A driver physical examination device and anti-cheating method, system and medium

Abstract

The application provides a driver physical examination device and an anti-cheating method, system and medium. The method comprises the following steps: collecting face recognition information of a target driver through a preset physical examination device recognition system, and performing identity verification and judgment on the target driver; if the identity verification of the target driver is successful, performing vision detection on the target driver according to the preset physical examination device, processing head position data to obtain head position deviation data, and performing position cheating judgment processing; performing recognition cheating judgment processing according to visual target recognition data; processing eye movement data to obtain an eye movement abnormality index and performing eye movement cheating judgment processing; processing vision data to obtain a vision comparison deviation coefficient and performing vision data cheating judgment processing; and generating a physical examination report and uploading the physical examination report to a background, so as to realize the driver physical examination device and the anti-cheating technology.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of driver physical examination, in particular to a driver physical examination device and an anti-cheating method, system and medium. BACKGROUND

[0002] In driver physical examination, accurate detection of driver vision is crucial for road traffic safety, however, there are currently some people who use various cheating methods to obtain physical examination qualified results that do not conform to the actual vision, which brings great hidden dangers to road traffic safety, and the existing vision physical examination method cannot effectively identify and prevent these cheating behaviors.

[0003] In view of the above problems, an effective technical solution is urgently needed. SUMMARY

[0004] The purpose of the present application is to provide a driver physical examination device and an anti-cheating method, system and medium, which can perform vision detection on a target driver according to a preset physical examination device, process head position data, obtain head position deviation data, and perform position cheating judgment processing, identify cheating judgment processing according to visual target recognition data, process eye movement data, obtain eye movement abnormality index, and perform eye movement cheating judgment processing, process vision data, obtain vision comparison deviation coefficient, and perform vision data cheating judgment processing, generate a physical examination report and upload it to the background, and realize the technology of driver physical examination device and anti-cheating.

[0005] The present application also provides a driver physical examination device and an anti-cheating method, comprising the following steps:

[0006] Collecting face recognition information of a target driver recognized by a preset physical examination device recognition system, and performing identity verification judgment on the target driver;

[0007] If the identity verification of the target driver is successful, performing vision detection on the target driver according to the preset physical examination device, and real-time acquiring head position data, visual target recognition data, vision data and eye movement data of the target driver;

[0008] Processing the head position data to obtain head position deviation data, and performing position cheating judgment processing;

[0009] Identifying cheating judgment processing according to the visual target recognition data;

[0010] Processing the eye movement data to obtain eye movement abnormality index, and performing eye movement cheating judgment processing;

[0011] According to the vision data, a vision comparison deviation coefficient is obtained, and vision data cheating judgment processing is performed;

[0012] A physical examination report is generated and uploaded to the background.

[0013] Optionally, in the driver physical examination equipment and anti-cheating method described in the present application, the head position data is processed to obtain head position deviation data, and position cheating judgment processing is performed, including:

[0014] The head position data includes head horizontal angle data, head vertical angle data, head front-back displacement data, and head left-right displacement data;

[0015] The head standard position data includes head horizontal standard angle data, head vertical standard angle data, head front-back standard displacement data, and head left-right standard displacement data;

[0016] According to the head position data and the head standard position data, statistical processing is performed to obtain corresponding head position deviation data, including head horizontal angle deviation data, head vertical angle deviation data, head front-back displacement deviation data, and head left-right displacement deviation data;

[0017] According to the head horizontal angle deviation data, head vertical angle deviation data, head front-back displacement deviation data, and head left-right displacement deviation data, a preset head deviation recognition model is used for processing to obtain head position deviation data;

[0018] According to the head position deviation data and a preset head position deviation threshold, a first threshold comparison result is obtained;

[0019] According to the first threshold comparison result, it is judged whether the head position of the target driver has a deviation exceeding the standard;

[0020] If there is a deviation exceeding the standard, it is determined as position cheating.

[0021] Optionally, in the driver physical examination equipment and anti-cheating method described in the present application, the target driver identification data is processed to obtain target driver identification data, and the target driver identification data is processed to obtain target driver identification data. The identification cheating judgment processing includes:

[0022] The visual target recognition data includes maximum recognition time data and visual target recognition error rate data;

[0023] The standard recognition time data is obtained, and the maximum recognition time data is compared to obtain recognition time deviation data;

[0024] The visual target recognition error rate mean data is obtained, and the visual target recognition error rate data is compared to obtain visual target recognition error rate deviation data;

[0025] obtaining a preset visual target recognition deviation threshold set, including a recognition time deviation threshold and a recognition error rate deviation threshold;

[0026] comparing the two threshold values corresponding to the recognition time deviation data and the visual target recognition error rate deviation data with the two threshold values corresponding to the preset visual target recognition deviation threshold set;

[0027] If the results of the two threshold value comparisons are not all less than the corresponding threshold values of the preset visual target recognition deviation threshold set, the visual target recognition exists cheating.

[0028] Optionally, in the driver physical examination device and the anti-cheating method described in the present application, the processing according to the eye movement data to obtain an eye movement abnormality index and the eye movement cheating judgment processing include:

[0029] The eye movement data includes blink frequency data, left and right eye rotation angle data, and up and down eye rotation angle data.

[0030] Obtain blink frequency standard data, and compare the blink frequency data to obtain blink frequency deviation data;

[0031] Obtain left and right eye rotation angle standard data and up and down eye rotation angle standard data, and compare the left and right eye rotation angle data and the up and down eye rotation angle data respectively to obtain corresponding left and right eye rotation angle deviation data and up and down eye rotation angle deviation data;

[0032] According to the blink frequency deviation data, the left and right eye rotation angle deviation data, and the up and down eye rotation angle deviation data, the eye movement abnormality index is obtained by weighted processing;

[0033] According to the eye movement abnormality index and a preset eye movement abnormality threshold, a second threshold comparison result is obtained;

[0034] According to the second threshold comparison result, it is judged whether the eye movement of the target driver is abnormal;

[0035] If the second threshold comparison result is greater than the preset threshold value, the eye movement of the target driver is abnormal, and it is determined that the eye movement is cheating.

