Man-vehicle inconsistency detection method and device, storage medium and computer equipment

Abstract

The invention provides a person-vehicle inconsistency detection method and device, a storage medium and computer equipment, and the method comprises the steps: obtaining the sampling inspection related information of a target driver, and configuring a sampling inspection triggering rate for the target driver according to the sampling inspection related information; carrying out spot check on the target driver based on the spot check trigger rate; when the target driver hits spot check, sending a spot check instruction to a driver end, and receiving image information fed back by the driver end; and detecting and identifying the image information by using pre-stored driver information to obtain a final detection result. According to the method and the system, the sampling inspection rule which is reasonable and can be flexibly adjusted is set, and the image identification technology is adopted to realize human-vehicle inconformity detection, so that the identification accuracy is ensured, equipment assistance is not needed, and the operation cost of an enterprise is greatly reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of online car-hailing operation management, and in particular to a method and device for detecting vehicle mismatch, a storage medium, and a computer device. Background Art

[0002] In the online ride-hailing industry, according to the safety and compliance regulations of the online ride-hailing industry, vehicles must be registered with the local public security vehicle management department, and drivers must hold a valid driver's license and obtain an online ride-hailing driver qualification certificate. Platform companies should ensure that the drivers and vehicles providing services online are consistent with the drivers and vehicles actually providing services offline. There is often a discrepancy between the drivers and vehicles entered during driver recruitment and registration and the drivers and vehicles actually operating after approval.

[0003] At present, the industry has adopted methods such as installing facial recognition monitoring equipment or using GPS positioning equipment to monitor whether people and vehicles match. However, the installation of facial recognition monitoring equipment has technical problems such as high cost and GPS positioning has monitoring loopholes. Summary of the invention

[0004] To this end, the present invention provides a method and device for detecting human-vehicle mismatch, a storage medium, and a computer device, aiming to solve the technical problems of low accuracy and high cost in the prior art for human-vehicle mismatch monitoring.

[0005] To achieve the above objectives, the present invention adopts the following technical solutions:

[0006] According to a first aspect of the present invention, the present invention provides a method for detecting a person-vehicle mismatch, the method comprising:

[0007] Obtaining random inspection related information of the target driver, and configuring a random inspection trigger rate for the target driver according to the random inspection related information;

[0008] Performing random inspections on the target driver based on the random inspection trigger rate;

[0009] When the target driver is selected for random inspection, a random inspection instruction is sent to the driver terminal, and image information fed back by the driver terminal is received;

[0010] The image information is detected and identified using the pre-stored driver information to obtain a final detection result.

[0011] Optionally, the sampling inspection related information includes at least one of the operating city, the number of historical completed orders, historical sampling inspection information, and driver-side login information.

[0012] Optionally, configuring a random inspection trigger rate for the target driver according to the random inspection related information includes:

[0013] The following rules are used to configure the sampling trigger rate of the target driver:

[0014] If the driver's login information is updated, the sampling trigger rate = 100%;

[0015] The driver's login information is not updated, and the historical random inspection pass rate is greater than the preset historical random inspection pass rate, and the number of historical completed orders within the first preset period is greater than the first preset number of orders, then the random inspection trigger rate = 0%;

[0016] If the driver's login information is not updated, and the number of historical completed orders within the second preset period is greater than the second preset number of orders, then the sampling inspection trigger rate = ((1-historical city sampling inspection pass rate) + (1-historical sampling inspection pass rate)) × N;

[0017] Wherein, N is the preset probability adjustment weight.

[0018] Optionally, the calculation formula for the historical random inspection pass rate is:

[0019] Historical sampling inspection pass rate = (historical sampling inspection pass number / historical sampling inspection total number) × 100%;

[0020] The calculation formula for the historical city random inspection pass rate is:

[0021] The pass rate of historical city random inspections = (the number of historical city random inspections that passed / the total number of historical city random inspections) × 100%.

[0022] Optionally, the image information includes a front picture of the vehicle and the people therein, and a rear picture of the vehicle;

[0023] The pre-stored driver information includes identity card information and registered license plate number information.

