Employment guidance method and system based on employment evaluation big data analysis

Abstract

The invention discloses an employment guidance method and system based on employment evaluation big data analysis, and relates to the technical field of employment guidance, the system comprises an acquisition module, a matching module, an analysis module, a display module and a return visit module; and the acquisition module is used for acquiring recruitment post data of an employment website through a crawler technology and acquiring user data by adopting an online information filling page. According to the invention, the matching unit sets rigid conditions for users through a hard filtering module in the cloud server, preliminarily screens recruitment post data, rejects posts which do not meet the conditions, improves the subsequent calculation speed, and flexibly sets personal feature weights of the users through quantification of post fields and user features and through personal demands of college students. And the matching degree between the qualified post information and the user is calculated and screened, so that the matching accuracy and personalization are improved, the work satisfaction degree after entry is high, and the employment guidance efficiency and scientificity are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of employment guidance, and particularly to a method and system for employment guidance based on big data analysis of employment evaluation. Background Art

[0002] With the intensification of social competition, the employment problem of college students has become increasingly prominent. According to statistical data, in recent years, the number of college graduates has been increasing year by year, while the growth rate of demand in the employment market is relatively slow, resulting in an increasing employment pressure on college students. In order to improve the employment competitiveness of college students, many universities and government departments have begun to attach importance to the employment guidance work of college students. Although there are already some employment guidance services at present, most of these services stay at the traditional level and cannot meet the personalized and precise employment needs of college students.

[0003] Currently, the existing employment guidance often lacks precision and cannot deeply understand the matching degree between college students and specific positions. After receiving employment guidance, many college students choose positions that do not match their skills, interests, and position preferences, resulting in low job satisfaction and high turnover rates after starting work. At the same time, employment guidance fails to consider the popularity and stability of positions and lacks foresight. College students are prone to choose positions that seem popular currently but have declining future demand, or ignore the potential positions in emerging fields; and blindly choosing based on popular positions makes the positions in short supply, facing more intense competition, and reducing the probability of obtaining a position stably.

[0004] Therefore, a method and system for employment guidance based on big data analysis of employment evaluation are proposed to solve the above problems. Summary of the Invention

[0005] The main purpose of the present invention is to provide a method and system for employment guidance based on big data analysis of employment evaluation to solve the problems raised in the above background.

[0006] To achieve the above purpose, the technical solution adopted by the present invention is: a method and system for employment guidance based on big data analysis of employment evaluation, the system includes a collection module, a matching module, an analysis module, a display module, and a return visit module; The collection module is used to obtain recruitment position data of employment websites through web crawler technology, and collect user data using an online information filling page, and preprocess the user data and recruitment position data and then transmit them to the cloud server for storage; The matching module is used to preliminarily screen the recruitment position data according to the rigid conditions set by the user, calculate the matching degree with the user after screening, and retain the recruitment position data with a high matching degree, and analyze the heat change of the recruitment position data with a high matching degree according to the real-time and historical position quantities; The analysis module is used to evaluate the stability of a position through recruitment position data, conduct position stability analysis, and issue risk warnings for the stability of the position; The display module is used to integrate the heat prediction information, position stability, and dynamic prediction analysis information of highly matched recruitment positions through Plotly and draw a bar chart; The follow-up visit module is used to regularly follow up on the user's situation through questionnaires or phone calls, calculate the satisfaction score of the user during their employment, predict the satisfaction score of the user, and determine whether to leave based on the prediction results.

[0007] Further, the acquisition module includes an acquisition unit, a collection unit, a preprocessing unit, and a storage unit; The acquisition unit is used to obtain recruitment position data of employment websites through web crawler technology. The recruitment position data includes position fields, the number of positions, and the number of applicants; The collection unit collects user data through an online information filling page. The user data includes personality, position preference, work experience, and educational background; The preprocessing unit is used to preprocess user data and recruitment position data through edge computing devices. The preprocessing includes cleaning, deduplication, and format unification; The storage unit is used to store the preprocessed user data and recruitment position data through a cloud server.

