Online car-hailing safety monitoring method and device, computer equipment and storage medium

Abstract

The invention relates to an online car-hailing safety monitoring method and device, computer equipment and a storage medium. The method comprises the steps of determining a safety monitoring mode in response to a selection operation on the safety monitoring mode of the online car-hailing; in response to the fact that the safety monitoring mode is a visual monitoring mode, obtaining visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data and context awareness feature data of the online car-hailing; performing data processing on the visual monitoring feature data, the sensor monitoring feature data, the positioning monitoring feature data and the context awareness feature data to obtain feature data after feature fusion; and inputting the feature data after feature fusion into a pre-trained vehicle safety monitoring network model to obtain a high-precision online car-hailing safety monitoring result. By adopting the method, the monitoring efficiency and accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of online car-hailing safety monitoring, and in particular to an online car-hailing safety monitoring method, apparatus, computer equipment and storage medium. Background Art

[0002] With the rapid development of Internet technology, online ride-hailing services are becoming more and more popular among users, and users can take rides more conveniently and quickly through online ride-hailing services. However, safety accidents caused by taking online ride-hailing services also occur frequently. Safety monitoring of online ride-hailing services is an effective measure to ensure the safety of users.

[0003] However, traditional online ride-hailing safety monitoring methods have problems such as low efficiency or low accuracy. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment and storage medium for online car-hailing safety monitoring that can improve monitoring efficiency and accuracy in response to the above-mentioned technical problems.

[0005] In a first aspect, a method for monitoring the safety of an online car-hailing service is provided, the method comprising:

[0006] In response to a selection operation of a safety monitoring mode of the online car-hailing vehicle, determining a safety monitoring mode; wherein the safety monitoring mode includes a visual monitoring mode and a sensor monitoring mode;

[0007] In response to the safety monitoring mode being the visual monitoring mode, obtaining visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data, and situational awareness feature data of the online car-hailing vehicle, and processing the visual monitoring feature data, the sensor monitoring feature data, the positioning monitoring feature data, and the situational awareness feature data to obtain feature data after feature fusion;

[0008] The feature data after feature fusion is input into the pre-trained vehicle safety monitoring network model to obtain high-precision online ride-hailing safety monitoring results; among them, the high-precision online ride-hailing safety monitoring results include abnormal driving behavior of the driver, abnormal riding behavior of the passenger, faulty driving behavior of the vehicle or normal driving behavior of the vehicle.

[0009] In one of the embodiments, the visual monitoring feature data of the online ride-hailing vehicle includes data collected by the front camera, data collected by the vehicle's main camera, and data collected by the vehicle's auxiliary camera; the sensor monitoring feature data includes acceleration sensor data, angular velocity sensor data, pressure sensor data, temperature and humidity sensor data, alcohol sensor data, and smoke sensor data; the positioning monitoring feature data includes global positioning system positioning data, Beidou satellite navigation system positioning data, Russian-developed satellite navigation system positioning data, and inertial navigation system data.

[0010] In one embodiment, obtaining context-aware feature data includes:

[0011] Obtaining driving time characteristic data, weather characteristic data, geographical area type characteristic data, and driving trip type characteristic data of online ride-hailing vehicles;

[0012] The driving time characteristic data, weather characteristic data, geographical area type characteristic data and driving trip type characteristic data are input into a pre-trained context-aware network model to obtain context-aware characteristic data; wherein the context-aware characteristic data is used to characterize the warning sensitivity of the online car-hailing vehicle at the current moment.

[0013] In one of the embodiments, visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data and situational awareness feature data are processed to obtain feature data after feature fusion, including: formatting the visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data and situational awareness feature data to obtain formatted visual monitoring feature data, formatted sensor monitoring feature data, formatted positioning monitoring feature data and formatted situational awareness feature data; wherein the formatting processing includes data integrity verification processing, data decryption processing and data compression combing; feature fusion processing is performed on the formatted visual monitoring feature data, formatted sensor monitoring feature data, formatted positioning monitoring feature data and formatted situational awareness feature data to obtain feature data after feature fusion.

[0014] In one of the embodiments, the method includes: in response to a high-precision online car-hailing safety monitoring result indicating abnormal driving behavior of the driver, outputting a warning prompt message of the driver's abnormal driving behavior to the passenger user terminal corresponding to the online car-hailing vehicle; in response to receiving a first emergency rescue message sent by the passenger user terminal, determining the contact information of the first emergency rescuer of the passenger user terminal according to the first emergency rescue message, and executing an emergency rescue call operation according to the contact information of the first emergency rescuer.

[0015] In one of the embodiments, the method includes: in response to a high-precision online car-hailing safety monitoring result indicating abnormal riding behavior of a passenger, outputting a warning prompt message of abnormal riding behavior of the passenger to a driver user terminal corresponding to the online car-hailing vehicle; in response to receiving a second emergency rescue message sent by the driver user terminal, determining the contact information of a second emergency rescuer of the passenger user terminal according to the second emergency rescue message, and executing an emergency rescue call operation according to the contact information of the second emergency rescuer.