[0036] Optionally, in the driver physical examination device and the anti-cheating method described in the present application, the processing according to the vision data to obtain a vision comparison deviation coefficient and the vision data cheating judgment processing include:

[0037] According to the vision detection result of the target driver, the current vision data is extracted;

[0038] acquire historical vision detection data of the target driver;

[0039] compare the current vision data with the historical vision detection data to obtain a vision comparison deviation coefficient;

[0040] compare the vision comparison deviation coefficient with a preset vision comparison deviation threshold to obtain a third threshold comparison result;

[0041] determine whether the eye movement of the target driver is abnormal according to the third threshold comparison result;

[0042] if the third threshold comparison result is greater than a preset threshold, the sixteen data of the target driver is abnormal, and the vision data cheating is determined.

[0043] Optionally, in the driver physical examination device and the anti-cheating method, the corresponding physical examination report is generated and uploaded to the background, including:

[0044] generating a physical examination report according to the vision detection result;

[0045] if the judgment results of the position cheating judgment, the identification cheating judgment, the eye movement cheating judgment, and the vision data judgment are all not cheating, the physical examination report is a normal report;

[0046] if the judgment results of the position cheating judgment, the identification cheating judgment, the eye movement cheating judgment, and the vision data judgment are any cheating, the physical examination report is marked as an abnormal report, which needs to be further audited;

[0047] uploading the physical examination report to the background.

[0048] In a second aspect, the present application provides a driver physical examination device and an anti-cheating system, which comprises a memory and a processor, the memory comprising a driver physical examination device and an anti-cheating method program, and the driver physical examination device and the anti-cheating method program are executed by the processor to realize the following steps:

[0049] collecting face recognition information of a target driver through a preset physical examination device identification system, and performing identity verification judgment on the target driver;

[0050] if the identity verification of the target driver is successful, performing vision detection on the target driver according to the preset physical examination device, and acquiring head position data, visual target identification data, vision data, and eye movement data of the target driver in real time;

[0051] According to the head position data, head position deviation data is obtained, and position cheating judgment processing is performed;

[0052] According to the target identification data, identification cheating judgment processing is performed;

[0053] According to the eye movement data, eye movement abnormality index is obtained, and eye movement cheating judgment processing is performed;

[0054] According to the vision data, vision comparison deviation coefficient is obtained, and vision data cheating judgment processing is performed;

[0055] Corresponding physical examination report is generated and uploaded to the background.

[0056] Optionally, in the driver physical examination equipment and anti-cheating system provided in the application, according to the head position data, head position deviation data is obtained, and position cheating judgment processing is performed, including:

[0057] The head position data includes head horizontal angle data, head vertical angle data, head front-back displacement data, and head left-right displacement data;

[0058] The head standard position data includes head horizontal standard angle data, head vertical standard angle data, head front-back standard displacement data, and head left-right standard displacement data;

[0059] According to the head position data and the head standard position data, corresponding head position deviation data is obtained through statistical processing, including head horizontal angle deviation data, head vertical angle deviation data, head front-back displacement deviation data, and head left-right displacement deviation data;

[0060] According to the head horizontal angle deviation data, head vertical angle deviation data, head front-back displacement deviation data, and head left-right displacement deviation data, head position deviation data is obtained through a preset head deviation identification model;

[0061] According to the head position deviation data and a preset head position deviation threshold, a first threshold comparison result is obtained;

[0062] According to the first threshold comparison result, it is judged whether the head position of the target driver has a deviation exceeding a standard;

[0063] If there is a deviation exceeding a standard, it is determined as position cheating.

[0064] Optionally, in the driver physical examination equipment and anti-cheating system provided in the application, according to the target identification data, identification cheating judgment processing is performed, including:

[0065] The target mark identification data includes maximum identification time data and target mark identification error rate data;

[0066] Obtain standard identification time data, and compare with the maximum identification time data to obtain identification time deviation data;

[0067] Obtain target mark identification error rate mean data, and compare with the target mark identification error rate data to obtain target mark identification error rate deviation data;

[0068] Obtain a preset target mark identification deviation limit threshold set, including identification time deviation limit threshold and identification error rate deviation limit threshold;

[0069] Compare the identification time deviation data and the target mark identification error rate deviation data with the two corresponding threshold values of the preset target mark identification deviation limit threshold set;

[0070] If the two threshold comparison results are not all less than the corresponding threshold values of the preset target mark identification deviation limit threshold set, the target mark identification exists cheating.

[0071] In a third aspect, the present application also provides a computer readable storage medium, which stores a driver physical examination device and anti-cheating method program, and the driver physical examination device and anti-cheating method program is executed by a processor to realize the steps of the driver physical examination device and anti-cheating method according to any one of the above.

[0072] As can be seen from the above, the driver physical examination device and anti-cheating method, system and medium disclosed by the present application, by collecting the face recognition information of the target driver through the preset physical examination device identification system, and performing identity verification on the target driver, if the target driver identity verification is successful, performing vision detection on the target driver according to the preset physical examination device, and real-time acquiring the head position data, target mark identification data, vision data and eye movement data of the target driver, processing the head position data to obtain head position deviation data, and performing position cheating judgment processing, processing the target mark identification data to obtain an eye movement abnormality index, and performing eye movement cheating judgment processing, processing the vision data to obtain a vision comparison deviation coefficient, and performing vision data cheating judgment processing, corresponding to generate a physical examination report and upload to the background, so as to realize the driver physical examination device and anti-cheating technology.

