Drunk driving detection method, device and equipment and storage medium

Abstract

The invention discloses a drunk driving detection method, device and equipment and a storage medium, and relates to the technical field of driver detection, and the method comprises the steps: carrying out the face recognition of a driver when the current driving environment of a vehicle meets a preset basic condition and the vehicle is in a starting state; if the driver passes the face recognition, drunk driving detection is carried out on the driver; if the driver passes the drunk driving detection, allowing the driver to start the vehicle; if the driver does not pass face recognition or drunk driving detection, the driver is forbidden to start the vehicle, and abnormal information is sent to a manager. According to the invention, face recognition and drunk driving detection are carried out on the driver in the cloud platform, on the premise of not additionally installing equipment, whether the driver drinks or not is remotely judged by using the advantages of convenience, high efficiency and iteratability of the cloud platform, and the vehicle is prohibited from being started when the driver does not pass face recognition or drunk driving detection, so that the driving safety of the driver is improved. Low cost and generalization of drunk driving detection are realized, and traffic drunk driving detection burden is reduced.

Description

Technical Field

[0001] The present application relates to the field of driver detection technology, and in particular to a drunk driving detection method, device, equipment and storage medium. Background Art

[0002] There are two common methods of drunk driving detection at present. One is that the traffic department sets up checkpoints at key intersections and uses handheld alcohol testers to test the alcohol content of passing car drivers. This method has disadvantages such as incomplete coverage and high labor costs. The other is to install an alcohol lock device on the car. When the driver starts the vehicle, he needs to use the on-board handheld device to perform an alcohol test. This method has disadvantages such as high installation cost and difficulty in popularization. Therefore, the industry is in urgent need of a drunk driving detection method that can take into account both universality and low cost. Summary of the invention

[0003] The main purpose of this application is to provide a drunk driving detection method, device, equipment and storage medium, aiming to solve the technical problem that existing drunk driving detection methods cannot take into account both versatility and low cost.

[0004] To achieve the above objectives, the present application provides a method for detecting drunk driving, which comprises the following steps:

[0005] When the current driving environment of the vehicle meets the preset basic conditions and the vehicle is in the starting state, performing face recognition on the driver;

[0006] If the driver passes the facial recognition, the driver is tested for drunk driving;

[0007] If the driver passes the drunk driving test, allowing the driver to start the vehicle;

[0008] If the driver fails the face recognition or the drunk driving test, the driver is prohibited from starting the vehicle and an abnormal information is sent to the management staff.

[0009] In one embodiment, when the current driving environment of the vehicle meets the preset basic conditions and the vehicle is in the starting state, before the step of performing face recognition on the driver, the method further includes:

[0010] Obtaining the driver's registration information and drunk driving test data, and determining whether the registration information and the drunk driving test data are qualified;

[0011] If both the registration information and the drunk driving test data are qualified, it is determined that the current driving environment of the vehicle meets the preset basic conditions;

[0012] If the registration information or the drunk driving detection data is unqualified, it is determined that the current driving environment of the vehicle does not meet the preset basic conditions.

[0013] In one embodiment, the drunk driving detection data includes visual direction detection data, auditory direction detection data and language direction detection data. The visual direction detection data includes an average picture recognition speed and a picture recognition accuracy rate. The auditory direction detection data includes an average speech recognition speed and a speech recognition accuracy rate. The language direction detection data includes an average sentence recognition speed and a sound matching rate.

[0014] In one embodiment, when the current driving environment of the vehicle meets the preset basic conditions and the vehicle is in the starting state, the step of performing face recognition on the driver includes:

[0015] When the current driving environment of the vehicle meets the preset basic conditions and the vehicle is in the starting state, the driver's facial feature information is uploaded to the cloud platform for feature comparison;

[0016] If the comparison result shows that the driver has the authority to start the vehicle, it is determined that the driver has passed the face recognition;

[0017] If the comparison result shows that the driver does not have the authority to start the vehicle, it is determined that the driver has failed the face recognition.

[0018] In one embodiment, if the driver passes the face recognition, the step of conducting a drunk driving test on the driver includes:

[0019] If the driver passes the facial recognition, a drunk driving test is conducted on the driver based on the facial recognition information of the driver;

[0020] If the driver passes a drunk driving test, it is determined that the driver is not suspected of drunk driving;

[0021] If the driver fails the first drunk driving test, the driver is determined to be suspected of drunk driving, and a second drunk driving test is conducted on the driver based on the drunk driving test items.

