data is wirelessly transmitted to the cloud platform via the vehicle communication unit.

[0018] Preferably, the specific steps of step 2 include:

[0019] Step 2.1: Remove abnormal data using a data cleaning algorithm. The abnormal data includes but is not limited to invalid location information, duplicate records, and erroneous data points.

[0020] Step 2.2: Use a machine learning model to perform predictive analysis on the vehicle's historical data to identify potential abnormal trends and early signs of vehicle performance degradation, including but not limited to abnormal fuel consumption and vehicle speed fluctuations.

[0021] Preferably, the specific steps of step 3 include:

[0022] Step 3.1: Build an intelligent database, which contains multiple data tables for storing different types of vehicle data, including but not limited to real-time positioning data, vehicle status data, driving behavior data, and historical trajectory data. Each of the multiple data tables is indexed.

[0023] Step 3.2: The processed data is stored in the corresponding data table according to the type. The vehicle status is classified using a status recognition algorithm based on the vehicle's real-time status and historical trajectory. The classification status includes normal status, abnormal status, waiting for repair status, and repaired status.

[0024] Step 3.4: Annotate each status change in the database, recording the time of status change, reason for change, duration of fault, fault type, repair measures, and responsible person information.

[0025] Preferably, the specific steps of the intelligent query interface in step 4 include:

[0026] Step 4.1: Receive query conditions entered by the user, including but not limited to vehicle number, driver name, and current status;

[0027] Step 4.2: Convert the natural language query entered by the user into a structured query that can be understood by the machine, and use the NLP algorithm to analyze the user's intention.

[0028] Preferably, the specific steps of querying the results in step 5 include:

[0029] Step 5.1: Dynamically adjust the order of query results based on different vehicle information;

[0030] Step 5.2: Personalize the displayed content by combining collaborative filtering algorithm with user preferences.

[0031] Preferably, the specific steps of generating the report in step 6 include:

[0032] Step 6.1: Obtain historical transportation data of vehicles from the database and analyze vehicle transportation efficiency using a deep learning model.

[0033] Step 6.2: Generate an analysis report, which includes a transportation efficiency score, influencing factor analysis, optimization suggestions, and historical trend analysis.

[0034] Preferably, the optimization suggestions include but are not limited to optimal route selection, driver behavior optimization, and vehicle maintenance cycle.

[0035] Preferably, the specific steps of step 7 include:

[0036] Step 7.1: Compare real-time data with historical data to identify potential failure risks and predict possible failure types.

[0037] Step 7.2: Send fault warning notifications to relevant personnel, which can be pushed via SMS and APP;

[0038] Step 7.3: Based on the warning results, adjust the transportation plan and dispatch vehicles.

[0039] A digital query system for logistics vehicle information, implementing any one of the above-mentioned digital query methods for logistics vehicle information, comprising:

[0040] The data acquisition module is used to obtain the real-time location data of logistics vehicles through smart devices and transmit the vehicle's driving trajectory, status information and driver identity data to the cloud platform for aggregation and storage;

[0041] The data processing module is used to dynamically process the received real-time data and perform predictive analysis on the data based on historical data to determine whether there are potential faults;

[0042] The intelligent database module is used to store the data obtained from dynamic data processing, classify the vehicle status according to the real-time status and historical trajectory of the vehicle, and perform data annotation;

[0043] The intelligent query module is used to provide an intelligent query interface based on natural language processing technology. Users can enter query conditions through voice and text. The system can understand natural language and automatically parse it into query instructions;

[0044] The display module is used to dynamically adjust the priority of query results according to the query conditions and display the query results including real-time location, vehicle status, and historical trajectory information;

[0045] The analysis report module is used to analyze vehicle transportation efficiency based on query results through deep learning models, generate analysis reports, and provide optimization suggestions based on big data analysis;

[0046] The fault warning module is used to compare real-time data with historical data, monitor and predict potential fault risks in real time, generate fault warnings in advance, notify relevant personnel via SMS or APP, and automatically adjust transportation plans or dispatch vehicles based on the warning information.