[0073] Other features and advantages of the present application will be described in the following description, and some will become apparent from the description, or will be understood by those skilled in the art through implementation of the embodiments of the present application. The purposes and other advantages of the present application can be achieved and obtained by the structures specifically pointed out in the written description and the drawings. Attached Figure Description

[0074] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0075] Figure 1 A flowchart illustrating the driver medical examination equipment and anti-cheating method provided in this application embodiment;

[0076] Figure 2 A flowchart illustrating the location cheating detection process of the driver physical examination equipment and anti-cheating method provided in this application embodiment;

[0077] Figure 3 A flowchart illustrating the cheating identification and judgment process of the driver physical examination equipment and anti-cheating method provided in this application embodiment;

[0078] Figure 4 This is a flowchart illustrating the eye movement cheating judgment process of the driver physical examination equipment and anti-cheating method provided in the embodiments of this application. Detailed Implementation

[0079] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0080] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0081] Please refer to Figure 1 , Figure 1is a flowchart of a driver physical examination device and anti-cheating method in some embodiments of the present application. The driver physical examination device and anti-cheating method are used in terminal devices such as computers, mobile phones, and the like. The driver physical examination device and anti-cheating method include the following steps:

[0082] S11, collecting face recognition information of a target driver through a preset physical examination device recognition system, and performing identity verification judgment on the target driver;

[0083] S12, if the target driver identity verification is successful, performing vision detection on the target driver according to the preset physical examination device, and real-time acquiring head position data, visual target recognition data, vision data, and eye movement data of the target driver;

[0084] S13, processing according to the head position data to obtain head position deviation data, and performing position cheating judgment processing;

[0085] S14, performing recognition cheating judgment processing according to the visual target recognition data;

[0086] S15, processing according to the eye movement data to obtain an eye movement abnormality index, and performing eye movement cheating judgment processing;

[0087] S16, processing according to the vision data to obtain a vision comparison deviation coefficient, and performing vision data cheating judgment processing;

[0088] S17, corresponding generation of a physical examination report and uploading to a background.

[0089] It should be noted that in the process of using the driver self-service physical examination device for physical examination, the user often cheats in the vision detection link. The existing vision physical examination method cannot effectively identify and prevent these cheating behaviors, therefore, a new method is needed to effectively and accurately prevent driver vision physical examination cheating. In the present embodiment, the face recognition information of the target driver through the preset physical examination device recognition system is collected, and identity verification judgment is performed. If the identity verification is successful, the target driver is subjected to vision detection according to the preset physical examination device, and data is collected, including head position data, visual target recognition data, vision data, and eye movement data. The head position data is processed to obtain head position deviation data, and position cheating judgment processing is performed. The visual target recognition data is processed to obtain recognition cheating judgment processing. The eye movement data is processed to obtain an eye movement abnormality index, and eye movement cheating judgment processing is performed. The vision data is processed to obtain a vision comparison deviation coefficient, and vision data cheating judgment processing is performed. A physical examination report is generated and uploaded to the background, thereby realizing the driver physical examination device and anti-cheating technology.

[0090] Please refer to Figure 2 , Figure 2 is a flowchart of a position cheating judgment process of a driver physical examination device and an anti-cheating method in some embodiments of the present application. According to the embodiments of the present application, the processing according to the head position data, obtaining head position deviation data, and performing position cheating judgment processing include:

[0091] S21, the head position data includes head horizontal angle data, head vertical angle data, head front-back displacement data, and head left-right displacement data;

[0092] S22, obtain head standard position data, including head horizontal standard angle data, head vertical standard angle data, head front-back standard displacement data, and head left-right standard displacement data;

[0093] S23, according to the head position data combined with the head standard position data statistical processing, obtain corresponding head position deviation data, including head horizontal angle deviation data, head vertical angle deviation data, head front-back displacement deviation data and head left-right displacement deviation data;

[0094] S24, according to the head horizontal angle deviation data, head vertical angle deviation data, head front-back displacement deviation data and head left-right displacement deviation data through the preset head deviation identification model processing, obtain head position deviation data;

[0095] S25, according to the head position deviation data and the preset head position deviation threshold value comparison, obtain the first threshold value comparison result;

[0096] S26, according to the first threshold value comparison result to judge whether the head position of the target driver exists deviation over standard;

[0097] S27, if there is deviation over standard, it is determined that the position cheating.

[0098] It should be noted that during the driver physical examination, the allowable angle deviation range of the head in the horizontal and vertical directions needs to be specified. For example, the allowable deviation angle in the horizontal direction (turning head left and right) is generally ±5, and the allowable deviation angle in the vertical direction (lifting and lowering head) is also ±5. If it exceeds this range, it may be judged as suspected of cheating, and the displacement of the head in front and back and left and right directions also needs to be limited. During normal detection, the distance between the head and the visual detection device should be kept relatively stable, and the front and back displacement is generally not more than ±3 cm, and the left and right displacement is not more than ±2 cm. If it exceeds this displacement range, the anti-cheating mechanism will be triggered. Therefore, the head position data of the driver, including the head horizontal angle, the head vertical angle, the head front and back displacement, and the head left and right displacement data, are obtained, and then compared with the corresponding standard values to obtain the corresponding head position deviation data, including the head horizontal angle deviation data, the head vertical angle deviation data, the head front and back displacement deviation data, and the head left and right displacement deviation data. Finally, the head position deviation data is processed by a preset head deviation identification model to obtain head position deviation data. The head deviation identification model belongs to a neural network model, which is trained according to a large amount of historical head horizontal angle deviation data, head vertical angle deviation data, head front and back displacement deviation data, and head left and right displacement deviation data to obtain a trained head deviation identification model. Then, the head position deviation data is compared with a preset head position deviation threshold, and according to the comparison result, it is judged whether the head position of the target driver has a deviation exceeding the standard. If so, it is judged as position cheating. For example, the preset head position deviation threshold is 0.5, and the head position deviation data is 0.7. At this time, the deviation exceeds the standard, and the target driver has a head position cheating situation.