[0022] In one embodiment, the step of performing a secondary drunk driving test on the driver according to the drunk driving test item includes:

[0023] Calculate the visual recognition deviation rate, auditory recognition deviation rate and language recognition deviation rate of the driver in the visual direction, auditory direction and language direction respectively according to the drunk driving detection item;

[0024] The driver is subjected to a secondary drunk driving test based on the visual recognition deviation rate, the auditory recognition deviation rate and the language recognition deviation rate.

[0025] In addition, to achieve the above purpose, the present application also proposes a drunk driving detection device, the drunk driving detection device comprising:

[0026] A face recognition module, used to perform face recognition on the driver when the current driving environment of the vehicle meets the preset basic conditions and the vehicle is in the starting state;

[0027] A drunk driving detection module, used to perform a drunk driving detection on the driver if the driver passes the face recognition;

[0028] A first management module, configured to allow the driver to start the vehicle if the driver passes the drunk driving test;

[0029] The second management module is used to prohibit the driver from starting the vehicle if the driver fails to pass the face recognition or the drunk driving test, and send an abnormal information to the management personnel.

[0030] In addition, to achieve the above-mentioned purpose, the present application also proposes a drunk driving detection device, which includes: a memory, a processor, and a drunk driving detection program stored on the memory and executable on the processor, wherein the drunk driving detection program is configured to implement the steps of the drunk driving detection method described above.

[0031] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a drunk driving detection program is stored on the storage medium. When the drunk driving detection program is executed by the processor, the steps of the drunk driving detection method described above are implemented.

[0032] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer program product, which includes a drunk driving detection program, and when the drunk driving detection program is executed by a processor, the steps of the drunk driving detection method described above are implemented.

[0033] This application performs facial recognition on the driver when the current driving environment of the vehicle meets the preset basic conditions and the vehicle is in the starting state; if the driver passes the facial recognition, the driver is tested for drunk driving; if the driver passes the drunk driving test, the driver is allowed to start the vehicle; if the driver fails the facial recognition or fails the drunk driving test, the driver is prohibited from starting the vehicle, and an abnormal message is sent to the manager. Compared with the traditional drunk driving detection method, since the above method of this application performs facial recognition and drunk driving detection on the driver in the cloud platform, without adding additional equipment, the advantages of the cloud platform are convenient, efficient and iterative, and the driver is remotely judged whether he is drinking. While improving the detection accuracy and speeding up the detection speed, the problem of dismantling and installing the alcohol detection equipment is avoided; and the vehicle is prohibited from starting when the driver fails the facial recognition or fails the drunk driving test, which realizes the low cost and universalization of drunk driving detection and reduces the burden of traffic drunk driving detection; in addition, the full amount of detection data of this application is stored on the cloud platform. Compared with the traditional method of only detecting whether the driver is drunk driving, this application can also expand the capabilities in other directions through the collected detection data. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A schematic diagram of the structure of a drunk driving detection device in the hardware operating environment involved in the embodiment of the present application;

[0035] Figure 2 This is a flow chart of the first embodiment of the drunk driving detection method of the present application;

[0036] Figure 3 This is a flow chart of the second embodiment of the drunk driving detection method of the present application;

[0037] Figure 4 This is a flow chart of the third embodiment of the drunk driving detection method of the present application;

[0038] Figure 5 This is a structural block diagram of the first embodiment of the drunk driving detection device of this application.

[0039] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0040] 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.

[0041] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of the drunk driving detection equipment in the hardware operating environment involved in the embodiment of the present application.

[0042] like Figure 1As shown, the drunk driving detection device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0043] Those skilled in the art will understand that Figure 1 The structure shown in does not constitute a limitation on the drunk driving detection equipment, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0044] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a drunk driving detection program.

[0045] exist Figure 1 In the drunk driving detection device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the drunk driving detection device of the present application can be set in the drunk driving detection device, and the drunk driving detection device calls the drunk driving detection program stored in the memory 1005 through the processor 1001, and executes the drunk driving detection method provided in the embodiment of the present application.

[0046] The present application embodiment provides a method for detecting drunk driving, referring to Figure 2 , Figure 2 This is a flow chart of the first embodiment of the drunk driving detection method of the present application.