[0047] Technical effects and advantages of the present invention:

[0048] The present invention obtains real-time vehicle data through intelligent devices and combines big data and deep learning technologies to dynamically process and predict the data. It can realize intelligent analysis of transportation efficiency, real-time monitoring of failure risks, and a natural language-based query interface, thereby providing logistics managers with more accurate and efficient decision-making support. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 Schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0051] The present invention provides Figure 1 A digital query method for logistics vehicle information shown includes the following steps:

[0052] Step 1: Obtain real-time location data of logistics vehicles through smart devices, and transmit the vehicle's driving trajectory, status information, and driver identity data to the cloud platform for aggregation and storage;

[0053] The specific steps of step 1 include:

[0054] Step 1.1: Use the vehicle's GPS to obtain the vehicle's real-time location data, including longitude, latitude, speed, driving direction, and location timestamp;

[0055] Step 1.2: Collect vehicle operating status information through onboard sensors, including but not limited to engine status, fuel level, temperature, oil pressure, and tire pressure indicators, and monitor vehicle driving behavior, including but not limited to sudden braking, sudden acceleration, and speeding;

[0056] Step 1.3: Use the vehicle-mounted RFID reader to obtain the driver's identity information, including the driver's ID number, boarding time, and disembarkation time;

[0057] Step 1.4: The collected real-time data is wirelessly transmitted to the cloud platform via the vehicle communication unit.

[0058] Through the collaborative work of multiple intelligent devices, the vehicle's dynamic information and driver identity data can be fully and in real time obtained to ensure the accuracy and comprehensiveness of the data. The combination of on-board GPS, sensors and RFID readers not only provides comprehensive monitoring of vehicle location, status and driving behavior, but also can identify the driver's identity in real time, improving the intelligent level of vehicle management. The data is transmitted to the cloud platform through wireless communication, ensuring the timely aggregation and storage of information, providing a reliable data foundation for subsequent fault prediction, transportation efficiency analysis and optimization.

[0059] Step 2: Dynamically process the received real-time data and perform predictive analysis on the data based on historical data to determine whether there is a potential fault;

[0060] The specific steps of step 2 include:

[0061] Step 2.1: Use data cleaning algorithms to remove abnormal data, including but not limited to invalid location information, duplicate records, and erroneous data points;

[0062] Step 2.2: Use a machine learning model to perform predictive analysis on the vehicle's historical data to identify potential abnormal trends and early signs of vehicle performance degradation, including but not limited to abnormal fuel consumption and vehicle speed fluctuations.

[0063] Data cleaning and machine learning-based predictive analysis effectively ensure data quality and accuracy. Data cleaning algorithms eliminate invalid and abnormal data, ensuring the reliability of analysis results. Machine learning analysis based on historical data can proactively identify potential vehicle failures and signs of performance degradation, such as abnormal fuel consumption or speed fluctuations. This provides timely support for fault warnings and maintenance decisions, enhancing the intelligence of vehicle management and reducing operational risks associated with unexpected failures.

[0064] Step 3: Build an intelligent database to store data obtained through dynamic data processing, classify vehicles according to their real-time status and historical trajectory, and perform data annotation;

[0065] The specific steps of step 3 include:

[0066] Step 3.1: Build an intelligent database. The database contains multiple data tables for storing different types of vehicle data, including but not limited to real-time positioning data, vehicle status data, driving behavior data, and historical trajectory data. Each of the multiple data tables is indexed.

[0067] Step 3.2: The processed data is stored in the corresponding data table according to the type. The vehicle status is classified using a status recognition algorithm based on the vehicle's real-time status and historical trajectory. The classification status includes normal status, abnormal status, waiting for repair status, and repaired status.

[0068] Step 3.4: Annotate each status change in the database, recording the time of status change, reason for change, duration of fault, fault type, repair measures, and responsible person information.