[0099] Please refer to Figure 3 , Figure 3 is a flowchart of the driver physical examination device and the anti-cheating method in some embodiments of the present application. According to the embodiment of the present application, the identification cheating judgment processing according to the target identification data includes:

[0100] S31, the target identification data includes maximum identification time data and target identification error rate data;

[0101] S32, the standard identification time data is obtained, and compared with the maximum identification time data to obtain identification time deviation data;

[0102] S33, the target identification error rate mean value data is obtained, and compared with the target identification error rate data to obtain target identification error rate deviation data;

[0103] S34, obtain a preset visual target identification deviation threshold set, including an identification time deviation threshold and an identification error rate deviation threshold;

[0104] S35, perform threshold comparison according to the identification time deviation data and the visual target identification error rate deviation data and the two threshold values corresponding to the preset visual target identification deviation threshold set;

[0105] S36, if the results of the two threshold comparisons are not all less than the corresponding threshold values of the preset visual target identification deviation threshold set, the visual target identification exists cheating.

[0106] It should be noted that a standard identification time is set for each visual target, which is usually between 3-5 seconds. If the time spent by the driver exceeds this limit, the system will consider this identification as suspicious. For example, for common E or C visual targets, if the time from the appearance of the visual target to the reaction of the driver exceeds 5 seconds, there may be a risk of cheating. In addition, the accuracy of the driver's identification of the visual target is compared with the expected accuracy of the normal vision population. If the error rate of the driver in identifying a certain size or type of visual target is significantly higher than the normal level (for example, the error rate of the normal vision population in identifying a certain row of visual targets is less than 10%, while the error rate of the driver is higher than 30%), or there are abnormal errors in identifying simple visual targets (such as frequent errors in identifying larger visual targets), this may be a sign of cheating. For this, the maximum identification time data and the visual target identification error rate data of the target driver during the vision test are obtained and compared with the standard identification time data and the average visual target identification error rate data, respectively, to obtain the corresponding identification time deviation data and the visual target identification error rate deviation data. The average visual target identification error rate data refers to the average value of the visual target identification error rate of the normal vision population. Then, according to the threshold comparison of the above data and the preset visual target identification deviation threshold set, if any of the data is greater than or equal to the threshold value, it is determined that there is a cheating situation.

[0107] Please refer to Figure 4 , Figure 4 is a flowchart of the driver examination equipment and the anti-cheating method in some embodiments of the present application for performing eye movement cheating judgment processing. According to the embodiment of the present application, the processing according to the eye movement data, obtaining an eye movement abnormality index, and performing eye movement cheating judgment processing, includes:

[0108] S41, the eye movement data includes blink frequency data, left and right eye rotation angle data, and up and down eye rotation angle data;

[0109] S42, obtain blink frequency standard data, and perform comparison processing combined with the blink frequency data to obtain blink frequency deviation data;

[0110] S43, acquire the left and right rotation angle standard data of eyeball and the up and down rotation angle standard data of eyeball, and process the left and right rotation angle data of eyeball and the up and down rotation angle data of eyeball respectively by comparison, to obtain the left and right rotation angle deviation data of eyeball and the up and down rotation angle deviation data of eyeball;

[0111] S44, perform weighted processing according to the blinking frequency deviation data, the left and right rotation angle deviation data of eyeball and the up and down rotation angle deviation data of eyeball, to obtain an eye movement abnormality index;

[0112] S45, compare the eye movement abnormality index with a preset eye movement abnormality threshold value, to obtain a second threshold comparison result;

[0113] S46, judge whether the eye movement of the target driver is abnormal according to the second threshold comparison result;

[0114] S47, if the second threshold comparison result is greater than a preset threshold value, the eye movement of the target driver is abnormal, and it is determined that the eye movement is cheated.

[0115] It should be noted that during the normal vision detection process, the blinking frequency is usually between 10-20 times per minute, and if the blinking frequency is lower than 5 times per minute or higher than 30 times per minute during the display of the key target, there may be a risk of cheating. In addition, when observing the target, the rotation angle of the eyeball is mainly concentrated in the direction and range of the target. Generally, the left and right rotation angle of the eyeball does not exceed ± 30°, and the up and down rotation angle does not exceed ± 20°. If the rotation angle of the eyeball exceeds this range, it will be considered as suspicious eye movement. Therefore, according to the blinking frequency deviation data, the left and right rotation angle deviation data of eyeball and the up and down rotation angle deviation data of eyeball, the eye movement abnormality index is obtained by weighted processing, and then compared with the preset eye movement abnormality threshold value. According to the comparison result, it is judged whether there is cheating. For example, the preset eye movement abnormality threshold value is 2.0, and when the obtained eye movement abnormality index is 2.5, it is greater than the preset threshold value, that is, it is determined that the eye movement is cheated during the physical examination.

[0116] According to the embodiment of the application, the processing according to the vision data to obtain a vision comparison deviation coefficient and the vision data cheating judgment processing include:

[0117] According to the vision detection result of the target driver, the current vision data is extracted;

[0118] Acquire the historical vision detection data of the target driver;

[0119] According to the comparison processing of the current vision data and the historical vision detection data, a vision comparison deviation coefficient is obtained;

[0120] According to the vision comparison deviation coefficient and a preset vision comparison deviation threshold, a third threshold comparison result is obtained;

[0121] According to the third threshold comparison result, it is determined whether the eye movement of the target driver is abnormal;

[0122] If the third threshold comparison result is greater than a preset threshold, the sixteen data of the target driver is abnormal, and it is determined that the vision data is cheated.

[0123] It should be noted that the vision detection result this time is compared with the vision detection record of the driver in the past. If the vision fluctuates greatly in a short time (such as the interval between two physical examinations is less than one year), and the fluctuation amplitude exceeds 0.3 (for example, in the decimal vision record method), and there is no reasonable vision correction surgery or other medical intervention proof, it will be determined as suspicious. For example, the last time the vision is 4.8, and this time it suddenly changes to 5.1, which needs to be further checked. Therefore, according to the vision data this time combined with the historical vision detection data, a vision comparison deviation coefficient is obtained, wherein the historical vision detection data refers to the vision result data corresponding to the nearest vision detection interval from the current vision detection, and there is no vision correction surgery or other medical intervention during the two detections.