[0047] In this embodiment, the drunk driving detection method includes the following steps:

[0048] Step S10: When the current driving environment of the vehicle meets the preset basic conditions and the vehicle is in the starting state, the driver's face is recognized.

[0049] It should be noted that the execution subject of the method of this embodiment can be a terminal device with face recognition, data processing and program running functions, such as an intelligent vehicle machine, a computer, etc., or an electronic device with the same or similar functions, such as the above-mentioned drunk driving detection device. The following takes the drunk driving detection device as an example to illustrate this embodiment and the following embodiments.

[0050] It should be understood that the above-mentioned preset basic conditions may include but are not limited to the following: first, the driver needs to complete the information registration on the mobile phone APP, including personal information and qualified facial photos; second, the driver needs to complete the entry of drunk driving detection data, and the cloud platform will select detection items including vision, hearing, and language in the drunk driving detection database to match the driver's drunk driving benchmark value; third, the vehicle computer needs to have drunk driving detection capabilities, including identifying the driver's drunk driving characteristics through the vehicle-side DMS (Driver Monitor System) unit, and verifying the driver's drunk driving benchmark value through the on-board drunk driving detection unit. This capability can be installed and remotely upgraded through OTA (Over-the-Air Technology).

[0051] In the specific implementation, if the vehicle's current driving environment meets the preset basic conditions and the vehicle is in the starting state, it means that the vehicle can be driven normally at this time, but before driving it is necessary to verify whether the driver has the authority to drive the vehicle to avoid the vehicle being stolen.

[0052] Step S20: If the driver passes the face recognition, the driver is tested for drunk driving.

[0053] It should be understood that if the driver passes facial recognition, it means that the driver has the authority to drive the vehicle. At this time, the driver can be remotely tested for drunk driving to determine whether the driver meets the drunk driving standard.

[0054] Step S30: If the driver passes the drunk driving test, the driver is allowed to start the vehicle.

[0055] Step S40: If the driver fails the face recognition or the drunk driving test, the driver is prohibited from starting the vehicle and an abnormal information is sent to the management staff.

[0056] It is understandable that if the driver fails to pass the facial recognition, it means that the driver currently does not have the authority to drive the vehicle. At this time, the driver should be prohibited from starting the vehicle and send abnormal information to the management personnel to prevent the vehicle from being stolen; if the driver fails the drunk driving test, it means that the driver currently meets the drunk driving standard. At this time, the driver should be prohibited from starting the vehicle and send abnormal information to the management personnel to prevent the driver from driving the vehicle after drinking and causing traffic accidents.

[0057] This embodiment performs facial recognition on the driver when the current driving environment of the vehicle meets the preset basic conditions and the vehicle is in the starting state; if the driver passes the facial recognition, the driver is tested for drunk driving; if the driver passes the drunk driving test, the driver is allowed to start the vehicle; if the driver fails the facial recognition or fails the drunk driving test, the driver is prohibited from starting the vehicle, and an abnormal message is sent to the manager. Compared with the traditional drunk driving detection method, since the above method of this embodiment performs facial recognition and drunk driving detection on the driver in the cloud platform, without adding additional equipment, the advantages of the cloud platform are convenient, efficient and iterative, and the driver is remotely judged whether he has drunk alcohol. While improving the detection accuracy and speeding up the detection speed, the problem of dismantling and installing the alcohol detection equipment for replacement is avoided; and the vehicle is prohibited from starting when the driver fails the facial recognition or fails the drunk driving test, realizing the low cost and universalization of drunk driving detection, and reducing the burden of traffic drunk driving detection; in addition, the full amount of detection data of this embodiment is stored on the cloud platform. Compared with the traditional method of only detecting whether the driver is drunk driving, this embodiment can also expand the capabilities in other directions through the collected detection data.

[0058] refer to Figure 3 , Figure 3 This is a flow chart of the second embodiment of the drunk driving detection method of the present application.

[0059] In a feasible implementation manner, before step S10, the following may also be included:

[0060] Step S1: Obtain the driver's registration information and drunk driving detection data, and determine whether the registration information and the drunk driving detection data are qualified.

[0061] Step S2: If both the registration information and the drunk driving detection data are qualified, it is determined that the current driving environment of the vehicle meets the preset basic conditions.

[0062] Step S3: If the registration information or the drunk driving detection data is unqualified, it is determined that the current driving environment of the vehicle does not meet the preset basic conditions.

