Zero-worker market post matching degree evaluation system

Abstract

The invention relates to the technical field of data processing, in particular to a zero-work market post matching degree evaluation system, which comprises a post data acquisition module, a post matching degree evaluation module and a post matching degree evaluation module, the job hunting data acquisition module is used for acquiring job hunter data; the intensity grade dividing module is used for dividing the intensity grades of the posts; the fatigue analysis module is used for constructing a fatigue index of the job seeker; the feature matching module is used for constructing matching indexes of job seekers and posts; the matching degree evaluation module is used for evaluating the matching degree of the job seeker and the post according to the division result of the post strength grade, the construction result of the job seeker fatigue index and the construction result of the matching index; and the data analysis module is used for analyzing the physical state of the job seeker according to the construction result of the historical monitoring period fatigue index, and adjusting the evaluation process of the matching degree according to the analysis result and the number of the job seekers. According to the invention, the accuracy of post matching degree evaluation is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a job matching evaluation system for a gig market. Background Art

[0002] With the rapid development of the gig economy, more and more labor and jobs are matched on open platforms. However, due to the diversity of jobs and individual differences of job seekers, the matching algorithms in the existing gig market can usually only recommend jobs through limited feature screening (such as job description, historical work records, etc.).

[0003] Chinese patent publication number CN117436661A discloses a job matching evaluation method for the gig market, which belongs to the field of data processing technology, and specifically includes: determining the type of job and the similarity between the job and other jobs in the gig market according to the job description, and determining similar jobs and related jobs of the job based on the similarity, screening job seekers based on historical job matching, screening job seekers' browsing job matching by screening job seekers' browsing search data within a recent preset time to determine the browsing job matching of jobs, similar jobs and related jobs, and determining job matching by historical job matching, recent job matching and browsing job matching; it can be seen that the scheme calculates matching by the similarity between the job and other jobs, browsing data and work records, but this scheme is too simple, only focusing on the similarity of jobs and the known records of job seekers, ignoring more fine-grained personalized indicators such as job intensity and job seekers' fatigue status, resulting in low accuracy of matching evaluation and difficulty in reflecting the actual adaptability between different jobs and job seekers. Summary of the invention

[0004] The purpose of the present invention is to provide a job matching evaluation system for the gig market to solve at least one of the problems existing in the prior art.

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

[0006] Position data collection module, used to collect position data;

[0007] Job search data collection module, used to collect job seeker data;

[0008] The intensity level classification module is used to classify the intensity level of the post according to the collected post cargo quality, cargo quantity and post working hours;

[0009] The fatigue analysis module is used to construct the job seeker's fatigue index based on the job intensity level classification results and the job seeker's historical work data collected during the monitoring period;

[0010] The feature matching module is used to match the collected job seekers' intended working hours, job working hours, and the distance between the job seekers and the job positions, so as to construct a matching index between the job seekers and the positions;

[0011] A matching evaluation module is used to evaluate the matching degree between job seekers and positions based on the classification results of job intensity levels, the construction results of job seeker fatigue index and the construction results of matching index;

[0012] The data analysis module is used to analyze the physical condition of job seekers based on the construction results of the fatigue index of the historical monitoring period, and to adjust the matching evaluation process based on the analysis results and the number of job seekers for the position.

[0013] Furthermore, the strength level classification module includes a first strength index construction unit, a second strength index construction unit and a level classification unit. The first strength index construction unit is used to construct a first strength index according to the collected job cargo quality and cargo quantity, and set the first strength index of the i-th job to Q1(i).

[0014] Furthermore, the second intensity index construction unit is used to construct the second intensity index according to the collected job cargo quality, cargo quantity and job working hours, and sets the second intensity index of the i-th job to Q2(i).

[0015] Furthermore, the grade classification unit is used to classify the job strength grade according to the construction results of the first strength index and the second strength index to obtain the job strength grade, and the job strength grade includes level one, level two and level three.

[0016] Furthermore, the fatigue analysis module constructs a fatigue index of the job seeker according to the classification result of the job intensity level and the job seeker's historical work data collected during the monitoring period, and sets the fatigue index of the j-th job seeker as L(j).

