Recruitment system based on Internet of Things

Abstract

The invention discloses a recruitment system based on the Internet of Things, and relates to the technical field of recruitment of the Internet of Things, and the system comprises an online recruitment monitoring module, an anti-cheating analysis module, a cheating early warning processing module and a local database. The situation that the line of sight of an enterprise recruiter is not on the body of an applicant is considered, the accuracy of cheating behavior judgment is improved by analyzing the comprehensive cheating early warning coefficient of the applicant, and the situation that sighting often has a certain time length and sometimes the applicant shifts the line of sight towards other directions due to tension is considered, so that the accuracy of cheating behavior judgment is improved. According to the method and the system, the recruitment efficiency is improved, but the duration time is often not too long, the cheating behaviors of the applicants are analyzed in detail, and the video images possibly having the cheating behaviors are screened, so that the enterprise recruiters can conveniently query the video images, and therefore, the recruitment efficiency is improved, and the workload of the enterprise recruiters is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things recruitment, and in particular to a recruitment system based on the Internet of Things. Background Art

[0002] Online video interview is an important interview method in current corporate recruitment. Corporate recruiters often ask candidates online questions and take exams. However, due to the lack of offline supervision, corporate interviewers often need to review a large number of video images during the interview to prevent cheating, and review whether the candidates have cheated, which leads to reduced recruitment efficiency. Therefore, it is necessary to reduce the workload of corporate interviewers by studying an anti-cheating analysis system during recruitment.

[0003] For example, the prior art, such as the invention patent application with the publication number: CN114943517A, discloses an electronic recruitment matching method, system and storage medium based on the Internet of Things, and the method includes: using a preset model of pre-set valid resume information to match and screen the preliminary resume information; parsing the valid resume information, determining the sorting of the valid resume information according to the number of characters in each field; and pushing all valid resumes in order according to the sorting results. Another example of the prior art, such as the invention patent application with the publication number: CN115983812A, discloses a recruitment system based on the Internet of Things, and the method includes: improving the applicant's attention to flyers, effectively reducing the random discarding of flyers, facilitating enterprises to recruit employees suitable for positions, and effectively improving the push effect of resume flyers. After the air bag strip is deflated, the net bag is restricted to separate the sticky rubber pad to prevent the sticky rubber pad from affecting the storage of the resume flyer, and the subsequent lifting cover presses the resume flyer that has not been taken away back to the equipment box, which is convenient for the recycling and reuse of the resume flyer.

[0004] It can be seen from the above scheme that the current recruitment system based on the Internet of Things lacks certain attention to judging whether the applicant has cheated by analyzing the direction of the eyes and the distance of pupil movement. When cheating, the applicant mostly uses communication devices such as mobile phones and cheats by sneaking glances. In the entire interview process, it is easy to sneak glances at the communication device many times, so that the applicant often sneaks glances in a specific direction and the pupil moves a large distance. If this is not analyzed, the accuracy of the applicant's cheating judgment is reduced. At the same time, there is a lack of attention to the comprehensive analysis of the eyes of the company's recruitment officer and the eyes of the applicant. During the interview process, the company's recruitment officer will inevitably not look at the applicant. The applicant often chooses to cheat by sneaking glances at this time and gets good results, which makes the company unable to accurately recruit high-quality employees, reduces the quality of corporate recruitment, and increases the workload of the company's recruitment officer's subsequent review. Summary of the invention

[0005] The purpose of the present invention is to provide a recruitment system based on the Internet of Things, which solves the problems existing in the background technology.

[0006] In order to solve the above technical problems, the present invention adopts the following technical solutions: The present invention provides a recruitment system based on the Internet of Things, including: an online recruitment monitoring module, which is used to obtain video images of the company's recruitment officers at each examination time point and video images of applicants at each examination time point during the interview examination period when the company conducts online video recruitment.

[0007] The anti-cheating analysis module is used to screen the candidate's target time points, capture the image coordinates of the candidate's eye contour feature points and pupil feature points at each target time point, analyze the candidate's pupil offset direction and pupil offset distance at each target time point, and evaluate the candidate's eye abnormality coefficient at each target time point.

[0008] The cheating warning processing module is used to determine whether the applicant is suspected of cheating by eye contact. If so, it analyzes the applicant's various estimated cheating time points, extracts the applicant's video images at each estimated cheating time point, and sends them to the company's recruitment officer.

[0009] The beneficial effects of the present invention are as follows: (1) The online recruitment monitoring module of the present invention obtains video images of enterprise recruiters and applicants, which facilitates subsequent analysis.