[0016] In one of the embodiments, the method includes: in response to a high-precision online car-hailing safety monitoring result indicating a vehicle faulty driving behavior, outputting vehicle faulty driving behavior warning prompt information to the passenger user terminal and driver user terminal corresponding to the online car-hailing vehicle.

[0017] In one of the embodiments, the method includes: in response to the safety monitoring mode being a sensor monitoring mode, obtaining sensor monitoring feature data; performing an online car-hailing safety analysis based on the sensor monitoring feature data to obtain low-precision online car-hailing safety monitoring results; the low-precision online car-hailing safety monitoring results are used to characterize the driving safety status and environmental safety status of the online car-hailing; and outputting comprehensive safety warning prompt information for the online car-hailing based on the low-precision online car-hailing safety monitoring results.

[0018] In a second aspect, a device for monitoring the safety of an online car-hailing service is provided, the device comprising a mode selection module, a data processing module and a model analysis module.

[0019] Among them, the mode selection module is used to determine the safety monitoring mode in response to the selection operation of the safety monitoring mode of the online car-hailing vehicle; wherein, the safety monitoring mode includes a visual monitoring mode and a sensor monitoring mode; the data processing module is used to obtain the visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data and situational perception feature data of the online car-hailing vehicle in response to the safety monitoring mode being the visual monitoring mode, and obtain the feature data after feature fusion after data processing of the visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data and situational perception feature data; the model analysis module is used to input the feature data after feature fusion into a pre-trained vehicle safety monitoring network model to obtain high-precision safety monitoring results of the online car-hailing vehicle; wherein, the high-precision safety monitoring results of the online car-hailing vehicle include abnormal driving behavior of the driver, abnormal riding behavior of the passenger, faulty driving behavior of the vehicle or normal driving behavior of the vehicle.

[0020] In a third aspect, a computer device is provided. The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the steps of any method in the above method embodiments are implemented.

[0021] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any method in the above method embodiments are implemented.

[0022] The above-mentioned online car-hailing safety monitoring method, device, computer equipment and storage medium determine the safety monitoring mode in response to selecting the safety monitoring mode of the online car-hailing; wherein the safety monitoring mode includes a visual monitoring mode and a sensor monitoring mode; then, in response to the safety monitoring mode being the visual monitoring mode, the visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data and situational perception feature data of the online car-hailing are obtained, and the visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data and situational perception feature data are processed to obtain feature data after feature fusion; then, the feature data after feature fusion is input into a pre-trained vehicle safety monitoring network model to obtain high-precision online car-hailing safety monitoring results; wherein the high-precision online car-hailing safety monitoring results include abnormal driving behavior of the driver, abnormal riding behavior of the passenger, faulty driving behavior of the vehicle or normal driving behavior of the vehicle; thus, the monitoring efficiency, accuracy and real-time performance are improved, and the accident rate is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is an application environment diagram of a method for monitoring the safety of online ride-hailing vehicles in one embodiment;

[0024] Figure 2 A schematic diagram of a first process of a method for monitoring the safety of online ride-hailing vehicles in one embodiment;

[0025] Figure 3 A schematic diagram of a process for obtaining context-aware feature data in one embodiment;

[0026] Figure 4 It is a flow chart of obtaining feature data after feature fusion after data processing of visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data and situational awareness feature data in one embodiment;

[0027] Figure 5 A second flow chart of the online car-hailing safety monitoring method in another embodiment;

[0028] Figure 6 A third flow chart of a method for monitoring the safety of online ride-hailing vehicles in another embodiment;

[0029] Figure 7 This is a structural block diagram of a safety monitoring device for online car-hailing in one embodiment;

[0030] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0032] In order to facilitate understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. Embodiments of the present application are provided in the drawings. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.

[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0034] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first resistor may be referred to as a second resistor, and similarly, a second resistor may be referred to as a first resistor. Both the first resistor and the second resistor are resistors, but they are not the same resistor.

[0035] It can be understood that the “connection” in the following embodiments should be understood as “electrical connection”, “communication connection”, etc. if the connected circuits, modules, units, etc. have electrical signals or data transmission between each other.

[0036] When used herein, the singular forms "a", "an", and "said / the" may also include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "include / comprise" or "have" etc. specify the presence of stated features, wholes, steps, operations, components, parts or combinations thereof, but do not exclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts or combinations thereof.

[0037] The online car-hailing safety monitoring method provided in this application can be applied to Figure 1 In the application environment shown, the driver user terminal 101 and the passenger user terminal 102 communicate with the server 104 through the network. The driver user terminal 101 and the passenger user terminal 102 can be, but are not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices, and the server 104 can be implemented by an independent server or a server cluster consisting of multiple servers.

[0038] In one embodiment, Figure 2 As shown, a method for monitoring the safety of online car-hailing is provided, and the method is applied to Figure 1 The server 104 in the example is used for explanation, and the steps include the following steps 201 to 203.