[0024] Optionally, the detecting and identifying the image information to obtain a final detection result includes:

[0025] Extracting features from the image information to obtain picture feature information;

[0026] Using the pre-stored information of the target driver, each item of image feature information is verified for consistency;

[0027] If all the image feature information passes the consistency verification, it is considered that the person and the car match, and the test result is passed the random inspection;

[0028] If there is image feature information that fails the consistency verification, it is considered that the person and the vehicle do not match, and the test result is that it fails the random inspection;

[0029] The image feature information includes the driver's head portrait information, the front license plate number information and the rear license plate number information.

[0030] Optionally, before detecting and identifying the image information, the method further includes:

[0031] Performing real-scene shooting recognition on the image information to determine whether the image information is a non-real-scene picture;

[0032] If the image information is not a real-life picture, detection is suspended and an error prompt is output to the driver.

[0033] According to a second aspect of the present invention, the present invention provides a person-vehicle mismatch detection device, the device comprising:

[0034] A probability configuration module, used to obtain the random inspection related information of the target driver, and configure the random inspection trigger rate for the target driver according to the random inspection related information;

[0035] A random inspection application module, used for performing random inspections on the target drivers based on the random inspection trigger rate;

[0036] An information feedback module, used for sending a sampling instruction to the driver side when the target driver is selected for sampling, and receiving image information fed back by the driver side;

[0037] The detection and recognition module is used to detect and recognize the image information using the pre-stored driver information to obtain a final detection result.

[0038] According to a third aspect of the present invention, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes a person-vehicle mismatch detection method as described in any one of the first aspect of the present invention.

[0039] According to a fourth aspect of the present invention, the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, a person-vehicle mismatch detection method as described in any one of the first aspect of the present invention is implemented.

[0040] The present invention adopts the above technical solution and has at least the following beneficial effects:

[0041] Through the scheme of the present invention, the sampling inspection related information of the target driver is obtained, and the sampling inspection trigger rate for the target driver is configured according to the sampling inspection related information; the target driver is sampled based on the sampling inspection trigger rate; when the target driver hits the sampling inspection, a sampling inspection instruction is sent to the driver end, and the image information fed back by the driver end is received; the image information is detected and identified using the pre-stored driver information to obtain the final detection result. Thus, reasonable sampling inspection rules are set, and image recognition technology is used to realize the detection of person-vehicle mismatch, which ensures the recognition accuracy and does not require equipment assistance, greatly reducing the operating costs of the enterprise.

[0042] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 A schematic diagram showing a flow chart of a method for detecting a person-vehicle mismatch provided by an embodiment of the present invention;

[0045] Figure 2 A schematic diagram of the structure of a vehicle-person mismatch detection device provided by an embodiment of the present invention is shown;

[0046] Figure 3 A schematic diagram showing the structure of a vehicle-person mismatch detection device provided by another embodiment of the present invention is shown;

[0047] Figure 4 A schematic diagram of the physical structure of a computer device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0048] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0049] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device 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 device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0050] The embodiment of the present invention provides a method for detecting a person-vehicle mismatch, such as Figure 1 As shown, at least the following steps S101 to S104 may be included:

[0051] Step S101, obtaining the random inspection related information of the target driver, and configuring the random inspection trigger rate for the target driver according to the random inspection related information.

[0052] First of all, it should be noted that the embodiment of the present invention performs random inspections on target drivers based on the random inspection trigger rate, and the random inspection trigger rate for drivers is not uniform, but is flexibly adjusted based on the target driver's city and its own historical random inspection situation. Specifically, the random inspection related information may include the target driver's operating city, the number of historical completed orders, historical random inspection information, and the driver's login information.

[0053] Specifically, the following rules can be used to configure the sampling trigger rate of target drivers:

[0054] If the driver's login information is updated, the sampling trigger rate = 100%;

[0055] The driver's login information is not updated, and the historical random inspection pass rate is greater than the preset historical random inspection pass rate, and the number of historical completed orders within the first preset period is greater than the first preset number of orders, then the random inspection trigger rate = 0%;

[0056] If the driver's login information is not updated, and the number of historical completed orders within the second preset period is greater than the second preset number of orders, then the sampling inspection trigger rate = ((1-historical city sampling inspection pass rate) + (1-historical sampling inspection pass rate)) × N; N is the preset probability adjustment weight, which can be adjusted according to actual needs. The calculation formula for the historical sampling inspection pass rate is:

[0057] Historical sampling inspection pass rate = (historical sampling inspection pass number / historical sampling inspection total number) × 100%;

[0058] The calculation formula for the historical city sampling pass rate is:

[0059] The pass rate of historical city random inspections = (the number of historical city random inspections that passed / the total number of historical city random inspections) × 100%.