[0063] It should be noted that the above registration information may include but is not limited to the driver's personal information and facial photos, and the above drunk driving detection data may include visual direction detection data, auditory direction detection data and language direction detection data. Among them, the above visual direction detection data may include the average image recognition speed and image recognition accuracy, the above auditory direction detection data may include the average voice recognition speed and voice recognition accuracy, and the above language direction detection data may include the average sentence recognition speed and sound matching rate.

[0064] In a feasible implementation manner, the step S10 may include:

[0065] Step S101: When the current driving environment of the vehicle meets the preset basic conditions and the vehicle is in the starting state, the driver's facial feature information is uploaded to the cloud platform for feature comparison.

[0066] Step S102: If the comparison result shows that the driver has the authority to start the vehicle, it is determined that the driver has passed the face recognition.

[0067] Step S103: If the comparison result shows that the driver does not have the authority to start the vehicle, it is determined that the driver has failed the face recognition.

[0068] In the specific implementation, if the driver of the vehicle has completed the information registration on the mobile phone APP, after the driver starts the vehicle, the vehicle-side DMS unit starts to read the driver's facial feature information, and first tries to upload the read information to the cloud platform for feature comparison. If the comparison result shows that the driver has the vehicle start permission, the driver is determined to have passed the face recognition. Otherwise, the vehicle is prohibited from starting, and the driver of the vehicle is notified of the abnormal situation through the cloud platform communication module.

[0069] This embodiment obtains the driver's registration information and drunk driving detection data, and determines whether the registration information and the drunk driving detection data are qualified; if the registration information and the drunk driving detection data are both qualified, it is determined that the current driving environment of the vehicle meets the preset basic conditions; if the registration information or the drunk driving detection data is unqualified, it is determined that the current driving environment of the vehicle does not meet the preset basic conditions; the drunk driving detection data includes visual direction detection data, auditory direction detection data and language direction detection data, the visual direction detection data includes the average image recognition speed and the image recognition accuracy, the auditory direction detection data includes the average voice recognition speed and the voice recognition accuracy, and the language direction detection data includes the average sentence recognition speed and the sound matching rate; when the current driving environment of the vehicle meets the preset basic conditions and the vehicle is in the starting state, the driver's facial feature information is uploaded to the cloud platform for feature comparison; if the comparison result shows that the driver has the vehicle start authority, it is determined that the driver has passed the face recognition; if the comparison result shows that the driver does not have the vehicle start authority, it is determined that the driver has not passed the face recognition. Compared with the traditional drunk driving detection method, the above method in this embodiment can complete the drunk driving status detection by using software capabilities through the interaction between the cloud platform and the vehicle computer. It has low vehicle intrusion, higher acceptance among car owners, and is easier to promote. At the same time, based on the computing power of the cloud platform and the software capabilities of the vehicle computer, there is no need to install alcohol detection equipment in the car, which can also reduce the pressure of manual checkpoints and is lower in cost.

[0070] refer to Figure 4 , Figure 4 This is a flow chart of the third embodiment of the drunk driving detection method of the present application.

[0071] In a feasible implementation manner, the step S20 may include:

[0072] Step S201: If the driver passes the face recognition, a drunk driving test is performed on the driver based on the driver's facial recognition information.

[0073] Step S202: If the driver passes a drunk driving test, it is determined that the driver is not suspected of drunk driving.

[0074] Step S203: If the driver fails the first drunk driving test, it is determined that the driver is suspected of drunk driving, and a second drunk driving test is performed on the driver according to the drunk driving test items.

[0075] In a specific implementation, after the driver passes the facial recognition, the facial recognition information can be compared with the normal driving facial state information and the drunk driving facial state information in the database to determine whether the driver is suspected of drunk driving. If there is no suspicion of drunk driving, the driver is allowed to start the vehicle, otherwise it enters the drunk driving benchmark check (i.e. the above-mentioned secondary drunk driving test).

[0076] In a feasible implementation manner, the step S203 may include:

[0077] Step S2031: Calculate the visual recognition deviation rate, auditory recognition deviation rate and language recognition deviation rate of the driver in the visual direction, auditory direction and language direction respectively according to the drunk driving detection item.