[0008] Further, the matching module includes a screening unit, a matching unit, and a prediction unit; The screening unit is used to initially screen the recruitment position data through a hard filtering module in the cloud server according to the rigid conditions set by the user. The rigid conditions include location, salary, and position type.

[0009] Further, the matching unit includes a similarity unit and a setting unit; The similarity unit calculates the matching degree between the position field and the user through weighted cosine similarity based on the position field data of the recruitment position data after initial screening. The calculation formula is as follows: ; Among them, represents the matching degree, represents the number of matching features, represents the weight of the th feature, represents the quantization value of the user on the th feature, represents the quantization value of the position field on the th feature.

[0010] Further, the setting unit is used to set the matching degree When the matching degree is greater than or equal to 0.85, it represents a job field with a high matching degree.

[0011] Further, the prediction unit is used to analyze the heat change of the job field with a high matching degree, and the calculation steps are as follows: Step 1, based on the job field with a high matching degree in the recruitment job data in the cloud server, select the data of the number of jobs in this job field for data smoothing, and the calculation formula is as follows: ; Among them, represents the moving average number of jobs at time point , that is, the average value of the number of jobs in the recruitment job data of the current week and the previous three weeks, represents the number of jobs in the recruitment job data of the th week, represents the average value of the number of jobs in 4 weeks; Step 2, analyze the heat of the job field with a high matching degree through the current four-week moving average number of jobs and the four-week-old moving average number of jobs, and the calculation formula is as follows: ; Among them, represents the heat growth rate; represents the current four-week moving average number of jobs, represents the four-week-old moving average number of jobs; Among them, when is greater than or equal to 12%, it represents that the heat is rising, and when is greater than or equal to -12% and less than or equal to -12%, it represents that the heat is stable, and when is less than or equal to 12%, it represents that the heat is falling.

[0012] Further, the analysis module includes an evaluation unit and an analysis unit; The evaluation unit calculates the job supply-demand ratio based on the number of jobs and the number of job applications in the recruitment job data to analyze job stability, and the calculation formula is as follows: ; When is greater than 1, it represents that the job demand is large and the job stability is high. When is less than 1, it represents that the job competition is fierce and the job stability is low; The analysis unit calculates the change rate through the job supply-demand ratio of this week and the job supply-demand ratio of last week, and the calculation formula is as follows: ; Among them, when the change rate is less than 10%, it represents the risk of decline in job demand and the risk of job stability. When the change rate is greater than 10, it represents the accelerated growth of job demand and the improvement of job stability.

[0013] Furthermore, the return visit module includes a return visit unit, a calculation unit, a future unit, and a judgment unit; The return visit unit is used to conduct regular return visits to the user's situation through questionnaires or phone calls. The user's situation includes salary and benefits, working environment, career development opportunities, interest in work content, and interpersonal relationships. By scoring multiple dimensions of the user's situation, each dimension has a full score of 10 points and a minimum of 1 point. At the same time, weights are assigned to multiple dimensions according to the user himself, and the sum of multiple dimensions is equal to 1; The calculation unit is used to collect the scores and weights of each dimension and calculate the satisfaction score during the on-the-job period. The calculation formula is as follows: ; Among them, represents the salary and benefits score; represents the working environment score; represents the career development opportunity score; represents the interest in work content score, represents the interpersonal relationship score, , , , and respectively represent the weights of salary and benefits, working environment, career development opportunities, interest in work content, and interpersonal relationships, and LP represents the satisfaction score; The prediction unit is used to predict the satisfaction score. The prediction formula is: ; Among them, represents the predicted satisfaction score, and represent the satisfaction scores of the previous and two time periods before the moment, represents the satisfaction score of the previous K time periods before the moment, and k represents the number of historical data used for calculation; The judgment unit is used to compare the calculated predicted score with the set score threshold to judge whether the user needs to leave the job; If is greater than or equal to 8 and less than or equal to 10, it represents that the user's satisfaction score is high and there is no need to leave the job; If When it is greater than or equal to 5 and less than or equal to 7, it represents that the user satisfaction score is medium, and there is no need to leave the job. However, it is necessary to analyze the long-term changes in the predicted satisfaction score. If it is in a continuous downward trend, leave planning should be done in advance; If When it is less than or equal to 4, it represents that the user satisfaction is poor and the user leaves the job.