[0017] Further, the feature matching module includes a position matching unit, a duration matching unit and a matching index building unit. The position matching unit is used to compare the distance between the job seeker and the position with the preset distance T0 to analyze the position status of the job seeker and the position. The position status includes normal and abnormal. If the position status of the j-th job seeker and the i-th position is normal, the position matching index is set to TQ1. If the position status of the j-th job seeker and the i-th position is abnormal, the position matching index is set to TQ2.

[0018] The duration matching unit is used to construct a duration matching index according to the intended working hours of the job seeker and the working hours of the position, and set the duration matching coefficient between the j-th job seeker and the i-th position to C(ji).

[0019] Furthermore, the matching index construction unit is used to construct the matching index between job seekers and positions according to the construction results of the position matching index and the construction results of the duration matching index, and sets the matching index between the j-th job seeker and the i-th position as PP(ji).

[0020] Furthermore, the matching evaluation module evaluates the matching degree between the job seeker and the position according to the classification result of the position intensity level, the construction result of the job seeker fatigue index and the construction result of the matching index, wherein:

[0021] When the strength level of the i-th position is level one, the matching evaluation module sets the matching degree between the j-th job seeker and the i-th position as D1(ji);

[0022] When the strength level of the i-th position is level 2, if L(j)≤L0, the matching evaluation module sets the matching degree between the j-th job seeker and the i-th position to D2(ji); if L(j)>L0, the matching evaluation module sets the matching degree between the j-th job seeker and the i-th position to D3(ji);

[0023] When the strength level of the i-th position is level three, if L(j)≤L0, the matching evaluation module sets the matching degree between the j-th job seeker and the i-th position to D4(ji); if L(j)>L0, the matching evaluation module sets the matching degree between the j-th job seeker and the i-th position to D5(ji);

[0024] Wherein, L0 is the first fatigue index threshold.

[0025] Furthermore, the data analysis module includes a state analysis unit and a quantity analysis unit. The state analysis unit is used to analyze the physical state of the job applicant based on the construction results of the fatigue index of each historical monitoring period. The physical state includes a normal state and a strong physical state. If the physical state of the jth job applicant is a strong physical state, the first adjustment ratio is set to α', and the second adjustment ratio is set to β'.

[0026] Furthermore, the quantity analysis unit is used to compare the number of job seekers for a position with a preset number m1, and analyze the abnormality of the number of job seekers for a position based on the comparison result. The abnormality of the number of job seekers for a position includes normal and abnormal. If the number of job seekers for the i-th position is abnormal, the preset adjustment coefficient is set to γ'.

[0027] The beneficial effects of the present invention are as follows: by making a fine division of job intensity and combining the fatigue status of job seekers, the mismatch caused by the mismatch between job requirements and job seekers' abilities in traditional matching systems is avoided, thereby greatly improving the accuracy and rationality of matching. In addition to matching jobs with job seekers, a comprehensive evaluation is also performed through multi-dimensional features such as distance and duration (such as location matching, time matching, etc.) to ensure that the recommended jobs are not only suitable in terms of work content, but also can meet other needs of job seekers, such as shorter commuting distances or reasonable working hours. The system also introduces a fatigue index detection mechanism to avoid recommending high-intensity jobs that exceed the physical load of job seekers, reduce the health risks of workers, and improve job seekers' job satisfaction while ensuring that the intervention of job opportunities is reasonable. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0029] Figure 1 Schematic diagram of the structure of the gig market job matching evaluation system of this embodiment.

[0030] Figure 2 It is a structural schematic diagram of the strength level classification module of this embodiment.

[0031] Figure 3 Schematic diagram of the structure of the feature matching module of this embodiment.

[0032] Figure 4 Schematic diagram of the structure of the data analysis module of this embodiment. DETAILED DESCRIPTION

[0033] In order to more clearly illustrate the present invention, the present invention is further described below in conjunction with preferred embodiments and accompanying drawings. Similar components in the accompanying drawings are represented by the same reference numerals. It should be understood by those skilled in the art that the content specifically described below is illustrative rather than restrictive, and should not be used to limit the scope of protection of the present invention.

