A method and system for dynamic analysis of recruitment post shortage degree based on evaluation model

Abstract

This invention relates to the field of human resource management technology, specifically a method and system for dynamic analysis of job shortage based on an evaluation model. The method includes: acquiring an initial recruitment dataset based on a preset collection time interval; integrating the initial recruitment dataset to obtain multiple target recruitment data sets; using the multiple target recruitment data sets to obtain multiple quantitative job node sets; acquiring multiple reference job nodes corresponding to multiple reference recruitment data sets; using the multiple reference job nodes and the multiple quantitative job node sets to obtain multiple job shortage evaluation values; identifying a sequence of job shortages based on the multiple job shortage evaluation values; and sending the sequence of job shortages to the initiator of a job analysis command, thereby achieving dynamic analysis of job shortage. This invention can improve the accuracy of analyzing job shortage.

Description

Technical Field

[0001] This invention relates to the field of human resource management technology, and in particular to a method and system for dynamic analysis of job shortage based on an evaluation model. Background Technology

[0002] With rapid economic development, enterprises face fierce market competition and ever-changing business demands. Effective and timely recruitment, along with finding talent that matches the job requirements, is essential for the healthy development of enterprises. Therefore, accurately analyzing the shortage of job openings has become a pressing issue.

[0003] Currently, traditional job posting analysis methods mainly rely on historical data and subjective judgment to assess and monitor job shortages.

[0004] While the methods described above can analyze job postings, they suffer from inaccuracies in analyzing the scarcity of these positions. Therefore, accurately analyzing the scarcity of job postings has become a pressing issue. Summary of the Invention

[0005] This invention provides a method for dynamic analysis of job shortage based on an evaluation model and a computer-readable storage medium, the main purpose of which is to improve the accuracy of job shortage analysis.

[0006] To achieve the above objectives, this invention provides a dynamic analysis method for the shortage of job positions based on an evaluation model, comprising:

[0007] The system receives job analysis instructions and confirms the job analysis system based on these instructions. The job analysis system includes a recruitment data collection unit, a recruitment data cleaning unit, a job requirement assessment unit, a job compensation assessment unit, a job analysis unit, and a result feedback unit.

[0008] Based on a preset collection time interval, an initial recruitment dataset is obtained using a recruitment data collection unit. The initial recruitment dataset includes multiple initial recruitment data sets, each containing the posting unit, posting unit address, posting position, posting industry, posting time, recruitment time interval, job requirements text, and job benefits text. The initial recruitment dataset is then integrated using a recruitment data cleaning unit to obtain multiple target recruitment data sets.

[0009] Perform the following operation for each of the multiple target recruitment data groups:

[0010] A quantitative job node set is obtained based on the job demand assessment unit, the job compensation assessment unit, and the target recruitment data group. The quantitative job node set is then summarized to obtain multiple quantitative job node sets. Each quantitative job node set includes multiple quantitative job nodes, and each quantitative job node includes a job evaluation value and a compensation evaluation value. Each quantitative job node corresponds one-to-one with the target recruitment data in the target recruitment data group.

[0011] Confirm receipt of job parsing instruction from job parsing unit, parse the job parsing instruction to obtain multiple reference recruitment data, and obtain multiple reference job nodes based on the multiple reference recruitment data;

[0012] Multiple job shortage assessment values ​​are obtained by using the multiple reference job nodes and multiple quantitative job node sets. Based on the multiple job shortage assessment values, a shortage job sequence group is identified. The shortage job sequence group is sent to the job analysis instruction initiator by the result feedback unit to realize dynamic analysis of the shortage of recruitment positions.

[0013] Optionally, the initial recruitment dataset is integrated using the recruitment data cleaning unit to obtain multiple target recruitment data sets, including:

[0014] Confirm receipt of data cleaning instructions from the recruitment data cleaning unit, parse the data cleaning instructions to obtain a classification time gradient set, wherein the classification time gradient set includes multiple classification time gradients, and use the classification time gradient set and the collection time interval to obtain a classification time range group, wherein the classification time range group includes multiple classification time ranges.

[0015] Perform the following operation for each of the multiple category time ranges:

[0016] The initial recruitment data in the initial recruitment dataset are summarized based on the classification time range, the industry in which the data is posted, and the job posting, to obtain a classification recruitment dataset sequence. The classification recruitment dataset sequence includes multiple classification recruitment datasets, and each classification recruitment dataset includes multiple classification recruitment data. The job posting time corresponding to the classification recruitment data is within the classification time range.

[0017] Perform the following operation on each category of the recruitment dataset in the sequence of categorized recruitment datasets:

[0018] The number of categorized recruitment data in the categorized recruitment dataset is counted to obtain the number of categorized recruitments. Recruitment time interval sets are extracted from the categorized recruitment dataset, and the recruitment time interval sets are clustered to obtain one or more target recruitment time interval sets.

[0019] For each of one or more target recruitment time interval sets, perform the following operation:

[0020] The number of target recruitment time intervals in the target recruitment time interval set is counted to obtain the target recruitment quantity. The ratio of the target recruitment quantity to the category recruitment quantity is calculated to obtain the initial recruitment ratio. The initial recruitment ratio is compared with the preset reference recruitment ratio. If the initial recruitment ratio is less than or equal to the reference recruitment ratio, the target recruitment time interval set is removed from one or more target recruitment time interval sets.

[0021] Summarize the retained target recruitment time interval sets to obtain one or more categorized recruitment time interval sets, and use the one or more categorized recruitment time interval sets to obtain multiple target recruitment data groups.

[0022] Optionally, obtaining multiple target recruitment data sets using the one or more categorized recruitment time interval sets includes:

[0023] For each of one or more category-specific recruitment time interval sets, perform the following operation:

[0024] Count the number of recruitment time intervals in each category within one or more category recruitment time interval sets to obtain a category recruitment quantity set, where the category recruitment quantity set includes one or more category recruitment quantities;

[0025] The recruitment time is calculated and analyzed using the aforementioned categorized recruitment quantity set, and the calculation formula is as follows:

[0026]

[0027] in, This indicates the analysis of recruitment time. Indicates the number of job postings categorized by category. Number of job openings in each category Indicates the number of job postings categorized by category. Number of job openings in each category This indicates that the number of recruitment positions is concentrated in a specific category. Number of job openings in each category Indicates the first The average of the time intervals between different categories of job postings, corresponding to the number of job postings in each category. Indicates the first The total number of job postings in each category corresponds to the total number of job posting time intervals for each category. Recruitment time intervals for each category Indicates the first The first category of recruitment time intervals corresponding to the number of recruitments in each category. Recruitment time intervals for each category;

[0028] By summarizing the recruitment time analysis, a recruitment time analysis set is obtained. The recruitment time series is then obtained by analyzing the time range corresponding to the recruitment time analysis set.

[0029] Using a preset sliding step size, a preset first sliding order, and a pre-constructed sliding window, the recruitment time group sequence is extracted from the recruitment time series analysis. The recruitment time group sequence includes multiple recruitment time groups.

[0030] Multiple target recruitment data sets are obtained by analyzing the recruitment time series.

[0031] Optionally, the step of obtaining multiple target recruitment data sets using the analyzed recruitment time series includes:

[0032] The first recruitment time group is extracted sequentially from the analyzed recruitment time group sequence, and the following operations are performed on the extracted first recruitment time group:

[0033] The mean and variance of recruitment time are obtained based on the first recruitment time group, where the mean and variance of recruitment time are the mean and variance of the recruitment time analyzed in the first recruitment time group, respectively.

[0034] By correlating the mean and variance of the recruitment time, analysis nodes are obtained. The analysis nodes are then summarized to obtain a set of analysis nodes. The analysis node set is then used to obtain a sequence of analysis nodes.

[0035] The first analysis node is extracted sequentially from the analysis node sequence, and the following operation is performed on each extracted first analysis node:

[0036] Using the first analysis node, a second analysis node is identified in the analysis node sequence. The second analysis node is adjacent to the first analysis node but lags behind it. The evaluation node difference is calculated using the first and second analysis nodes, as shown in the following formula:

[0037]

[0038] in, Indicates the difference between the evaluation nodes. Let represent the mean and variance of the recruitment time corresponding to the first analysis node, respectively. These represent the mean and variance of recruitment time corresponding to the second analysis node, respectively.