[0014] Furthermore, the display module is used to integrate and draw a bar chart of the heat prediction information, job stability, and change rate in the job fields with high user matching degree through Plotly.

[0015] An employment guidance method based on big data analysis of employment evaluation includes the following steps: S1: Enter the acquisition module, obtain the recruitment position data of the employment website and collect user data, preprocess the user data and recruitment position data, and then transmit them to the cloud server for storage; S2: Enter the matching module. The user sets rigid conditions to preliminarily screen the recruitment position data, perform similarity matching between the screened recruitment position data and the user, and retain the recruitment position data with high matching degree for heat change analysis; S3: Enter the analysis module, calculate the recruitment position data with rising heat and high similarity with the user, analyze the job stability by calculating the job supply-demand ratio, and calculate the change rate for risk warning; S4: Enter the display module, integrate the calculated multiple pieces of information and draw a bar chart for display; S5: Enter the return visit module, regularly return visit the user situation through questionnaires or phone calls, calculate the satisfaction score of the user during the job and predict the future satisfaction score, and judge whether to leave the job according to the prediction result.

[0016] The present invention has the following beneficial effects: 1. In the present invention, the matching unit preliminarily screens the recruitment position data according to the rigid conditions set by the user through the hard filtering module in the cloud server, eliminates the positions that do not meet the conditions, improves the subsequent calculation speed, quantifies the job fields and user characteristics, and flexibly sets the user personal characteristic weights according to the personal needs of college students, calculates the matching degree between the qualified job information and the user, thereby improving the accuracy and personalization of the matching, making the job satisfaction after entry high, and improving the efficiency and scientificity of employment guidance.

[0017] 2. In the present invention, in the prediction unit, the heat growth rate is calculated through historical and current data to predict the heat of job fields with high matching degrees, which can help college students clearly understand the dynamic change trend of jobs when seeking employment. When the heat growth rate is higher than the set threshold, it indicates that the job heat is on the rise, and it is recommended that students give priority attention. When the heat growth rate is lower than the set threshold, it indicates that the job heat is on the decline, and it is recommended that students choose carefully. According to the rise or fall of the job heat, reasonably select the jobs to be concerned about or carefully selected, and make a more sensible employment decision.

[0018] 3. In the present invention, the evaluation unit evaluates the job stability by calculating the job supply-demand ratio, which can intuitively reflect the job demand situation. When the job supply-demand ratio is greater than 1, the job stability is high. When the job supply-demand ratio is less than 1, the competition is fierce and the stability is low. This helps college students understand the job competition situation, calculates the change rate based on the real-time and previous job supply-demand ratios, can judge the change trend of job demand, predict the recession risk and growth rate, plan in advance, and presents the overall information in a bar chart, visually presenting information such as heat prediction, job stability, and supply-demand ratio change rate, facilitating college students to quickly understand complex data and improving the employment decision-making efficiency.

[0019] 4. In the present invention, in the follow-up visit module, regular follow-up visits are conducted on multiple dimensions through questionnaires or calls, and users assign weights to each dimension according to their own situations, making subsequent analysis and decision-making more in line with personal actual situations, providing a rich data basis. Calculate the satisfaction score during the job based on the scores and weights of each dimension, convert the user's subjective feelings about the job into specific quantitative values, and use the historical satisfaction score data to predict the future satisfaction. It can enable users to understand the change trend of job satisfaction in advance, compare the predicted score with the set score threshold, and give decision-making suggestions corresponding to different score intervals, more rationally planning the user's career development. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is the flowchart of the method and system for employment guidance based on big data analysis of employment evaluation of the present invention; Figure 2 is the flowchart of the acquisition module of the method and system for employment guidance based on big data analysis of employment evaluation of the present invention; Figure 3 is the flowchart of the analysis module of the method and system for employment guidance based on big data analysis of employment evaluation of the present invention; Figure 4 is the flowchart of the matching module of the method and system for employment guidance based on big data analysis of employment evaluation of the present invention; Figure 5 is the flowchart of the method of the method and system for employment guidance based on big data analysis of employment evaluation of the present invention; Figure 6 This is the flowchart of the method return visit module for the employment guidance method and system based on big data analysis of employment evaluation. Specific implementation manners