[0034] It should be noted that, although the terms first, second, third, etc. may be used to describe in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0035] See also Figure 1As shown, it is a structural diagram of the gig market job matching evaluation system of this embodiment, and the system includes:

[0036] A job data collection module is used to collect job data, wherein the job data includes the quality of goods at the job, the quantity of goods and the working hours at the job, and the job data is the published job information;

[0037] The job search data collection module is used to collect job seeker data, which includes working hours, job seeker's intended working hours, the distance between the job seeker and each position, and historical work data. The job seeker's historical work data is the data of the positions where the job seeker has worked in the past.

[0038] It is understandable that the present implementation does not impose any specific limitation on the method of collecting job data and job seeker data, and those skilled in the art may freely set it as long as the method of collecting job data and job seeker data is satisfied, wherein the job data may be obtained through interaction, and the job seeker data may be collected through system background data import.

[0039] Please continue reading Figure 1 As shown, the system includes an intensity level classification module, which is used to classify the intensity level of the post according to the collected post cargo quality, cargo quantity and post working hours, and the intensity level classification module is connected to the post data collection module.

[0040] See also Figure 2 As shown, the strength level classification module includes a first strength index construction unit, which is used to construct the first strength index according to the collected post cargo quality and cargo quantity to improve the accuracy of the first strength index construction, wherein:

[0041] The first strength index construction unit sets the first strength index of the i-th position to Q1(i), setting:

[0042] Q1(i)=x1×ln{m(i) / [m0+m(i)]+1} / l n2+x2×exp{3×n(i) / [n0+n(i)]-3};

[0043] Among them, m(i) is the mass of goods in the i-th position, n(i) is the quantity of goods in the i-th position, m0 is the weight threshold, n0 is the quantity threshold, x1 is the quality weight, x2 is the quantity weight, and x1+x2=1. By constructing the first intensity index, an accurate value of the specific work intensity of the position is provided, and the multi-dimensional characteristics of the position work are considered through formula calculation, which improves the accuracy of the position intensity division.

[0044] It can be understood that in this implementation, there is no specific limitation on the setting of weight threshold, quantity threshold and each weight, and those skilled in the art can set them freely as long as the setting requirements of weight threshold, quantity threshold and each weight are met. Among them, the optimal value of m0 is 50 kg, the optimal value of n0 is 500 pieces, the optimal value of x1 is 0.4, and the optimal value of x2 is 0.6.

[0045] Please continue reading Figure 2 As shown, the intensity level classification module includes a second intensity index construction unit, which is used to construct the second intensity index according to the collected job cargo quality, cargo quantity and job job working hours to improve the accuracy of the second intensity index construction, wherein:

[0046] The second intensity index construction unit sets the second intensity index of the i-th position as Q2(i), and sets: Q2(i)=m(i)×n(i)×p0 / t(i), t(i) is the working time of the i-th position, and p0 is the workload threshold; by constructing the second intensity index to improve the accuracy of the job work intensity level classification, the accuracy of the job matching assessment is thereby improved.

[0047] It is understandable that the setting of the workload threshold is not specifically limited in the present embodiment, and those skilled in the art can freely set it as long as the setting requirements of the workload threshold are met, wherein the optimal value of p0 is 3500 kg / h.

[0048] Please continue reading Figure 2 As shown, the intensity level classification module includes a level classification unit, which is connected to the first intensity index construction unit and the second intensity index construction unit. The level classification unit is used to classify the position intensity level according to the construction results of the first intensity index and the second intensity index, wherein:

[0049] If w1×Q1(i)+w2×Q2(i)≤q1, the level classification unit determines that the strength level of the i-th position is level one;

[0050] If q1<w1×Q1(i)+w2×Q2(i)<q2, the level classification unit determines that the strength level of the i-th position is level 2;

[0051] If w1×Q1(i)+w2×Q2(i)≥q2, the level classification unit determines that the strength level of the i-th position is level three;

[0052] Among them, w1 is the first weight, w2 is the second weight, w1+w2=1, q1 is the first intensity threshold, q2 is the second intensity threshold, q1<q2; the job intensity is divided according to the comprehensive results of the first and second intensity indexes, which effectively avoids the mismatch between work intensity and the physical condition of job seekers, and ultimately improves the accuracy of job matching analysis.