[0039] Compare the evaluation node difference with a preset evaluation node threshold. If the evaluation node difference is less than or equal to the evaluation node threshold, then the second analysis node is taken as the first analysis node, and the process returns to the step of using the first analysis node to identify the second analysis node in the analysis node sequence, until the evaluation node difference is greater than the evaluation node threshold.

[0040] If the difference between the evaluation nodes is greater than the evaluation node threshold, the second analysis node is removed from the analysis node sequence to obtain an updated node sequence. The updated node sequence is then used as the analysis node sequence, and the step of identifying the second analysis node in the analysis node sequence using the first analysis node is returned. This process continues until all analysis nodes in the analysis node sequence have been extracted. Then, the extracted first analysis node is used to extract the target analysis time group from the recruitment time group sequence. The target analysis time group includes multiple target analysis times. The number of target analysis times in the target analysis time group is counted to obtain the target analysis quantity.

[0041] Compare the target number of analyses with the preset analysis number threshold. If the target number of analyses is greater than or equal to the analysis number threshold, then the multiple initial recruitment data corresponding to the target analysis time group will be used as the target recruitment data group.

[0042] Otherwise, the optimized time interval is calculated using the target number of analyses, the analysis number threshold, and the collection time interval. The optimized time interval is used as the collection time interval. The steps of obtaining the initial recruitment dataset using the recruitment data collection unit based on the preset collection time interval are returned until the target number of analyses is greater than or equal to the analysis number threshold.

[0043] By aggregating the target recruitment data groups, multiple target recruitment data groups are obtained.

[0044] Optionally, the optimization time interval is calculated using the target number of analyses, the analysis number threshold, and the collection time interval, and the calculation formula is as follows:

[0045]

[0046] in, Indicates the optimization time interval. Indicates the collection time interval. Indicates the threshold for the number of analyses. Indicates the number of target analyses. These are preset coefficients.

[0047] Optionally, the step of obtaining a quantitative set of job nodes based on job requirement assessment units, job compensation assessment units, and target recruitment data groups includes:

[0048] The system receives job requirement assessment instructions from the job requirement assessment unit and job benefit assessment instructions from the job benefit assessment unit, and parses the job requirement assessment instructions and job benefit assessment instructions to obtain a set of job requirement assessment indicators and a set of job benefit assessment indicators.

[0049] Perform the following operations on each target recruitment data point in the target recruitment data group:

[0050] Using the address of the publishing unit corresponding to the target recruitment data, the target compensation evaluation indicator set is retrieved from the job compensation evaluation indicator set. The job demand evaluation indicator set, the target compensation evaluation indicator set, the job demand text corresponding to the target recruitment data, the job compensation text corresponding to the target recruitment data, the pre-built analytic hierarchy process, and the pre-built data analysis method are used to obtain the job evaluation value and compensation evaluation value.

[0051] This involves using a set of job requirement assessment indicators, a set of target compensation assessment indicators, job requirement texts corresponding to target recruitment data, job compensation texts corresponding to target recruitment data, pre-built analytic hierarchy process (AHP), and pre-built data analysis methods to obtain job evaluation values ​​and compensation assessment values, including:

[0052] The job compensation scale value set is obtained by using a pre-constructed scaling method and job compensation text. The job evaluation weight value set is obtained based on the analytic hierarchy process, the target compensation evaluation index set, and the job compensation text. The job compensation scale value set includes one or more job compensation scale values, and the job evaluation weight value set includes one or more job evaluation weight values.

[0053] The set of job analysis weight values ​​is obtained based on the data analysis method and the job compensation text. The set of job analysis weight values ​​includes one or more job analysis weight values, and the job compensation scale value, job evaluation weight value and job analysis weight value correspond one-to-one.

[0054] The job evaluation node set is obtained based on the job compensation scale value set, the job evaluation weight value set, and the job analysis weight value set. The job evaluation node set includes multiple job evaluation nodes, as shown below:

[0055]

[0056] in, Indicates the first stage of the job evaluation process. Each job evaluation stage This indicates the first position in the set of job evaluation weight values. Each job evaluation weight value This indicates the first value in the set of job analysis weight values. Analyze the weight values ​​for each job position. This indicates the first value in the set of job compensation scale values. Salary scale value for each position;

[0057] The compensation assessment value is calculated based on the job assessment nodes in the job assessment node set. The calculation formula is as follows:

[0058]

[0059] in, This indicates the assessment value of the compensation. This indicates that the job evaluation nodes are centrally shared. Each job evaluation stage;

[0060] Job evaluation values ​​are obtained based on scaling methods, job requirement texts, job requirement evaluation indicator sets, analytic hierarchy process, and data analysis methods.

[0061] By associating the job evaluation value and the compensation evaluation value, quantitative job nodes are obtained. By summarizing the quantitative job nodes, a set of quantitative job nodes is obtained.

[0062] Optionally, obtaining multiple job shortage assessment values ​​using the multiple reference job nodes and multiple quantified job node sets includes:

[0063] Based on the job postings and the industry they belong to, multiple reference job posting nodes are divided to obtain one or more target search node sets. Each target search node set includes multiple target search nodes, and the job postings and industries corresponding to the target search nodes are all the same.

[0064] For each of one or more target retrieval node sets, perform the following operation:

[0065] By utilizing the job postings and industries corresponding to the target retrieval node set, the target job posting node set can be retrieved from multiple quantitative job posting node sets;

[0066] For each target retrieval node in the target retrieval node set, perform the following operations:

[0067] Optimized search nodes are obtained based on the target search node and the corresponding reference recruitment data. The optimized search nodes are shown below:

[0068]

[0069] in, This indicates optimization of the search node. This indicates the address of the posting organization corresponding to the reference recruitment data. These represent longitude and latitude, respectively. These represent the reference job evaluation value and reference salary evaluation value corresponding to the target search node, respectively.

[0070] The optimized job node set is obtained by using the target job node set. The optimized search nodes and the optimized job node set are summarized to obtain the search job node set. The search job node set is clustered to obtain one or more optimized search node sets. The evaluation search node set is identified from the one or more optimized search node sets. The evaluation search node set is the optimized search node set that includes the optimized search nodes.

[0071] The job shortage assessment value is obtained by retrieving the set of evaluation nodes, and the job shortage assessment values ​​are summarized to obtain multiple job shortage assessment values.

[0072] Optionally, obtaining the job shortage assessment value based on the evaluation retrieval node set includes:

[0073] The maximum recruitment time, job evaluation scope, and compensation evaluation scope are retrieved from the evaluation and retrieval nodes.

[0074] The average evaluation time is obtained by using the optimized job node set corresponding to the evaluation retrieval node set. The reference job evaluation value and reference compensation evaluation value corresponding to the optimized retrieval node are normalized by using the job evaluation range and the compensation evaluation range respectively, so as to obtain the normalized job evaluation value and normalized compensation evaluation value. The job evaluation recruitment time is calculated by using the normalized job evaluation value, the normalized compensation evaluation value and the average evaluation time. If the job evaluation recruitment time is greater than the maximum recruitment time, the absolute difference between the maximum recruitment time and the job evaluation recruitment time is calculated to obtain the job shortage evaluation value.

[0075] Optionally, the calculation of the job evaluation recruitment time using the normalized job evaluation value, the normalized compensation evaluation value, and the average evaluation time is shown in the following formula:

[0076]

[0077] in, Indicates the recruitment time for job evaluation. This represents the preset coefficient. These represent the normalized job evaluation value and the normalized compensation evaluation value, respectively. This represents the average value over the evaluation period.

[0078] To achieve the above objectives, the present invention also provides a dynamic analysis system for the shortage of job positions based on an evaluation model, comprising:

[0079] The job analysis preparation module is used to receive job analysis instructions and confirm the job analysis system based on the job analysis instructions. The job analysis system includes a recruitment data collection unit, a recruitment data cleaning unit, a job requirement assessment unit, a job compensation assessment unit, a job analysis unit, and a result feedback unit.