[0010] (2) The anti-cheating analysis module of the present invention determines whether the applicant's line of sight frequently deviates in a certain direction by analyzing the pupil deviation direction and pupil deviation distance of the applicant at each target time point. In addition, the anti-cheating analysis module considers the situation that the company's recruiter's line of sight is not on the applicant, and comprehensively analyzes the above situations, thereby improving the accuracy of the judgment on whether the applicant has cheated by peeking.

[0011] (3) The cheating warning processing module of the present invention improves the accuracy of judging cheating behavior by analyzing the comprehensive cheating warning coefficient of the applicant. Considering that sneak glances often last for a certain period of time, and sometimes the applicant's eyes shift to other directions just because of nervousness, but the duration is usually not too long, the eye warning coefficient is analyzed to conduct a more detailed analysis of the applicant's cheating behavior, and screen video images that may show cheating behavior, which is convenient for corporate recruiters to query, thereby improving recruitment efficiency and reducing the workload of corporate recruiters. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] 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.

[0013] Figure 1 It is a schematic diagram of the system module of the present invention. DETAILED DESCRIPTION

[0014] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0015] Reference Figure 1 As shown, the present invention provides a recruitment system based on the Internet of Things, including: an online recruitment monitoring module, an anti-cheating analysis module, a cheating early warning processing module and a local database.

[0016] It should be noted that the online recruitment monitoring module is connected to the anti-cheating analysis module, the anti-cheating analysis module is connected to the cheating early warning processing module, and the local database is connected to the anti-cheating analysis module and the cheating early warning processing module.

[0017] It should also be mentioned that the local database is used to store the distance values ​​between each pupil feature point and each eye contour feature point of the applicant in the normal state, the adjustment parameter values ​​at normal time points and the adjustment parameter values ​​at alert time points, each offset direction range, the comprehensive cheating warning coefficient threshold, the preset analysis time, and the eye warning coefficient threshold corresponding to the comprehensive cheating warning coefficient interval.

[0018] The online recruitment monitoring module is used to obtain video images of the company's recruitment officers at various examination time points and video images of applicants at various examination time points during the interview examination period when the company conducts online video recruitment.

[0019] In a specific embodiment, the video images of the company recruiter at each examination time point and the video images of the applicant at each examination time point during the interview examination period are obtained by a specific method: the video images of the corresponding company recruiter at each examination time point and the video images of the applicant at each examination time point are obtained through the video recording device of the company recruiter and the video recording device of the applicant.

[0020] It should be noted that before the video image is acquired, the enterprise recruiter and the applicant are reminded to authorize, and the video image is acquired after obtaining the authorization of the enterprise recruiter and the applicant.

[0021] The online recruitment monitoring module of the present invention obtains video images of enterprise recruiters and applicants to facilitate subsequent analysis.

[0022] The anti-cheating analysis module is used to screen the candidate's target time points, capture the image coordinates of the candidate's eye contour feature points and pupil feature points at the target time points, analyze the candidate's pupil offset direction and pupil offset distance at the target time points, and evaluate the candidate's eye abnormality coefficient at the target time points.

[0023] In a specific embodiment, the target time points for screening the candidates are screened by a specific screening method: by using existing image open and closed eye recognition technology and video images of the candidates at various test time points, the target time points for the candidates can be screened.

[0024] In a specific embodiment of the present invention, the specific method for capturing the image coordinates of each eye contour feature point and the image coordinates of each pupil feature point of the candidate at each target time point is: based on the video image of the candidate at each test time point, the video image of the candidate at each target time point is extracted.

[0025] An xy coordinate system is established with the lower left corner of the video image of the applicant at each target time point as the coordinate origin, the lower left corner to the lower right corner as the positive direction of the x-axis, and the lower left corner to the upper left corner as the positive direction of the y-axis.

[0026] Through the eye contour image capture technology, the eye contour feature points and their positions of the applicant in the video image at each target time point are obtained, and according to the positions of the eye contour feature points of the applicant in the video image at each target time point, they are mapped one by one to the xy coordinate system, so as to obtain the image coordinates of the eye contour feature points of the applicant at each target time point.

[0027] By using pupil contour image capture technology, the image coordinates of each pupil feature point of the applicant at each target time point are obtained in the same way.

