Fatigue driving detection method, device, equipment and medium

Abstract

The invention discloses a fatigue driving detection method, apparatus and device, and a medium. The method comprises the steps of obtaining an operating vehicle list; for a plurality of operating vehicles on the operating vehicle list, obtaining vehicle passing data corresponding to each operating vehicle; screening the plurality of operating vehicles according to the vehicle passing data corresponding to the operating vehicles to obtain a suspected fatigue operating vehicle list; acquiring face snapshot data corresponding to a plurality of operating vehicles; and determining a fatigue driving operator list according to the suspected fatigue operation vehicle list and the face snapshot data corresponding to the plurality of operation vehicles. The invention belongs to the field of traffic monitoring, not only can carry out afterward study and judgment on fatigue driving, but also realizes the functions of real-time monitoring and early warning, and by collecting and analyzing human-vehicle sensing data and vehicle operation data, early warning can be immediately given out when a driver has a sign of fatigue driving, so that the driver is reminded to have a rest or change in time, and the driving safety is improved. And traffic accidents can be effectively prevented.

Description

Technical Field

[0001] The present invention relates to the field of traffic monitoring, and in particular to a fatigue driving detection method, device, equipment and medium. Background Art

[0002] The changes and development of transportation have brought great convenience to citizens' travel, but the complex legal relationships, legislative and regulatory loopholes and social security risks that come with it should not be underestimated. As the industry further evolves and becomes more prominent, traffic accidents caused by driver fatigue driving occur from time to time, posing challenges to citizens' life safety, property safety and social security.

[0003] Therefore, how to detect fatigue driving and issue risk warnings is an urgent problem to be solved. Summary of the invention

[0004] The embodiments of the present invention solve the technical problem that it is difficult to identify fatigue drivers in batches in the prior art by providing a fatigue driving detection method, device, equipment and medium, and achieve the technical effect of being able to identify fatigue drivers in batches.

[0005] In a first aspect, the present invention provides a method for detecting fatigue driving, the method comprising:

[0006] Get the list of operating vehicles;

[0007] For a number of operating vehicles on the operating vehicle list, obtain the vehicle passing data corresponding to each operating vehicle;

[0008] According to the passing data of the operating vehicles, several operating vehicles are screened to obtain a list of suspected fatigue operating vehicles;

[0009] Obtain facial capture data corresponding to several operating vehicles;

[0010] Based on the list of suspected fatigue operating vehicles and the facial capture data corresponding to several operating vehicles, the list of fatigue driving operators is determined.

[0011] Furthermore, obtain the list of operating vehicles, including:

[0012] Obtain a list of pending operating vehicles in the target area within a historical period. The list of pending operating vehicles includes a real-time active online car-hailing list and a real-time active taxi list.

[0013] The operating vehicles in the list of operating vehicles to be processed are deduplicated to obtain a list of operating vehicles.

[0014] Furthermore, according to the passing data corresponding to the operating vehicles, several operating vehicles are screened to obtain a list of suspected fatigue operating vehicles, including:

[0015] According to the vehicle passing data corresponding to the operating vehicles, it is determined whether the continuous operation time of the operating vehicle exceeds the preset operation time, and whether the time interval between two consecutive vehicle passing data of the operating vehicle is less than the preset interval time;

[0016] If all conditions are met, it is determined whether the number of checkpoints during the continuous operation time of the operating vehicle is greater than the preset number of checkpoints;

[0017] If it is greater, the operating vehicle will be included in the list of suspected fatigue operating vehicles.

[0018] Furthermore, based on the list of suspected fatigued operating vehicles and the facial capture data corresponding to several operating vehicles, the list of fatigued driving operators is determined, including:

[0019] Determine the main driver of the operating vehicle based on the facial capture data of the operating vehicle;

[0020] Based on the face capture data of the operating vehicle, determine whether the number of times the driver corresponding to the operating vehicle has been captured is greater than the preset number of captures;

[0021] If it is greater than, the personnel information and operating vehicle information corresponding to the operating vehicle are determined according to the facial capture data corresponding to the operating vehicle;

[0022] The personnel information, operating vehicle information and the operating trajectory of the operating vehicle are packaged and included in the list of fatigue driving operators.

