Unit vehicle monitoring system, method and equipment based on multi-source information fusion

Abstract

The invention provides a unit vehicle use monitoring system, method and device based on multi-source information fusion, and relates to the field of vehicle management. The system comprises an information acquisition module used for acquiring various detection data through a vehicle-mounted multi-source information acquisition terminal of a unit vehicle to obtain a first data set; the data preprocessing module is used for classifying and cleaning various detection data in the first data set to obtain a second data set; the data fusion module is used for carrying out fusion processing on various detection data in the second data set, and determining the comprehensive state and behavior information of the unit vehicle according to the fused data; and the result application module is used for carrying out real-time monitoring, alarm management, data analysis and management optimization processing on the fused data. The system can realize omnibearing and multi-angle monitoring of vehicle usage of a unit, improves the management efficiency, guarantees the life and property safety of employees, and meets increasingly strict supervision requirements.

Description

Technical Field

[0001] The present application relates to the field of vehicle management, and more specifically, to a unit vehicle monitoring system, method and equipment based on multi-source information fusion. Background Art

[0002] In the daily operation of modern enterprises and institutions, the management efficiency and safety of unit vehicles as an important means of transportation are directly related to the smooth development of business and the safety of life and property of employees. Traditional unit vehicle monitoring methods often rely on a single monitoring method, such as GPS positioning, video monitoring, etc. However, these methods have certain limitations in information acquisition and cannot fully and accurately reflect the real-time status and behavior of unit vehicles. It is difficult for governments, enterprises and institutions to accurately monitor the application behavior of vehicles at all levels. With the increasingly strict management of unit vehicles and the increase in the demand for intelligence, traditional unit vehicle monitoring methods can no longer meet the comprehensiveness, accuracy and safety requirements of unit vehicle supervision. Summary of the invention

[0003] The purpose of this application is to provide a unit vehicle monitoring system, method and equipment based on multi-source information fusion, which can realize all-round and multi-angle monitoring of unit vehicles, improve management efficiency, protect the life and property safety of employees, and meet increasingly stringent regulatory needs.

[0004] This application is implemented as follows:

[0005] In a first aspect, the present application provides a unit vehicle monitoring system based on multi-source information fusion, comprising:

[0006] The information collection module is used to collect various detection data through the multi-source information collection terminal on the unit's vehicle to obtain a first data set; wherein the detection data in the first data set includes video monitoring data, GPS positioning data, oil sensor data, alcohol test sensor data and smoke sensor data. The data preprocessing module is used to classify and clean the various detection data in the first data set to obtain a second data set. The data fusion module is used to fuse the various detection data in the second data set and determine the comprehensive status and behavior information of the unit's vehicle based on the fused data. The result application module is used to perform real-time monitoring, alarm management, data analysis and management optimization processing on the fused data.

[0007] In some implementations, the comprehensive status and behavior information of the unit vehicle is determined based on the fused data, including: regularly capturing the driver's facial information during vehicle driving, and comparing it with the driver's basic information to perform driver identity recognition and driver substitution detection.

[0008] In some implementations, the comprehensive status and behavior information of the unit's vehicles is determined based on the fused data, including: determining fatigue driving judgment results based on data obtained by fusion of video surveillance data and GPS positioning data; determining smoking driving judgment results based on data obtained by fusion of fused video surveillance data and smoke sensor data; determining drunk driving judgment results based on data obtained by fusion of fused video surveillance data and alcohol test sensor data.

[0009] In some implementations, the data obtained by fusing video surveillance data and GPS positioning data is used to determine the result of fatigue driving judgment, including: when the fatigue state value P is greater than a first predetermined threshold, it is determined that fatigue driving exists; wherein the calculation formula of the fatigue state value P is P=α1I+α2W; α1 and α2 are correlation coefficients, I is the fatigue driving confidence given when the GPS positioning data shows that the vehicle speed is lower than the first preset speed value for a first preset time period, and W is the fatigue driving confidence given when the video surveillance data shows that the eye closing time exceeds a second preset time period.

[0010] In some implementations, the data obtained by fusing the fused video surveillance data and the smoke sensor data is used to determine the result of driving while smoking, including: when the smoking driving state value C is greater than a second predetermined threshold, it is determined that smoking driving exists; wherein the calculation formula of the smoking driving state value C is C=β1F+β2R; β1 and β2 are correlation coefficients, F is the smoke sensor confidence given when the fused video surveillance data shows that the windows in the car are open and the smoke sensor data is greater than the first smoke threshold, or when the fused video surveillance data shows that the windows in the car are closed and the smoke sensor data is greater than the second smoke threshold, and R is the confidence level of the cigarette information detected when the fused video surveillance data shows.

[0011] In some implementations, the data obtained by fusing the fused video surveillance data and the alcohol test sensor data is used to determine the drunk driving judgment result, including: when the drunk driving status value Z is greater than a third predetermined threshold, it is determined that drunk driving exists; wherein the calculation formula for the drunk driving status value Z is Z=γ1Q+γ2L; γ1 and γ2 are correlation coefficients, Q is the alcohol test sensor confidence given when the fused video surveillance data shows that the windows in the car are open and the alcohol test sensor data is greater than the first alcohol threshold, or when the fused video surveillance data shows that the windows in the car are closed and the alcohol test sensor data is greater than the second alcohol threshold, and L is the confidence when the fused video surveillance data shows that the coordination of the driver's facial expressions and body movements is drunk driving.