[0028] In a specific embodiment of the present invention, the pupil displacement direction and pupil displacement distance of the applicant at each target time point are analyzed by: according to the image coordinates of each pupil feature point and the image coordinates of each eye contour feature point of the applicant at each target time point, the distance value between each pupil feature point and each eye contour feature point of the applicant at each target time point is calculated. , where n represents the number of each target time point, , m is a positive integer greater than 2, i represents the number of each pupil feature point, , j is a positive integer greater than 2, p represents the number of each eye contour feature point, , q is a positive integer greater than 2.

[0029] Calculate the distance reduction change ratio between each pupil feature point and each eye contour feature point of the candidate at each target time point, extract the pupil feature points and eye contour feature points with the largest distance reduction change ratio at each target time point, and mark them as target pupil feature points and target eye contour feature points, thereby obtaining the target pupil feature points and target eye contour feature points of the candidate at each target time point, and use the direction in which the target pupil feature point of the candidate at each target time point points to the target eye contour feature point as the pupil deviation direction, thereby obtaining the pupil deviation direction of the candidate at each target time point.

[0030] The distance value between the target pupil feature point and the target eye contour feature point of the candidate at each target time point is extracted, and the pupil offset distance of the candidate at each target time point is calculated based on the distance.

[0031] In a specific embodiment, the calculation method of calculating the change ratio of the distance between each pupil feature point and each eye contour feature point of the applicant at each target time point is as follows: obtaining the distance value between each pupil feature point and each eye contour feature point of the applicant in the normal state from the local database , calculate the change ratio of the distance between each pupil feature point and each eye contour feature point at each target time point .

[0032] It should be noted that the distance values ​​between each pupil feature point and each eye contour feature point of the applicant when in a normal state are obtained by obtaining a video image of the applicant in a normal state before the applicant takes an interview test, and by calculating the distance values ​​between each pupil feature point and each eye contour feature point of the applicant at each target time point, the distance values ​​between each pupil feature point and each eye contour feature point of the applicant when in a normal state are obtained.

[0033] In a specific embodiment, the pupil offset distance of the candidate at each target time point is calculated by: according to the distance value between each pupil feature point and each eye contour feature point of the candidate in the normal state, the distance value between the target pupil feature point and the target eye contour feature point of the candidate in the normal state is extracted. , and based on the distance between the target pupil feature point and the target eye contour feature point of the applicant at each target time point , calculate the pupil displacement distance of the applicant at each target time point .

[0034] In a specific embodiment of the present invention, the distance between each pupil feature point and each eye contour feature point of the applicant at each target time point is calculated by: And the image coordinates of each eye contour feature point , calculate the distance between each pupil feature point and each eye contour feature point of the applicant at each target time point .

[0035] In a specific embodiment of the present invention, the specific evaluation method for evaluating the abnormal eye coefficient of the applicant at each target time point is: based on the video images of the company's recruitment officer at each examination time point, the applicant's normal time points and vigilance time points are screened.

[0036] According to the pupil deviation direction of the applicant at each target time point, the deviation distance hazard coefficient of the applicant at each target time point is analyzed, and the deviation distance hazard coefficient of the applicant at each normal time point is extracted. and the offset distance hazard coefficient at each alert time point , where t represents the number of each normal time point, , w is a positive integer greater than 2, u represents the number of each alert time point, , v is a positive integer greater than 2.

[0037] Obtain the normal time point adjustment parameter value A and the vigilance time point adjustment parameter value B from the local database, and calculate the applicant's eye abnormality coefficient at each normal time point , and calculate the applicant's eye abnormality coefficient at each alert time point .

[0038] Summarize the applicants’ eye gaze abnormality coefficients at each target time point.

[0039] In a specific embodiment of the present invention, the normal time points and alert time points of the applicants are screened by a specific screening method: based on the video images of the corporate recruiter at each examination time point, the effective capture time points and the inability to capture time points of the pupils of the corporate recruiter are screened.

[0040] In a specific embodiment, the method for screening the effective capture time points and the uncapture time points of the pupils of the corporate recruiters is as follows: based on the existing pupil contour image capture technology, the effective capture time points and the uncapture time points of the pupils of the corporate recruiters can be screened.

[0041] If a target time point of an applicant is consistent with a pupil effective capture time point of the corporate recruiter, the target time point is marked as a normal time point, thereby screening the applicant's normal time points.

[0042] If a target time point of an applicant coincides with a time point that the pupil of the corporate recruiter cannot capture, the target time point is marked as a vigilance time point, thereby screening the applicant's various vigilance time points.