[0039] Step 201, in response to a selection operation on a safety monitoring mode of an online car-hailing service, determines a safety monitoring mode.

[0040] The safety monitoring mode includes a visual monitoring mode and a sensor monitoring mode. Specifically, the server 104 determines the safety monitoring mode in response to a selection operation on the safety monitoring mode of the online car-hailing service.

[0041] In a specific example, in response to selecting a safety monitoring mode for an online car-hailing service, determining the safety monitoring mode includes:

[0042] Obtain the permission data of the driver user terminal and the passenger user terminal corresponding to the online car-hailing service;

[0043] Analyze the permission data of the driver user terminal to obtain the driver user visual monitoring permission setting result; the driver user visual monitoring permission setting result includes opening permission or closing permission;

[0044] Analyze the permission data of the passenger user terminal to obtain the result of setting the visual monitoring permission of the passenger user; the result of setting the visual monitoring permission of the passenger user includes opening the permission or closing the permission;

[0045] In response to the driver user's visual monitoring permission setting result being an enabled permission and the passenger user's visual monitoring permission setting result being an enabled permission, automatically selecting the safety monitoring mode of the online car-hailing vehicle as a visual monitoring mode;

[0046] In response to the driver user's visual monitoring permission setting result being closed permission or the passenger user's visual monitoring permission setting result being closed permission, the safety monitoring mode of the online car-hailing service is automatically selected as the creative monitoring mode.

[0047] Through the above steps, the safety monitoring mode can be automatically selected according to the permission data corresponding to the driver user and the passenger user, thereby improving the privacy and security of the online car-hailing safety monitoring. The above is only a specific example, and in actual applications, it can be flexibly set according to user needs and is not limited here.

[0048] Step 202, in response to the safety monitoring mode being the visual monitoring mode, obtain the visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data and situational awareness feature data of the online car-hailing service, and process the visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data and situational awareness feature data to obtain feature data after feature fusion.

[0049] Specifically, in response to the safety monitoring mode being the visual monitoring mode, the server 104 obtains the visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data and situational awareness feature data of the online car-hailing service, and processes the visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data and situational awareness feature data to obtain feature data after feature fusion.

[0050] In one of the embodiments, the visual monitoring feature data of the online ride-hailing vehicle includes data collected by the front camera, data collected by the vehicle's main camera, and data collected by the vehicle's auxiliary camera; the sensor monitoring feature data includes acceleration sensor data, angular velocity sensor data, pressure sensor data, temperature and humidity sensor data, alcohol sensor data, and smoke sensor data; the positioning monitoring feature data includes global positioning system positioning data, Beidou satellite navigation system positioning data, Russian-developed satellite navigation system positioning data, and inertial navigation system data.

[0051] In a specific example, the data collected by the front camera is used to capture the road conditions, traffic signs and signal light information in front of the vehicle, provide assistance for safe driving, and provide key evidence when an accident occurs. The main camera in the car is installed at the top center of the online car-hailing car, which can achieve 360° panoramic shooting. The data collected by the main camera of the vehicle is used to monitor the behavior, expressions, movements and other details of the driver and passengers in real time. The auxiliary camera in the car is installed in the corner of the car, and the data collected by the auxiliary camera in the car is used to cover the monitoring blind spots. These cameras are equipped with infrared night vision, autofocus and automatic exposure adjustment functions, and can clearly image under different lighting conditions (such as strong light, weak light, backlight, etc.). At the same time, the camera is equipped with an intelligent image pre-processing chip, which can perform preliminary noise removal, image enhancement and other processing on the collected images. The above is only a specific example. In actual application, it is flexibly set according to user needs and is not limited here.

[0052] In a specific example, the acceleration sensor and angular velocity sensor can accurately measure the linear acceleration and angular acceleration of the vehicle. The acceleration sensor data and angular velocity sensor data are used to detect abnormal driving conditions such as sudden braking, sudden acceleration, sharp turns, and side slips of the vehicle; the pressure sensor is installed under the seat and can sense the pressure distribution on the seat in real time. The pressure sensor data is used to determine the number, position, and posture changes of people in the car; the temperature and humidity sensor data is used to monitor the temperature and humidity of the vehicle environment to ensure that the vehicle environment is comfortable and prevent safety hazards caused by excessive temperature or humidity; the alcohol sensor data is used to detect the alcohol content in the driver's exhaled gas to prevent drunk driving; the smoke sensor data is used to promptly detect fire hazards in the car. The above are only specific examples. In actual applications, they are flexibly set according to user needs and are not limited here.

[0053] In a specific example, the positioning monitoring feature data includes global positioning system positioning data (GPS), Beidou satellite navigation system positioning data (COMPASS), Russian satellite navigation system positioning data (GLOBAL NAVI GATION SATELLITE SYSTEM, GLONASS) and inertial navigation system data, so as to achieve high-precision and high-reliability positioning through positioning monitoring feature data, and the positioning accuracy can reach centimeter level. The positioning module outputs the position coordinates, speed, driving direction and other information of the vehicle in real time. The above is only a specific example, and it is flexibly set according to user needs in actual application, and is not limited here.