[0124] According to the embodiment of the present application, the corresponding physical examination report is generated and uploaded to the background, including:

[0125] According to the vision detection result, a physical examination report is generated;

[0126] If the judgment results of the position cheating judgment, the identification cheating judgment, the eye movement cheating judgment, and the vision data judgment are all not cheating, the physical examination report is a normal report;

[0127] If any of the judgment results of the position cheating judgment, the identification cheating judgment, the eye movement cheating judgment, and the vision data judgment is cheating, the physical examination report is marked as an abnormal report, which needs to be further audited;

[0128] The physical examination report is uploaded to the background.

[0129] It should be noted that after the whole complete vision detection is finished, the corresponding physical examination report is automatically generated, and the report is divided into a normal report and an abnormal report according to the previous four cheating judgment results. If one or more of the previous four cheating judgment results is cheating, it is an abnormal report. The abnormal report is specially marked, and is uploaded to the background for next step auditing.

[0130] In a second aspect, the present application also discloses a driver physical examination device and anti-cheating system, comprising a memory and a processor, the memory comprising a driver physical examination device and anti-cheating method program, the driver physical examination device and anti-cheating method program being executed by the processor to implement the following steps:

[0131] Collecting face recognition information of a target driver through a preset physical examination device recognition system and performing identity verification on the target driver;

[0132] If the identity verification of the target driver is successful, performing vision detection on the target driver according to the preset physical examination device, and acquiring head position data, visual target recognition data, vision data and eye movement data of the target driver in real time;

[0133] Processing the head position data to obtain head position deviation data and performing position cheating judgment processing;

[0134] Processing the visual target recognition data to obtain visual target recognition data and performing recognition cheating judgment processing;

[0135] Processing the eye movement data to obtain an eye movement abnormality index and performing eye movement cheating judgment processing;

[0136] Processing the vision data to obtain a vision comparison deviation coefficient and performing vision data cheating judgment processing;

[0137] Correspondingly generating a physical examination report and uploading it to a background.

[0138] It should be noted that in the process of using the driver self-service physical examination device, the user often cheats in the vision detection step, and the existing vision physical examination method cannot effectively identify and prevent these cheating behaviors, therefore, a new method is needed to effectively and accurately prevent driver vision physical examination cheating. In the present embodiment, the face recognition information of a target driver through a preset physical examination device recognition system is collected, and identity verification is performed. If the identity verification is successful, vision detection is performed on the target driver according to the preset physical examination device, and data including head position data, visual target recognition data, vision data and eye movement data are collected. The head position data is processed to obtain head position deviation data, and position cheating judgment processing is performed. The visual target recognition data is processed to obtain visual target recognition data, and recognition cheating judgment processing is performed. The eye movement data is processed to obtain an eye movement abnormality index, and eye movement cheating judgment processing is performed. The vision data is processed to obtain a vision comparison deviation coefficient, and vision data cheating judgment processing is performed. Correspondingly, a physical examination report is generated and uploaded to a background, thereby realizing the driver physical examination device and anti-cheating technology.

[0139] According to the embodiment of the present application, the processing according to the head position data, obtaining head position deviation data, and performing position cheating judgment processing, comprises:

[0140] The head position data comprises head horizontal angle data, head vertical angle data, head front-back displacement data, and head left-right displacement data;

[0141] The head standard position data comprises head horizontal standard angle data, head vertical standard angle data, head front-back standard displacement data, and head left-right standard displacement data;

[0142] According to the statistical processing of the head position data in combination with the head standard position data, corresponding head position deviation data is obtained, comprising head horizontal angle deviation data, head vertical angle deviation data, head front-back displacement deviation data, and head left-right displacement deviation data;

[0143] According to the head horizontal angle deviation data, head vertical angle deviation data, head front-back displacement deviation data, and head left-right displacement deviation data, the processing is performed through a preset head deviation identification model to obtain head position deviation data;

[0144] According to the comparison of the head position deviation data with a preset head position deviation threshold, a first threshold comparison result is obtained;

[0145] According to the first threshold comparison result, it is judged whether the head position of the target driver has a deviation exceeding a standard;

[0146] If there is a deviation exceeding a standard, it is determined as position cheating.

[0147] It should be noted that during the driver physical examination, the allowable angle deviation range of the head in the horizontal and vertical directions needs to be specified. For example, the allowable deviation angle in the horizontal direction (turning head left and right) is generally ±5, and the allowable deviation angle in the vertical direction (looking up and down) is also ±5. If it exceeds this range, it may be judged as cheating, and the displacement of the head in front and back and left and right directions is also limited. During normal detection, the distance between the head and the visual detection equipment should be kept relatively stable, and the front and back displacement is generally not more than ±3 cm, and the left and right displacement is not more than ±2 cm. If it exceeds this displacement range, the anti-cheating mechanism will be triggered. Therefore, the head position data of the driver, including the head horizontal angle, the head vertical angle, the head front and back displacement, and the head left and right displacement data, are obtained, and then compared with the corresponding standard values to obtain the corresponding head position deviation data, including the head horizontal angle deviation data, the head vertical angle deviation data, the head front and back displacement deviation data, and the head left and right displacement deviation data. Finally, the head position deviation data is processed by a preset head deviation identification model to obtain the head position deviation data, wherein the head deviation identification model belongs to a neural network model, which is trained according to a large amount of historical head horizontal angle deviation data, head vertical angle deviation data, head front and back displacement deviation data, and head left and right displacement deviation data to obtain a trained head deviation identification model. Then, the head position deviation data is compared with a preset head position deviation threshold, and the comparison result is used to judge whether the head position of the target driver has a deviation exceeding the standard. If so, it is judged as position cheating. For example, the preset head position deviation threshold is 0.5, and the head position deviation data is 0.7. At this time, the deviation exceeds the standard, and the target driver has a head position cheating situation.