[0043] In a specific embodiment of the present invention, the specific analysis method for analyzing the offset distance hazard coefficient of the candidate at each target time point is as follows: each offset direction range is obtained from the local database; if the pupil offset direction of the candidate at a certain target time point is included in a certain offset direction range, the offset direction range is used as the analysis offset direction range of the candidate at the target time point, thereby screening the analysis offset direction range of the candidate at each target time point, mapping the candidate's target time points in each analysis offset direction range, and counting the number of the candidate's target time points in each analysis offset direction range. , where r represents the number of each analysis offset direction range, , s is a positive integer greater than 2, and the offset frequency hazard coefficient of the candidate in each analysis offset direction range is calculated , where e represents a natural constant and s represents the number of analysis offset direction ranges.

[0044] It should be noted that each offset direction range is obtained by taking the pupil center as the origin, starting from the due north direction, and dividing the range into 22.5° angles.

[0045] If the pupil deviation direction of the candidate at a certain target time point is included in a certain analysis deviation direction range, the deviation frequency hazard coefficient of the analysis deviation direction range is used as the deviation direction hazard coefficient of the target time point, thereby obtaining the deviation direction hazard coefficient of the candidate at each target time point. .

[0046] Based on the pupil displacement distance of the applicant at each target time point , calculate the candidate's offset distance hazard coefficient at each target time point , where m is the number of target time points.

[0047] The anti-cheating analysis module of the present invention determines whether the applicant's line of sight frequently deviates in a certain direction by analyzing the pupil deviation direction and pupil deviation distance of the applicant at each target time point, and takes into account the situation that the company's recruitment officer's line of sight is not on the applicant, and comprehensively analyzes the above situations, thereby improving the accuracy of judging whether the applicant has cheated or sneaked glances.

[0048] The cheating warning processing module is used to determine whether the applicant is suspected of cheating with eyes. If so, it analyzes the applicant's various cheating estimated time points, extracts the applicant's video images at each cheating estimated time point, and sends them to the company's recruitment officer.

[0049] In a specific embodiment of the present invention, the specific method for judging whether an applicant is suspected of cheating by eye contact is as follows: analyzing the applicant's comprehensive cheating warning coefficient based on the applicant's eye contact abnormality coefficient at each target time point.

[0050] A comprehensive cheating warning coefficient threshold is obtained from a local database. If the comprehensive cheating warning coefficient of the applicant is greater than the comprehensive cheating warning coefficient threshold, the applicant is judged to be suspected of eye cheating.

[0051] In a specific embodiment of the present invention, the comprehensive cheating warning coefficient of the applicant is analyzed by a specific analysis method as follows: a preset analysis time is obtained from a local database, a target time point of the applicant is randomly selected as the time point to be analyzed, and each target time point before the time point to be analyzed of the applicant within the preset analysis time is used as each comparison time point, and at the same time, each target time point after the time point to be analyzed of the applicant within the preset analysis time is used as each comparison time point, thereby obtaining the time point to be analyzed of the applicant and its comparison time points.

[0052] It should be noted that the preset analysis time is set by enterprise personnel and can be set to 1s, 2s, 3s, etc. If the enterprise personnel are more strict with the examination, the preset analysis time can be set to a shorter value, such as 1s.

[0053] Based on the applicant's eye abnormality coefficient at each target time point , extract the applicant's eye abnormality coefficient D at the time point to be analyzed and the eye abnormality coefficient at each comparison time point , where N represents the number of each comparison time point, , M is a positive integer greater than 2, and the eye warning coefficient of the candidate at the time point to be analyzed is calculated , where M represents the number of comparison time points, and so on, the eye warning coefficient of the applicant at each target time point is obtained , calculate the comprehensive cheating warning coefficient of the applicant .

[0054] In a specific embodiment of the present invention, the specific analysis method for analyzing the estimated cheating time points of the applicants is as follows: obtaining the eye warning coefficient threshold corresponding to each comprehensive cheating warning coefficient interval from the local database, and mapping the eye warning coefficient threshold of the applicant based on the comprehensive cheating warning coefficient of the applicant.

[0055] If the eye warning coefficient of the applicant at a certain target time point is greater than the eye warning coefficient threshold, the target time point is marked as a cheating estimated time point, thereby screening the applicant's various cheating estimated time points.

[0056] It should be noted that the larger the comprehensive cheating warning coefficient, the smaller the corresponding eye warning coefficient threshold. This data is set by the staff. The larger the comprehensive cheating warning coefficient, the more likely the applicant is to cheat, and more video images need to be submitted to the company's recruitment officer for review. At this time, the eye warning coefficient threshold used for interception needs to be set smaller to obtain more video images.