[0023] Furthermore, it also includes:

[0024] When the number of main drivers in the target operating company in the list of fatigue driving operators exceeds the preset number, the alarm information will be pushed to the target client.

[0025] Furthermore, the method further comprises:

[0026] The main drivers in the list of fatigue driving operators are used as the sample set;

[0027] Associate the driving characteristics of the main driver, including driving behavior habits, vehicle driving status, historical fatigue driving experience, address, driving area, and fatigue driving location;

[0028] Build a decision tree and input a sample set to predict whether the driver is driving fatigued;

[0029] If all predictions can be made accurately, the decision tree will be pushed to the target receiving end.

[0030] Furthermore, after determining the list of fatigue driving operators, the method further includes:

[0031] Determine the number of drivers corresponding to the operating vehicle based on the facial capture data of the operating vehicle;

[0032] When the number of main drivers corresponding to the operating vehicle is greater than or equal to 2, if the number of times any main driver is photographed is greater than the preset number of snapshots, the personnel information, operating vehicle information and operating trajectory of the operating vehicle will be removed from the list of fatigue driving operators.

[0033] In a second aspect, the present invention provides a fatigue driving detection device, the device comprising:

[0034] The first acquisition module is used to obtain a list of operating vehicles;

[0035] The second acquisition module is used to acquire the vehicle passing data corresponding to each of the operating vehicles on the operating vehicle list;

[0036] A screening module is used to screen a number of operating vehicles according to the passing data corresponding to each operating vehicle, and obtain a list of suspected fatigue operating vehicles;

[0037] The third acquisition module is used to obtain face capture data corresponding to a number of operating vehicles;

[0038] The list determination module is used to determine the list of fatigue driving operators based on the list of suspected fatigue operating vehicles and the facial capture data corresponding to several operating vehicles.

[0039] In a third aspect, the present invention provides an electronic device, comprising:

[0040] processor;

[0041] a memory for storing processor-executable instructions;

[0042] The processor is configured to execute to implement a fatigue driving detection method as provided in the first aspect.

[0043] In a fourth aspect, the present invention provides a non-temporary computer-readable storage medium, which, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to implement a fatigue driving detection method as provided in the first aspect.

[0044] One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:

[0045] The present invention provides a fatigue driving detection method, the method comprising: obtaining a list of operating vehicles; obtaining the passing data corresponding to each operating vehicle for several operating vehicles on the list of operating vehicles; screening several operating vehicles according to the passing data corresponding to the operating vehicles, and obtaining a list of suspected fatigue operating vehicles; obtaining the face capture data corresponding to several operating vehicles; and determining the list of fatigue driving operators according to the list of suspected fatigue operating vehicles and the face capture data corresponding to several operating vehicles. The present invention can exchange information with enterprises associated with online car-hailing vehicles related to fatigue driving, and promote drivers to pay attention to the combination of work and rest from the enterprise level; according to the list of fatigue driving drivers, the enterprise can be required to provide video surveillance, conduct targeted investigations, and check whether there are fatigue driving personnel to give relevant warnings to the enterprise. The present invention can not only conduct post-event judgment on fatigue driving, but also realize real-time monitoring and early warning functions. By collecting and analyzing human and vehicle perception data and vehicle operation data in real time, it can immediately issue an early warning when the driver shows signs of fatigue driving, thereby timely reminding the driver to rest or change the driver, and effectively preventing the occurrence of traffic accidents. The present invention is not only applicable to operating vehicles, but also can be widely used in other types of vehicles, such as private cars, trucks, etc. At the same time, this method can also provide strong technical support for traffic management departments, helping them to better monitor road traffic conditions and improve road traffic safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0047] Figure 1 A schematic diagram of a process flow of a fatigue driving detection method provided by the present invention;

[0048] Figure 2 A schematic diagram of the structure of a fatigue driving detection device provided by the present invention;

[0049] Figure 3 The present invention provides a schematic structural diagram of an electronic device. DETAILED DESCRIPTION

[0050] The embodiment of the present invention solves the technical problem in the prior art that it is difficult to identify fatigue drivers in batches by providing a fatigue driving detection method.