[0148] According to the embodiment of the application, the identification cheating judgment processing according to the target identification data comprises:

[0149] The target identification data comprises maximum identification time data and target identification error rate data;

[0150] The standard identification time data is obtained, and the maximum identification time data is compared to obtain identification time deviation data;

[0151] The target identification error rate mean value data is obtained, and the target identification error rate data is compared to obtain target identification error rate deviation data;

[0152] A preset target identification deviation limit threshold set is obtained, including identification time deviation limit threshold and identification error rate deviation limit threshold;

[0153] The identification time deviation data and the target identification error rate deviation data are compared with the two threshold values corresponding to the preset target identification deviation limit threshold set.

[0154] If both threshold comparison results are not less than the corresponding threshold of the preset visual target recognition deviation limit threshold set, the visual target recognition is determined as cheating.

[0155] It should be noted that the standard recognition time is set for each visual target, which is usually between 3-5 seconds. If the time spent by the driver exceeds this limit, the system will consider this recognition as suspicious. For example, for common E or C visual target, if the time from the appearance of the visual target to the reaction of the driver exceeds 5 seconds, there may be a risk of cheating. In addition, the accuracy of the driver's recognition of the visual target is compared with the expected accuracy of the normal vision population. If the error rate of the driver in recognizing a certain size or type of visual target is significantly higher than the normal level (for example, the error rate of the normal vision population in recognizing a certain row of visual target is less than 10%, while the error rate of the driver is higher than 30%), or there is an abnormal error in recognizing simple visual target (such as frequent errors in recognizing larger visual target), it may be a sign of cheating. For this purpose, the maximum recognition time data and the visual target recognition error rate data of the target driver during the visual examination are obtained, and are compared with the standard recognition time data and the average visual target recognition error rate data, respectively, to obtain the corresponding recognition time deviation data and the visual target recognition error rate deviation data. The average visual target recognition error rate data refers to the average value of the visual target recognition error rate of the normal vision population. Then, according to the threshold comparison of the above data with the preset visual target recognition deviation limit threshold set, if any of the data is greater than or equal to the threshold, it is determined that there is a cheating situation.

[0156] According to the embodiment of the present application, the processing according to the eye movement data, obtaining an eye movement abnormality index, and performing eye movement cheating judgment processing, comprises:

[0157] The eye movement data includes blink frequency data, left and right eye rotation angle data, and up and down eye rotation angle data;

[0158] Blink frequency standard data is obtained, and the blink frequency data is compared to obtain blink frequency deviation data;

[0159] Eye rotation angle standard data and up and down eye rotation angle standard data are obtained, and the left and right eye rotation angle data and the up and down eye rotation angle data are compared respectively to obtain corresponding left and right eye rotation angle deviation data and up and down eye rotation angle deviation data;

[0160] The blink frequency deviation data, the left and right eye rotation angle deviation data, and the up and down eye rotation angle deviation data are weighted to obtain an eye movement abnormality index;

[0161] According to the eye movement anomaly index and a preset eye movement anomaly threshold, a second threshold comparison result is obtained.

[0162] According to the second threshold comparison result, whether the eye movement of the target driver is abnormal is determined.

[0163] If the second threshold comparison result is greater than a preset threshold, the eye movement of the target driver is abnormal, and it is determined that the eye movement is cheated.

[0164] It should be noted that during the normal vision detection process, the blinking frequency is usually between 10-20 times per minute. If the blinking frequency is lower than 5 times per minute or higher than 30 times per minute during the display of the key target, there may be a risk of cheating. In addition, when observing the target, the eye rotation angle is mainly concentrated in the direction and range of the target. Generally, the left and right rotation angles of the eye are not more than ±30°, and the up and down rotation angles of the eye are not more than ±20°. If the eye rotation angle exceeds this range, it will be considered as suspicious eye movement. Therefore, according to the blinking frequency deviation data, the left and right rotation angle deviation data of the eye, and the up and down rotation angle deviation data of the eye, the eye movement anomaly index is obtained by weighted processing, and then compared with the preset eye movement anomaly threshold. According to the comparison result, whether there is cheating is determined. For example, the preset eye movement anomaly threshold is 2.0, and when the obtained eye movement anomaly index is 2.5, it is greater than the preset threshold, that is, it is determined that the eye movement is cheated during the physical examination.

[0165] According to the embodiment of the present application, the vision data is processed according to the vision data to obtain a vision comparison deviation coefficient, and the vision data cheating judgment processing is performed, which comprises:

[0166] According to the vision detection result of the target driver, the current vision data is extracted;

[0167] The historical vision detection data of the target driver is obtained;

[0168] According to the comparison processing of the current vision data and the historical vision detection data, a vision comparison deviation coefficient is obtained;

[0169] According to the vision comparison deviation coefficient and a preset vision comparison deviation threshold, a third threshold comparison result is obtained;

[0170] According to the third threshold comparison result, whether the eye movement of the target driver is abnormal is determined.

[0171] If the third threshold comparison result is greater than a preset threshold, the sixteen data of the target driver is abnormal, and it is determined that the vision data is cheated.

[0172] It should be noted that the current visual acuity test result is compared with the driver's previous visual acuity test record. If the visual acuity fluctuates greatly in a short period of time (for example, the interval between two physical examinations is less than one year), and the fluctuation amplitude exceeds 0.3 (for example, in the decimal visual acuity record method), and there is no reasonable visual correction surgery or other medical intervention proof, it will be judged as suspicious. For example, the last visual acuity is 4.8, and the current visual acuity suddenly changes to 5.1, which needs to be further checked. Therefore, according to the current visual acuity data combined with the historical visual acuity test data, the visual acuity comparison deviation coefficient is obtained, wherein the historical visual acuity test data refers to the visual acuity result data corresponding to the nearest visual acuity test between the current visual acuity test, and there is no visual correction surgery or other medical intervention during the two tests.