[0057] The cheating warning processing module of the present invention improves the accuracy of judging cheating behavior by analyzing the comprehensive cheating warning coefficient of the applicant. Taking into account that sneak glances often last for a certain period of time, and sometimes the applicant's sight shifts to other directions due to nervousness, but the duration is often not too long, and based on this analysis of the eye warning coefficient, a more detailed analysis of the applicant's cheating behavior is performed, and video images that may show cheating behavior are screened to facilitate inquiries by corporate recruiters, thereby improving recruitment efficiency and reducing the workload of corporate recruiters.

[0058] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they shall all fall within the protection scope of the present invention.

Claims

1. A recruitment system based on the Internet of Things, characterized in that: include: The online recruitment monitoring module is used to obtain the video images of the enterprise recruitment officer at each examination time point and the video images of the applicant at each examination time point during the interview examination period when the enterprise conducts online video recruitment; The anti-cheating analysis module is used to screen the target time points of the applicants, capture the image coordinates of the eye contour feature points and pupil feature points of the applicants at the target time points, analyze the pupil displacement direction and pupil displacement distance of the applicants at the target time points, and evaluate the eye abnormality coefficient of the applicants at the target time points; The specific evaluation method for evaluating the abnormal eye gaze coefficient of the applicant at each target time point is as follows: Screen the normal time points and alert time points of applicants based on the video images of the company's recruiters at various test time points; According to the pupil deviation direction of the applicant at each target time point, the deviation distance hazard coefficient of the applicant at each target time point is analyzed, and the deviation distance hazard coefficient of the applicant at each normal time point is extracted. and the offset distance hazard coefficient at each alert time point , where t represents the number of each normal time point, , w is a positive integer greater than 2, u represents the number of each alert time point, , v is a positive integer greater than 2; Obtain the normal time point adjustment parameter value A and the vigilance time point adjustment parameter value B from the local database, and calculate the applicant's eye abnormality coefficient at each normal time point , and calculate the applicant's eye abnormality coefficient at each alert time point ; Summarize the applicants' eye gaze abnormality coefficients at each target time point; The cheating warning processing module is used to determine whether the applicant is suspected of cheating by eye contact. If so, it analyzes the applicant's various estimated cheating time points, extracts the applicant's video images at each estimated cheating time point, and sends them to the company's recruitment officer.

2. The IoT-based recruitment system according to claim 1, characterized in that: The specific method of capturing the image coordinates of each eye contour feature point and each pupil feature point of the applicant at each target time point is as follows: Extracting the video images of the applicant at each target time point based on the video images of the applicant at each test time point; Take the lower left corner of the video image of the applicant at each target time point as the coordinate origin, the lower left corner to the lower right corner as the positive direction of the x-axis, and the lower left corner to the upper left corner as the positive direction of the y-axis, and establish an xy coordinate system; By using the eye contour image capture technology, the eye contour feature points and their positions of the applicant in the video image at each target time point are obtained, and according to the positions of the eye contour feature points of the applicant in the video image at each target time point, they are mapped one by one to the xy coordinate system, thereby obtaining the image coordinates of the eye contour feature points of the applicant at each target time point; By using pupil contour image capture technology, the image coordinates of each pupil feature point of the applicant at each target time point are obtained in the same way.

3. The IoT-based recruitment system according to claim 1, characterized in that: The specific analysis method for analyzing the pupil shift direction and pupil shift distance of the applicant at each target time point is as follows: According to the image coordinates of each pupil feature point and each eye contour feature point of the applicant at each target time point, calculate the distance value between each pupil feature point and each eye contour feature point of the applicant at each target time point , where n represents the number of each target time point, , m is a positive integer greater than 2, i represents the number of each pupil feature point, , j is a positive integer greater than 2, p represents the number of each eye contour feature point, , q is a positive integer greater than 2; Calculate the distance reduction change ratio between each pupil feature point and each eye contour feature point of the candidate at each target time point, extract the pupil feature point and eye contour feature point with the largest distance reduction change ratio at each target time point of the candidate, and mark them as target pupil feature points and target eye contour feature points, thereby obtaining the target pupil feature points and target eye contour feature points of the candidate at each target time point, and use the direction in which the target pupil feature point of the candidate at each target time point points to the target eye contour feature point as the pupil deviation direction, thereby obtaining the pupil deviation direction of the candidate at each target time point; The distance value between the target pupil feature point and the target eye contour feature point of the candidate at each target time point is extracted, and the pupil offset distance of the candidate at each target time point is calculated based on the distance.