[0078] In the specific implementation, the cloud platform selects detection items including vision, hearing, and language from the drunk driving detection database. The visual direction mainly detects whether the driver can find the difference in the picture according to the benchmark state, and the parameters involved are the average picture recognition speed v1 and the picture recognition accuracy p1; the auditory direction mainly detects whether the driver can recognize the voice according to the benchmark state, and the parameters involved are the average voice recognition speed v2 and the voice recognition accuracy p2; the language direction mainly detects whether the driver can read the sentence according to the benchmark state, and the parameters involved are the average sentence recognition speed v3 and the sound matching rate p3.

[0079] Step S2032: Conduct a secondary drunk driving test on the driver based on the visual recognition deviation rate, the auditory recognition deviation rate and the language recognition deviation rate.

[0080] In the specific implementation, the actual recognition value of each detection direction The benchmark recognition value is calculated when the driver matches the drunk driving benchmark value, and the value is b i, then the recognition deviation rate Comprehensive deviation rate D = ∑(d i ×o i ), where o represents the ratio of the number of detection items in each direction to the total number of detection items. If the recognition deviation rate of a single direction is negative, the data of this direction will not be calculated when the comprehensive deviation rate is calculated. X , it means that the driver has a risk of drunk driving, where D X It represents the credible deviation rate, which is preset to 20% and can be adjusted through the cloud platform. The cloud platform randomly selects certain drunk driving test items (such as 10 items) from the database. After the driver completes the test, the comprehensive deviation rate D is calculated according to the above rules. If D≤D X , the vehicle is allowed to start, otherwise the detection level is increased, and a certain number of drunk driving detection items (such as 30 items) are extracted from the database in proportion. The proportion is based on the deviation of each detection direction. The greater the deviation, the greater the extraction ratio. After the driver completes the test, the comprehensive deviation rate is calculated according to the above rules. If D≤D X , the vehicle is allowed to start, otherwise it is considered that the driver has a risk of drunk driving and the vehicle is prohibited from starting. At the same time, the driver is notified of the risk situation through the cloud platform communication module.

[0081] In addition, in this embodiment, there are two risks for the driver. One is that the unauthorized user starts the vehicle, resulting in the failure of facial recognition, and the second is that the drunk driving detection fails when the driver starts the vehicle. The strategies for dealing with the above risks are as follows: when facial recognition fails, it means that the driver has not passed the face authentication. If the vehicle has been registered, the abnormal information of the face authentication failure will be sent to the registrant through the cloud platform communication module by SMS or AI phone; when the drunk driving detection fails, it means that the driver has passed the face authentication, but there is a risk of drunk driving. If the driver has filled in the drunk driving contact information when registering, the abnormal information of the drunk driving detection failure will be sent to the contact through the cloud platform communication module. SMS or AI phone call, if the drunk driving contact believes that the driver has not drunk alcohol, can remotely unlock the vehicle lock state and allow the vehicle to start. After the vehicle starts, the driver-related information will be reported to the relevant transportation department through the cloud platform communication module for processing.

[0082] In particular, in this embodiment, a set of facial recognition - drunk driving feature recognition - drunk driving benchmark verification actions is regarded as a successful drunk driving detection cycle. Each successful drunk driving detection cycle will upload the detection data and detection results to the cloud platform. The cloud platform will regularly adjust the drunk driving feature recognition data and benchmark verification detection item data based on past data, and remotely upgrade them through OTA to improve the drunk driving detection accuracy and detection speed of the present invention.

[0083] In this embodiment, if the driver passes the face recognition, the driver is tested for drunk driving according to the facial recognition information of the driver; if the driver passes the drunk driving test once, it is determined that the driver does not have a drunk driving suspicion; if the driver fails the drunk driving test once, it is determined that the driver has a drunk driving suspicion, and the visual recognition deviation rate, auditory recognition deviation rate and language recognition deviation rate corresponding to the driver in the visual direction, auditory direction and language direction are calculated according to the drunk driving detection items; the driver is tested for drunk driving twice based on the visual recognition deviation rate, auditory recognition deviation rate and language recognition deviation rate. Compared with the traditional drunk driving detection method, the above method of this embodiment establishes a complete set of automobile drunk driving management and detection means, firstly, the driver's identity is judged by facial recognition, if it fails, the vehicle is prohibited from starting, otherwise, the driver is judged by facial features whether he is suspected of drunk driving; if so, the vehicle is prohibited from starting, and then the driver is judged by the drunk driving benchmark check whether he is drunk driving; if so, the vehicle is prohibited from starting, and after the vehicle is prohibited from starting, the abnormal information will be sent to the management personnel to avoid the possible risk of misjudgment and further prevent the problem of drunk driving. After completing the drunk driving test, the test data will be uploaded to the cloud platform for data analysis to improve the detection accuracy and speed of this method.