[0021] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0022] Embodiment 1 Please refer to Figures 1 to 5 , the present invention provides a technical solution: an employment guidance method and system based on big data analysis of employment evaluation. The system includes a collection module, a matching module, an analysis module, and a display module; The collection module is used to obtain recruitment position data of employment websites through web crawler technology, and collect user data through an online information filling page, and preprocess the user data and recruitment position data and then transmit them to the cloud server for storage; The matching module is used to initially screen the recruitment position data according to the rigid conditions set by the user, calculate the matching degree with the user through similarity calculation after screening, and retain the recruitment position data with a high matching degree, and analyze the heat change of the recruitment position data with a high matching degree according to the real-time and historical position quantities; The analysis module is used to evaluate the stability of the position through the recruitment position data, conduct position stability analysis, and at the same time conduct risk early warning on the stability of the position; The display module is used to integrate the heat prediction information, position stability, and dynamic prediction analysis information of the recruitment positions with a high matching degree through Plotly and draw a bar chart.

[0023] The collection module includes a collection unit, a collection unit, a preprocessing unit, and a storage unit; The collection unit is used to obtain recruitment position data of employment websites through web crawler technology. The recruitment position data includes position fields, position quantities, and the number of applicants; The collection unit collects user data through an online information filling page. The user data includes personality, position tendency, work experience, and educational background; The preprocessing unit is used to preprocess the user data and recruitment position data through an edge computing device. The preprocessing includes cleaning, duplicate removal, and format unification; The storage unit is used to store the preprocessed user data and recruitment position data through the cloud server.

[0024] The matching module includes a screening unit, a matching unit, and a prediction unit; The screening unit is used to preliminarily screen the recruitment position data through the hard filtering module in the cloud server according to the rigid conditions set by the user. The rigid conditions include location, salary, and position type.

[0025] The matching unit includes a similarity unit and a setting unit; The similarity unit is based on the position field data of the recruitment position data after preliminary screening, and calculates the matching degree between the position field and the user through weighted cosine similarity. The calculation formula is as follows: ; Among them, represents the matching degree, represents the number of matching features, represents the weight of the th feature, represents the quantization value of the user on the th feature, represents the quantization value of the position field on the

[0026] The setting unit is used to set the matching degree . When the matching degree is greater than or equal to 0.85, it represents a position field with a high matching degree.

[0027] In the acquisition unit, the recruitment position information on the employment website is collected in real time through crawler calculation, including the position field, the number of positions, and the number of applicants, etc. At the same time, the user data is collected on the online information filling page, including personality, position preference, work experience, and educational background, etc., to ensure the comprehensiveness of data collection. Then, the collected user data and recruitment position information are subjected to data cleaning, format unification, and duplicate information removal through the edge computing device to reduce the usage load of the subsequent cloud server. In the matching unit, the recruitment position data is preliminarily screened through the hard filtering module in the cloud server according to the rigid conditions set by the user, including location, salary, and position type, to eliminate the positions that do not meet the conditions and improve the subsequent calculation speed. By quantifying the position field and user characteristics, and flexibly setting the user personal characteristic weights according to the personal needs of college students, the matching degree between the qualified position information and the user is calculated, thereby improving the accuracy and personalization of the matching and making the job satisfaction high after employment.

[0028] Embodiment 2 Please refer to Figure 1 、 Figure 4 and Figure 5 . The present invention provides a technical solution: Based on the basis of Embodiment 1, the prediction unit is used to analyze the heat change of the position field with a high matching degree. The calculation steps are as follows: Step 1: Based on the job fields with high matching degrees in the recruitment job data in the cloud server, select the data on the number of jobs in this job field for data smoothing. The calculation formula is as follows: ; Wherein, represents the moving average number of jobs at time point , that is, the average value of the number of jobs in the recruitment job data for the current week and the previous three weeks, represents the number of jobs in the recruitment job data for the th week, represents the average value of the number of jobs for 4 weeks; Step 2: Conduct a heat analysis on the job fields with high matching degrees through the current four-week moving average number of jobs and the four-week-old moving average number of jobs. The calculation formula is as follows: ; Wherein, represents the heat growth rate; represents the current four-week moving average number of jobs, represents the four-week-old moving average number of jobs; Among them, when is greater than or equal to 12%, it means the heat is rising. When is greater than or equal to -12% and less than or equal to -12%, it means the heat is stable. When is less than or equal to 12%, it means the heat is falling.