[0173] According to the embodiment of the present application, the corresponding physical examination report is generated and uploaded to the background, comprising:

[0174] According to the visual acuity test result, a physical examination report is generated;

[0175] If the judgment results of the position cheating judgment, the identification cheating judgment, the eye movement cheating judgment and the visual acuity data judgment are all not cheating, the physical examination report is a normal report;

[0176] If the judgment results of the position cheating judgment, the identification cheating judgment, the eye movement cheating judgment and the visual acuity data judgment are all not cheating, the physical examination report is a normal report;

[0177] The physical examination report is uploaded to the background.

[0178] It should be noted that after the whole complete visual acuity test is finished, the corresponding physical examination report is automatically generated, and the report is divided into normal report and abnormal report according to the previous four cheating judgment results. If one or more of the previous four cheating judgment results is cheating, it is an abnormal report. The abnormal report is specially marked, and is uploaded to the background for next step of auditing.

[0179] The third aspect of the present application provides a readable storage medium, wherein the readable storage medium stores the driver physical examination equipment and the anti-cheating method program. When the driver physical examination equipment and the anti-cheating method program are executed by the processor, the steps of the driver physical examination equipment and the anti-cheating method of any one of the above are realized.

[0180] The application discloses a driver physical examination device and an anti-cheating method and system and a medium.

[0181] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other manners. The above described device embodiments are merely schematic, for example, the division of the units is only a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling, or direct coupling or communication connection between the components can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or in other forms.

[0182] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units; they can be located in one place or distributed on multiple network units; and part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0183] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; and the integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional unit.

[0184] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by relevant hardware of program instructions, and the foregoing program can be stored in a readable storage medium, and the program executes the steps of the above-mentioned method embodiments when executed; and the foregoing storage medium includes various media capable of storing program codes, such as a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disc or an optical disc.

[0185] Alternatively, the integrated unit of the present application can also be stored in a readable storage medium if it is realized in the form of a software function module and sold or used as an independent product. Based on such understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product in essence or in the form of a part of the prior art that makes a contribution, and the software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present application. The foregoing storage medium includes various media capable of storing program codes, such as a mobile storage device, a ROM, a RAM, a magnetic disc or an optical disc.

Claims

1. A method for preventing cheating in driver's medical examination equipment, characterized in that, Includes the following steps: Collect facial recognition information of the target driver through a preset medical examination equipment recognition system, and verify the identity of the target driver; If the target driver's identity is successfully verified, a vision test is performed on the target driver according to the preset physical examination device, and the target driver's head position data, visual target recognition data, vision data and eye movement data are acquired in real time. The head position data is processed to obtain head position deviation data, and position cheating detection processing is performed. The cheating detection process is performed based on the visual target recognition data. The eye movement data is processed to obtain an abnormal eye movement index, and eye movement cheating is judged and processed. The visual acuity data is processed to obtain a visual acuity comparison deviation coefficient, and visual acuity data cheating judgment processing is performed. The corresponding medical examination report is generated and uploaded to the backend; The step of processing the eye movement data to obtain an abnormal eye movement index and performing eye movement cheating detection includes: The eye movement data includes blink frequency data, left-right eye rotation angle data, and up-down eye rotation angle data. Obtain standard blink frequency data, and compare it with the blink frequency data to obtain blink frequency deviation data; Obtain standard data for the left and right rotation angles of the eyeball and the up and down rotation angles of the eyeball. Compare and process these data to obtain the corresponding deviation data for the left and right rotation angles of the eyeball and the deviation data for the up and down rotation angles of the eyeball. The blink frequency deviation data, the left-right eye rotation angle deviation data, and the up-down eye rotation angle deviation data are weighted and processed to obtain the abnormal eye movement index. The second threshold comparison result is obtained by comparing the abnormal eye movement index with the preset abnormal eye movement threshold. Based on the comparison result of the second threshold, determine whether there is any abnormality in the target driver's eye movements; If the comparison result of the second threshold is greater than the preset threshold, then the target driver's eye movements are abnormal and are determined to be cheating by eye movements. The step of processing the visual acuity data to obtain a visual acuity comparison deviation coefficient and performing visual acuity data cheating detection processing includes: Extract the vision data based on the vision test results of the target driver; Obtain the target driver's historical vision test data; The visual acuity data from this test is compared with the historical visual acuity test data to obtain the visual acuity comparison deviation coefficient. The third threshold comparison result is obtained by comparing the visual acuity comparison deviation coefficient with the preset visual acuity comparison deviation threshold. Based on the comparison results of the third threshold, it is determined whether there is any abnormality in the target driver's eye movements; If the comparison result of the third threshold is greater than the preset threshold, then the vision data of the target driver is abnormal and is determined to be vision data cheating.

2. The anti-cheating method for the driver's physical examination equipment according to claim 1, characterized in that, The step of processing the head position data to obtain head position deviation data and performing position cheating detection processing includes: The head position data includes head horizontal angle data, head vertical angle data, head front-to-back displacement data, and head left-to-right displacement data. Obtain standard head position data, including standard head horizontal angle data, standard head vertical angle data, standard head front-back displacement data, and standard head left-right displacement data; Based on the head position data and the standard head position data, statistical processing is performed to obtain the corresponding head position deviation data, including head horizontal angle deviation data, head vertical angle deviation data, head front-back displacement deviation data, and head left-right displacement deviation data. Based on the head horizontal angle deviation data, head vertical angle deviation data, head front-to-back displacement deviation data, and head left-to-right displacement deviation data, the head position deviation data is obtained by processing the head deviation recognition model through a preset head deviation recognition model. The head position deviation data is compared with a preset head position deviation threshold to obtain a first threshold comparison result; Based on the comparison results of the first threshold, it is determined whether the head position of the target driver deviates by an excessive amount; If the deviation exceeds the limit, it will be judged as position cheating.