[0069] By building an intelligent database, different types of vehicle data can be effectively stored in a structured manner to ensure data organization and query efficiency. The status recognition algorithm can classify vehicles in real time, clearly grasp the current status of the vehicle, and help monitor vehicle operation in real time. By making detailed annotations for each status change, the system can accurately record the occurrence, processing and repair of faults, providing reliable historical data and analysis basis for subsequent fault analysis, maintenance planning and decision support, thereby improving the level of refinement of vehicle management.

[0070] Step 4: Provide an intelligent query interface based on natural language processing technology. Users can enter query conditions through voice and text. The system can understand natural language and automatically parse it into query instructions.

[0071] The specific steps of step 4 of the intelligent query interface include:

[0072] Step 4.1: Receive query conditions entered by the user, including but not limited to vehicle number, driver name, and current status;

[0073] Step 4.2: Convert the natural language query entered by the user into a structured query that can be understood by the machine, and use the NLP algorithm to analyze the user's intention.

[0074] The intelligent query interface is realized through natural language processing technology, allowing users to directly enter query conditions through voice or text, simplifying the operation process. The system can automatically parse the natural language input by the user and convert it into structured query instructions, improving the convenience and accuracy of the query. Users do not need to master complex query syntax, enhancing the system's ease of use and interactivity, and effectively improving query efficiency and user experience.

[0075] Step 5: Dynamically adjust the priority of the query results based on the query conditions, and display the query results including real-time location, vehicle status, and historical trajectory information;

[0076] The specific steps of querying the results in step 5 include:

[0077] Step 5.1: Dynamically adjust the order of query results based on different vehicle information;

[0078] Step 5.2: Personalize the displayed content by combining collaborative filtering algorithm with user preferences.

[0079] By dynamically adjusting the priority of query results, users are ensured to receive the most relevant and important information. Collaborative filtering algorithms, combined with user preferences, personalize displayed content to better align query results with user needs and interests, enhancing the system's intelligence and user experience. This process not only improves query efficiency but also enhances the pertinence and practicality of information displayed, helping users quickly obtain key information.

[0080] Step 6: Based on the query results, analyze vehicle transportation efficiency through a deep learning model, generate an analysis report, and provide optimization suggestions based on big data analysis;

[0081] The specific steps for generating the report in step 6 include:

[0082] Step 6.1: Obtain historical transportation data of vehicles from the database and analyze vehicle transportation efficiency using a deep learning model.

[0083] Step 6.2: Generate an analysis report, which includes transportation efficiency score, influencing factor analysis, optimization suggestions, and historical trend analysis.

[0084] Among them, optimization suggestions include but are not limited to optimal route selection, driver behavior optimization, and vehicle maintenance cycle.

[0085] By analyzing historical transportation data through deep learning models, it is possible to accurately assess vehicle transportation efficiency and generate detailed analysis reports. The reports not only provide transportation efficiency scores, but also conduct a comprehensive analysis of influencing factors and provide optimization suggestions based on big data, such as optimal route selection, driver behavior optimization, and vehicle maintenance cycles. These optimization suggestions help improve transportation efficiency, reduce operating costs, and provide managers with data-driven decision support, thereby improving the intelligence and efficiency of overall logistics operations.

[0086] Step 7: Based on the comparison of real-time data and historical data, potential failure risks are monitored and predicted in real time, and failure warnings are generated in advance. Relevant personnel are notified via SMS and APP, and transportation plans or vehicle dispatch are adjusted based on the warning information.

[0087] The specific steps of step 7 include:

[0088] Step 7.1: Compare real-time data with historical data to identify potential failure risks and predict possible failure types.

[0089] Step 7.2: Send fault warning notifications to relevant personnel, which can be pushed via SMS and APP;

[0090] Step 7.3: Based on the warning results, adjust the transportation plan and dispatch vehicles.