[0051] The technical solution of the embodiment of the present invention is to solve the above technical problems, and the overall idea is as follows:

[0052] A fatigue driving detection method comprises: obtaining a list of operating vehicles; obtaining vehicle passing data corresponding to a number of operating vehicles on the list of operating vehicles; screening a number of operating vehicles according to the vehicle passing data corresponding to the operating vehicles to obtain a list of suspected fatigue operating vehicles; obtaining facial capture data corresponding to the number of operating vehicles; and determining a list of fatigue driving operators according to the list of suspected fatigue operating vehicles and the facial capture data corresponding to the number of operating vehicles.

[0053] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0054] First of all, the term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0055] Fatigue driving refers to the provisions of the new "Road Traffic Safety Violation Points Management Measures" that will be implemented on April 1, 2022, that is, continuous driving of medium-sized and larger passenger cars or dangerous goods transport vehicles for more than 4 hours without stopping to rest or the rest time is less than 20 minutes, it will be recorded as fatigue driving; continuous driving of trucks for more than 4 hours without stopping to rest or the rest time is less than 20 minutes, it will be recorded as fatigue driving.

[0056] The present invention is mainly aimed at operating vehicles, including online-hailing vehicles and taxis, and the operating vehicles in the invention refer to the provisions of the "Road Traffic Safety Violation Points Management Measures".

[0057] The present invention provides Figure 1 A fatigue driving detection method is shown, the method comprising:

[0058] Regarding step S11, a list of operating vehicles is obtained.

[0059] Specifically, it includes: obtaining a list of pending operating vehicles in the target area within a historical period, the list of pending operating vehicles including a real-time active online car-hailing list and a real-time active taxi list; deduplicating the operating vehicles in the list of pending operating vehicles to obtain a list of operating vehicles.

[0060] The target area refers to the area where fatigue driving monitoring is required. There are several shooting devices (such as surveillance cameras, etc.) in the target area. The historical period can refer to the past few days. The operating vehicles in the past few days can be collected to form a list of operating vehicles to be processed.

[0061] It is understandable that since it can be obtained from multiple data sources, some operating vehicles in the list of operating vehicles to be processed may be repeated. Therefore, the operating vehicles in the list of operating vehicles to be processed can be deduplicated, and the deduplicated list of operating vehicles to be processed can be used as the operating vehicle list.

[0062] Operating vehicles may include online-hailing taxis and taxis. Online-hailing taxis may constitute a real-time active online-hailing taxi list with an online-hailing taxi label attached; taxis may constitute a real-time active taxi list with a taxi label attached.

[0063] The deduplicated real-time active online car-hailing vehicle list and real-time active taxi list can be used as the operating vehicle list.

[0064] Regarding step S12, for a number of operating vehicles on the operating vehicle list, the vehicle passing data corresponding to each operating vehicle is obtained.

[0065] The vehicle passing data corresponding to each operating vehicle refers to the photo data of the operating vehicle. It can be understood that there are several camera devices in the target area, so there may be several photos of the operating vehicles.

[0066] All vehicle passing data corresponding to the operating vehicles can be screened and cleaned to obtain vehicle passing data corresponding to the operating vehicles that can be used for identification.

[0067] It is understandable that each vehicle passing data includes a shooting time, and therefore, the vehicle passing data of the operating vehicles can be sorted according to the shooting time.

[0068] If the shooting time difference between consecutive passing vehicle data is greater than 20 minutes, it can be marked as 1, otherwise it can be marked as 0, and both 1 and 0 are track identifiers.

[0069] Regarding step S13, a number of operating vehicles are screened according to the vehicle passing data corresponding to each operating vehicle to obtain a list of suspected fatigue operating vehicles.

[0070] Specifically, it includes: judging, based on the vehicle passing data corresponding to the operating vehicles, whether the continuous operating time of the operating vehicle exceeds the preset operating time, and whether the time interval between two consecutive vehicle passing data of the operating vehicle is less than the preset interval time; if both are satisfied, judging whether the number of checkpoints within the continuous operating time of the operating vehicle is greater than the preset number of checkpoints; if greater, the operating vehicle is included in the list of suspected fatigue operating vehicles.