[0012] In some implementations, the result application module also includes a small program unit for employees to initiate vehicle applications, vehicle approvals, view real-time vehicle status, and receive alarm information.

[0013] In some implementations, the result application module further includes: a real-time monitoring unit for displaying the real-time fuel consumption of official vehicles and specific information on the driver's driving behavior; an alarm management unit for sending specific alarm content and suggestions to drivers and managers through sound, light or text messages; a data analysis unit for evaluating the vehicle's utilization efficiency and the compliance of driving behavior; and a management optimization processing unit for improving the vehicle management process based on the fused data.

[0014] In a second aspect, the present application provides a unit vehicle monitoring method based on multi-source information fusion, which comprises the following steps:

[0015] A variety of detection data are collected through a multi-source information collection terminal on the unit vehicle to obtain a first data set; wherein the detection data in the first data set includes video surveillance data, GPS positioning data, oil sensor data, alcohol test sensor data and smoke sensor data; various detection data in the first data set are classified and cleaned to obtain a second data set; the various detection data in the second data set are fused, and the comprehensive status and behavior information of the unit vehicle is determined based on the fused data; the fused data is subjected to real-time monitoring, alarm management, data analysis and management optimization processing.

[0016] In a third aspect, the present application provides an electronic device, comprising a memory for storing one or more programs; a processor; when the one or more programs are executed by the processor, the method described in the second aspect is implemented.

[0017] Compared with the prior art, the present invention has at least the following advantages or beneficial effects:

[0018] This application proposes a unit vehicle monitoring system based on multi-source information fusion, which uses a multi-source information collection terminal on the unit vehicle to widely collect various data including video monitoring, GPS positioning, oil status, alcohol testing and smoke sensors, thereby realizing the diversification and comprehensiveness of monitoring data and providing a rich information basis for subsequent processing. In addition, by fusing and processing multiple detection data and comprehensively evaluating the vehicle status and behavior, the limitations of single data source monitoring are overcome, and the real situation of the vehicle can be more accurately reflected, such as timely discovering and warning of potential safety hazards or violations. Moreover, through the application of functions such as real-time monitoring, alarm management, data analysis and management optimization, not only the real-time and response speed of monitoring are improved, but also problems in management can be discovered through data analysis, providing a scientific basis for optimizing vehicle use and management strategies, thereby improving management efficiency and safety levels. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 This is a structural block diagram of an embodiment of a unit vehicle monitoring system based on multi-source information fusion in this application;

[0021] Figure 2 This is a schematic diagram of the structure of a multi-source information acquisition terminal in one embodiment of the present application;

[0022] Figure 3 This is a structural diagram of data preprocessing and data fusion in one embodiment of the present application;

[0023] Figure 4 This is a schematic diagram of the structure of the result application module in one embodiment of the present application;

[0024] Figure 5 This is a schematic diagram of the vehicle monitoring process in one embodiment of the present application;

[0025] Figure 6 This is a flow chart of an embodiment of a method for monitoring vehicle use in a unit based on multi-source information fusion according to the present application;

[0026] Figure 7 A structural block diagram of an electronic device provided in an embodiment of the present application.

[0027] Icon: 201, processor; 202, memory; 203, communication interface. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution 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, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0029] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative work are within the scope of protection of the present application. In this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations.

[0030] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0031] Example 1

[0032] See also Figure 1 The unit vehicle monitoring system based on multi-source information fusion includes: an information acquisition module, which is used to collect various detection data through a multi-source information acquisition terminal on the unit vehicle to obtain a first data set; wherein the detection data in the first data set includes video monitoring data, GPS positioning data, oil sensor data, alcohol test sensor data and smoke sensor data. A data preprocessing module is used to classify and clean various detection data in the first data set to obtain a second data set. A data fusion module is used to fuse the various detection data in the second data set, and determine the comprehensive status and behavior information of the unit vehicle based on the fused data. A result application module is used to perform real-time monitoring, alarm management, data analysis and management optimization processing on the fused data.

[0033] In the above embodiment, through the multi-source information collection terminal on the company's vehicle, the system can simultaneously collect video monitoring data (used to monitor the inside and outside of the vehicle), GPS positioning data (used to determine the vehicle's location), oil sensor data (used to monitor the vehicle's oil status, such as engine oil, brake oil, etc.), alcohol test sensor data (used to detect whether the driver is drunk driving) and smoke sensor data (used to detect whether there is smoke in the vehicle, prevent fire, and detect whether someone is smoking in the vehicle) and other types of information. This diversified information collection method ensures the comprehensiveness and accuracy of the data. Through multi-source data collection, the accuracy and reliability of the data are improved, and the errors that may be caused by a single data source are reduced.