[0053] Specifically, the first intensity level described in this embodiment is a light work task with low work intensity, the second intensity level is a medium intensity work task, and the third intensity level is a high intensity work task.

[0054] It can be understood that in this implementation, there is no specific limitation on the setting of each weight and each intensity threshold, and those skilled in the art can set them freely as long as the setting requirements of each weight and each intensity threshold are met. Among them, the optimal value of w1 is 0.55, the optimal value of w2 is 0.45, the optimal value of q1 is 0.2, and the optimal value of x2 is 0.4.

[0055] Please continue reading Figure 1 As shown, the system includes a fatigue analysis module, which is connected to the job seeker data collection module and the intensity level classification module. The fatigue analysis module is used to construct a job seeker's fatigue index according to the job seeker's intensity level classification result and the job seeker's historical work data collected during the monitoring period to improve the accuracy of the fatigue index construction, wherein:

[0056] The fatigue analysis module sets the fatigue index of the jth job seeker as L(j), and sets: L(j)=[k1×tz1(j)+k2×tz2(j)+k3×tz3(j)] / TZ;

[0057] Among them, tz1(j) is the working time of the j-th job seeker in the position with intensity level 1 during the monitoring period, tz2(j) is the working time of the j-th job seeker in the position with intensity level 2 during the monitoring period, tz3(j) is the working time of the j-th job seeker in the position with intensity level 3 during the monitoring period, k1 is the first-level intensity weight, k2 is the second-level intensity weight, and k3 is the third-level intensity weight. By analyzing the job seekers' historical working hours and intensity and calculating the fatigue index, we can avoid recommending high-intensity work to job seekers with excessive fatigue, which helps to maintain a balance between tasks and job seekers' actual abilities and status, and improves the accuracy of job matching assessment.

[0058] It is understandable that the present embodiment does not impose any specific limitation on the setting of the monitoring period, and those skilled in the art may freely set it as long as the setting requirements of the monitoring period are met, wherein the monitoring period may be set to 7 days, 15 days, 30 days, etc.

[0059] It can be understood that in this implementation, there is no specific limitation on the setting of each weight, and those skilled in the art can set it freely as long as the setting requirements of each weight are met. Among them, the optimal value of k1 is 1, the optimal value of k2 is 1.1, and the optimal value of k3 is 1.35. When the monitoring period is 7 days, the optimal value of TZ is 56h.

[0060] Please continue reading Figure 1 As shown, the system includes a feature matching module, which is connected to the fatigue index analysis module and is used to match the collected job seekers' intended working hours, job working hours and the distance between the job seekers and the jobs, so as to construct a matching index between the job seekers and the jobs.

[0061] See also Figure 3 As shown, the feature matching module includes a position matching unit, which is used to compare the distance between the job seeker and the position with the preset distance T0 to analyze the position status of the job seeker and the position, and construct a position matching index according to the analysis result to improve the accuracy of the position matching index construction, wherein:

[0062] If T(ji)≤T0, the position matching unit determines that the position status between the j-th job seeker and the i-th position is normal, and sets the position matching index to TQ1, setting TQ1=1; if T(ji)>T0, the position matching unit determines that the position status between the j-th job seeker and the i-th position is abnormal, and sets the position matching index to TQ2, setting TQ2=1-[T(ji)-T0] / T0, where T(ji) is the distance between the j-th job seeker and the i-th position; by constructing the position matching index, it helps to recommend positions that are closer to job seekers, shorten commuting time, and improve work convenience, so as to improve the accuracy of matching index construction, thereby improving the accuracy of job matching assessment.

[0063] It is understandable that the setting of the preset distance is not specifically limited in the present embodiment, and those skilled in the art can freely set it as long as the setting requirements of the preset distance are met, wherein the best value of T0 is 6 km.