[0054] In one embodiment, if Figure 3 As shown, obtaining context-aware feature data includes steps 301 to 302.

[0055] Step 301, obtaining driving time characteristic data, weather characteristic data, geographical area type characteristic data and driving itinerary type characteristic data of the online car-hailing vehicle;

[0056] Step 302 , input the driving time characteristic data, weather characteristic data, geographical area type characteristic data and driving trip type characteristic data into a pre-trained context-aware network model to obtain context-aware characteristic data.

[0057] Among them, the context-aware feature data is used to characterize the warning sensitivity of the online car-hailing vehicle at the current moment. Specifically, the server 104 obtains the driving time feature data, weather feature data, geographic area type feature data, and driving trip type feature data of the online car-hailing vehicle; then, the driving time feature data, weather feature data, geographic area type feature data, and driving trip type feature data are input into the pre-trained context-aware network model to obtain the context-aware feature data, so as to facilitate understanding the warning sensitivity of the online car-hailing vehicle at the current moment, and to achieve more accurate and effective warning by integrating the context-aware feature data and the feature data after the feature fusion.

[0058] In a specific example, driving time characteristic data includes daytime periods, nighttime periods, peak passenger flow periods, and low passenger flow periods; weather characteristic data includes sunny days, rainy days, snowy days, and foggy days; geographical area type characteristic data includes bustling urban areas, remote suburbs, high-crime areas, and safe driving areas; driving trip type characteristic data includes short-distance driving and long-distance driving. The above are only specific examples. In actual applications, they are flexibly set according to user needs and are not limited here.

[0059] In this embodiment, the driving time characteristic data, weather characteristic data, geographic area type characteristic data and driving trip type characteristic data of the online-hailing vehicle are obtained; then, the driving time characteristic data, weather characteristic data, geographic area type characteristic data and driving trip type characteristic data are input into a pre-trained context-aware network model to obtain context-aware feature data, thereby facilitating the understanding of the warning sensitivity of the online-hailing vehicle at the current moment, and achieving more accurate and effective warning by fusing the context-aware feature data and the feature data after feature fusion.

[0060] In one embodiment, if Figure 4 As shown, after data processing is performed on the visual monitoring feature data, the sensor monitoring feature data, the positioning monitoring feature data and the situational awareness feature data, feature data after feature fusion is obtained, including step 401 and step 402.

[0061] Step 401, formatting the visual monitoring feature data, the sensor monitoring feature data, the positioning monitoring feature data, and the situational awareness feature data to obtain formatted visual monitoring feature data, formatted sensor monitoring feature data, formatted positioning monitoring feature data, and formatted situational awareness feature data;

[0062] Step 402 , performing feature fusion processing on the formatted visual monitoring feature data, the formatted sensor monitoring feature data, the formatted positioning monitoring feature data, and the formatted situational awareness feature data to obtain feature fused feature data.

[0063] Among them, format processing includes data integrity verification processing, data decryption processing and data compression combing. Specifically, the server 104 performs format processing on the visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data and situational awareness feature data to obtain format-processed visual monitoring feature data, format-processed sensor monitoring feature data, format-processed positioning monitoring feature data and format-processed situational awareness feature data; then, feature fusion processing is performed on the format-processed visual monitoring feature data, format-processed sensor monitoring feature data, format-processed positioning monitoring feature data and format-processed situational awareness feature data to obtain feature-fused feature data, which improves the efficiency and convenience of obtaining feature-fused feature data, and can improve the comprehensiveness of feature data through feature-fused feature data, thereby improving monitoring efficiency and accuracy.

[0064] In this embodiment, the visual monitoring feature data, the sensor monitoring feature data, the positioning monitoring feature data and the situational awareness feature data are formatted to obtain the formatted visual monitoring feature data, the formatted sensor monitoring feature data, the formatted positioning monitoring feature data and the formatted situational awareness feature data; then, feature fusion processing is performed on the formatted visual monitoring feature data, the formatted sensor monitoring feature data, the formatted positioning monitoring feature data and the formatted situational awareness feature data to obtain feature data after feature fusion, which improves the efficiency and convenience of obtaining the feature data after feature fusion, and can improve the comprehensiveness of the feature data through the feature data after feature fusion, thereby improving the monitoring efficiency and accuracy.

[0065] Step 203, input the feature data after feature fusion into a pre-trained vehicle safety monitoring network model to obtain high-precision online car-hailing safety monitoring results.

[0066] Among them, the high-precision online car-hailing safety monitoring results include abnormal driving behavior of the driver, abnormal riding behavior of the passenger, driving behavior of vehicle failure or normal driving behavior of the vehicle. Specifically, the server 104 inputs the feature data after feature fusion into the pre-trained vehicle safety monitoring network model to obtain high-precision online car-hailing safety monitoring results, which improves the monitoring efficiency, accuracy and real-time performance and reduces the accident rate.