[0091] By comparing and analyzing real-time and historical data, we can monitor and predict potential failure risks in real time, generate early warnings, and mitigate the impact of unexpected failures on transportation. We notify relevant personnel via SMS and app push notifications to ensure timely communication. These warnings enable timely adjustments to transportation plans and vehicle dispatch, optimizing resource allocation and improving response times, ensuring smooth transportation and minimizing operational risks and costs.

[0092] A digital query system for logistics vehicle information, implementing any one of the above-mentioned digital query methods for logistics vehicle information, comprising:

[0093] The data acquisition module is used to obtain the real-time location data of logistics vehicles through smart devices and transmit the vehicle's driving trajectory, status information and driver identity data to the cloud platform for aggregation and storage;

[0094] The data processing module is used to dynamically process the received real-time data and perform predictive analysis on the data based on historical data to determine whether there are potential faults;

[0095] The intelligent database module is used to store the data obtained from dynamic data processing, classify the vehicle status according to the real-time status and historical trajectory of the vehicle, and perform data annotation;

[0096] The intelligent query module is used to provide an intelligent query interface based on natural language processing technology. Users can enter query conditions through voice and text. The system can understand natural language and automatically parse it into query instructions;

[0097] The display module is used to dynamically adjust the priority of query results according to the query conditions and display the query results including real-time location, vehicle status, and historical trajectory information;

[0098] The analysis report module is used to analyze vehicle transportation efficiency based on query results through deep learning models, generate analysis reports, and provide optimization suggestions based on big data analysis;

[0099] The fault warning module is used to compare real-time data with historical data, monitor and predict potential fault risks in real time, generate fault warnings in advance, notify relevant personnel via SMS or APP, and automatically adjust transportation plans or dispatch vehicles based on the warning information.

[0100] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A digital query method for logistics vehicle information, characterized in that: The following steps are involved: Step 1: Obtain real-time location data of logistics vehicles through smart devices, and transmit the vehicle's driving trajectory, status information, and driver identity data to the cloud platform for aggregation and storage; Step 2: Dynamically process the received real-time data and perform predictive analysis on the data based on historical data to determine whether there is a potential fault; Step 3: Build an intelligent database to store data obtained through dynamic data processing, classify vehicles according to their real-time status and historical trajectory, and perform data annotation; Step 4: Provide an intelligent query interface based on natural language processing technology. Users can enter query conditions through voice and text. The system can understand natural language and automatically parse it into query instructions. Step 5: Dynamically adjust the priority of the query results based on the query conditions, and display the query results including real-time location, vehicle status, and historical trajectory information; Step 6: Based on the query results, analyze vehicle transportation efficiency through a deep learning model, generate an analysis report, and provide optimization suggestions based on big data analysis; Step 7: Based on the comparison of real-time data and historical data, potential failure risks are monitored and predicted in real time, and failure warnings are generated in advance. Relevant personnel are notified via SMS and APP, and transportation plans or vehicle dispatch are adjusted based on the warning information.

2. A digital query method for logistics vehicle information according to claim 1, characterized in that: The specific steps of step 1 include: Step 1.1: Use the vehicle's GPS to obtain the vehicle's real-time location data, including longitude, latitude, speed, driving direction, and location timestamp; Step 1.2: Collect vehicle operating status information through onboard sensors, including but not limited to engine status, fuel level, temperature, oil pressure, and tire pressure indicators, and monitor vehicle driving behavior, including but not limited to sudden braking, sudden acceleration, and speeding; Step 1.3: Use the vehicle-mounted RFID reader to obtain the driver's identity information, including the driver's ID number, boarding time, and disembarkation time; Step 1.4: The collected real-time data is wirelessly transmitted to the cloud platform via the vehicle communication unit.