[0064] Please continue reading Figure 3 As shown, the feature matching module includes a duration matching unit, which is used to construct a duration matching index according to the job seeker's intended working hours and the position working hours. The duration matching unit sets the duration matching coefficient between the j-th job seeker and the i-th position as C(ji), and sets C(ji)=1-|Sj-Gi| / Gi, wherein Sj is the j-th job seeker's intended working hours, and Gi is the duration of the i-th position.

[0065] Please continue reading Figure 3As shown, the feature matching module includes a matching index construction unit, which is connected to the position matching unit and the duration matching unit. The matching index construction unit is used to construct a matching index between a job seeker and a position according to the construction results of the position matching index and the construction results of the duration matching index, wherein:

[0066] The matching index construction unit sets the matching index between the j-th job seeker and the i-th position as PP(ji), and sets PP(ji)=R1×position matching index+R2×G(ji), R1+R2=1.

[0067] It is understandable that the setting of each weight is not specifically limited in the present embodiment, and those skilled in the art can set it freely as long as the setting requirements of each weight are met. Among them, the best value of R1 is 0.36, and the best value of R2 is 0.64. By combining the position matching index and the working time matching index, a more comprehensive matching evaluation of positions and job seekers is provided, thereby improving the scientificity and accuracy of recommendations.

[0068] Please continue reading Figure 1 As shown, the system includes a matching evaluation module, which is connected to the feature matching module. The matching evaluation module is used to evaluate the matching degree between the job seeker and the position according to the division result of the position intensity level, the construction result of the job seeker fatigue index and the construction result of the matching index, so as to improve the accuracy of the matching evaluation, wherein:

[0069] When the strength level of the i-th position is level one, the matching evaluation module sets the matching degree between the j-th job seeker and the i-th position as D1(ji), setting: D1(ji)=PP(ji);

[0070] When the strength level of the i-th position is level 2, if L(j)≤L0, the matching evaluation module sets the matching degree between the j-th job seeker and the i-th position to D2(ji), setting: D2(ji)=PP(ji); if L(j)>L0, the matching evaluation module sets the matching degree between the j-th job seeker and the i-th position to D3(ji), setting: D3(ji)=PP(ji)-α××{[e 4×[L(j)-L0] -1] / [e 4 -1]};

[0071] When the strength level of the i-th position is level three, if L(j)≤L0, the matching evaluation module sets the matching degree between the j-th job seeker and the i-th position to D4(ji), setting: D4(ji)=PP(ji); if L(j)>L0, the matching evaluation module sets the matching degree between the j-th job seeker and the i-th position to D5(ji), setting: D5(ji)=PP(ji)-β××{[e4×[L(j)-L0] -1] / [e 4 -1]};

[0072] Wherein, L0 is the first fatigue index threshold, α is the first adjustment ratio, β is the second adjustment ratio, α<β;

[0073] The matching evaluation module pushes the job that matches the jth job seeker most to the job seeker as a recommended job; through multi-dimensional data collection, job intensity level classification, and matching analysis of job seeker fatigue and work characteristics, the accuracy and efficiency of matching between jobs and job seekers are significantly improved.

[0074] It can be understood that in this implementation, there is no specific limitation on the setting of the first fatigue threshold, the first adjustment ratio and the second adjustment ratio. The technology in the field can be freely set, and it is only necessary to meet the setting requirements of the first fatigue threshold, the first adjustment ratio and the second adjustment ratio. Among them, the optimal value of L0 is 1, the optimal value of α is 0.23, and the optimal value of β is 0.45.

[0075] It is understandable that the maximum matching degree screening method is not specifically limited in this embodiment, and those skilled in the art can freely set it as long as the maximum matching degree screening requirement is met, wherein the maximum matching degree can be screened by bubble sorting method.

[0076] Please continue reading Figure 1 As shown, the system includes a data analysis module, which is connected to the matching evaluation module. The data analysis module is used to adjust the matching evaluation process according to the construction results of the fatigue index of the historical monitoring cycle and the number of job seekers.