[0071] The preset operation time can be 4 hours, the number of checkpoints refers to the number of operating vehicles passing through the camera. The preset number of checkpoints can be 10, and the preset interval time can be 20 minutes.

[0072] In other words, the number of vehicle passing data of operating vehicles is at least greater than or equal to the number of checkpoints within the continuous operation time (operating vehicles may pass by the same shooting device multiple times).

[0073] The following are examples:

[0074] According to the passing data corresponding to operating vehicle A, operating vehicle A has been running for 5 consecutive hours, and the trajectory of operating vehicle A is identified as 11111111111111111111, indicating whether the continuous operating time of operating vehicle A exceeds the preset operating time, and the time interval between two consecutive passing data of operating vehicle A is less than 20 minutes.

[0075] It is then determined whether the number of checkpoints during the continuous operation time of operating vehicle A is greater than 10. If greater than 10, operating vehicle A is included in the list of suspected fatigue operating vehicles.

[0076] Regarding step S14, facial capture data corresponding to a number of operating vehicles are obtained.

[0077] The facial capture data corresponding to each operating vehicle refers to the facial data of the main driver in the main driving position when the operating vehicle is photographed, and can be determined based on the above-mentioned vehicle passing data through cropping, cleaning and correction.

[0078] It can be understood that the number of main drivers may not be 1 during the continuous operation period.

[0079] Regarding step S15, a list of fatigued driving operators is determined based on the list of suspected fatigued operating vehicles and the facial capture data corresponding to a number of operating vehicles.

[0080] Specifically, it includes: determining the main driver corresponding to the operating vehicle based on the facial capture data of the operating vehicle; judging whether the number of times the main driver corresponding to the operating vehicle has been captured is greater than the preset number of captures based on the facial capture data of the operating vehicle; if greater, determining the personnel information and operating vehicle information corresponding to the operating vehicle based on the facial capture data corresponding to the operating vehicle; packaging the personnel information, operating vehicle information and the operating trajectory of the operating vehicle, and including them in the list of fatigue driving operators.

[0081] In China, the left front row seat is the main driver's seat. By trimming, cleaning and correcting the passing vehicle data, the facial capture data can be determined, and the main driver corresponding to the operating vehicle can be determined based on the facial capture data.

[0082] The preset number of snapshots can be determined according to actual conditions, and is set to 3 in the present invention.

[0083] When the number of times the driver corresponding to the operating vehicle is captured is greater than 3, the personnel information and operating vehicle information corresponding to the operating vehicle are determined based on the facial capture data corresponding to the operating vehicle, and the operating trajectory is the "trajectory identification" mentioned above.

[0084] The personnel information, operating vehicle information and operating trajectory corresponding to the operating vehicle are packaged and constructed into a fatigue driving information and included in the list of fatigue driving operators.

[0085] After determining the list of fatigue driving operators, the method also includes:

[0086] Determine the number of drivers corresponding to the operating vehicle based on the facial capture data of the operating vehicle;

[0087] When the number of main drivers corresponding to the operating vehicle is greater than or equal to 2, if the number of times any main driver is photographed is greater than the preset number of snapshots, the personnel information, operating vehicle information and operating trajectory of the operating vehicle will be removed from the list of fatigue driving operators.

[0088] It should be noted that, generally speaking, the number of main drivers corresponding to an operating vehicle is 1, but there may be multiple drivers changing shifts. In order to improve the accuracy of fatigue driving identification, it is possible to determine whether the number of main drivers of an operating vehicle is greater than or equal to 2. If it is greater than or equal to 2, then determine whether the number of times any main driver of the operating vehicle has been captured during the continuous operation time is greater than 3. If it is greater than 3, it means that there is a shift change, and the main driver is not driving fatigued. The personnel information, operating vehicle information, and operating trajectory of the operating vehicle can be removed from the list of fatigue driving operators. In addition, in order to further improve the accuracy, when it is determined that there is a shift change, the operating time of each main driver is re-determined, and whether there is fatigue driving is re-determined.