[0080] The initial job data integration module is used to acquire an initial job dataset based on a preset collection time interval using the recruitment data collection unit. The initial job dataset includes multiple initial job data, and each initial job data includes the posting unit, posting unit address, posting job, posting industry, job posting time, recruitment time interval, job requirements text, and job benefits text. The recruitment data cleaning unit integrates the initial job dataset to obtain multiple target job data groups.

[0081] Perform the following operation for each of the multiple target recruitment data groups:

[0082] A quantitative job node set is obtained based on the job demand assessment unit, the job compensation assessment unit, and the target recruitment data group. The quantitative job node set is then summarized to obtain multiple quantitative job node sets. Each quantitative job node set includes multiple quantitative job nodes, and each quantitative job node includes a job evaluation value and a compensation evaluation value. Each quantitative job node corresponds one-to-one with the target recruitment data in the target recruitment data group.

[0083] The job data confirmation module is used to confirm receipt of job parsing instructions from the job parsing unit, parse the job parsing instructions to obtain multiple reference recruitment data, and obtain multiple reference job nodes based on the multiple reference recruitment data;

[0084] The job shortage analysis module is used to obtain multiple job shortage assessment values ​​by using multiple reference job nodes and multiple quantitative job node sets, identify a shortage job sequence group based on the multiple job shortage assessment values, and send the shortage job sequence group to the job analysis command initiator using the result feedback unit to realize dynamic analysis of the job shortage of recruitment positions.

[0085] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0086] A memory that stores at least one instruction; and a processor that executes the instructions stored in the memory to implement the above-described dynamic analysis method for job shortage based on an evaluation model.

[0087] To address the aforementioned issues, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned method for dynamic analysis of job shortage based on an evaluation model.

[0088] To address the problems described in the background art, this invention, based on a preset collection time interval, utilizes a recruitment data collection unit to acquire an initial recruitment dataset. This initial recruitment dataset includes multiple initial recruitment data sets, each containing information such as the posting organization, address, job title, industry, posting time, recruitment time interval, job requirements text, and salary / benefit text. A recruitment data cleaning unit then integrates these initial recruitment datasets to obtain multiple target recruitment data sets. Therefore, this invention integrates the initial recruitment data from multiple dimensions before considering any shortage analysis of the job postings. Furthermore, to ensure the credibility of the integrated initial recruitment data, a dynamic update of the collection time interval is adopted to improve the credibility of the acquired target recruitment data set. This, in turn, enhances the accuracy of using the target recruitment data set to analyze the shortage of reference recruitment data. Based on the job requirement assessment unit, job compensation assessment unit, and target recruitment data set, a quantified job node set is obtained. This quantified job node set is then aggregated to obtain multiple quantified job node sets. Thus, this invention quantifies the job requirement and compensation text in the target recruitment data by combining its features, thereby improving the accuracy of the quantified target recruitment data. Therefore, this invention can improve the accuracy of analyzing the shortage of recruitment positions. Attached Figure Description

[0089] Figure 1 This is a flowchart illustrating a method for dynamic analysis of job shortage based on an evaluation model, as provided in an embodiment of the present invention.

[0090] Figure 2 A functional block diagram of a dynamic analysis system for job shortage based on an evaluation model provided in an embodiment of the present invention;

[0091] Figure 3 This is a schematic diagram of the structure of an electronic device that implements the dynamic analysis method for job shortage based on the evaluation model, according to an embodiment of the present invention.

[0092] Explanation of reference numerals in the attached figures:

[0093] 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0094] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0095] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0096] This application provides a method for dynamically analyzing the shortage of job postings based on an evaluation model. The executing entity of this method includes, but is not limited to, at least one electronic device that can be configured to execute the method provided in this application, such as a server or a terminal. In other words, the method can be executed by software or hardware installed on a terminal device or server device, and the software may be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0097] Reference Figure 1 The diagram shown is a flowchart illustrating a method for dynamic analysis of job shortage based on an evaluation model, according to an embodiment of the present invention. In this embodiment, the method for dynamic analysis of job shortage based on an evaluation model includes:

[0098] S1. Receive job analysis instructions, and confirm the job analysis system based on the job analysis instructions. The job analysis system includes a recruitment data collection unit, a recruitment data cleaning unit, a job requirement assessment unit, a job compensation assessment unit, a job analysis unit, and a result feedback unit.

[0099] It should be explained that the job analysis instruction refers to the instruction issued to assess the scarcity of a job. The job analysis system refers to an APP or mini-program used to assess the scarcity of a job, and the job analysis system includes a recruitment data collection unit, a recruitment data cleaning unit, a job requirement assessment unit, a job compensation assessment unit, a job analysis unit, and a result feedback unit.

[0100] For example, to better manage talent allocation, job analysts issue job analysis instructions, which are then confirmed by the job analysis system. The system determines the scarcity of available positions, allowing the analysts to better publish or modify job postings and facilitate talent recruitment. Here, job analysts include, but are not limited to, recruitment personnel. Therefore, the main objective of this invention is to improve the accuracy of dynamic analysis of job scarcity.

[0101] S2. Based on a preset collection time interval, an initial recruitment dataset is obtained using a recruitment data collection unit. The initial recruitment dataset includes multiple initial recruitment data sets, which include the posting unit, posting unit address, posting position, posting industry, posting time, recruitment time interval, job requirements text, and job benefits text. The initial recruitment dataset is then integrated using a recruitment data cleaning unit to obtain multiple target recruitment data sets.

[0102] It should be explained that the initial recruitment dataset can be obtained from publicly available recruitment databases. "Posting Unit" refers to the organization that posts the job openings. Examples include companies, schools, and hospitals. "Posting Unit Address" refers to the address of the posting unit; for example, when the posting unit is a hospital, the posting unit address is the hospital's actual geographical location. "Posting Industry" refers to the industry sector in which the job posting is located, such as forestry, automotive, and banking. Optionally, the posting industry can be obtained through the National Economic Industry Classification Standard. Generally, different industries have different talent reserves and different talent requirements; therefore, considering the posting industry in this invention can improve the accuracy of analyzing job shortages. "Job Requirements Text" refers to a description of the skills required for the job. For example, five years of work experience is required. "Job Benefits Text" refers to the benefits offered to applicants for the job. For example, the salary. "Recruitment Interval" refers to the time interval between posting a job and successfully recruiting a candidate. For example, if a job is posted on March 1st and a candidate is successfully recruited on April 1st, the recruitment interval for this job is one month. Generally speaking, when a suitable candidate has not yet been recruited for a position, the recruitment time interval can be considered nonexistent. The collection time interval is a numerical value used to ensure the timeliness of the collected data, and it can be set manually. For example, setting the collection time interval to 6 months indicates that the data from the previous 6 months, starting from the current time, serves as the initial recruitment dataset. The job posting time refers to the time when a job posting is published.

[0103] Understandably, the initial recruitment dataset is integrated using the recruitment data cleaning unit to obtain multiple target recruitment data sets, including:

[0104] Confirm receipt of data cleaning instructions from the recruitment data cleaning unit, parse the data cleaning instructions to obtain a classification time gradient set, wherein the classification time gradient set includes multiple classification time gradients, and use the classification time gradient set and the collection time interval to obtain a classification time range group, wherein the classification time range group includes multiple classification time ranges.

[0105] Perform the following operation for each of the multiple category time ranges:

[0106] The initial recruitment data in the initial recruitment dataset are summarized based on the classification time range, the industry in which the data is posted, and the job posting, to obtain a classification recruitment dataset sequence. The classification recruitment dataset sequence includes multiple classification recruitment datasets, and each classification recruitment dataset includes multiple classification recruitment data. The job posting time corresponding to the classification recruitment data is within the classification time range.

[0107] Perform the following operation on each category of the recruitment dataset in the sequence of categorized recruitment datasets:

[0108] The number of categorized recruitment data in the categorized recruitment dataset is counted to obtain the number of categorized recruitments. Recruitment time interval sets are extracted from the categorized recruitment dataset, and the recruitment time interval sets are clustered to obtain one or more target recruitment time interval sets.