[0067] In a specific example, abnormal driving behavior of a driver may include but is not limited to driving under the influence of alcohol, driving while fatigued, driving under the influence of drugs, and speeding; abnormal riding behavior of a passenger may include but is not limited to alcoholism, smoking, swearing, quarreling, and making loud noises; and abnormal driving behavior of the vehicle may include but is not limited to abnormal noises, abnormal instrument readings, weak acceleration, brake failure, and difficulty starting. The above are only specific examples and can be flexibly set according to user needs in actual applications and are not limited here.

[0068] In a specific example, the method further includes:

[0069] Obtaining a preset number of historical visual monitoring feature data, historical sensor monitoring feature data, historical positioning monitoring feature data, and historical situational awareness feature data of online ride-hailing vehicles; performing data processing on each historical visual monitoring feature data, the corresponding historical sensor monitoring feature data, the corresponding historical positioning monitoring feature data, and the corresponding historical situational awareness feature data to obtain the corresponding feature-fused historical feature data;

[0070] The historical feature data after the fusion of each feature is randomly divided to generate a training sample set and a test sample set;

[0071] The preset vehicle safety monitoring network model is trained according to the training sample set, and the vehicle safety monitoring network model is tested according to the test sample set. The model parameters of the vehicle safety monitoring network model are adjusted based on the indicators obtained from the training and testing until the indicators meet the preset requirements, and a trained vehicle safety monitoring network model is generated to output the high-precision online car-hailing safety monitoring results based on the trained vehicle safety monitoring network model. In addition, the vehicle safety monitoring network model can be, but is not limited to, a CNN neural network model. The above is only a specific example. In actual applications, it is flexibly set according to user needs and is not limited here.

[0072] Based on this, the above-mentioned online car-hailing safety monitoring method determines the safety monitoring mode in response to the selection operation of the safety monitoring mode of the online car-hailing; wherein the safety monitoring mode includes a visual monitoring mode and a sensor monitoring mode; then, in response to the safety monitoring mode being the visual monitoring mode, the visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data and situational perception feature data of the online car-hailing are obtained, and the visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data and situational perception feature data are processed to obtain feature data after feature fusion; then, the feature data after feature fusion is input into a pre-trained vehicle safety monitoring network model to obtain high-precision online car-hailing safety monitoring results; wherein the high-precision online car-hailing safety monitoring results include abnormal driving behavior of the driver, abnormal riding behavior of the passenger, faulty driving behavior of the vehicle or normal driving behavior of the vehicle; thus, the monitoring efficiency, accuracy and real-time performance are improved, and the accident rate is reduced.

[0073] In one embodiment, if Figure 5 As shown, the method includes step 501 to step 502.

[0074] Step 501, in response to the high-precision online car-hailing safety monitoring result indicating abnormal driving behavior of the driver, outputting warning information of abnormal driving behavior of the driver to the passenger user terminal corresponding to the online car-hailing vehicle;

[0075] Step 502, in response to receiving the first emergency rescue information sent by the passenger user terminal, determining the first emergency rescuer contact information of the passenger user terminal according to the first emergency rescue information, and performing an emergency rescue call operation according to the first emergency rescuer contact information.

[0076] Specifically, in response to the high-precision online car-hailing safety monitoring result of the driver's abnormal driving behavior, server 104 outputs an abnormal driving behavior warning prompt information of the driver to the passenger user terminal corresponding to the online car-hailing; then, in response to receiving the first emergency rescue information sent by the passenger user terminal, it determines the contact information of the first emergency rescuer of the passenger user terminal according to the first emergency rescue information, and executes the emergency rescue call operation according to the contact information of the first emergency rescuer, thereby improving the personalization of the warning prompt and also improving the riding safety of the passenger users.

[0077] In this embodiment, in response to the high-precision online car-hailing safety monitoring result of abnormal driving behavior of the driver, an abnormal driving behavior warning prompt information of the driver is output to the passenger user terminal corresponding to the online car-hailing; then, in response to receiving the first emergency rescue information sent by the passenger user terminal, the contact information of the first emergency rescuer of the passenger user terminal is determined according to the first emergency rescue information, and an emergency rescue call operation is performed according to the contact information of the first emergency rescuer, thereby improving the personalization of the warning prompt and also improving the riding safety of the passenger users.

[0078] In one embodiment, if Figure 5 As shown, the method includes steps 503 to 504.

[0079] Step 503, in response to the high-precision online car-hailing safety monitoring result being abnormal passenger riding behavior, outputting a warning prompt message of abnormal passenger riding behavior to the driver user terminal corresponding to the online car-hailing vehicle;

[0080] Step 504, in response to receiving the second emergency rescue information sent by the driver user terminal, determine the second emergency rescuer contact information of the passenger user terminal according to the second emergency rescue information, and perform an emergency rescue call operation according to the second emergency rescuer contact information.