3. A digital query method for logistics vehicle information according to claim 1, characterized in that: The specific steps of step 2 include: Step 2.1: Remove abnormal data using a data cleaning algorithm. The abnormal data includes but is not limited to invalid location information, duplicate records, and erroneous data points. Step 2.2: Use a machine learning model to perform predictive analysis on the vehicle's historical data to identify potential abnormal trends and early signs of vehicle performance degradation, including but not limited to abnormal fuel consumption and vehicle speed fluctuations.

4. A method for digitally querying logistics vehicle information according to claim 1, characterized in that: The specific steps of step 3 include: Step 3.1: Build an intelligent database, which contains multiple data tables for storing different types of vehicle data, including but not limited to real-time positioning data, vehicle status data, driving behavior data, and historical trajectory data. Each of the multiple data tables is indexed. Step 3.2: The processed data is stored in the corresponding data table according to the type. The vehicle status is classified using a status recognition algorithm based on the vehicle's real-time status and historical trajectory. The classification status includes normal status, abnormal status, waiting for repair status, and repaired status. Step 3.4: Annotate each status change in the database, recording the time of status change, reason for change, duration of fault, fault type, repair measures, and responsible person information.

5. A digital query method for logistics vehicle information according to claim 1, characterized in that: The specific steps of the intelligent query interface in step 4 include: Step 4.1: Receive query conditions entered by the user, including but not limited to vehicle number, driver name, and current status; Step 4.2: Convert the natural language query entered by the user into a structured query that can be understood by the machine, and use the NLP algorithm to analyze the user's intention.

6. A digital query method for logistics vehicle information according to claim 1, characterized in that: The specific steps of querying the results in step 5 include: Step 5.1: Dynamically adjust the order of query results based on different vehicle information; Step 5.2: Personalize the displayed content by combining collaborative filtering algorithm with user preferences.

7. A method for digitally querying logistics vehicle information according to claim 1, characterized in that: The specific steps of generating the report in step 6 include: Step 6.1: Obtain historical transportation data of vehicles from the database and analyze vehicle transportation efficiency using a deep learning model. Step 6.2: Generate an analysis report, which includes a transportation efficiency score, influencing factor analysis, optimization suggestions, and historical trend analysis.

8. A digital query method for logistics vehicle information according to claim 7, characterized in that: The optimization suggestions include but are not limited to optimal route selection, driver behavior optimization, and vehicle maintenance cycle.

9. A method for digitally querying logistics vehicle information according to claim 1, characterized in that: The specific steps of step 7 include: Step 7.1: Compare real-time data with historical data to identify potential failure risks and predict possible failure types. Step 7.2: Send fault warning notifications to relevant personnel, which can be pushed via SMS and APP; Step 7.3: Based on the warning results, adjust the transportation plan and dispatch vehicles.

10. A digital query system for logistics vehicle information, implementing a digital query method for logistics vehicle information as claimed in any one of claims 1 to 9, characterized in that: include: The data acquisition module is used to obtain the real-time location data of logistics vehicles through smart devices and transmit the vehicle's driving trajectory, status information and driver identity data to the cloud platform for aggregation and storage; The data processing module is used to dynamically process the received real-time data and perform predictive analysis on the data based on historical data to determine whether there are potential faults; The intelligent database module is used to store the data obtained from dynamic data processing, classify the vehicle status according to the real-time status and historical trajectory of the vehicle, and perform data annotation; The intelligent query module is used to provide an intelligent query interface based on natural language processing technology. Users can enter query conditions through voice and text. The system can understand natural language and automatically parse it into query instructions; The display module is used to dynamically adjust the priority of query results according to the query conditions and display the query results including real-time location, vehicle status, and historical trajectory information; The analysis report module is used to analyze vehicle transportation efficiency based on query results through deep learning models, generate analysis reports, and provide optimization suggestions based on big data analysis; The fault warning module is used to compare real-time data with historical data, monitor and predict potential fault risks in real time, generate fault warnings in advance, notify relevant personnel via SMS or APP, and automatically adjust transportation plans or dispatch vehicles based on the warning information.

Images