[0109] For each of one or more target recruitment time interval sets, perform the following operation:

[0110] The number of target recruitment time intervals in the target recruitment time interval set is counted to obtain the target recruitment quantity. The ratio of the target recruitment quantity to the category recruitment quantity is calculated to obtain the initial recruitment ratio. The initial recruitment ratio is compared with the preset reference recruitment ratio. If the initial recruitment ratio is less than or equal to the reference recruitment ratio, the target recruitment time interval set is removed from one or more target recruitment time interval sets.

[0111] Summarize the retained target recruitment time interval sets to obtain one or more categorized recruitment time interval sets, and use the one or more categorized recruitment time interval sets to obtain multiple target recruitment data groups.

[0112] It should be noted that the classification time gradient is a ratio used to divide the collection time interval. The classification time range refers to the range formed by the divided time points after the collection time interval is divided using the classification time gradient. A classification time range group refers to a set of classification time ranges. For example, if the classification time gradient set includes 5 classification time gradients, and these 5 gradients are 0.2, 0.4, 0.6, 0.8, and 1, and the collection time interval is 10 months, then the classification time range groups obtained using the classification time gradient set and the collection time interval are: 0 to 2, 2 to 4, 4 to 6, 6 to 8, and 8 to 10. Here, 0 to 2 can refer to the interval from the current time, i.e., within two months before the current time. The initial recruitment data in the initial recruitment dataset is aggregated based on the classification time range, industry, and job posting, resulting in a sequence of categorized recruitment datasets. This sequence involves: aggregating the initial recruitment data in the initial recruitment dataset based on the classification time range, industry, and job posting, resulting in multiple categorized recruitment datasets; sorting the categorized recruitment datasets according to their corresponding time ranges from earliest to latest, to obtain the categorized recruitment dataset sequence. In this sequence, the industries and job postings corresponding to the categorized recruitment data in each dataset are identical, and the posting times for the corresponding job postings all fall within their respective classification time ranges. A job posting refers to a position requiring recruitment, such as a sales position.

[0113] Understandably, a recruitment time interval set refers to the collection of recruitment time intervals corresponding to categorized recruitment data in a categorized recruitment dataset. The purpose of clustering this set is to clarify the time required to recruit talent for specific positions within a specific industry, thereby improving the accuracy of analysis on in-demand positions. Optionally, k-means clustering can be used to cluster the recruitment time intervals within the set; other techniques can achieve the same effect. For example, using k-means clustering to cluster the recruitment time interval set yields three clusters, where the recruitment time intervals included in each cluster constitute a target recruitment time interval set.

[0114] It should be explained that obtaining multiple target recruitment data groups using the one or more classified recruitment time interval sets includes:

[0115] For each of one or more category-specific recruitment time interval sets, perform the following operation:

[0116] Count the number of recruitment time intervals in each category within one or more category recruitment time interval sets to obtain a category recruitment quantity set, where the category recruitment quantity set includes one or more category recruitment quantities;

[0117] The recruitment time is calculated and analyzed using the aforementioned categorized recruitment quantity set, and the calculation formula is as follows:

[0118]

[0119] in, This indicates the analysis of recruitment time. Indicates the number of job postings categorized by category. Number of job openings in each category Indicates the number of job postings categorized by category. Number of job openings in each category This indicates that the number of recruitment positions is concentrated in a specific category. Number of job openings in each category Indicates the first The average of the time intervals between different categories of job postings, corresponding to the number of job postings in each category. Indicates the first The total number of job postings in each category corresponds to the total number of job posting time intervals for each category. Recruitment time intervals for each category Indicates the first The first category of recruitment time intervals corresponding to the number of recruitments in each category. Recruitment time intervals for each category;

[0120] By summarizing the recruitment time analysis, a recruitment time analysis set is obtained. The recruitment time series is then obtained by analyzing the time range corresponding to the recruitment time analysis set.

[0121] Using a preset sliding step size, a preset first sliding order, and a pre-constructed sliding window, the recruitment time group sequence is extracted from the recruitment time series analysis. The recruitment time group sequence includes multiple recruitment time groups.

[0122] Multiple target recruitment data sets are obtained by analyzing the recruitment time series.

[0123] Understandably, in this invention, the proportion of the number of recruitment positions in each category to the total number of recruitment positions in each category is used as a weight value. The time intervals of recruitment positions that meet the majority of criteria are given a larger weight to improve the accuracy of the obtained recruitment time analysis. The sliding window refers to a fixed window of a certain size. The first sliding order refers to the order from latest to earliest time, starting from the current time. For example, sorting the recruitment time sets in the order from earliest to latest time yields the recruitment time sequence, which includes: 3, 4, 5, 6, 10, 11, 12, and 13. Here, 3, 4, 5, 6, 10, 11, 12, and 13 all represent recruitment times. The sliding window size is 3, and the sliding step size is 1. The recruitment time group sequences that can be extracted from the recruitment time sequence are: (13, 12, 11), (12, 11, 10), ..., (5, 4, 3).

[0124] It should be explained that the process of obtaining multiple target recruitment data sets by analyzing the recruitment time series includes:

[0125] The first recruitment time group is extracted sequentially from the analyzed recruitment time group sequence, and the following operations are performed on the extracted first recruitment time group:

[0126] The mean and variance of recruitment time are obtained based on the first recruitment time group, where the mean and variance of recruitment time are the mean and variance of the recruitment time analyzed in the first recruitment time group, respectively.

[0127] By correlating the mean and variance of the recruitment time, analysis nodes are obtained. The analysis nodes are then summarized to obtain a set of analysis nodes. The analysis node set is then used to obtain a sequence of analysis nodes.

[0128] The first analysis node is extracted sequentially from the analysis node sequence, and the following operation is performed on each extracted first analysis node:

[0129] Using the first analysis node, a second analysis node is identified in the analysis node sequence. The second analysis node is adjacent to the first analysis node but lags behind it. The evaluation node difference is calculated using the first and second analysis nodes, as shown in the following formula:

[0130]

[0131] in, Indicates the difference between the evaluation nodes. Let represent the mean and variance of the recruitment time corresponding to the first analysis node, respectively. These represent the mean and variance of recruitment time corresponding to the second analysis node, respectively.

[0132] Compare the evaluation node difference with a preset evaluation node threshold. If the evaluation node difference is less than or equal to the evaluation node threshold, then the second analysis node is taken as the first analysis node, and the process returns to the step of using the first analysis node to identify the second analysis node in the analysis node sequence, until the evaluation node difference is greater than the evaluation node threshold.

[0133] If the difference between the evaluation nodes is greater than the evaluation node threshold, the second analysis node is removed from the analysis node sequence to obtain an updated node sequence. The updated node sequence is then used as the analysis node sequence, and the step of identifying the second analysis node in the analysis node sequence using the first analysis node is returned. This process continues until all analysis nodes in the analysis node sequence have been extracted. Then, the extracted first analysis node is used to extract the target analysis time group from the recruitment time group sequence. The target analysis time group includes multiple target analysis times. The number of target analysis times in the target analysis time group is counted to obtain the target analysis quantity.

[0134] Compare the target number of analyses with the preset analysis number threshold. If the target number of analyses is greater than or equal to the analysis number threshold, then the multiple initial recruitment data corresponding to the target analysis time group will be used as the target recruitment data group.

[0135] Otherwise, the optimized time interval is calculated using the target number of analyses, the analysis number threshold, and the collection time interval. The optimized time interval is used as the collection time interval. The steps of obtaining the initial recruitment dataset using the recruitment data collection unit based on the preset collection time interval are returned until the target number of analyses is greater than or equal to the analysis number threshold.

[0136] By aggregating the target recruitment data groups, multiple target recruitment data groups are obtained.