[0077] See also Figure 4 As shown, the data analysis module includes a state analysis unit, which is used to analyze the physical state of the job seeker according to the construction results of the fatigue index of each historical monitoring period, and adjust the matching evaluation process according to the analysis results, wherein:

[0078] like The state analysis unit determines that the physical state of the j-th job seeker is normal and does not make any adjustments; if The state analysis unit determines that the physical state of the j-th job seeker is a strong physical state, and sets the first adjustment ratio to α', setting:

[0079] Set the second adjustment ratio to β' and set:

[0080]

[0081] Wherein, Lh(j) is the fatigue index of the j-th job seeker in the h-th historical monitoring period, H is the number of historical monitoring periods in which the j-th job seeker worked, L1 is the second fatigue index threshold, and γ is the preset adjustment coefficient; by analyzing the physical status of job seekers, the influence of job seekers' physical factors on job matching assessment is reduced, thereby improving the accuracy of job matching assessment.

[0082] It can be understood that, in this implementation, there is no specific limitation on the method for obtaining H, and those skilled in the art can set it freely, as long as the requirements for obtaining H are met, wherein H can be obtained by importing system background data. In this embodiment, there is no specific limitation on the value of the preset adjustment coefficient and the second fatigue index threshold, and those skilled in the art can set it freely, as long as the requirements for the value of the preset adjustment coefficient and the second fatigue index threshold are met, wherein the optimal value of γ is 0.3, and the optimal value of L1 is 1.1.

[0083] Please continue reading Figure 4 As shown, the data analysis module includes a quantity analysis unit, which is connected to the state analysis unit, and the quantity analysis unit is used to compare the number of job seekers for a position with a preset number m1, and analyze the abnormality of the number of job seekers for a position according to the comparison result, and optimize the adjustment process of the matching evaluation process according to the analysis result, wherein;

[0084] If mi0≤m1, the quantity analysis unit determines that the number of job seekers for the i-th position is normal and does not perform optimization;

[0085] If mi0>m1, the quantity analysis unit determines that the number of job seekers for the ith position is abnormal, and sets the preset adjustment coefficient to γ', setting γ'=γ×[1-η×(mi0-m1) / (mi0+m1)], where mi0 is the number of job seekers for the ith position, and η is the preset optimization ratio; by analyzing the abnormality of the number of job seekers for the position, the impact of the excessive number of job seekers on the job matching assessment is reduced, thereby improving the accuracy of the job matching assessment.

[0086] Specifically, the number of job seekers is the number of job seekers in the job area, and the job area is a circular area with the job location as the center and a radius of 6 km. In this embodiment, there is no specific limitation on the method for obtaining the number of job seekers, and technical personnel in this field can set it freely as long as the requirements for obtaining the number of job seekers are met, which can be obtained through GIS.

[0087] It can be understood that in this embodiment, there is no specific limitation on the setting of the preset number and the preset optimization ratio, and those skilled in the art can set them freely as long as the setting requirements of the preset number and the preset optimization ratio are met. Among them, the optimal value of m1 is 500 people, and the optimal value of η is 0.24.

[0088] Specifically, the system described in this embodiment is applied to the evaluation of the matching degree between warehousing part-time jobs and positions. Through multi-dimensional data collection, classification of job intensity levels, and matching analysis of job seeker fatigue and work characteristics, the accuracy and efficiency of matching between positions and job seekers are significantly improved. Dynamic feedback optimization is performed through historical data to ensure continuous improvement of the matching process between positions and job seekers.

[0089] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not limitations on the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is impossible to list all the embodiments here. All obvious changes or modifications derived from the technical solution of the present invention are still within the protection scope of the present invention.

Claims

1. A job matching evaluation system for the gig market, characterized in that: Including, a job data collection module, used to collect job data; Job search data collection module, used to collect job seeker data; The intensity level classification module is used to classify the intensity level of the post according to the collected post cargo quality, cargo quantity and post working hours; The fatigue analysis module is used to construct the job seeker's fatigue index based on the job intensity level classification results and the job seeker's historical work data collected during the monitoring period; The feature matching module is used to match the collected job seekers' intended working hours, job working hours, and the distance between the job seekers and the job positions, so as to construct a matching index between the job seekers and the positions; A matching evaluation module is used to evaluate the matching degree between job seekers and positions based on the classification results of job intensity levels, the construction results of job seeker fatigue index and the construction results of matching index; The data analysis module is used to analyze the physical condition of job seekers based on the construction results of the fatigue index of the historical monitoring period, and to adjust the matching evaluation process based on the analysis results and the number of job seekers for the position.