[0060] Preferably, the preset historical sampling pass rate can be 99%; the first preset period can be one month, one week, etc. The first preset number of orders is related to the first preset period and can be set according to actual needs, for example, the number of completed orders within 30 days is greater than 10 orders. The second preset period is generally less than the first preset period, and the second preset number of orders is also related to the second preset period and can also be set according to actual needs, for example, the number of completed orders within 3 days is greater than 1 order.

[0061] Based on the above rules, when the driver changes the driver client, the risk of mismatch between the driver and the vehicle is higher, so mandatory random inspection is performed; when the driver's historical random inspection results are good, a lower random inspection trigger rate can be set; in other cases, the current random inspection pass rate can be configured in coordination with the city's historical random inspection pass rate and the driver's own historical random inspection pass rate.

[0062] Step S102: Perform random inspections on target drivers based on the random inspection trigger rate.

[0063] The sampling inspection trigger rate calculated in step S101 can be understood as the current sampling inspection trigger probability of the computing node. If the current sampling inspection trigger rate for the target driver is 100%, the target driver will be subject to mandatory sampling inspection; if the current sampling inspection trigger rate for the target driver is 0%, the target driver will not be subject to sampling inspection; if the current sampling inspection trigger rate for the target driver is (0% to 100%), the probability of whether the target driver is subject to sampling inspection can be determined based on the specific value to obtain the result of whether the sampling inspection is hit.

[0064] It is understandable that, as time goes by, the random inspection-related information is updated in real time, and the random inspection trigger rate of the target driver is also updated in real time.

[0065] Step S103, when the target driver is selected for random inspection, a random inspection instruction is sent to the driver side, and image information fed back by the driver side is received.

[0066] When the target driver is selected for random inspection, the background system can send a random inspection instruction with the random inspection operation process to the driver. In the embodiment of the present invention, when the driver triggers the random inspection, he needs to upload two real photos, that is, image information. One photo of the front of the car (the photo must include the driver's face information and the license plate number information of the front of the car), and one photo of the rear of the car (the photo must include the license plate number information of the rear of the car).

[0067] Step S104, using the pre-stored driver information to detect and identify the image information to obtain a final detection result.

[0068] Before detecting and identifying the image information, the embodiment of the present invention may first perform real-scene shooting identification on the image information to determine whether the image information is a non-real-scene picture.

[0069] That is to say, after the driver uploads the image information, it automatically identifies whether the uploaded image is a real image, that is, whether the image is reflective and not real, to avoid Photoshop of the image. If the image information is identified as a non-real image, the detection is suspended and an error prompt is output to the driver; if the image information is identified as a real image, the person-vehicle mismatch detection continues.

[0070] Furthermore, feature extraction is performed on the image information to obtain picture feature information; and the consistency of each item of picture feature information is verified using pre-stored information of the target driver.

[0071] The feature extraction in the embodiment of the present invention refers to extracting the driver's head portrait information, the front plate number information and the rear plate number information from the image information by using the image extraction technology, that is, the image feature information. The pre-stored driver information refers to the ID card information and the registered license plate number information reported by the driver when registering in the background system.

[0072] Then, the driver's head portrait information and ID card information are verified by face recognition; the front plate number information and the rear plate number information are judged for consistency with the registered license plate number information. If all the image feature information passes the consistency verification, it is considered that the person and the car are consistent, and the test result is passed the random inspection; if there is image feature information that fails the consistency verification, it is considered that the person and the car are inconsistent, and the test result is failed the random inspection. In other words, if the driver's head portrait information is consistent with the ID card information, and the front plate number information and the rear plate number information are consistent with the registered license plate number information, the verification is passed; if the driver's head portrait information is inconsistent with the ID card information, or the front plate number information / rear plate number information is inconsistent with the registered license plate number information, the verification is not passed.

[0073] Therefore, mature image recognition technology and image extraction technology are used to implement a person-vehicle mismatch inspection method, and the detection results are sent to the driver side so that the driver side can perform corresponding follow-up operations based on the detection results.