[0034] Then, after data collection, the system classifies and cleans the data through the data preprocessing module. Classification is to divide the data into different types (such as video surveillance, GPS positioning, etc.) for subsequent processing; cleaning is to remove invalid, duplicate or abnormal data to ensure the accuracy and consistency of the data. This step provides a reliable data foundation for subsequent data fusion and analysis.

[0035] Next, the data fusion module integrates the various pre-processed detection data to form a more comprehensive and integrated data set. Fusion processing refers to the integration of data from different sources and different types to form a more comprehensive and integrated data set. These data sets can reflect the comprehensive status of the vehicle (such as operating status, oil condition, etc.) and behavioral information (such as driver behavior, driving trajectory, etc.). Through data fusion, information integration and sharing can be achieved, and the comprehensive utilization rate of data can be improved. It can also provide more comprehensive data support for subsequent real-time monitoring, alarm management, data analysis and management optimization.

[0036] Finally, the system uses the result application module to perform real-time monitoring, alarm management, data analysis, and management optimization on the fused data. This step converts the value of data into actual management benefits, improves the safety and reliability of vehicle operation, and reduces operating costs. Among them, real-time monitoring refers to real-time tracking and monitoring of vehicle status and behavior; alarm management refers to timely alarms for abnormal situations based on preset rules and thresholds; data analysis refers to statistical analysis of collected data to mine valuable information; management optimization is to optimize vehicle management, driver training, etc. based on the analysis results.

[0037] Exemplarily, in some implementations of the present application, the steps of classifying and cleaning data may be as follows:

[0038] GPS positioning data: mainly records the real-time location, speed and driving trajectory of the vehicle. Due to the instability of GPS positioning accuracy, GPS data often has large deviations, such as abnormal GPS coordinates and large deviations in calculated speeds. At this time, it is necessary to identify and delete unreasonable data points. At the same time, because GPS positioning always reports location information, it is necessary to clean up invalid or duplicate reported data points.

[0039] Video surveillance data: Video data is first stored, and then AI capabilities are used to identify behaviors such as face capture, fatigue driving, dangerous driving, and whether the window is open. For video data, blurry and unrecognizable video frames need to be cleaned up first. Sometimes the camera is interfered by strong light, and some of the collected video images may not be able to see the driver's behavior clearly, resulting in inaccurate AI judgment. These video clips need to be cleaned up. Then, the different types of content identified by the AI ​​capability are classified and processed, and duplicate and invalid data are cleared.

[0040] Oil sensor data: records the vehicle's fuel consumption. Due to problems with the electronic components themselves, the oil sensor will occasionally have unreasonable values ​​that are too high or too low, and the data will obviously deviate from the normal range. This part of the data needs to be cleaned up. For missing data, the median and average values ​​are interpolated based on data with similar situations.

[0041] Alcohol test sensor data: records the driver's alcohol test results. It is necessary to perform threshold judgment on the alcohol sensor data. There are three thresholds in this system: one is the detection threshold before getting on the car, one is the real-time detection threshold for closing the windows while driving (information provided by integrated video AI capabilities), and one is the real-time detection threshold for opening the windows while driving. Test results that exceed the threshold are marked as abnormal, and alarms are issued and driving behavior is subsequently evaluated. Like other oil sensors, unreasonable values ​​that are too high or too low will appear, and the data will deviate significantly from the normal range. This part of the data needs to be cleaned up. For missing data, the median and average values ​​are interpolated based on data from similar situations.

[0042] Smoke sensor data: records the smoke concentration in the car. It is necessary to make a threshold judgment on the smoke sensor and mark the smoke concentration exceeding the threshold as abnormal. There are two thresholds in this system, one is the real-time detection threshold for closing windows while driving, and the other is the real-time detection threshold for opening windows while driving. Others, like oil sensors, will have unreasonable values ​​that are too high or too low, and the data will have values ​​that are obviously deviated from the normal range. This part of the data needs to be cleaned up. For missing data, the median and average values ​​are interpolated based on data in similar situations.

[0043] Based on the aforementioned scheme, in some implementation methods of the present application, the comprehensive status and behavior information of the unit vehicle is determined based on the fused data, including: regularly capturing the driver's facial information during the vehicle's driving, and comparing it with the driver's basic information to perform driver identity recognition and driver change detection.

[0044] In the above implementation, by regularly capturing the driver's facial information and comparing it with the data in the driver's basic information database, the system can confirm the identity of the current driver in real time. This function is crucial to ensure that only authorized personnel can drive the company's vehicles, and helps prevent the theft or abuse of vehicles. During continuous driving, if the system detects different facial information, it indicates that there may be a change of driving. This detection capability is of great significance in ensuring driving safety, preventing fatigue driving, and complying with traffic rules.

[0045] This processing method, which incorporates the results of driver identity recognition and driver substitution detection into the comprehensive status and behavior information of the unit's vehicle use, enables the system to provide more comprehensive and accurate vehicle usage reports, bringing users a safer, more efficient and compliant vehicle use experience.