[0137] It should be understood that when the difference between evaluation nodes is less than or equal to the evaluation node threshold, it indicates that the difference between the recruitment time corresponding to the second analysis node and the first analysis node is small, meaning that the recruitment time corresponding to the second analysis node also has reference value. The method for obtaining the analysis node sequence is the same as the method for obtaining the recruitment time group sequence, and will not be repeated here. The analysis quantity threshold can be obtained manually, and the purpose of setting the analysis quantity threshold is to ensure the credibility of the target recruitment data in the obtained target recruitment data group. Analysis nodes include the recruitment time mean and recruitment time variance. The first analysis node refers to the analysis node extracted from the analysis node sequence.

[0138] It is understandable that when all the analysis nodes in the analysis node sequence are extracted, it means that all the analysis nodes in the analysis node sequence participate in the calculation. In this invention, the first analysis node extracted is the last analysis node in the analysis node sequence that satisfies the evaluation node difference being less than or equal to the evaluation node threshold. Here, using the extracted first analysis node to extract the target analysis time group in the analysis recruitment time group sequence means: extracting and summarizing the analysis recruitment time corresponding to each first analysis node in the analysis recruitment time group sequence that satisfies the evaluation node difference being less than or equal to the evaluation node threshold, and the last analysis recruitment time extracted in the analysis recruitment time group sequence is the analysis recruitment time in the extracted first analysis node.

[0139] It should be explained that the calculation of the optimization time interval using the target number of analyses, the analysis number threshold, and the collection time interval is as follows:

[0140]

[0141] in, Indicates the optimization time interval. Indicates the collection time interval. Indicates the threshold for the number of analyses. Indicates the number of target analyses. These are preset coefficients.

[0142] Understandably, the purpose of calculating the optimization time interval here is to expand the time dimension of the initial recruitment dataset that can be obtained, so as to obtain more initial recruitment data and improve the credibility of the target recruitment data set. Optionally, the coefficient used to calculate the optimization time interval can be set manually, i.e., the preset coefficient. For example, if the collection time interval is 3 months, the analysis quantity threshold is 50, the target analysis quantity is 40, and the preset coefficient is 2, then the optimization time interval calculated using the collection time interval is 7.5, indicating that the acquisition time range of the initial recruitment dataset is expanded from the first 3 months to the first 7.5 months, so as to obtain more initial recruitment data.

[0143] S3. Based on the job requirement assessment unit, job compensation assessment unit and target recruitment data group, obtain a quantitative job node set, summarize the quantitative job node set to obtain multiple quantitative job node sets, wherein the quantitative job node set includes multiple quantitative job nodes, and the quantitative job node includes job evaluation value and compensation evaluation value, and the quantitative job node corresponds one-to-one with the target recruitment data in the target recruitment data group.

[0144] It should be explained that the acquisition of a quantitative set of job nodes based on job requirement assessment units, job compensation assessment units, and target recruitment data groups includes:

[0145] The system receives job requirement assessment instructions from the job requirement assessment unit and job benefit assessment instructions from the job benefit assessment unit, and parses the job requirement assessment instructions and job benefit assessment instructions to obtain a set of job requirement assessment indicators and a set of job benefit assessment indicators.

[0146] Perform the following operations on each target recruitment data point in the target recruitment data group:

[0147] Using the address of the publishing unit corresponding to the target recruitment data, the target compensation evaluation indicator set is retrieved from the job compensation evaluation indicator set. The job demand evaluation indicator set, the target compensation evaluation indicator set, the job demand text corresponding to the target recruitment data, the job compensation text corresponding to the target recruitment data, the pre-built analytic hierarchy process, and the pre-built data analysis method are used to obtain the job evaluation value and compensation evaluation value.

[0148] This involves using a set of job requirement assessment indicators, a set of target compensation assessment indicators, job requirement texts corresponding to target recruitment data, job compensation texts corresponding to target recruitment data, pre-built analytic hierarchy process (AHP), and pre-built data analysis methods to obtain job evaluation values ​​and compensation assessment values, including:

[0149] The job compensation scale value set is obtained by using a pre-constructed scaling method and job compensation text. The job evaluation weight value set is obtained based on the analytic hierarchy process, the target compensation evaluation index set, and the job compensation text. The job compensation scale value set includes one or more job compensation scale values, and the job evaluation weight value set includes one or more job evaluation weight values.

[0150] The set of job analysis weight values ​​is obtained based on the data analysis method and the job compensation text. The set of job analysis weight values ​​includes one or more job analysis weight values, and the job compensation scale value, job evaluation weight value and job analysis weight value correspond one-to-one.

[0151] The job evaluation node set is obtained based on the job compensation scale value set, the job evaluation weight value set, and the job analysis weight value set. The job evaluation node set includes multiple job evaluation nodes, as shown below:

[0152]

[0153] in, Indicates the first stage of the job evaluation process. Each job evaluation stage This indicates the first position in the set of job evaluation weight values. Each job evaluation weight value This indicates the first value in the set of job analysis weight values. Analyze the weight values ​​for each job position. This indicates the first value in the set of job compensation scale values. Salary scale value for each position;

[0154] The compensation assessment value is calculated based on the job assessment nodes in the job assessment node set. The calculation formula is as follows:

[0155]

[0156] in, This indicates the assessment value of the compensation. This indicates that the job evaluation nodes are centrally shared. Each job evaluation stage;

[0157] Job evaluation values ​​are obtained based on scaling methods, job requirement texts, job requirement evaluation indicator sets, analytic hierarchy process, and data analysis methods.

[0158] By associating the job evaluation value and the compensation evaluation value, quantitative job nodes are obtained. By summarizing the quantitative job nodes, a set of quantitative job nodes is obtained.

[0159] Understandably, a job requirement assessment indicator set refers to a collection of indicators used to assess job requirements. A job compensation assessment indicator set refers to a collection of indicators used to assess job compensation. Both job requirement assessment indicator sets and job compensation assessment indicator sets can be obtained through pre-defined methods. Generally, the obtained job requirement assessment indicator sets and job compensation assessment indicator sets should be related to the posted positions and industries corresponding to the target recruitment data group. However, special geographical locations may result in special compensation; therefore, different job compensation assessment indicators need to be set based on different geographical locations before setting the job compensation assessment indicator set. For example, when the posting unit address is in a tropical region, there may be high-temperature subsidies, while when the posting unit address is in a cold region, there may be low-temperature subsidies. Therefore, different target compensation assessment indicator sets will exist for different posting unit addresses. Generally, when retrieving the target compensation assessment indicator set from the job compensation assessment indicator set using the posting unit address, it is not necessary to search to the specific address; it is sufficient to search for the region where the posting unit address is located. In this embodiment of the invention, a higher job evaluation value is considered to indicate that the qualifications required for the position are more easily met, and a higher compensation evaluation value is considered to indicate that the compensation for the position is better. Optionally, after setting corresponding job compensation evaluation index sets for different regions, a search is performed in the pre-defined regions using the address of the publishing unit to retrieve the target compensation evaluation index set corresponding to the address of the publishing unit.

[0160] It should be understood that the data analysis method refers to a method capable of assigning weights to job requirement texts. Optionally, ridge regression or linear regression can be used as the data analysis method. Here, the purpose of using the data analysis method is to achieve objective analysis of the job requirement text and job compensation text, so as to obtain the weight value corresponding to each job requirement in the job requirement text. The technique of using linear regression or ridge regression to evaluate job compensation text is existing technology. Generally, when quantifying the characteristics of job compensation text, the data analysis method should be flexibly selected according to the actual data characteristics. When the correlation between job compensation features is low and the sample size is sufficient, linear regression is preferred for weight modeling; while when the features have strong correlation or the sample size is limited, ridge regression is preferred to suppress multicollinearity through L2 regularization, thereby improving model stability and prediction accuracy. By reasonably selecting the regression method, the scientific nature and practicality of the quantification results can be ensured. For example, job compensation text includes text describing bonuses, salaries, benefits, and working hours. Features are extracted from the text describing bonuses, salaries, benefits, and working hours, and linear regression is used to obtain weight values ​​for bonuses, salaries, benefits, and working hours. Here, the weight values ​​refer to job analysis weight values. The technique of obtaining a set of job evaluation weight values ​​based on the analytic hierarchy process (AHP), a target compensation evaluation index set, and job compensation text is existing technology and will not be elaborated here. The job evaluation weight values ​​are obtained by evaluating the text in the job compensation text that represents different compensations using the AHP and the target compensation evaluation index set. Here, the text representing different compensations is the same as the text describing bonuses, salaries, benefits, and working hours mentioned above. Therefore, there is a one-to-one correspondence between the job evaluation weight values ​​and the job analysis weight values.