[0074] The embodiment of the present invention provides a method for detecting mismatches between a person and a vehicle, which obtains the sampling inspection related information of the target driver, configures the sampling inspection trigger rate for the target driver according to the sampling inspection related information; performs sampling inspection on the target driver based on the sampling inspection trigger rate; when the target driver hits the sampling inspection, sends a sampling inspection instruction to the driver end, and receives the image information fed back by the driver end; uses the pre-stored driver information to detect and identify the image information to obtain the final detection result. Thus, reasonable and flexibly adjustable sampling inspection rules are set, and image recognition technology is used to realize mismatch detection between a person and a vehicle, which ensures the recognition accuracy and does not require equipment assistance, greatly reducing the operating costs of the enterprise.

[0075] Further, as Figure 1 In a specific implementation, an embodiment of the present invention provides a person-vehicle mismatch detection device, such as Figure 2 As shown, the device may include: a probability configuration module 210 , a sampling application module 220 , an information feedback module 230 , and a detection and identification module 240 .

[0076] The probability configuration module 210 can be used to obtain the random inspection related information of the target driver and configure the random inspection trigger rate for the target driver according to the random inspection related information;

[0077] The sampling inspection application module 220 can be used to perform sampling inspections on target drivers based on the sampling inspection trigger rate;

[0078] The information feedback module 230 can be used to send a sampling inspection instruction to the driver side when the target driver hits the sampling inspection, and receive the image information fed back by the driver side;

[0079] The detection and recognition module 240 can be used to detect and recognize the image information using the pre-stored driver information to obtain a final detection result.

[0080] Alternatively, if Figure 3 As shown, another embodiment of the present invention provides a person-vehicle mismatch detection device, which also includes: a real scene recognition module 250.

[0081] The real scene recognition module 250 can be used to perform real scene shooting recognition on the image information before detecting and recognizing the image information, and determine whether the image information is a non-real scene picture;

[0082] If the image information is not a real picture, the detection is suspended and an error prompt is output to the driver.

[0083] Optionally, the probability configuration module 210 may also be used to configure the sampling trigger rate of the target driver using the following rules:

[0084] If the driver's login information is updated, the sampling trigger rate = 100%;

[0085] The driver's login information is not updated, and the historical random inspection pass rate is greater than the preset historical random inspection pass rate, and the number of historical completed orders within the first preset period is greater than the first preset number of orders, then the random inspection trigger rate = 0%;

[0086] If the driver's login information is not updated, and the number of historical completed orders within the second preset period is greater than the second preset number of orders, then the sampling inspection trigger rate = ((1-historical city sampling inspection pass rate) + (1-historical sampling inspection pass rate)) × N;

[0087] Wherein, N is the preset probability adjustment weight.

[0088] Optionally, the detection and recognition module 240 may also be used to extract features from the image information to obtain picture feature information;

[0089] Use the pre-stored information of the target driver to verify the consistency of each image feature information;

[0090] If all the image feature information passes the consistency verification, it is considered that the person and the car match, and the test result is passed the random inspection;

[0091] If there is image feature information that fails the consistency verification, it is considered that the person and the vehicle do not match, and the test result is that it fails the random inspection;

[0092] Among them, the image feature information includes the driver’s portrait information, the front license plate information and the rear license plate information.

[0093] It should be noted that for other corresponding descriptions of the functional modules involved in the vehicle-person mismatch detection device provided in the embodiment of the present invention, reference can be made to Figure 1 The corresponding description of the method shown will not be repeated here.

[0094] Based on the above Figure 1 The method shown, accordingly, an embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the person-vehicle mismatch detection method of any of the above embodiments are implemented.

[0095] Based on the above Figure 1 The method shown and Figure 3 The embodiment of the device shown in the figure, the embodiment of the present invention also provides a physical structure diagram of a computer device, such as Figure 4 As shown, the computer device may include a communication bus, a processor, a memory and a communication interface, and may also include an input and output interface and a display device, wherein each functional unit may communicate with each other through the bus. The memory stores a computer program, and the processor is used to execute the program stored in the memory and execute the steps of the vehicle-person mismatch detection method of the above embodiment.

[0096] Those skilled in the art can clearly understand that the specific working processes of the systems, devices, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and for the sake of brevity, they are not further described here.

[0097] In addition, the functional units in various embodiments of the present invention may be physically independent of each other, or two or more functional units may be integrated together, or all functional units may be integrated into one processing unit. The above integrated functional units may be implemented in the form of hardware, or in the form of software or firmware.