[0046] Based on the aforementioned scheme, in some implementation methods of the present application, the comprehensive status and behavior information of the unit vehicle is determined based on the fused data, including: determining the fatigue driving judgment result based on the data obtained by fusion of video surveillance data and GPS positioning data; determining the smoking driving judgment result based on the data obtained by fusion of fused video surveillance data and smoke sensor data; determining the drunk driving judgment result based on the data obtained by fusion of fused video surveillance data and alcohol test sensor data.

[0047] In the above embodiment, the driver's blinking frequency, head posture, facial expression and other characteristics are analyzed through video monitoring data to determine whether he is in a state of fatigue. At the same time, GPS positioning data can assist in determining the driving status of the vehicle, such as frequent lane deviations, unstable driving speed, etc., which may also be signs of fatigue driving. Therefore, by combining the data of both, the system can more accurately determine whether the driver is in a state of fatigue driving and issue a warning in time.

[0048] Video surveillance data can be used to capture whether the driver is holding a cigarette or lighting a cigarette. The smoke sensor can detect whether there are smoke particles in the air inside the car, which can serve as direct evidence of smoking. When both data indicate that the driver is smoking, the system will make a judgment that the driver is driving while smoking and take corresponding measures, such as issuing a warning or recording a violation.

[0049] Video surveillance data can be used to observe the driver's facial expressions and movements, as well as any abnormal behavior. Using alcohol test sensor data, the alcohol content in the driver's body can be detected by contact or non-contact methods. For example, video surveillance data can capture abnormal behaviors such as slurred speech and slow reaction of the driver that may be caused by drinking. The alcohol test sensor provides more direct and accurate alcohol content data. Therefore, by combining the data of both, the system can determine whether the driver is in a drunk driving state and take immediate measures, such as prohibiting the vehicle from starting or notifying relevant departments.

[0050] In summary, the above implementation method is used to integrate multiple data sources to determine the comprehensive status and behavior information of the unit’s vehicles, which not only improves the accuracy and comprehensiveness of the monitoring system, but also can bring significant safety, management and compliance benefits.

[0051] Based on the aforementioned scheme, in some implementation methods of the present application, the data obtained by fusing the video surveillance data and the GPS positioning data is used to determine the result of fatigue driving judgment, including: when the fatigue state value P is greater than a first predetermined threshold, it is determined that fatigue driving exists; wherein the calculation formula of the fatigue state value P is P=α1I+α2W; α1 and α2 are correlation coefficients, I is the fatigue driving confidence given when the GPS positioning data shows that the vehicle speed is lower than the first preset speed value for a first preset time period, and W is the fatigue driving confidence given when the video surveillance data shows that the eye closure time exceeds a second preset time period.

[0052] In the above implementation, it is shown how to integrate video surveillance data and GPS positioning data, comprehensively consider multiple factors such as the driver's eye closing time and the vehicle's driving speed, so as to more accurately judge whether there is fatigue driving. Among them, α1 and α2 are correlation coefficients, which are used to adjust the contribution of different data sources to the fatigue state value P. These coefficients can be set or adjusted according to actual conditions to optimize the accuracy of the judgment result. I is the fatigue driving confidence given when the GPS positioning data shows that the vehicle speed continues to be lower than the first preset speed value (such as 30km / h) for the first preset time period (such as 5 minutes). This confidence reflects the possibility that the low-speed driving of the vehicle may be related to the driver's fatigue driving. W is the fatigue driving confidence given when the video surveillance data shows that the driver's eye closing time exceeds the second preset time period (such as 2 seconds). This confidence reflects the possibility that the driver's eye closing may be directly related to fatigue driving.

[0053] Based on the aforementioned scheme, in some implementation methods of the present application, the data obtained by fusing the fused video surveillance data and the smoke sensor data is used to determine the result of smoking driving judgment, including: when the smoking driving state value C is greater than the second predetermined threshold, it is determined that smoking driving exists; wherein the calculation formula of the smoking driving state value C is C=β1F+β2R; β1 and β2 are correlation coefficients, F is the smoke sensor confidence given when the fused video surveillance data shows that the window in the car is open and the smoke sensor data is greater than the first smoke threshold, or when the fused video surveillance data shows that the window in the car is closed and the smoke sensor data is greater than the second smoke threshold, and R is the confidence level of the cigarette information detected when the fused video surveillance data shows.

[0054] In the above implementation, it is given how to accurately judge whether the driver smokes during driving by fusing video surveillance data and smoke sensor data, and take corresponding response measures, thereby improving driving safety and vehicle management efficiency. Among them, β1 and β2 are correlation coefficients, which are used to adjust the contribution of different data sources to the smoking driving state value C. These coefficients can be set or adjusted according to actual conditions to optimize the accuracy of the judgment result. F is the smoke sensor confidence given when the fused video surveillance data shows that the window in the car is open and the smoke sensor data is greater than the first smoke threshold, or when the window in the car is closed and the smoke sensor data is greater than the second smoke threshold. This confidence reflects the degree of correlation between the smoke concentration in the car and the smoking behavior. It should be noted that the corresponding smoke thresholds may be different in the open and closed window states, because the smoke may be easier to dissipate when the window is open, while the smoke concentration may be higher when the window is closed. R is the confidence of the detected cigarette information shown by the fused video surveillance data. This confidence directly reflects the degree of correlation between the cigarette detected in the video surveillance data and the smoking behavior.