[0089] In order to standardize company operations and improve driving safety, when the number of main drivers in the target operating company on the list of fatigue driving operators exceeds the preset number, an alarm message will be pushed to the target client (which can be the department managing traffic operations).

[0090] In order to improve data utilization and accurately predict fatigue driving, it also includes: taking the main drivers in the list of fatigue driving operators as the sample set; associating the driving characteristics of the main driver, which include driving behavior habits, vehicle driving status, historical fatigue driving experience, address, driving area and fatigue driving location; building a decision tree and inputting the sample set to predict whether the main driver has fatigue driving; if all predictions can be accurate, the decision tree will be pushed to the target receiving end.

[0091] The target receiving end receives the decision tree, and relevant personnel can predict fatigue driving for operating vehicles in the target area based on the decision tree.

[0092] In summary, the present invention provides a fatigue driving detection method, the method comprising: obtaining a list of operating vehicles; obtaining the passing data corresponding to each operating vehicle for several operating vehicles on the list of operating vehicles; screening several operating vehicles according to the passing data corresponding to the operating vehicles, and obtaining a list of suspected fatigue operating vehicles; obtaining the face capture data corresponding to several operating vehicles; and determining the list of fatigue driving operators according to the list of suspected fatigue operating vehicles and the face capture data corresponding to several operating vehicles. The present invention can exchange information with enterprises associated with fatigue driving related online car-hailing vehicles, and promote drivers to pay attention to work and rest from the enterprise level; according to the list of fatigue driving drivers, the enterprise can be required to provide video surveillance, conduct targeted investigations, and check whether there are fatigue driving personnel to give relevant warnings to the enterprise. The present invention can not only conduct post-event judgment on fatigue driving, but also realize real-time monitoring and early warning functions. By collecting and analyzing human and vehicle perception data and vehicle operation data in real time, it can immediately issue an early warning when the driver shows signs of fatigue driving, thereby timely reminding the driver to rest or change the driver, and effectively preventing the occurrence of traffic accidents. The present invention is not only applicable to operating vehicles, but also can be widely used in other types of vehicles, such as private cars, trucks, etc. At the same time, this method can also provide strong technical support for traffic management departments, helping them to better monitor road traffic conditions and improve road traffic safety.

[0093] Based on the same inventive concept, the present invention provides Figure 2 A fatigue driving detection device shown includes:

[0094] The first acquisition module 21 is used to obtain a list of operating vehicles;

[0095] The second acquisition module 22 is used to acquire the vehicle passing data corresponding to each of the operating vehicles on the operating vehicle list;

[0096] The screening module 23 is used to screen a number of operating vehicles according to the passing vehicle data corresponding to the operating vehicles, and obtain a list of suspected fatigue operating vehicles;

[0097] The third acquisition module 24 is used to obtain face capture data corresponding to a number of operating vehicles;

[0098] The list determination module 25 is used to determine the list of fatigue driving operators based on the list of suspected fatigue operating vehicles and the facial capture data corresponding to a number of operating vehicles.

[0099] Based on the same inventive concept, the present invention also provides Figure 3 An electronic device as shown includes:

[0100] Processor 31;

[0101] A memory 32 for storing instructions executable by the processor 31;

[0102] The processor 31 is configured to execute to implement a fatigue driving detection method as provided above.

[0103] Based on the same inventive concept, the present invention also provides a non-temporary computer-readable storage medium. When the instructions in the storage medium are executed by the processor 51 of the electronic device, the electronic device can execute a fatigue driving detection method as provided above.

[0104] Since the electronic device introduced in this embodiment is an electronic device used to implement the information processing method in the embodiment of the present invention, based on the information processing method introduced in the embodiment of the present invention, a person skilled in the art can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of the present invention is not described in detail here. As long as the electronic device used by a person skilled in the art to implement the information processing method in the embodiment of the present invention, it belongs to the scope of protection of the present invention.