[0161] It should be explained that scaling the job compensation text using a scaling method facilitates the quantification of job requirements and compensation. The existing technology for scaling job compensation text using this method will not be elaborated upon here. Generally, job compensation texts may contain different texts representing compensation; therefore, a scaling method can be used to scale the texts in the job requirement text that represent different compensation levels. Optionally, a 1-9 scaling method can be used. The job compensation scaling value refers to the scaling value obtained after scaling the job compensation text to represent different compensation levels using a scaling method.

[0162] Furthermore, in this embodiment of the invention, the purpose of combining the job evaluation weight value and the job analysis weight value used to describe the same compensation is to: combine the subjective evaluation weight value (job evaluation weight value) and the objective evaluation weight value (job analysis weight value) to achieve a combination of subjective and objective factors, thereby improving the accuracy of the obtained compensation evaluation value. The method for obtaining the compensation evaluation value is the same as the method for obtaining the job evaluation value, and will not be repeated here.

[0163] S4. Confirm receipt of the job parsing instruction from the job parsing unit, parse the job parsing instruction to obtain multiple reference recruitment data, and obtain multiple reference job nodes based on the multiple reference recruitment data.

[0164] It should be explained that the definition of reference recruitment data is the same as that of initial recruitment data, and will not be repeated here. The difference between reference recruitment data and initial recruitment data is that reference recruitment data refers to the data corresponding to positions for which suitable candidates have not yet been recruited. Therefore, there is no recruitment time interval in reference recruitment data.

[0165] It is understandable that the method for obtaining reference job nodes is the same as that for obtaining quantitative job nodes, and will not be repeated here. Reference job nodes include reference job evaluation values ​​and reference compensation evaluation values.

[0166] S5. Obtain multiple job shortage assessment values ​​using the multiple reference job nodes and multiple quantitative job node sets. Based on the multiple job shortage assessment values, identify a shortage job sequence group. Use the result feedback unit to send the shortage job sequence group to the job analysis instruction initiator to realize dynamic analysis of the shortage of recruitment positions.

[0167] It should be explained that obtaining multiple job shortage assessment values ​​using the multiple reference job nodes and multiple quantified job node sets includes:

[0168] Based on the job postings and the industry they belong to, multiple reference job posting nodes are divided to obtain one or more target search node sets. Each target search node set includes multiple target search nodes, and the job postings and industries corresponding to the target search nodes are all the same.

[0169] For each of one or more target retrieval node sets, perform the following operation:

[0170] By utilizing the job postings and industries corresponding to the target retrieval node set, the target job posting node set can be retrieved from multiple quantitative job posting node sets;

[0171] For each target retrieval node in the target retrieval node set, perform the following operations:

[0172] Optimized search nodes are obtained based on the target search node and the corresponding reference recruitment data. The optimized search nodes are shown below:

[0173]

[0174] in, This indicates optimization of the search node. This indicates the address of the posting organization corresponding to the reference recruitment data. These represent longitude and latitude, respectively. These represent the reference job evaluation value and reference salary evaluation value corresponding to the target search node, respectively.

[0175] The optimized job node set is obtained by using the target job node set. The optimized search nodes and the optimized job node set are summarized to obtain the search job node set. The search job node set is clustered to obtain one or more optimized search node sets. The evaluation search node set is identified from the one or more optimized search node sets. The evaluation search node set is the optimized search node set that includes the optimized search nodes.

[0176] The job shortage assessment value is obtained by retrieving the set of evaluation nodes, and the job shortage assessment values ​​are summarized to obtain multiple job shortage assessment values.

[0177] It is understood that the method for obtaining the optimized job node set is the same as the method for obtaining the optimized search nodes, and will not be repeated here. The method for clustering the search job node set is the same as the method for clustering the recruitment time interval set, and will not be repeated here. The job postings and industries corresponding to the target job nodes in the target job node set are the same as the job postings and industries corresponding to the target search node set.

[0178] Furthermore, the step of obtaining the job shortage assessment value based on the evaluation retrieval node set includes:

[0179] The maximum recruitment time, job evaluation scope, and compensation evaluation scope are retrieved from the evaluation and retrieval nodes.

[0180] The average evaluation time is obtained by using the optimized job node set corresponding to the evaluation retrieval node set. The reference job evaluation value and reference compensation evaluation value corresponding to the optimized retrieval node are normalized by using the job evaluation range and the compensation evaluation range respectively, so as to obtain the normalized job evaluation value and normalized compensation evaluation value. The job evaluation recruitment time is calculated by using the normalized job evaluation value, the normalized compensation evaluation value and the average evaluation time. If the job evaluation recruitment time is greater than the maximum recruitment time, the absolute difference between the maximum recruitment time and the job evaluation recruitment time is calculated to obtain the job shortage evaluation value.

[0181] It should be explained that the maximum recruitment time refers to the maximum recruitment time interval corresponding to the set of evaluation search nodes. The minimum and maximum values ​​corresponding to the job evaluation range are the minimum and maximum job evaluation values ​​corresponding to the set of evaluation search nodes, respectively. The minimum and maximum values ​​corresponding to the compensation evaluation range are the minimum and maximum compensation evaluation values ​​corresponding to the set of evaluation search nodes, respectively. The average evaluation time is the average recruitment time interval corresponding to the set of evaluation search nodes.

[0182] It is understood that the present invention uses the min-max normalization method to normalize the reference job evaluation value and the reference compensation evaluation value, which is existing technology and will not be described in detail here.

[0183] Furthermore, the calculation formula for the job evaluation recruitment time using the normalized job evaluation value, the normalized compensation evaluation value, and the average evaluation time is as follows:

[0184]

[0185] in, Indicates the recruitment time for job evaluation. This represents the preset coefficient. These represent the normalized job evaluation value and the normalized compensation evaluation value, respectively. This represents the average value over the evaluation period.

[0186] Understandably, when calculating the recruitment time for job evaluation, setting a coefficient allows control over the sensitivity of evaluating different job positions to adapt to the needs of different application scenarios. This coefficient can be manually set to assess the scarcity of different job positions. The process of identifying a shortage job sequence group based on the multiple job scarcity assessment values ​​includes: sorting multiple reference recruitment data according to the job scarcity assessment values ​​from largest to smallest to obtain a shortage job sequence; summarizing the shortage job sequences to obtain a shortage job sequence group, where each shortage job sequence corresponds to the same job posting and industry. It is generally understood that there is a one-to-one correspondence between job scarcity assessment values ​​and reference recruitment data; therefore, the job scarcity assessment values ​​can be used to sort the reference recruitment data.

[0187] To address the problems described in the background art, this invention, based on a preset collection time interval, utilizes a recruitment data collection unit to acquire an initial recruitment dataset. This initial recruitment dataset includes multiple initial recruitment data sets, each containing information such as the posting organization, address, job title, industry, posting time, recruitment time interval, job requirements text, and salary / benefit text. A recruitment data cleaning unit then integrates these initial recruitment datasets to obtain multiple target recruitment data sets. Therefore, this invention integrates the initial recruitment data from multiple dimensions before considering any shortage analysis of the job postings. Furthermore, to ensure the credibility of the integrated initial recruitment data, a dynamic update of the collection time interval is adopted to improve the credibility of the acquired target recruitment data set. This, in turn, enhances the accuracy of using the target recruitment data set to analyze the shortage of reference recruitment data. Based on the job requirement assessment unit, job compensation assessment unit, and target recruitment data set, a quantified job node set is obtained. This quantified job node set is then aggregated to obtain multiple quantified job node sets. Thus, this invention quantifies the job requirement and compensation text in the target recruitment data by combining its features, thereby improving the accuracy of the quantified target recruitment data. Therefore, this invention can improve the accuracy of analyzing the shortage of recruitment positions.