[0081] Specifically, in response to the high-precision online car-hailing safety monitoring results of abnormal passenger riding behavior, server 104 outputs warning prompt information about the passenger's abnormal riding behavior to the driver user terminal corresponding to the online car-hailing vehicle; then, in response to receiving the second emergency rescue information sent by the driver user terminal, it determines the contact information of the second emergency rescuer of the passenger user terminal according to the second emergency rescue information, and executes an emergency rescue call operation according to the second emergency rescuer contact information, thereby improving the personalization of the warning prompt and also improving the driving safety of the driver user.

[0082] In this embodiment, in response to the high-precision online car-hailing safety monitoring result of abnormal passenger riding behavior, an abnormal passenger riding behavior warning prompt information is output to the driver user terminal corresponding to the online car-hailing vehicle; then, in response to receiving the second emergency rescue information sent by the driver user terminal, the second emergency rescuer contact information of the passenger user terminal is determined according to the second emergency rescue information, and an emergency rescue call operation is performed according to the second emergency rescuer contact information, which improves the personalization of the warning prompt and also improves the driving safety of the driver user.

[0083] In one embodiment, if Figure 5 As shown, the method includes step 505.

[0084] Step 505, in response to the high-precision online car-hailing safety monitoring result being a vehicle faulty driving behavior, outputting vehicle faulty driving behavior warning prompt information to the passenger user terminal and driver user terminal corresponding to the online car-hailing.

[0085] Specifically, in response to the high-precision online car-hailing safety monitoring results of vehicle faulty driving behavior, server 104 outputs vehicle faulty driving behavior warning prompt information to the passenger user terminal and driver user terminal corresponding to the online car-hailing, thereby improving the personalization of the warning prompts and also improving the driving safety of the driver user and the riding safety of the passenger user.

[0086] In this embodiment, in response to the high-precision online car-hailing safety monitoring result of vehicle faulty driving behavior, vehicle faulty driving behavior warning prompt information is output to the passenger user terminal and driver user terminal corresponding to the online car-hailing, thereby improving the personalization of the warning prompt and also improving the driving safety of the driver user and the riding safety of the passenger user.

[0087] In one embodiment, if Figure 6 As shown, the method includes steps 601 to 603.

[0088] Step 601, in response to the security monitoring mode being the sensor monitoring mode, obtaining sensor monitoring characteristic data;

[0089] Step 602, performing a safety analysis of the online car-hailing service based on the sensor monitoring feature data to obtain a low-precision online car-hailing service safety monitoring result;

[0090] Step 603: Output comprehensive safety warning information of online ride-hailing vehicles based on the low-precision online ride-hailing vehicle safety monitoring results.

[0091] Among them, the low-precision online car-hailing safety monitoring results are used to characterize the driving safety status and environmental safety status of the online car-hailing. Specifically, in response to the safety monitoring mode being the sensor monitoring mode, the server 104 obtains the sensor monitoring feature data; then, the online car-hailing safety analysis is performed based on the sensor monitoring feature data to obtain the low-precision online car-hailing safety monitoring results; then, the online car-hailing comprehensive safety warning prompt information is output based on the low-precision online car-hailing safety monitoring results, thereby improving the convenience of full monitoring of the online car-hailing.

[0092] In this embodiment, in response to the safety monitoring mode being the sensor monitoring mode, sensor monitoring feature data is acquired; then, the online car-hailing safety analysis is performed based on the sensor monitoring feature data to obtain low-precision online car-hailing safety monitoring results; then, comprehensive safety warning prompt information for the online car-hailing is output based on the low-precision online car-hailing safety monitoring results, thereby improving the convenience of complete monitoring of the online car-hailing.

[0093] It should be understood that although Figure 2-6 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-6 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0094] Second, as Figure 7 As shown, a device for monitoring the safety of an online car-hailing service is provided, the device comprising a mode selection module 710, a data processing module 720 and a model analysis module 730.

[0095] Among them, the mode selection module 710 is used to determine the safety monitoring mode in response to the selection operation of the safety monitoring mode of the online car-hailing vehicle; wherein, the safety monitoring mode includes a visual monitoring mode and a sensor monitoring mode; the data processing module 720 is used to obtain the visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data and situational perception feature data of the online car-hailing vehicle in response to the safety monitoring mode being the visual monitoring mode, and perform data processing on the visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data and situational perception feature data to obtain feature data after feature fusion; the model analysis module 730 is used to input the feature data after feature fusion into a pre-trained vehicle safety monitoring network model to obtain high-precision safety monitoring results of the online car-hailing vehicle; wherein, the high-precision safety monitoring results of the online car-hailing vehicle include abnormal driving behavior of the driver, abnormal riding behavior of the passenger, faulty driving behavior of the vehicle or normal driving behavior of the vehicle.