[0029] In the prediction unit, by calculating the heat growth rate through historical and current data, the heat of the job fields with high matching degrees is predicted, which can help college students understand the dynamic change trend of jobs more clearly when they are employed. When the heat growth rate is higher than the set threshold, it means the job heat is on the rise, and it is recommended that students pay priority attention. When the heat growth rate is lower than the set threshold, it means the job heat is on the decline, and it is recommended that students choose carefully. According to the rise or fall of the job heat, reasonably select the jobs to pay attention to or choose carefully, make a more sensible employment decision, and improve the forward-looking nature of employment guidance.

[0030] Implementation Three Please refer to Figure 1 , Figure 3 and Figure 5 , the present invention provides a technical solution: based on the basis of Embodiment 1, the analysis module includes an evaluation unit and an analysis unit; The evaluation unit calculates the job supply-demand ratio based on the number of jobs and the number of job applications in the recruitment job data to analyze the job stability. The calculation formula is as follows: ; When When it is greater than 1, it indicates a large demand for the position and high job stability. When When it is less than 1, it indicates fierce competition for the position and low job stability.

[0031] The analysis unit calculates the change rate based on the job supply-demand ratio this week and the job supply-demand ratio last week. The calculation formula is as follows: 00%; Among them, when the change rate is less than 10%, it indicates a risk of decline in job demand and a risk in job stability. When the change rate is greater than 10, it indicates an accelerated growth in job demand and an improvement in job stability.

[0032] The display module is used to integrate and plot a bar chart of the heat prediction information, job stability, and change rate in the job fields with high user matching degree through Plotly.

[0033] The evaluation unit evaluates job stability by calculating the job supply-demand ratio, which can intuitively reflect the job demand situation. When the job supply-demand ratio is greater than 1, the job stability is high. When the job supply-demand ratio is less than 1, the competition is fierce and the stability is low. It helps college students understand the job competition situation, calculates the change rate based on the real-time and past job supply-demand ratios, can judge the change trend of job demand, predict the decline risk and growth rate, plan in advance, and draw the overall information into a bar chart to visually present information such as heat prediction, job stability, and supply-demand ratio change rate, facilitating college students to quickly understand complex data and improve the efficiency of employment decision-making.

[0034] Embodiment 4 Please refer to Figure 1 and Figure 6 Based on Embodiment 1, the return visit module includes a return visit unit, a calculation unit, a future unit, and a judgment unit; The return visit unit is used to conduct regular return visits to the user's situation through questionnaires or phone calls. The user's situation includes salary and benefits, working environment, career development opportunities, interest in job content, and interpersonal relationships. By scoring multiple dimensions of the user's situation, with each dimension having a full score of 10 and a minimum of 1, and at the same time assigning weights to multiple dimensions according to the user himself / herself, and the sum of multiple dimensions is equal to 1; The calculation unit is used to collect the scores and weights of each dimension and calculate the satisfaction score during the on-the-job period. The calculation formula is as follows: ; Among them, represents the score of salary and benefits; represents the score of the working environment; represents the score of career development opportunities; represents the score of interest in job content, Represents the interpersonal relationship score, , , , and represent the weights of salary and benefits, working environment, career development opportunities, interest in job content, and interpersonal relationships respectively. LP represents the satisfaction score; The prediction unit is used to predict the satisfaction score, and the prediction formula is: ; Among them, represents the predicted satisfaction score, and represent the satisfaction scores in the previous one and two time periods before the moment, represents the satisfaction score in the previous K time periods before the moment. k represents the number of historical data used for calculation; The judgment unit is used to compare the calculated predicted score with the set score threshold to judge whether the user needs to leave the job; If is greater than or equal to 8 and less than or equal to 10, it means that the user's satisfaction score is high and there is no need to leave the job; If is greater than or equal to 5 and less than or equal to 7, it means that the user's satisfaction score is medium and there is no need to leave the job, but it is necessary to analyze the long-term change of the predicted satisfaction score. If it is in a continuous downward trend, leave the job plan should be made in advance; If is less than or equal to 4, it means that the user's satisfaction is poor and the user leaves the job.