[0055] Based on the aforementioned scheme, in some implementation methods of the present application, the data obtained by fusing the fused video surveillance data and the alcohol test sensor data is used to determine the drunk driving judgment result, including: when the drunk driving status value Z is greater than the third predetermined threshold, it is determined that drunk driving exists; wherein the calculation formula of the drunk driving status value Z is Z=γ1Q+γ2L; γ1 and γ2 are correlation coefficients, Q is the alcohol test sensor confidence given when the fused video surveillance data shows that the windows in the car are open and the alcohol test sensor data is greater than the first alcohol threshold, or when the fused video surveillance data shows that the windows in the car are closed and the alcohol test sensor data is greater than the second alcohol threshold, and L is the confidence when the fused video surveillance data shows that the coordination of the driver's facial expressions and body movements is drunk driving.

[0056] In the above implementation, it is given how to accurately judge whether the driver is driving after drinking by fusing video surveillance data and alcohol test sensor data, and take corresponding response measures, thereby improving driving safety and traffic management efficiency. Among them, γ1 and γ2 are correlation coefficients, which are used to adjust the contribution of different data sources to the drunk driving state value Z. These coefficients can be set or adjusted according to actual conditions to optimize the accuracy of the judgment result. Q is the confidence of the alcohol test sensor given when the fused video surveillance data shows that the window in the car is open and the alcohol test sensor data is greater than the first alcohol threshold, or when the window in the car is closed and the alcohol test sensor data is greater than the second alcohol threshold. This confidence reflects the degree of correlation between the alcohol concentration in the car and the drunk driving behavior. It should be noted that the corresponding alcohol thresholds may be different in the open and closed window states, because alcohol may be easier to dissipate when the window is open, and the alcohol concentration may be higher when the window is closed. L is the confidence when the fused video surveillance data shows that the coordination of the driver's facial expressions and body movements is drunk driving. This confidence level is determined by analyzing the driver's facial expressions (such as blurred eyes and dull expression) and body movements (such as slow reactions and uncoordinated operations).

[0057] Based on the aforementioned scheme, in some implementations of the present application, the result application module also includes a small program unit for employees to initiate vehicle applications, vehicle approvals, view real-time vehicle status, and receive alarm information.

[0058] In the above implementation, employees can quickly fill in the car application information through the mini program unit, including the time, location, purpose, model requirements, etc. After submitting the application, the system will automatically send the application information to the relevant department or approver for approval. Then, the approver can easily view the list of car applications to be approved through the mini program unit; they can also agree or reject each application and attach approval opinions. The approval result will be fed back to the applicant employee in real time so that the employee can make subsequent arrangements based on the approval situation.

[0059] At the same time, employees can view the current status of the vehicle in real time through the mini-program unit, such as vehicle location, driving speed, whether it is idle, etc. This function helps employees better plan their vehicle use time and avoid vehicle resource conflicts. In addition, when the vehicle is abnormal or the system detects potential risks, the mini-program unit will send warning information to employees in real time. Warning information may include vehicle failure, traffic violations, drunk driving or fatigue driving detection, etc. Therefore, employees can take corresponding measures based on the warning information to ensure driving safety and normal use of the vehicle.

[0060] Based on the aforementioned scheme, in some implementation methods of the present application, the result application module further includes: a real-time monitoring unit for displaying the real-time fuel consumption of official vehicles and specific information on the driver's driving behavior; an alarm management unit for sending specific alarm content and suggestions to drivers and managers through sound, light or text messages; a data analysis unit for evaluating the vehicle's utilization efficiency and the compliance of driving behavior; a management optimization processing unit for improving the vehicle management process based on the fused data.

[0061] In the above implementation, by expanding the functions of the result application module, a comprehensive solution is provided for official vehicle management and driving behavior monitoring, which helps to improve vehicle utilization efficiency, ensure driving safety, and optimize management processes.

[0062] Specifically, the real-time monitoring unit is responsible for displaying the real-time fuel consumption of official vehicles and specific information about the driver's driving behavior. This information includes but is not limited to: 1) Real-time fuel consumption: Displays the current vehicle's fuel consumption rate, remaining fuel, and estimated cruising range, helping drivers and managers to understand the vehicle's fuel status in a timely manner and avoid the embarrassing situation of running out of fuel. 2) Driving behavior information: including vehicle speed, acceleration, braking force, steering angle, etc., as well as judgments on whether the driver follows traffic rules, whether he is driving fatigued, whether he is driving distracted, etc. This information helps to evaluate the driver's driving skills and compliance.