[0096] In one of the embodiments, the visual monitoring feature data of the online ride-hailing vehicle includes data collected by the front camera, data collected by the vehicle's main camera, and data collected by the vehicle's auxiliary camera; the sensor monitoring feature data includes acceleration sensor data, angular velocity sensor data, pressure sensor data, temperature and humidity sensor data, alcohol sensor data, and smoke sensor data; the positioning monitoring feature data includes global positioning system positioning data, Beidou satellite navigation system positioning data, Russian-developed satellite navigation system positioning data, and inertial navigation system data.

[0097] In one embodiment, the data processing module 720 includes a data acquisition unit.

[0098] Among them, the data acquisition unit is used to obtain the driving time characteristic data, weather characteristic data, geographical area type characteristic data and driving trip type characteristic data of the online-hailing vehicle; the data acquisition unit is used to input the driving time characteristic data, weather characteristic data, geographical area type characteristic data and driving trip type characteristic data into a pre-trained context-aware network model to obtain context-aware characteristic data; among them, the context-aware characteristic data is used to characterize the warning sensitivity of the online-hailing vehicle at the current moment.

[0099] In one embodiment, the data processing module 720 includes a data processing unit.

[0100] Among them, the data processing unit is used to perform format processing on the visual monitoring feature data, the sensor monitoring feature data, the positioning monitoring feature data and the situational awareness feature data to obtain the formatted visual monitoring feature data, the formatted sensor monitoring feature data, the formatted positioning monitoring feature data and the formatted situational awareness feature data; wherein the format processing includes data integrity verification processing, data decryption processing and data compression combing; the data processing unit is used to perform feature fusion processing on the formatted visual monitoring feature data, the formatted sensor monitoring feature data, the formatted positioning monitoring feature data and the formatted situational awareness feature data to obtain feature fusion feature data.

[0101] In one of the embodiments, the device includes an early warning module.

[0102] Among them, the early warning module is used to respond to the high-precision online car-hailing safety monitoring results of the driver's abnormal driving behavior, and output the driver's abnormal driving behavior early warning prompt information to the passenger user terminal corresponding to the online car-hailing; the early warning module is used to respond to the first emergency rescue information received from the passenger user terminal, determine the contact information of the first emergency rescuer of the passenger user terminal according to the first emergency rescue information, and execute the emergency rescue call operation according to the contact information of the first emergency rescuer.

[0103] In one of the embodiments, the early warning module is used to respond to abnormal passenger riding behavior as a result of high-precision online car-hailing safety monitoring, and output a warning prompt message of abnormal passenger riding behavior to the driver user terminal corresponding to the online car-hailing vehicle; the early warning module is used to respond to receiving a second emergency rescue message sent by the driver user terminal, determine the contact information of the second emergency rescuer of the passenger user terminal according to the second emergency rescue message, and execute an emergency rescue call operation according to the contact information of the second emergency rescuer.

[0104] In one of the embodiments, the early warning module is used to output vehicle faulty driving behavior early warning prompt information to the passenger user terminal and driver user terminal corresponding to the online car-hailing vehicle in response to the high-precision online car-hailing vehicle safety monitoring result indicating vehicle faulty driving behavior.

[0105] In one embodiment, the device includes a sensor monitoring module.

[0106] Among them, the sensor monitoring module is used to obtain sensor monitoring feature data in response to the safety monitoring mode being the sensor monitoring mode; the sensor monitoring module is used to perform online car-hailing safety analysis based on the sensor monitoring feature data to obtain low-precision online car-hailing safety monitoring results; the low-precision online car-hailing safety monitoring results are used to characterize the driving safety status and environmental safety status of the online car-hailing; the sensor monitoring module is used to output comprehensive safety warning prompt information of the online car-hailing based on the low-precision online car-hailing safety monitoring results.

[0107] For the specific limitations of the online car-hailing safety monitoring device, please refer to the limitations of the online car-hailing safety monitoring method above, which will not be repeated here. Each module in the above-mentioned online car-hailing safety monitoring device can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0108] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data and situational awareness feature data of the online car-hailing vehicle. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for monitoring the safety of an online car-hailing vehicle is implemented.

[0109] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0110] In a third aspect, a computer device is provided. The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the steps of any method in the above method embodiments are implemented.

[0111] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any method in the above method embodiments are implemented.

[0112] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0113] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0114] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for monitoring the safety of online ride-hailing vehicles, the method comprising: In response to a selection operation of a safety monitoring mode of the online car-hailing vehicle, determining the safety monitoring mode; wherein the safety monitoring mode includes a visual monitoring mode and a sensor monitoring mode; In response to the safety monitoring mode being the visual monitoring mode, obtaining visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data, and situational awareness feature data of the online car-hailing vehicle, and performing data processing on the visual monitoring feature data, the sensor monitoring feature data, the positioning monitoring feature data, and the situational awareness feature data to obtain feature data after feature fusion; The feature data after the feature fusion is input into a pre-trained vehicle safety monitoring network model to obtain high-precision online car-hailing safety monitoring results; wherein, the high-precision online car-hailing safety monitoring results include abnormal driving behavior of the driver, abnormal riding behavior of the passenger, faulty driving behavior of the vehicle or normal driving behavior of the vehicle.