[0084] In addition, an embodiment of the present application further proposes a storage medium, on which a drunk driving detection program is stored. When the drunk driving detection program is executed by a processor, the steps of the drunk driving detection method described above are implemented.

[0085] Reference Figure 5 , Figure 5 This is a structural block diagram of the first embodiment of the drunk driving detection device of this application.

[0086] like Figure 5 As shown, the drunk driving detection device proposed in the embodiment of the present application includes:

[0087] The face recognition module 501 is used to perform face recognition on the driver when the current driving environment of the vehicle meets the preset basic conditions and the vehicle is in the starting state;

[0088] A drunk driving detection module 502 is used to perform a drunk driving detection on the driver if the driver passes the face recognition;

[0089] A first management module 503, configured to allow the driver to start the vehicle if the driver passes the drunk driving test;

[0090] The second management module 504 is used to prohibit the driver from starting the vehicle if the driver fails the face recognition or the drunk driving test, and send an abnormal information to the management personnel.

[0091] This embodiment performs facial recognition on the driver when the current driving environment of the vehicle meets the preset basic conditions and the vehicle is in the starting state; if the driver passes the facial recognition, the driver is tested for drunk driving; if the driver passes the drunk driving test, the driver is allowed to start the vehicle; if the driver fails the facial recognition or fails the drunk driving test, the driver is prohibited from starting the vehicle, and an abnormal message is sent to the manager. Compared with the traditional drunk driving detection method, since the above method of this embodiment performs facial recognition and drunk driving detection on the driver in the cloud platform, without adding additional equipment, the advantages of the cloud platform are convenient, efficient and iterative, and the driver is remotely judged whether he has drunk alcohol. While improving the detection accuracy and speeding up the detection speed, the problem of dismantling and installing the alcohol detection equipment for replacement is avoided; and the vehicle is prohibited from starting when the driver fails the facial recognition or fails the drunk driving test, realizing the low cost and universalization of drunk driving detection, and reducing the burden of traffic drunk driving detection; in addition, the full amount of detection data of this embodiment is stored on the cloud platform. Compared with the traditional method of only detecting whether the driver is drunk driving, this embodiment can also expand the capabilities in other directions through the collected detection data.

[0092] Based on the first embodiment of the drunk driving detection device of the present application, a second embodiment of the drunk driving detection device of the present application is proposed.

[0093] In this embodiment, the face recognition module 501 is also used to obtain the driver's registration information and drunk driving detection data, and determine whether the registration information and the drunk driving detection data are qualified; if the registration information and the drunk driving detection data are both qualified, it is determined that the current driving environment of the vehicle meets the preset basic conditions; if the registration information or the drunk driving detection data is unqualified, it is determined that the current driving environment of the vehicle does not meet the preset basic conditions; the drunk driving detection data includes visual direction detection data, auditory direction detection data and language direction detection data, the visual direction detection data includes the average picture recognition speed and the picture recognition accuracy, the auditory direction detection data includes the average voice recognition speed and the voice recognition accuracy, and the language direction detection data includes the average sentence recognition speed and the sound matching rate.

[0094] Furthermore, the face recognition module 501 is also used to upload the driver's facial feature information to the cloud platform for feature comparison when the vehicle's current driving environment meets preset basic conditions and the vehicle is in a starting state; if the comparison result shows that the driver has the authority to start the vehicle, it is determined that the driver has passed the face recognition; if the comparison result shows that the driver does not have the authority to start the vehicle, it is determined that the driver has not passed the face recognition.

[0095] Furthermore, the drunk driving detection module 502 is also used to, if the driver passes face recognition, conduct a drunk driving test on the driver based on the driver's facial recognition information; if the driver passes the drunk driving test once, it is determined that the driver is not suspected of drunk driving; if the driver fails the drunk driving test once, it is determined that the driver is suspected of drunk driving, and the driver is subjected to a second drunk driving test based on the drunk driving test items.

[0096] Furthermore, the drunk driving detection module 502 is also used to calculate the visual recognition deviation rate, auditory recognition deviation rate and language recognition deviation rate of the driver in the visual direction, auditory direction and language direction respectively according to the drunk driving detection items; and perform a secondary drunk driving test on the driver based on the visual recognition deviation rate, auditory recognition deviation rate and language recognition deviation rate.