3. The anti-cheating method for the driver's physical examination equipment according to claim 2, characterized in that, The process of identifying cheating based on the visual target recognition data includes: The target recognition data includes maximum recognition time data and target recognition error rate data; Obtain standard recognition time data and compare it with the maximum recognition time data to obtain recognition time deviation data; Obtain the mean target recognition error rate data and compare it with the target recognition error rate data to obtain target recognition error rate deviation data; Obtain a preset set of target recognition deviation limit thresholds, including recognition time deviation limit thresholds and recognition error rate deviation limit thresholds; The thresholds are compared based on the recognition time deviation data and the target recognition error rate deviation data with the two thresholds corresponding to the preset target recognition deviation limit threshold set; If the comparison results of the two thresholds are not both less than the corresponding threshold of the preset target recognition deviation limit threshold set, then there is cheating in target recognition.

4. The anti-cheating method for the driver's physical examination equipment according to claim 3, characterized in that, The corresponding generation of physical examination reports and uploading to the backend includes: A medical examination report will be generated based on the vision test results. If the results of the location cheating judgment, identification cheating judgment, eye movement cheating judgment, and vision data judgment are all negative, then the physical examination report is a normal report. If any of the judgment results of the location cheating judgment, identification cheating judgment, eye movement cheating judgment, and vision data judgment are found to be cheating, the physical examination report will be marked as an abnormal report and will require further review and processing. Upload the medical examination report to the backend.

5. A cheating prevention system for driver's medical examination equipment, characterized in that, The system includes a memory and a processor. The memory contains a program for an anti-cheating method for a driver's medical examination device. When the program for the anti-cheating method for the driver's medical examination device is executed by the processor, it performs the following steps: Collect facial recognition information of the target driver through a preset medical examination equipment recognition system, and verify the identity of the target driver; If the target driver's identity is successfully verified, a vision test is performed on the target driver according to the preset physical examination device, and the target driver's head position data, visual target recognition data, vision data and eye movement data are acquired in real time. The head position data is processed to obtain head position deviation data, and position cheating detection processing is performed. The cheating detection process is performed based on the visual target recognition data. The eye movement data is processed to obtain an abnormal eye movement index, and eye movement cheating is judged and processed. The visual acuity data is processed to obtain a visual acuity comparison deviation coefficient, and visual acuity data cheating judgment processing is performed. The corresponding medical examination report is generated and uploaded to the backend; The step of processing the eye movement data to obtain an abnormal eye movement index and performing eye movement cheating detection includes: The eye movement data includes blink frequency data, left-right eye rotation angle data, and up-down eye rotation angle data. Obtain standard blink frequency data, and compare it with the blink frequency data to obtain blink frequency deviation data; Obtain standard data for the left and right rotation angles of the eyeball and the up and down rotation angles of the eyeball. Compare and process these data to obtain the corresponding deviation data for the left and right rotation angles of the eyeball and the deviation data for the up and down rotation angles of the eyeball. The blink frequency deviation data, the left-right eye rotation angle deviation data, and the up-down eye rotation angle deviation data are weighted and processed to obtain the abnormal eye movement index. The second threshold comparison result is obtained by comparing the abnormal eye movement index with the preset abnormal eye movement threshold. Based on the comparison result of the second threshold, determine whether there is any abnormality in the target driver's eye movements; If the comparison result of the second threshold is greater than the preset threshold, then the target driver's eye movements are abnormal and are determined to be cheating by eye movements. The step of processing the visual acuity data to obtain a visual acuity comparison deviation coefficient and performing visual acuity data cheating detection processing includes: Extract the vision data based on the vision test results of the target driver; Obtain the target driver's historical vision test data; The visual acuity data from this test is compared with the historical visual acuity test data to obtain the visual acuity comparison deviation coefficient. The third threshold comparison result is obtained by comparing the visual acuity comparison deviation coefficient with the preset visual acuity comparison deviation threshold. Based on the comparison results of the third threshold, it is determined whether there is any abnormality in the target driver's eye movements; If the comparison result of the third threshold is greater than the preset threshold, then the vision data of the target driver is abnormal and is determined to be vision data cheating.

6. The anti-cheating system for driver's physical examination equipment according to claim 5, characterized in that, The step of processing the head position data to obtain head position deviation data and performing position cheating detection processing includes: The head position data includes head horizontal angle data, head vertical angle data, head front-to-back displacement data, and head left-to-right displacement data. Obtain standard head position data, including standard head horizontal angle data, standard head vertical angle data, standard head front-back displacement data, and standard head left-right displacement data; Based on the head position data and the standard head position data, statistical processing is performed to obtain the corresponding head position deviation data, including head horizontal angle deviation data, head vertical angle deviation data, head front-back displacement deviation data, and head left-right displacement deviation data. Based on the head horizontal angle deviation data, head vertical angle deviation data, head front-to-back displacement deviation data, and head left-to-right displacement deviation data, the head position deviation data is obtained by processing the head deviation recognition model through a preset head deviation recognition model. The head position deviation data is compared with a preset head position deviation threshold to obtain a first threshold comparison result; Based on the comparison results of the first threshold, it is determined whether the head position of the target driver deviates by an excessive amount; If the deviation exceeds the limit, it will be judged as position cheating.

7. The anti-cheating system for driver's physical examination equipment according to claim 5, characterized in that, The process of identifying cheating based on the visual target recognition data includes: The target recognition data includes maximum recognition time data and target recognition error rate data; Obtain standard recognition time data and compare it with the maximum recognition time data to obtain recognition time deviation data; Obtain the mean target recognition error rate data and compare it with the target recognition error rate data to obtain target recognition error rate deviation data; Obtain a preset set of target recognition deviation limit thresholds, including recognition time deviation limit thresholds and recognition error rate deviation limit thresholds; The thresholds are compared based on the recognition time deviation data and the target recognition error rate deviation data with the two thresholds corresponding to the preset target recognition deviation limit threshold set; If the comparison results of the two thresholds are not both less than the corresponding threshold of the preset target recognition deviation limit threshold set, then there is cheating in target recognition.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a method program for preventing cheating in a driver's medical examination device. When the method program is executed by a processor, it implements the steps of the method for preventing cheating in a driver's medical examination device as described in any one of claims 1 to 4.

Images