4. The IoT-based recruitment system according to claim 3, characterized in that: The specific calculation method for calculating the distance between each pupil feature point and each eye contour feature point of the applicant at each target time point is: Based on the image coordinates of each pupil feature point of the applicant at each target time point And the image coordinates of each eye contour feature point , calculate the distance between each pupil feature point and each eye contour feature point of the applicant at each target time point .

5. The IoT-based recruitment system according to claim 1, characterized in that: The specific screening method for the normal time points and alert time points for screening applicants is as follows: Based on the video images of the enterprise recruiter at each test time point, the time points at which each pupil of the enterprise recruiter can effectively capture and the time points at which each pupil cannot capture are screened; If a certain target time point of the applicant is consistent with a certain pupil effective capture time point of the enterprise recruiter, the target time point is marked as a normal time point, thereby screening the normal time points of the applicant; If a target time point of an applicant coincides with a time point that the pupil of the corporate recruiter cannot capture, the target time point is marked as a vigilance time point, thereby screening the applicant's various vigilance time points.

6. The IoT-based recruitment system according to claim 3, characterized in that: The specific analysis method for analyzing the offset distance hazard coefficient of the candidate at each target time point is as follows: Obtain each offset direction range from the local database. If the pupil offset direction of the candidate at a certain target time point is included in a certain offset direction range, use the offset direction range as the analysis offset direction range of the candidate at the target time point, thereby screening the analysis offset direction range of the candidate at each target time point, mapping the candidate's target time points in each analysis offset direction range, and counting the number of the candidate's target time points in each analysis offset direction range. , where r represents the number of each analysis offset direction range, , s is a positive integer greater than 2, and the offset frequency hazard coefficient of the candidate in each analysis offset direction range is calculated , where e represents a natural constant and s represents the number of the analysis offset direction range; If the pupil deviation direction of the candidate at a certain target time point is included in a certain analysis deviation direction range, the deviation frequency hazard coefficient of the analysis deviation direction range is used as the deviation direction hazard coefficient of the target time point, thereby obtaining the deviation direction hazard coefficient of the candidate at each target time point. ; Based on the pupil displacement distance of the applicant at each target time point , calculate the candidate's offset distance hazard coefficient at each target time point , where m is the number of target time points.

7. The IoT-based recruitment system according to claim 1, characterized in that: The specific method for judging whether an applicant is suspected of cheating by eye contact is as follows: Analyze the comprehensive cheating warning coefficient of the applicant based on the applicant's eye abnormality coefficient at each target time point; A comprehensive cheating warning coefficient threshold is obtained from a local database. If the comprehensive cheating warning coefficient of the applicant is greater than the comprehensive cheating warning coefficient threshold, the applicant is judged to be suspected of eye cheating.

8. The IoT-based recruitment system according to claim 7, characterized in that: The specific analysis method for analyzing the comprehensive cheating warning coefficient of the applicant is as follows: Obtaining a preset analysis time from a local database, randomly selecting a target time point of the candidate as the time point to be analyzed, taking each target time point before the time point to be analyzed of the candidate within the preset analysis time as each comparison time point, and taking each target time point after the time point to be analyzed of the candidate within the preset analysis time as each comparison time point, thereby obtaining the time point to be analyzed of the candidate and each comparison time point; Based on the applicant's eye abnormality coefficient at each target time point , extract the applicant's eye abnormality coefficient D at the time point to be analyzed and the eye abnormality coefficient at each comparison time point , where N represents the number of each comparison time point, , M is a positive integer greater than 2, and the eye warning coefficient of the candidate at the time point to be analyzed is calculated , where M represents the number of comparison time points, and so on, the eye warning coefficient of the applicant at each target time point is obtained , calculate the comprehensive cheating warning coefficient of the applicant .

9. The IoT-based recruitment system according to claim 8, characterized in that: The specific analysis method for analyzing the estimated cheating time points of the applicants is as follows: Obtain the eye warning coefficient threshold corresponding to each comprehensive cheating warning coefficient interval from the local database, calculate the comprehensive cheating warning coefficient of the applicant based on it, and map the eye warning coefficient threshold of the applicant; If the eye warning coefficient of the applicant at a certain target time point is greater than the eye warning coefficient threshold, the target time point is marked as a cheating estimated time point, thereby screening the applicant's various cheating estimated time points.

Images