[0063] The alarm management unit is responsible for sending specific alarm content and suggestions to drivers and managers through sound, light or text messages. Alarms may include: 1) Abnormal driving behavior alarm: such as speeding, sudden braking, sudden acceleration, distracted driving, etc., the system will immediately send an alarm message to remind the driver to pay attention to driving safety. 2) Vehicle fault alarm: such as engine failure, insufficient tire pressure, abnormal braking system, etc., the system will promptly notify the driver and management personnel so that repairs can be carried out as soon as possible. 3) Maintenance reminder: According to the vehicle's usage and maintenance plan, the system will send maintenance reminders to ensure that the vehicle is in the best working condition.

[0064] The data analysis unit is responsible for evaluating the efficiency of vehicle use and the compliance of driving behavior. By collecting and analyzing a large amount of data, the system can: 1) evaluate vehicle use efficiency: such as vehicle utilization, mileage, fuel efficiency, etc., to help managers optimize vehicle scheduling and allocation and improve vehicle use efficiency. 2) evaluate driving behavior compliance: score and rank drivers' driving behaviors, identify high-risk drivers and driving behaviors with poor compliance, so as to carry out targeted training and improvement.

[0065] The management optimization processing unit is responsible for improving the vehicle management process based on the fused data. This includes: 1) Optimizing vehicle dispatch: Intelligently dispatching vehicles based on real-time vehicle location and driver status to reduce idle time and resource waste. 2) Improving driving training: Developing personalized training plans for high-risk drivers and non-compliant driving behaviors to improve drivers' driving skills and compliance. 3) Optimizing maintenance plans: Developing more reasonable maintenance plans based on the actual use of vehicles and data analysis results to extend vehicle service life and reduce maintenance costs.

[0066] In order to enable those skilled in the art to understand the present application more intuitively, a specific example will be used here to illustrate.

[0067] To support the implementation of the above system, it is necessary to install multiple source information collection terminals on the vehicle, such as vehicle-mounted cameras, vehicle-mounted smoke sensors, vehicle-mounted fuel consumption detection sensors, vehicle-mounted alcohol testers and other sensors, so as to construct a source information collection terminal such as Figure 2 As shown. Among them, the information collection device is powered by the vehicle power supply, and uses wireless communication technology to transmit relevant data back to the data preprocessing module. Among them, the alcohol sensor will not only transmit the alcohol detection value, but also if the alcohol detection exceeds the standard before getting on the car, the sensor will have sound and light warning prompts, and will send the driver alcohol detection warning SMS to the dispatcher; video surveillance in addition to transmitting the video information collection module, the video data is stored in the video middle platform, and through AI capabilities, the driver's facial information is captured regularly and compared with the driver's basic information. If the driver is changed, an alarm will be issued. At the same time, the driver's fatigue driving, dangerous driving, smoking and other dangerous driving behaviors are identified, and relevant evidence is transmitted back, and sound and light alarms are issued through the camera; the smoke alarm monitors the smoke concentration in the car in real time, monitors the driver's smoking star network, and if the monitoring concentration exceeds the control, the relevant smoke alarm data will be reported to the information collection module, and the smoke alarm will be used through sound and light to alarm.

[0068] Then, various sensor information and video stream data are reported to the data preprocessing module through wireless communication technology. The data preprocessing module classifies, cleans and processes the collected information, and then uses the data fusion module to fuse the preprocessed multi-source information to obtain the comprehensive status and behavior information of the official vehicle. Among them, the structure of the data fusion module is as follows Figure 3Then, the various alarm data (including alcohol sensor alarms, smoke sensor alarms) and fuel consumption data obtained are stored in the business database to associate official vehicles and vehicle users; video data is stored in the video database, and the business database calls the video database related data through related functions, including viewing real-time video, historical video, illegal video clips and alarm information; the device's own data is stored in the device database, recording the basic information and status information of the device; the vehicle's longitude and latitude data is processed by the information fusion system and stored in the trajectory database. The business system draws real-time trajectory, historical trajectory and mileage calculation through the longitude and latitude information in the trajectory database.

[0069] Finally, if Figure 4 As shown, the constructed result application module can include a PC-side backend management system and a WeChat applet, integrating functions such as vehicle management, vehicle application, vehicle statistics, and real-time alarms. Management scheduling can be viewed at any time, and statistics on the number of vehicle dispatches and vehicle operating status can be obtained.

[0070] Among them, the equipment management module manages the establishment of management records for all sensors and cameras, including the entire process of equipment procurement, warehousing, vehicle binding, and scrapping. It can monitor the operating status of the equipment in real time, understand the operating status of the equipment, and help users discover and solve equipment problems in a timely manner.

[0071] The vehicle management module maintains and manages the basic information of the vehicle, including the basic attributes of the vehicle, such as license plate, model, frame number, engine number, displacement, age, annual inspection, insurance, ETC card number, gas card number, vehicle type, bound sensors and cameras, and other basic information maintenance and entry.

[0072] The vehicle management module includes functions such as vehicle application, vehicle approval, vehicle dispatch, travel trajectory, fuel consumption analysis, real-time / historical driving video, driving warning violation records, etc. Through the digital integration, sharing and use of vehicle management information and multi-source information, it can better monitor the vehicle driving status, improve the management level and utilization efficiency of official vehicles, and reduce illegal vehicle use.