[0098] Those skilled in the art can understand that if the integrated functional unit is implemented in the form of software and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can essentially or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, which includes a number of instructions to enable a computing device (such as a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention when running the instructions. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk and other media that can store program codes.

[0099] Alternatively, all or part of the steps of implementing the aforementioned method embodiments may be accomplished by hardware associated with program instructions (such as a computing device such as a personal computer, a server, or a network device), and the program instructions may be stored in a computer-readable storage medium. When the program instructions are executed by a processor of a computing device, the computing device executes all or part of the steps of the methods described in the embodiments of the present invention.

[0100] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that within the spirit and principles of the present invention, the technical solutions described in the aforementioned embodiments can still be modified, or some or all of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate from the protection scope of the present invention.

Claims

1. A method for detecting mismatch between a person and a vehicle, characterized in that: The method comprises: Obtaining random inspection related information of the target driver, and configuring a random inspection trigger rate for the target driver according to the random inspection related information; Performing random inspections on the target driver based on the random inspection trigger rate; When the target driver is selected for random inspection, a random inspection instruction is sent to the driver terminal, and image information fed back by the driver terminal is received; The image information is detected and identified using the pre-stored driver information to obtain a final detection result.

2. The method according to claim 1, characterized in that: The sampling inspection related information includes at least one of the operating city, the number of historical completed orders, the historical sampling inspection information, and the driver's login information.

3. The method according to claim 2, characterized in that The configuring the sampling inspection trigger rate for the target driver according to the sampling inspection related information includes: The following rules are used to configure the sampling trigger rate of the target driver: If the driver's login information is updated, the sampling trigger rate = 100%; The driver's login information is not updated, and the historical random inspection pass rate is greater than the preset historical random inspection pass rate, and the number of historical completed orders within the first preset period is greater than the first preset number of orders, then the random inspection trigger rate = 0%; If the driver's login information is not updated, and the number of historical completed orders within the second preset period is greater than the second preset number of orders, then the sampling inspection trigger rate = ((1-historical city sampling inspection pass rate) + (1-historical sampling inspection pass rate)) × N; Wherein, N is the preset probability adjustment weight.

4. The method according to claim 3, characterized in that The calculation formula for the historical sampling pass rate is: Historical sampling inspection pass rate = (historical sampling inspection pass number / historical sampling inspection total number) × 100%; The calculation formula for the historical city random inspection pass rate is: The pass rate of historical city random inspections = (the number of historical city random inspections that passed / the total number of historical city random inspections) × 100%.

5. The method according to claim 1, characterized in that The image information includes a front picture of the vehicle and a photo of the vehicle and the people therein, and a rear picture of the vehicle; The pre-stored driver information includes identity card information and registered license plate number information.

6. The method according to claim 5, characterized in that The detecting and identifying the image information to obtain a final detection result includes: Extracting features from the image information to obtain picture feature information; Using the pre-stored information of the target driver, each item of image feature information is verified for consistency; If all the image feature information passes the consistency verification, it is considered that the person and the car match, and the test result is passed the random inspection; If there is image feature information that fails the consistency verification, it is considered that the person and the vehicle do not match, and the test result is that it fails the random inspection; The image feature information includes the driver's head portrait information, the front license plate number information and the rear license plate number information.

7. The method according to claim 6, characterized in that Before detecting and identifying the image information, the method further includes: Performing real-scene shooting recognition on the image information to determine whether the image information is a non-real-scene picture; If the image information is not a real-life picture, detection is suspended and an error prompt is output to the driver.

8. A person-vehicle mismatch detection device, characterized in that: The device comprises: A probability configuration module, used to obtain the random inspection related information of the target driver, and configure the random inspection trigger rate for the target driver according to the random inspection related information; A random inspection application module, used for performing random inspections on the target drivers based on the random inspection trigger rate; An information feedback module, used for sending a sampling instruction to the driver side when the target driver is selected for sampling, and receiving image information fed back by the driver side; The detection and recognition module is used to detect and recognize the image information using the pre-stored driver information to obtain a final detection result.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the vehicle-person mismatch detection method according to any one of claims 1 to 7.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the vehicle-person mismatch detection method according to any one of claims 1 to 7 is implemented.

Images