2. The method according to claim 1, characterized in that The visual monitoring feature data of the online car-hailing vehicle includes data collected by the front camera, data collected by the vehicle's main camera, and data collected by the vehicle's auxiliary camera; the sensor monitoring feature data includes acceleration sensor data, angular velocity sensor data, pressure sensor data, temperature and humidity sensor data, alcohol sensor data, and smoke sensor data; the positioning monitoring feature data includes global positioning system positioning data, Beidou satellite navigation system positioning data, Russian-developed satellite navigation system positioning data, and inertial navigation system data.

3. The method according to claim 1, characterized in that The acquiring of context awareness feature data includes: Acquire the driving time characteristic data, weather characteristic data, geographical area type characteristic data and driving itinerary type characteristic data of the online car-hailing vehicle; The driving time characteristic data, the weather characteristic data, the geographical area type characteristic data and the driving trip type characteristic data are input into a pre-trained context-aware network model to obtain the context-aware characteristic data; wherein the context-aware characteristic data is used to characterize the warning sensitivity of the online car-hailing vehicle at the current moment.

4. The method according to claim 1, characterized in that: The step of processing the visual monitoring feature data, the sensor monitoring feature data, the positioning monitoring feature data and the situational awareness feature data to obtain feature data after feature fusion includes: Performing format processing on the visual monitoring feature data, the sensor monitoring feature data, the positioning monitoring feature data and the situational awareness feature data to obtain the visual monitoring feature data after format processing, the sensor monitoring feature data after format processing, the positioning monitoring feature data after format processing and the situational awareness feature data after format processing; wherein the format processing includes data integrity verification processing, data decryption processing and data compression combing; Feature fusion processing is performed on the visual monitoring feature data processed in the format, the sensor monitoring feature data processed in the format, the positioning monitoring feature data processed in the format, and the situational awareness feature data processed in the format to obtain the feature data after feature fusion.

5. The method according to claim 1, characterized in that: The method comprises: In response to the high-precision online car-hailing safety monitoring result being abnormal driving behavior of the driver, outputting warning information of abnormal driving behavior of the driver to the passenger user terminal corresponding to the online car-hailing vehicle; In response to receiving the first emergency rescue information sent by the passenger user terminal, determining the first emergency rescuer contact information of the passenger user terminal according to the first emergency rescue information, and performing an emergency rescue call operation according to the first emergency rescuer contact information.

6. The method according to claim 1, characterized in that The method comprises: In response to the high-precision online car-hailing safety monitoring result being abnormal riding behavior of the passenger, outputting warning information of abnormal riding behavior of the passenger to a driver user terminal corresponding to the online car-hailing vehicle; In response to receiving the second emergency rescue information sent by the driver user terminal, determining the second emergency rescuer contact information of the passenger user terminal according to the second emergency rescue information, and performing an emergency rescue call operation according to the second emergency rescuer contact information.

7. The method according to claim 1, characterized in that The method comprises: In response to the high-precision online car-hailing safety monitoring result being the vehicle's faulty driving behavior, vehicle faulty driving behavior warning prompt information is output to the passenger user terminal and driver user terminal corresponding to the online car-hailing.

8. The method according to claim 1, characterized in that The method comprises: In response to the security monitoring mode being the sensor monitoring mode, acquiring the sensor monitoring characteristic data; Performing a safety analysis of the online car-hailing vehicle based on the sensor monitoring characteristic data to obtain a low-precision online car-hailing vehicle safety monitoring result; the low-precision online car-hailing vehicle safety monitoring result is used to characterize the driving safety status and environmental safety status of the online car-hailing vehicle; Output comprehensive safety warning information of online-hailing vehicles based on the low-precision online-hailing vehicle safety monitoring results.

9. A safety monitoring device for online car-hailing, characterized in that: The device comprises: A mode selection module, configured to determine the safety monitoring mode in response to a selection operation of the safety monitoring mode of the online car-hailing vehicle; wherein the safety monitoring mode includes a visual monitoring mode and a sensor monitoring mode; a data processing module, for obtaining visual monitoring feature data, sensor monitoring feature data, positioning monitoring feature data, and situational awareness feature data of the online car-hailing vehicle in response to the safety monitoring mode being the visual monitoring mode, and performing data processing on the visual monitoring feature data, the sensor monitoring feature data, the positioning monitoring feature data, and the situational awareness feature data to obtain feature data after feature fusion; The model analysis module is used to input the feature data after the feature fusion into a pre-trained vehicle safety monitoring network model to obtain high-precision online car-hailing safety monitoring results; wherein, the high-precision online car-hailing safety monitoring results include abnormal driving behavior of the driver, abnormal riding behavior of the passenger, faulty driving behavior of the vehicle or normal driving behavior of the vehicle.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images