[0035] In this embodiment, in the return visit module, regular (semi-monthly) return visits are made to multiple dimensions through questionnaires or calls, and the user assigns weights to each dimension according to their own situation, making the subsequent analysis and decision-making more in line with the individual actual situation, providing a rich data basis, calculating the satisfaction score during the on-the-job period based on the scores and weights of each dimension, converting the user's subjective feelings about the job into specific quantitative values, and using the historical satisfaction score data to predict the future satisfaction, enabling the user to understand the change trend of job satisfaction in advance, comparing the predicted score with the set score threshold, and giving decision-making suggestions corresponding to different score intervals, and more rationally planning the user's career development.

[0036] In the present invention, there is provided a method and system for career guidance based on big data analysis of employment assessment. In this system, in the acquisition unit, web crawlers are used to calculate and collect recruitment position information on employment websites in real time, including position fields, the number of positions, and the number of applicants. At the same time, user data is collected through an online information filling page, including personality, position preference, work experience, and educational background, etc., to ensure the comprehensiveness of data collection. Then, the collected user data and recruitment position information are processed by edge computing devices for data cleaning, format unification, and removal of duplicate information, reducing the usage load of the subsequent cloud server. In the matching unit, a hard filtering module in the cloud server is used to preliminarily screen the recruitment position data according to the rigid conditions set by the user, including location, salary, and position type, eliminating positions that do not meet the conditions and improving the subsequent calculation speed. By quantifying the position fields and user characteristics, and flexibly setting the weights of user personal characteristics according to the individual needs of college students, the matching degree between the qualified position information and the user is calculated, thereby improving the accuracy and personalization of the matching. At the same time, the heat growth rate is calculated through historical and current data, and the heat of position fields with high matching degrees is predicted, which can help college students understand the dynamic change trend of positions more clearly when seeking employment. When the heat growth rate is higher than the set threshold, it indicates that the position heat is on the rise, and it is recommended that students pay priority attention. When the heat growth rate is lower than the set threshold, it indicates that the position heat is on the decline, and it is recommended that students choose carefully. By calculating the position supply-demand ratio to evaluate the position stability, the position demand situation can be intuitively reflected. When the position supply-demand ratio is greater than 1, the position stability is high. When the position supply-demand ratio is less than 1, the competition is fierce and the stability is low. This helps college students understand the position competition situation, and by calculating the change rate based on the real-time and past position supply-demand ratios, the change trend of position demand can be judged, predicting the recession risk and growth rate, and making advance plans. The overall information is plotted into a bar chart, presenting information such as heat prediction, position stability, and supply-demand ratio change rate intuitively, facilitating college students to quickly understand complex data and improving the accuracy and adaptability of career guidance. In the follow-up visit module, regular (semi-monthly) follow-up visits are conducted in multiple dimensions through questionnaires or phone calls, and users assign weights to each dimension according to their own situations, making subsequent analysis and decision-making more in line with individual actual situations and providing a rich data basis. The satisfaction score during employment is calculated based on the scores and weights of each dimension, converting the user's subjective feeling about the job into specific quantitative values, and predicting the future satisfaction using historical satisfaction score data, enabling users to understand the change trend of job satisfaction in advance. The predicted score is compared with the set score threshold, and decision-making suggestions corresponding to different score intervals are given, more rationally planning the user's career development.