[0073] The driver management module includes functions such as driver records, violation records, and vehicle dispatch records, which are designed to comprehensively manage and monitor the driver's various activities and performances, analyze the driver's vehicle dispatch records, violation records and other data, evaluate the driver's driving skills and safety, and fully understand the driver's driving level. Based on the evaluation results, feedback and suggestions are provided to the driver to help them improve their driving level.

[0074] The alarm management module is mainly used to monitor the driver's violations when using the vehicle. The collected alarm information will be analyzed and processed to determine the severity and urgency of the alarm. The system will respond differently according to the different levels of the alarm. For example, an alcohol test is performed before the vehicle is started. After the alarm is generated, the sensor will have an audible and visual alarm, and the system oil will automatically send a text message to the vehicle dispatcher and driver, and the dispatcher will go to stop the driver's driving. Ordinary alarms are recorded in the driver's alarm record and the vehicle driving record. According to the evaluation results of the violation record, excellent drivers will be rewarded and drivers with poor performance will be punished.

[0075] All equipment will be notified of violations and alarm information will be issued promptly to attract the attention of managers and prompt them to take timely measures to minimize losses and make every effort to ensure the continuity, reliability and stability of services.

[0076] The statistical report module mainly includes reports related to vehicle usage statistics, violation statistics, and vehicle expense statistics.

[0077] The system management module provides basic support for the use of the vehicle management system, including organizational structure, role management, user management, and permission management.

[0078] Thus, after the corresponding program product is constructed based on the system of the present application, the vehicle monitoring process can be as follows: Figure 5 As shown:

[0079] Employees apply for a car on the mini program. After approval by relevant leaders, the dispatcher dispatches the car and the driver starts to get on the car. When the driver gets on the car, the on-board monitoring system first performs facial recognition on the driver to confirm whether it is the driver himself. If it is not the driver himself, the platform will generate an alarm message and send a text message to the dispatcher.

[0080] After passing the video authentication, the driver needs to undergo an alcohol test before departure. If alcohol is detected, the platform will generate relevant alarm information and send an alarm text message to the dispatcher.

[0081] After passing the video authentication and alcohol test, the driver can set off on the road. During the journey, the platform determines whether there is any violation by integrating information from multiple sources, such as whether the driver has changed (face capture), whether he has smoked (camera + smoke sensor), whether he has drunk driving (alcohol sensor), and whether he has exceeded the speed limit (GPS). Different warnings are issued for different violation levels, and relevant alarm data is fed back to the platform.

[0082] After the driving is finished, the driver stops the car and clicks on the mini program to collect the car, and the car is turned off at the same time, ending the dispatch. The platform will calculate the real record of the fuel consumption based on the fuel consumption detection sensor and GPS track positioning, and generate a driving track map.

[0083] Finally, a driving report for the vehicle is generated, including alarms, mileage, fuel consumption, average speed, etc. during driving, and the comprehensive assessment information is bound to the driver as the basis for annual data analysis.

[0084] Example 2

[0085] See also Figure 6 The embodiment of the present application provides a unit vehicle monitoring method based on multi-source information fusion, which includes the following steps:

[0086] Step S101: Collect various detection data through the multi-source information collection terminal on the unit vehicle to obtain a first data set; wherein the detection data in the first data set includes video monitoring data, GPS positioning data, oil sensor data, alcohol test sensor data and smoke sensor data; Step S102: Classify and clean the various detection data in the first data set to obtain a second data set; Step S103: Fuse the various detection data in the second data set, and determine the comprehensive status and behavior information of the unit vehicle based on the fused data; Step S104: Perform real-time monitoring, alarm management, data analysis and management optimization processing on the fused data.

[0087] For the specific implementation process of the above method, please refer to the unit vehicle monitoring system based on multi-source information fusion provided in Example 1, which will not be repeated here.

[0088] Example 3

[0089] See also Figure 7 , the embodiment of the present application provides an electronic device, which includes at least one processor 201 and at least one memory 202; wherein the processor 201 and the memory 202 are directly connected to each other, or communicate with each other through a communication interface 203, or are electrically connected through one or more communication buses or signal lines to achieve data transmission or interaction; the memory 202 stores program instructions that can be executed by the processor 201, and the processor 201 calls the program instructions to execute a unit vehicle monitoring method based on multi-source information fusion. For example, the following is realized:

[0090] A variety of detection data are collected through a multi-source information collection terminal on the unit vehicle to obtain a first data set; wherein the detection data in the first data set includes video surveillance data, GPS positioning data, oil sensor data, alcohol test sensor data and smoke sensor data; various detection data in the first data set are classified and cleaned to obtain a second data set; the various detection data in the second data set are fused, and the comprehensive status and behavior information of the unit vehicle is determined based on the fused data; the fused data is subjected to real-time monitoring, alarm management, data analysis and management optimization processing.

[0091] Among them, the memory 202 can be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc.