2. The job matching evaluation system for the gig market according to claim 1, characterized in that: The strength level classification module includes a first strength index construction unit, a second strength index construction unit and a level classification unit. The first strength index construction unit is used to construct a first strength index according to the collected quality and quantity of goods at the post, and set the first strength index of the i-th post to Q1(i).

3. The job matching evaluation system for the gig market according to claim 2, characterized in that: The second intensity index construction unit is used to construct the second intensity index according to the collected job cargo quality, cargo quantity and job working hours, and sets the second intensity index of the i-th job to Q2(i).

4. The job matching evaluation system for the gig market according to claim 3 is characterized in that: The grade classification unit is used to classify the job strength grade according to the construction results of the first strength index and the second strength index to obtain the job strength grade, and the job strength grade includes level one, level two and level three.

5. The job matching evaluation system for the gig market according to claim 4, characterized in that: The fatigue analysis module constructs a fatigue index of job seekers according to the classification results of job intensity levels and the job seekers' historical work data collected during the monitoring period, and sets the fatigue index of the j-th job seeker as L(j).

6. The job matching evaluation system for the gig market according to claim 5, characterized in that: The feature matching module includes a position matching unit, a duration matching unit and a matching index building unit. The position matching unit is used to compare the distance between the job seeker and the position with the preset distance T0 to analyze the position status of the job seeker and the position. The position status includes normal and abnormal. If the position status of the j-th job seeker and the i-th position is normal, the position matching index is set to TQ1. If the position status of the j-th job seeker and the i-th position is abnormal, the position matching index is set to TQ2. The duration matching unit is used to construct a duration matching index according to the intended working hours of the job seeker and the working hours of the position, and set the duration matching coefficient between the j-th job seeker and the i-th position to C(ji).

7. The gig market job matching evaluation system according to claim 6, characterized in that: The matching index construction unit is used to construct the matching index between job seekers and positions according to the construction results of the position matching index and the construction results of the duration matching index, and sets the matching index between the j-th job seeker and the i-th position as PP(ji).

8. The job matching evaluation system for the gig market according to claim 7, characterized in that: The matching evaluation module evaluates the matching degree between the job seeker and the job position according to the classification result of the job intensity level, the construction result of the job seeker fatigue index and the construction result of the matching index, wherein: When the strength level of the i-th position is level one, the matching evaluation module sets the matching degree between the j-th job seeker and the i-th position as D1(ji); When the strength level of the i-th position is level 2, if L(j)≤L0, the matching evaluation module sets the matching degree between the j-th job seeker and the i-th position to D2(ji); if L(j)>L0, the matching evaluation module sets the matching degree between the j-th job seeker and the i-th position to D3(ji); When the strength level of the i-th position is level three, if L(j)≤L0, the matching evaluation module sets the matching degree between the j-th job seeker and the i-th position to D4(ji); if L(j)>L0, the matching evaluation module sets the matching degree between the j-th job seeker and the i-th position to D5(ji); Wherein, L0 is the first fatigue index threshold.

9. The job matching evaluation system for the gig market according to claim 8, characterized in that: The data analysis module includes a state analysis unit and a quantity analysis unit. The state analysis unit is used to analyze the physical state of the job seeker according to the construction results of the fatigue index of each historical monitoring period. The physical state includes a normal state and a strong physical state. If the physical state of the jth job seeker is a strong physical state, the first adjustment ratio is set to α', and the second adjustment ratio is set to β'.

10. The job matching evaluation system for the gig market according to claim 9, characterized in that: The quantity analysis unit is used to compare the number of job seekers for a position with a preset number m1, and analyze the abnormality of the number of job seekers for a position based on the comparison result. The abnormality of the number of job seekers for a position includes normal and abnormal. If the number of job seekers for the i-th position is abnormal, the preset adjustment coefficient is set to γ'.

Images