[0105] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0106] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0107] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0108] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0109] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0110] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for detecting fatigue driving, characterized in that: The method comprises: Get the list of operating vehicles; For a number of operating vehicles on the operating vehicle list, obtaining vehicle passing data corresponding to each operating vehicle; According to the passing data of the operating vehicles, several operating vehicles are screened to obtain a list of suspected fatigue operating vehicles; Obtain facial capture data corresponding to several operating vehicles; A list of fatigued driving operators is determined based on the list of suspected fatigued operating vehicles and the facial capture data corresponding to several operating vehicles.

2. A fatigue driving detection method as claimed in claim 1, characterized in that: The obtaining of the list of operating vehicles includes: Obtain a list of pending operating vehicles in a target area within a historical period, wherein the list of pending operating vehicles includes a real-time active online car-hailing list and a real-time active taxi list; The operating vehicles in the list of operating vehicles to be processed are deduplicated to obtain the list of operating vehicles.

3. A fatigue driving detection method as claimed in claim 1, characterized in that: According to the vehicle passing data corresponding to the operating vehicles, a number of operating vehicles are screened to obtain a list of suspected fatigue operating vehicles, including: According to the vehicle passing data corresponding to the operating vehicles, determine whether the continuous operation time of the operating vehicle exceeds the preset operation time, and whether the time interval between two consecutive vehicle passing data of the operating vehicle is less than the preset interval time; If all conditions are met, it is determined whether the number of checkpoints during the continuous operation time of the operating vehicle is greater than the preset number of checkpoints; If it is greater, the operating vehicle will be included in the list of suspected fatigue operating vehicles.

4. A fatigue driving detection method as claimed in claim 1, characterized in that: Determining a list of fatigue driving operators based on the list of suspected fatigue operating vehicles and the facial capture data corresponding to a number of operating vehicles includes: Determine the main driver of the operating vehicle based on the facial capture data of the operating vehicle; Based on the face capture data of the operating vehicle, determine whether the number of times the driver corresponding to the operating vehicle has been captured is greater than the preset number of captures; If it is greater than, the personnel information and operating vehicle information corresponding to the operating vehicle are determined according to the facial capture data corresponding to the operating vehicle; The personnel information, the operating vehicle information and the operating track of the operating vehicle are packaged and included in the list of fatigue driving operators.

5. A fatigue driving detection method as claimed in claim 4, characterized in that: Also includes: When the number of main drivers in the target operating company in the list of fatigue driving operators exceeds a preset number, an alarm message is pushed to the target client.

6. A fatigue driving detection method as claimed in claim 1, characterized in that: The method further comprises: The main drivers in the list of fatigue driving operators are used as the sample set; Associating the driving characteristics of the main driver, the driving characteristics include driving behavior habits, vehicle driving status, historical fatigue driving experience, address, driving area and fatigue driving location; Build a decision tree and input a sample set to predict whether the driver is driving fatigued; If all predictions can be made accurately, the decision tree will be pushed to the target receiving end.

7. A fatigue driving detection method as claimed in claim 4, characterized in that: After determining the list of fatigue driving operators, the method further includes: Determine the number of drivers corresponding to the operating vehicle based on the facial capture data of the operating vehicle; When the number of main drivers corresponding to the operating vehicle is greater than or equal to 2, if the number of times any main driver is captured is greater than the preset number of captures, the personnel information, operating vehicle information and operating trajectory of the operating vehicle will be removed from the list of fatigue driving operators.

8. A fatigue driving detection device, characterized in that: The device comprises: The first acquisition module is used to obtain a list of operating vehicles; The second acquisition module is used to acquire the vehicle passing data corresponding to each of the operating vehicles on the operating vehicle list; A screening module is used to screen a number of operating vehicles according to the passing data corresponding to each operating vehicle, and obtain a list of suspected fatigue operating vehicles; The third acquisition module is used to obtain face capture data corresponding to a number of operating vehicles; The list determination module is used to determine the list of fatigue driving operators based on the list of suspected fatigue operating vehicles and the facial capture data corresponding to a number of operating vehicles.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute to implement a fatigue driving detection method as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to implement a fatigue driving detection method as described in any one of claims 1 to 7.

Images