[0188] like Figure 2 The diagram shown is a functional block diagram of a dynamic analysis system for job shortage based on an evaluation model provided in an embodiment of the present invention.

[0189] The job shortage dynamic analysis system 100 based on the evaluation model described in this invention can be installed in an electronic device. Depending on the functions implemented, the job shortage dynamic analysis system 100 may include a job analysis preparation module 101, an initial job data integration module 102, an evaluation job data confirmation module 103, and a job shortage analysis module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, stored in the memory of the electronic device.

[0190] The job analysis preparation module 101 is used to receive job analysis instructions and confirm the job analysis system based on the job analysis instructions. The job analysis system includes a recruitment data collection unit, a recruitment data cleaning unit, a job requirement assessment unit, a job compensation assessment unit, a job analysis unit, and a result feedback unit.

[0191] The initial job data integration module 102 is used to acquire an initial recruitment dataset using a recruitment data collection unit based on a preset collection time interval. The initial recruitment dataset includes multiple initial recruitment data, and the initial recruitment data includes the posting unit, posting unit address, posting position, posting industry, posting time, recruitment time interval, job requirement text, and job compensation text. The initial recruitment dataset is integrated using a recruitment data cleaning unit to obtain multiple target recruitment data groups.

[0192] Perform the following operation for each of the multiple target recruitment data groups:

[0193] A quantitative job node set is obtained based on the job demand assessment unit, the job compensation assessment unit, and the target recruitment data group. The quantitative job node set is then summarized to obtain multiple quantitative job node sets. Each quantitative job node set includes multiple quantitative job nodes, and each quantitative job node includes a job evaluation value and a compensation evaluation value. Each quantitative job node corresponds one-to-one with the target recruitment data in the target recruitment data group.

[0194] The evaluation job data confirmation module 103 is used to confirm receiving the job parsing instruction from the job parsing unit, parse the job parsing instruction to obtain multiple reference recruitment data, and obtain multiple reference job nodes based on the multiple reference recruitment data.

[0195] The job shortage analysis module 104 is used to obtain multiple job shortage assessment values ​​using the multiple reference job nodes and multiple quantitative job node sets, identify a shortage job sequence group based on the multiple job shortage assessment values, and send the shortage job sequence group to the job analysis instruction initiator using the result feedback unit, thereby realizing dynamic analysis of the job shortage of recruitment positions.

[0196] In detail, the modules in the recruitment position shortage dynamic analysis system 100 based on the evaluation model described in this embodiment of the invention adopt the same approach as described above when in use. Figure 1 The method used here is the same as the dynamic analysis method for job shortage based on the evaluation model described above, and it can produce the same technical effect, so it will not be elaborated here.

[0197] like Figure 3 The diagram shown is a structural schematic of an electronic device for implementing a dynamic analysis method for job shortage based on an evaluation model, according to an embodiment of the present invention.

[0198] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a dynamic analysis method program for job shortage based on an evaluation model.

[0199] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as the portable hard drive of the electronic device 1. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of a dynamic analysis method program for recruitment job shortages based on an evaluation model, but also to temporarily store data that has been output or will be output.

[0200] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a dynamic analysis method program for job shortages based on an evaluation model), and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0201] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0202] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0203] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management system, thereby enabling functions such as charging management, discharging management, and power consumption management through the power management system. The power supply may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0204] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0205] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0206] The program for dynamic analysis of job shortage based on an evaluation model, stored in the memory 11 of the electronic device 1, is a combination of multiple instructions. When run in the processor 10, it can achieve the following:

[0207] The system receives job analysis instructions and confirms the job analysis system based on these instructions. The job analysis system includes a recruitment data collection unit, a recruitment data cleaning unit, a job requirement assessment unit, a job compensation assessment unit, a job analysis unit, and a result feedback unit.

[0208] Based on a preset collection time interval, an initial recruitment dataset is obtained using a recruitment data collection unit. The initial recruitment dataset includes multiple initial recruitment data sets, each containing the posting unit, posting unit address, posting position, posting industry, posting time, recruitment time interval, job requirements text, and job benefits text. The initial recruitment dataset is then integrated using a recruitment data cleaning unit to obtain multiple target recruitment data sets.

[0209] Perform the following operation for each of the multiple target recruitment data groups:

[0210] A quantitative job node set is obtained based on the job demand assessment unit, the job compensation assessment unit, and the target recruitment data group. The quantitative job node set is then summarized to obtain multiple quantitative job node sets. Each quantitative job node set includes multiple quantitative job nodes, and each quantitative job node includes a job evaluation value and a compensation evaluation value. Each quantitative job node corresponds one-to-one with the target recruitment data in the target recruitment data group.

[0211] Confirm receipt of job parsing instruction from job parsing unit, parse the job parsing instruction to obtain multiple reference recruitment data, and obtain multiple reference job nodes based on the multiple reference recruitment data;

[0212] Multiple job shortage assessment values ​​are obtained by using the multiple reference job nodes and multiple quantitative job node sets. Based on the multiple job shortage assessment values, a shortage job sequence group is identified. The shortage job sequence group is sent to the job analysis instruction initiator by the result feedback unit to realize dynamic analysis of the shortage of recruitment positions.

[0213] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0214] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0215] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0216] The system receives job analysis instructions and confirms the job analysis system based on these instructions. The job analysis system includes a recruitment data collection unit, a recruitment data cleaning unit, a job requirement assessment unit, a job compensation assessment unit, a job analysis unit, and a result feedback unit.

[0217] Based on a preset collection time interval, an initial recruitment dataset is obtained using a recruitment data collection unit. The initial recruitment dataset includes multiple initial recruitment data sets, each containing the posting unit, posting unit address, posting position, posting industry, posting time, recruitment time interval, job requirements text, and job benefits text. The initial recruitment dataset is then integrated using a recruitment data cleaning unit to obtain multiple target recruitment data sets.

[0218] Perform the following operation for each of the multiple target recruitment data groups:

[0219] A quantitative job node set is obtained based on the job demand assessment unit, the job compensation assessment unit, and the target recruitment data group. The quantitative job node set is then summarized to obtain multiple quantitative job node sets. Each quantitative job node set includes multiple quantitative job nodes, and each quantitative job node includes a job evaluation value and a compensation evaluation value. Each quantitative job node corresponds one-to-one with the target recruitment data in the target recruitment data group.

[0220] Confirm receipt of job parsing instruction from job parsing unit, parse the job parsing instruction to obtain multiple reference recruitment data, and obtain multiple reference job nodes based on the multiple reference recruitment data;

[0221] Multiple job shortage assessment values ​​are obtained by using the multiple reference job nodes and multiple quantitative job node sets. Based on the multiple job shortage assessment values, a shortage job sequence group is identified. The shortage job sequence group is sent to the job analysis instruction initiator by the result feedback unit to realize dynamic analysis of the shortage of recruitment positions.