[0097] Other embodiments or specific implementations of the drunk driving detection device of the present application can refer to the above-mentioned method embodiments and will not be repeated here.

[0098] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0099] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0100] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0101] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A drunk driving detection method, characterized in that: The drunk driving detection method is applied to a cloud platform, and the method comprises the following steps: When the current driving environment of the vehicle meets the preset basic conditions and the vehicle is in the starting state, performing face recognition on the driver; If the driver passes the facial recognition, the driver is tested for drunk driving; If the driver passes the drunk driving test, allowing the driver to start the vehicle; If the driver fails the face recognition or the drunk driving test, the driver is prohibited from starting the vehicle and an abnormal information is sent to the management staff.

2. The drunk driving detection method according to claim 1, characterized in that: When the current driving environment of the vehicle meets the preset basic conditions and the vehicle is in the starting state, before the step of performing face recognition on the driver, the method further includes: Obtaining the driver's registration information and drunk driving test data, and determining whether the registration information and the drunk driving test data are qualified; If both the registration information and the drunk driving test data are qualified, it is determined that the current driving environment of the vehicle meets the preset basic conditions; If the registration information or the drunk driving detection data is unqualified, it is determined that the current driving environment of the vehicle does not meet the preset basic conditions.

3. The drunk driving detection method according to claim 2, characterized in that: The drunk driving detection data includes visual direction detection data, auditory direction detection data and language direction detection data. The visual direction detection data includes an average picture recognition speed and a picture recognition accuracy rate. The auditory direction detection data includes an average speech recognition speed and a speech recognition accuracy rate. The language direction detection data includes an average sentence recognition speed and a sound matching rate.

4. The drunk driving detection method according to claim 1, characterized in that: The step of performing face recognition on the driver when the current driving environment of the vehicle meets the preset basic conditions and the vehicle is in a starting state includes: When the current driving environment of the vehicle meets the preset basic conditions and the vehicle is in the starting state, the driver's facial feature information is uploaded to the cloud platform for feature comparison; If the comparison result shows that the driver has the authority to start the vehicle, it is determined that the driver has passed the face recognition; If the comparison result shows that the driver does not have the authority to start the vehicle, it is determined that the driver has failed the face recognition.

5. The drunk driving detection method according to claim 1, characterized in that: If the driver passes the face recognition, the step of conducting a drunk driving test on the driver comprises: If the driver passes the facial recognition, a drunk driving test is conducted on the driver based on the facial recognition information of the driver; If the driver passes a drunk driving test, it is determined that the driver is not suspected of drunk driving; If the driver fails the first drunk driving test, the driver is determined to be suspected of drunk driving, and a second drunk driving test is conducted on the driver based on the drunk driving test items.

6. The drunk driving detection method according to claim 5, characterized in that: The step of performing a secondary drunk driving test on the driver according to the drunk driving test items comprises: Calculate the visual recognition deviation rate, auditory recognition deviation rate and language recognition deviation rate of the driver in the visual direction, auditory direction and language direction respectively according to the drunk driving detection item; The driver is subjected to a secondary drunk driving test based on the visual recognition deviation rate, the auditory recognition deviation rate and the language recognition deviation rate.

7. A drunk driving detection device, characterized in that: The drunk driving detection device comprises: A face recognition module, used to perform face recognition on the driver when the current driving environment of the vehicle meets the preset basic conditions and the vehicle is in the starting state; A drunk driving detection module, used to perform a drunk driving detection on the driver if the driver passes the face recognition; A first management module, configured to allow the driver to start the vehicle if the driver passes the drunk driving test; The second management module is used to prohibit the driver from starting the vehicle if the driver fails to pass the face recognition or the drunk driving test, and send an abnormal information to the management personnel.

8. A drunk driving detection device, characterized in that: The device comprises: a memory, a processor, and a drunk driving detection program stored in the memory and executable on the processor, wherein the drunk driving detection program is configured to implement the steps of the drunk driving detection method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a drunk driving detection program is stored on the storage medium. When the drunk driving detection program is executed by a processor, the steps of the drunk driving detection method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product includes a drunk driving detection program, which, when executed by a processor, implements the steps of the drunk driving detection method according to any one of claims 1 to 6.

Images