[0037] A method for career guidance based on big data analysis of employment assessment includes the following steps: S1: Enter the collection module, obtain the job data of the employment website and collect user data, pre-process the user data and job data, and then transmit them to the cloud server for storage; S2: Enter the matching module, the user sets rigid conditions to preliminarily screen the recruitment data, and then matches the screened recruitment data with the user for similarity, and retains the recruitment data with high matching degree, and performs heat change analysis; S3: Enter the analysis module, calculate the job data of the job that is on the rise and has a high similarity match with the user, analyze the job stability by calculating the job supply-demand ratio, and calculate Risk warning of the rate of change of S4: Enter the display module, integrate the calculated information and draw a bar chart for display; S5: Enter the follow-up module, conduct regular follow-up visits to users through questionnaires or phone calls, calculate the user's satisfaction score while on the job and predict the future satisfaction score, and determine whether to resign based on the prediction results.

[0038] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0039] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and the scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. An employment guidance system based on big data analysis of employment evaluation, characterized in that, The system includes a collection module, a matching module, an analysis module, a display module, and a follow-up visit module; The collection module is used to obtain recruitment position data of employment websites through web crawler technology, and collect user data using an online information filling page. After preprocessing the user data and recruitment position data, it is transmitted to the cloud server for storage; The matching module is used to initially screen the recruitment position data according to the rigid conditions set by the user, calculate the matching degree with the user through similarity calculation after screening, retain the recruitment position data with a high matching degree, and analyze the heat change of the recruitment position data with a high matching degree according to the real-time and historical number of positions; The analysis module is used to evaluate the stability of the position through the recruitment position data, conduct position stability analysis, and issue a risk warning for the stability of the position; The display module is used to integrate the heat prediction information, position stability, and dynamic prediction analysis information of the recruitment positions with a high matching degree through Plotly and draw a bar chart; The follow-up visit module is used to conduct regular follow-up visits to the user's situation through questionnaires or phone calls, calculate the satisfaction score of the user during the job, and predict the satisfaction score of the user. According to the prediction result, it is judged whether to leave the job.

2. The employment guidance system based on big data analysis of employment assessment according to claim 1, characterized in that, The collection module includes a collection unit, a collection unit, a preprocessing unit, and a storage unit; The collection unit is used to obtain recruitment position data of employment websites through web crawler technology. The recruitment position data includes the position field, the number of positions, and the number of applicants; The collection unit collects user data using an online information filling page. The user data includes personality, position preference, work experience, and educational background; The preprocessing unit is used to preprocess the user data and recruitment position data through an edge computing device. The preprocessing includes cleaning, duplicate removal, and format unification; The storage unit is used to store the preprocessed user data and recruitment position data through a cloud server.

3. The employment guidance system based on big data analysis of employment assessment according to claim 2, wherein The matching module includes a screening unit, a matching unit, and a prediction unit; The screening unit is used to initially screen the recruitment position data according to the rigid conditions set by the user through a hard filtering module in the cloud server. The rigid conditions include location, salary, and position type.

4. The employment guidance system based on big data analysis of employment assessment according to claim 3, wherein, The matching unit includes a similarity unit and a setting unit; The similarity unit calculates the matching degree between the position field and the user through weighted cosine similarity based on the position field data of the recruitment position data after initial screening. The calculation formula is as follows: ； Among them, represents the matching degree, represents the number of matching features, represents the weight of the th feature, represents the quantization value of the user on the th feature, represents the quantization value of the job field on the th feature.

5. The employment guidance system based on big data analysis of employment assessment according to claim 4, wherein The setting unit is used to set the matching degree When the matching degree is greater than or equal to 0.85, it represents a job field with a high matching degree.

6. The employment guidance system based on big data analysis of employment assessment according to claim 5, characterized in that, The prediction unit is used to analyze the heat change of the position field with a high matching degree. The calculation steps are as follows: Step 1, based on the position field with a high matching degree in the recruitment position data in the cloud server, select the data of the number of positions in this position field for data smoothing. The calculation formula is as follows: ； Among them, represents the moving average number of positions at the time point, that is, the average value of the number of positions in the recruitment position data of the current week and the previous three weeks, represents the number of positions in the recruitment position data of the week, and represents the average value of the number of positions over 4 weeks; Step 2, conduct heat analysis on the position field with a high matching degree through the current four-week moving average number of positions and the four-week-old moving average number of positions. The calculation formula is as follows: ； Among them, represents the heat growth rate; represents the current four-week moving average number of jobs, represents the four-week-old moving average number of jobs; Among them, when is greater than or equal to 12%, it represents an increase in popularity. When is greater than or equal to -12% and less than or equal to -12%, it represents stable popularity. When is less than or equal to 12%, it represents a decrease in popularity.