[0092] The processor 201 may be an integrated circuit chip with signal processing capability. The processor 201 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0093] Understandably, Figure 7 The structure shown is for illustration only. The electronic device may also include Figure 7 More or fewer components as shown, or with Figure 7 Different configurations shown. Figure 7 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0094] It will be apparent to those skilled in the art that the present application is not limited to the details of the exemplary embodiments described above, and that the present application can be implemented in other specific forms without departing from the spirit or essential features of the present application. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the present application is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims be included in the present application. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A unit vehicle monitoring system based on multi-source information fusion, characterized in that: include: An information collection module is used to collect a variety of detection data through a multi-source information collection terminal on a company vehicle to obtain a first data set; wherein the detection data in the first data set includes video monitoring data, GPS positioning data, oil sensor data, alcohol test sensor data and smoke sensor data; A data preprocessing module, used for classifying and cleaning various detection data in the first data set to obtain a second data set; A data fusion module, used for fusing the various detection data in the second data set, and determining the comprehensive status and behavior information of the unit vehicle according to the fused data; The result application module is used to perform real-time monitoring, alarm management, data analysis and management optimization processing on the fused data.

2. The system according to claim 1, characterized in that The comprehensive status and behavior information of the unit vehicle is determined based on the fused data, including: The driver's facial information is captured regularly while the vehicle is driving and compared with the driver's basic information to perform driver identity recognition and driver substitution detection.

3. The system according to claim 1, characterized in that The comprehensive status and behavior information of the unit vehicle is determined based on the fused data, including: Determine the result of fatigue driving judgment based on the data obtained by fusing video monitoring data and GPS positioning data; Determine the smoking driving judgment result based on the data obtained by fusing the video monitoring data and the smoke sensor data; The drunk driving judgment result is determined based on the data obtained by fusing the video surveillance data and the alcohol test sensor data.

4. The system according to claim 3, characterized in that The method of determining the fatigue driving judgment result based on the data obtained by fusing the video monitoring data and the GPS positioning data includes: When the fatigue state value P is greater than a first predetermined threshold, fatigue driving is determined to exist; wherein the calculation formula for the fatigue state value P is P=α1I+α2W; α1 and α2 are correlation coefficients, I is the fatigue driving confidence level given when the GPS positioning data shows that the vehicle speed is lower than the first preset speed value for a first preset time period, and W is the fatigue driving confidence level given when the video monitoring data shows that the eye closing time exceeds a second preset time period.

5. The system according to claim 3, characterized in that The method of determining the smoking driving judgment result based on the data obtained by fusing the video monitoring data and the smoke sensor data includes: When the smoking driving state value C is greater than the second predetermined threshold, it is determined that smoking driving exists; wherein the calculation formula of the smoking driving state value C is C=β1F+β2R; β1 and β2 are correlation coefficients, F is the smoke sensor confidence given when the fused video surveillance data shows that the windows in the car are open and the smoke sensor data is greater than the first smoke threshold, or when the fused video surveillance data shows that the windows in the car are closed and the smoke sensor data is greater than the second smoke threshold, and R is the confidence level of the cigarette information detected when the fused video surveillance data shows.

6. The system according to claim 3, characterized in that The method of determining the drunk driving judgment result based on the data obtained by fusing the video monitoring data and the alcohol test sensor data includes: When the drunk driving status value Z is greater than the third predetermined threshold, it is determined that drunk driving exists; wherein, the calculation formula of the drunk driving status value Z is Z=γ1Q+γ2L; γ1 and γ2 are correlation coefficients, Q is the confidence of the alcohol test sensor given when the fused video surveillance data shows that the windows in the car are open and the alcohol test sensor data is greater than the first alcohol threshold, or when the fused video surveillance data shows that the windows in the car are closed and the alcohol test sensor data is greater than the second alcohol threshold, and L is the confidence when the fused video surveillance data shows that the coordination of the driver's facial expressions and body movements is drunk driving.

7. The system according to claim 1, characterized in that The result application module also includes a small program unit, which is used by employees to initiate vehicle application, vehicle approval, view real-time vehicle status and receive alarm information.

8. The system according to claim 1, characterized in that The result application module further comprises: A real-time monitoring unit is used to display the real-time fuel consumption of official vehicles and detailed information on the driver's driving behavior; The warning management unit is used to send specific warning content and suggestions to drivers and managers through sound, light or text message; Data analysis unit, used to evaluate the efficiency of vehicle use and the compliance of driving behavior; The management optimization processing unit is used to improve the vehicle management process based on the fused data.

9. A unit vehicle monitoring method based on multi-source information fusion, characterized in that: The following steps are involved: A plurality of detection data are collected through a multi-source information collection terminal on a unit vehicle to obtain a first data set; wherein the detection data in the first data set includes video monitoring data, GPS positioning data, oil sensor data, alcohol test sensor data and smoke sensor data; Classifying and cleaning various detection data in the first data set to obtain a second data set; Fusing the various detection data in the second data set, and determining the comprehensive status and behavior information of the unit vehicle based on the fused data; The fused data is subjected to real-time monitoring, alarm management, data analysis and management optimization.

10. An electronic device, characterized in that: include: A memory for storing one or more programs; processor; When the one or more programs are executed by the processor, the method according to claim 9 is implemented.

Images