7. The employment guidance system based on big data analysis of employment assessment according to claim 1, characterized in that The analysis module includes an evaluation unit and an analysis unit; The evaluation unit calculates the position supply-demand ratio based on the number of positions and the number of applicants in the recruitment position data to analyze the position stability. The calculation formula is as follows: ； When is greater than 1, it indicates a high demand for the position and high job stability. When is less than 1, it indicates fierce competition for the position and low job stability; The analysis unit calculates the change rate based on the job supply-demand ratio this week and the job supply-demand ratio last week. The calculation formula is as follows: ； Among them, when the change rate is less than 10%, it indicates that there is a risk of decline in job demand and a risk of job stability. When the change rate is greater than 10, it indicates that job demand is accelerating and job stability is improving.

8. The employment guidance system based on big data analysis of employment assessment according to claim 1, characterized in that, The display module is used to integrate the heat prediction information, job stability, and change rate in the job fields with high user matching degree through Plotly and draw a bar chart.

9. The employment guidance system based on big data analysis of employment assessment according to claim 1, characterized in that, The return visit module includes a return visit unit, a calculation unit, a future unit, and a judgment unit; The return visit unit is used to conduct regular return visits to user conditions through questionnaires or phone calls. The user conditions include salary and benefits, working environment, career development opportunities, interest in job content, and interpersonal relationships. By scoring multiple dimensions of user conditions, with a full score of 10 points for each dimension and a minimum of 1 point, and at the same time assigning weights to multiple dimensions according to the user himself, and the sum of multiple dimensions is equal to 1; The calculation unit is used to collect the scores and weights of each dimension and calculate the satisfaction score during employment. The calculation formula is as follows: ； Among them, represents the salary and welfare score; represents the work environment score; represents the career development opportunity score; represents the work content interest score, represents the interpersonal relationship score, , , , and represent the weights of salary and welfare, work environment, career development opportunities, work content interest, and interpersonal relationships respectively, and LP represents the satisfaction score; The prediction unit is used to predict the satisfaction score. The prediction formula is: ； Among them, represents the predicted satisfaction score, and represents the satisfaction scores at one and two time periods before time, represents the satisfaction scores at the K time periods before time, where k represents the number of historical data used for calculation; The judgment unit is used to compare the calculated predicted score with the set score threshold to judge whether the user needs to leave the job; If When it is greater than or equal to 8 and less than or equal to 10, it means that the user satisfaction score is high and there is no need to leave the job; If is greater than or equal to 5 and less than or equal to 7, it represents that the user satisfaction score is medium, and there is no need to leave the job. However, it is necessary to analyze the long-term changes in the predicted satisfaction score. If it is in a continuous downward trend, then make an early departure plan; If is less than or equal to 4, it means that the user satisfaction is poor and the user leaves the job.

10. The method of using an employment guidance system based on big data analysis of employment assessment according to any one of claims 1-9, characterized in that, It includes the following steps: S1: Enter the acquisition module. By obtaining the recruitment position data of the employment website and collecting user data, the user data and recruitment position data are preprocessed and then transmitted to the cloud server for storage; S2: Enter the matching module. The user sets rigid conditions to initially screen the recruitment position data, perform similarity matching between the screened recruitment position data and the user, and retain the recruitment position data with a high matching degree for heat change analysis; S3: Enter the analysis module to calculate the recruitment position data with rising popularity and high user similarity. Analyze the stability of the position by calculating the supply-demand ratio of the position, and calculate the change rate for risk warning; S4: Enter the display module. By integrating the calculated multiple pieces of information and drawing a bar chart for display; S5: Enter the return visit module. Conduct regular return visits to user conditions through questionnaires or phone calls, calculate the satisfaction score during the user's employment, and predict the future satisfaction score, and judge whether to leave the job according to the prediction result.

Images