[0222] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0223] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0224] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0225] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0226] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for dynamically analyzing the vacancy degree of a recruitment position based on an evaluation model, characterized by, The method comprises: receiving a post analysis instruction, and confirming a post analysis system based on the post analysis instruction, wherein the post analysis system comprises a recruitment data collection unit, a recruitment data cleaning unit, a post demand evaluation unit, a post treatment evaluation unit, a post analysis unit, and a result feedback unit; based on a preset collection time interval, obtaining an initial recruitment data set by using the recruitment data collection unit, wherein the initial recruitment data set comprises a plurality of initial recruitment data, and the initial recruitment data comprises a publishing unit, a publishing unit address, a published post, a published industry, a post publishing time, a recruitment time interval, a post demand text, and a post treatment text, and integrating the initial recruitment data set by using the recruitment data cleaning unit to obtain a plurality of target recruitment data groups; wherein the integration of the initial recruitment data set by using the recruitment data cleaning unit to obtain a plurality of target recruitment data groups comprises: confirming a data cleaning instruction received from the recruitment data cleaning unit, analyzing the data cleaning instruction to obtain a classification time gradient set, wherein the classification time gradient set comprises a plurality of classification time gradients, and obtaining a classification time range group by using the classification time gradient set and the collection time interval, wherein the classification time range group comprises a plurality of classification time ranges; for each classification time range in the plurality of classification time ranges, the following operations are performed: based on the classification time range, the published industry, and the published post, the initial recruitment data in the initial recruitment data set is summarized to obtain a classification recruitment data set sequence, wherein the classification recruitment data set sequence comprises a plurality of classification recruitment data sets, and each classification recruitment data set in the plurality of classification recruitment data sets comprises a plurality of classification recruitment data, and the post publishing time corresponding to the classification recruitment data is located in the classification time range; for each classification recruitment data set in the classification recruitment data set sequence, the following operations are performed: counting the number of classification recruitment data in the classification recruitment data set to obtain a classification recruitment number, extracting a recruitment time interval set from the classification recruitment data set, and clustering the recruitment time interval set to obtain one or more target recruitment time interval sets; for each target recruitment time interval set in the one or more target recruitment time interval sets, the following operations are performed: counting the number of target recruitment time intervals in the target recruitment time interval set to obtain a target recruitment number, calculating the ratio of the target recruitment number to the classification recruitment number to obtain an initial recruitment ratio, comparing the initial recruitment ratio with a preset reference recruitment ratio, and if the initial recruitment ratio is less than or equal to the reference recruitment ratio, eliminating the target recruitment time interval set from the one or more target recruitment time interval sets; summarizing the retained target recruitment time interval sets to obtain one or more classification recruitment time interval sets, and obtaining a plurality of target recruitment data groups by using the one or more classification recruitment time interval sets; for each target recruitment data group in the plurality of target recruitment data groups, the following operations are performed: The post demand evaluation unit, the post treatment evaluation unit, and the target recruitment data group obtain a quantitative post node set, and the quantitative post node set is summarized to obtain a plurality of quantitative post node sets. The quantitative post node set includes a plurality of quantitative post nodes, and the quantitative post node includes a post evaluation value and a treatment evaluation value. The quantitative post node corresponds to the target recruitment data in the target recruitment data group one by one. The post analysis unit receives the post analysis instruction from the post analysis unit, analyzes the post analysis instruction, obtains a plurality of reference recruitment data, and obtains a plurality of reference post nodes based on the plurality of reference recruitment data. The reference post node is obtained in the same way as the quantitative post node. The plurality of reference post nodes and the plurality of quantitative post node sets are used to obtain a plurality of post shortage evaluation values, and the plurality of post shortage evaluation values are used to determine a shortage post sequence group. The result feedback unit sends the shortage post sequence group to the initiator of the post analysis instruction, and realizes dynamic analysis of the shortage of the recruitment post.

2. The method of claim 1, wherein the method further comprises: determining the number of the job vacancies based on the number of the job vacancies and the number of the job applicants; and determining the number of the job vacancies based on the number of the job vacancies and the number of the job applicants. The one or more classification recruitment time interval sets are used to obtain a plurality of target recruitment data groups, including: Each classification recruitment time interval set in the one or more classification recruitment time interval sets is executed as follows: The number of classification recruitment time intervals in each classification recruitment time interval set in the one or more classification recruitment time interval sets is counted to obtain a classification recruitment number set. The classification recruitment number set includes one or more classification recruitment numbers. The classification recruitment number set is used to calculate the analysis recruitment time, and the calculation formula is as follows: wherein, represents the analysis recruitment time, represents the classification recruitment quantity concentrated first classification recruitment quantity, represents the classification recruitment quantity concentrated first classification recruitment quantity, represents the classification recruitment quantity concentrated total classification recruitment quantity, represents the average value of the classification recruitment time interval in the classification recruitment time interval corresponding to the first classification recruitment quantity, represents the total number of classification recruitment time intervals in the classification recruitment time interval corresponding to the first classification recruitment quantity, represents the first classification recruitment time interval in the classification recruitment time interval corresponding to the first classification recruitment quantity, classification recruitment time interval. The analysis recruitment time is summarized to obtain an analysis recruitment time set, and the classification time range corresponding to the analysis recruitment time in the analysis recruitment time set is used to obtain an analysis recruitment time sequence. A preset sliding step, a preset first sliding sequence, and a pre-constructed sliding window are used to extract an analysis recruitment time group sequence from the analysis recruitment time sequence. The analysis recruitment time group sequence includes a plurality of analysis recruitment time groups. The analysis recruitment time group sequence is used to obtain a plurality of target recruitment data groups.

3. The method of claim 2, wherein the method further comprises: determining the number of the job vacancies based on the number of the job vacancies and the number of the job applicants; and determining the number of the job vacancies based on the number of the job vacancies and the number of the job applicants. The analysis recruitment time group sequence is used to obtain a plurality of target recruitment data groups, including: The first recruitment time group is extracted from the analysis recruitment time group sequence, and the following operations are performed on the extracted first recruitment time group: The first recruitment time group is used to obtain a recruitment time mean and a recruitment time variance. The recruitment time mean and the recruitment time variance are the mean and the variance of the analysis recruitment time in the first recruitment time group, respectively. The recruitment time mean and the recruitment time variance are associated to obtain an analysis node. The analysis nodes are summarized to obtain an analysis node set, and the analysis node set is used to obtain an analysis node sequence. The first analysis node is extracted from the analysis node sequence, and the following operations are performed on the extracted first analysis node: Confirming a second analysis node in the sequence of analysis nodes by using the first analysis node, wherein the second analysis node is adjacent to and lags behind the first analysis node, and calculating an evaluation node difference by using the first analysis node and the second analysis node, and the calculation formula is as follows: wherein, represents an evaluation node difference value, respectively represent a recruitment time mean value and a recruitment time variance corresponding to the first analysis node, respectively represent a recruitment time mean value and a recruitment time variance corresponding to the second analysis node; Comparing the evaluation node difference with a preset evaluation node threshold value, if the evaluation node difference is less than or equal to the evaluation node threshold value, taking the second analysis node as the first analysis node, and returning to the step of confirming the second analysis node in the sequence of analysis nodes by using the first analysis node until the evaluation node difference is greater than the evaluation node threshold value; If the evaluation node difference is greater than the evaluation node threshold value, eliminating the second analysis node in the sequence of analysis nodes to obtain an updated node sequence, taking the updated node sequence as the sequence of analysis nodes, and returning to the step of confirming the second analysis node in the sequence of analysis nodes by using the first analysis node until all the analysis nodes in the sequence of analysis nodes are extracted, extracting a target analysis time group from the sequence of analysis recruitment time groups by using the extracted first analysis node, wherein the target analysis time group includes a plurality of target analysis times, and obtaining a target analysis quantity by counting the number of target analysis times in the target analysis time group; Comparing the target analysis quantity with a preset analysis quantity threshold value, if the target analysis quantity is greater than or equal to the analysis quantity threshold value, taking the plurality of initial recruitment data corresponding to the target analysis time group as a target recruitment data group; Otherwise, calculating an optimized time interval by using the target analysis quantity, the analysis quantity threshold value and the collection time interval, taking the optimized time interval as the collection time interval, and returning to the step of obtaining the initial recruitment data set by using the recruitment data collection unit based on the preset collection time interval until the target analysis quantity is greater than or equal to the analysis quantity threshold value; Summarizing the target recruitment data group to obtain a plurality of target recruitment data groups.

4. The method of claim 3, wherein the method further comprises: determining the number of the job vacancies based on the number of the job vacancies and the number of the job applicants; and determining the number of the job vacancies based on the number of the job vacancies and the number of the job applicants. The calculation formula of calculating the optimized time interval by using the target analysis quantity, the analysis quantity threshold value and the collection time interval is as follows: wherein, represents an optimization time interval, represents a collection time interval, represents an analysis number threshold, represents a target analysis number, is a preset coefficient.

5. The method of claim 4, wherein the method further comprises: determining the number of the job vacancies based on the number of the job vacancies and the number of the job applicants; and determining the number of the job vacancies based on the number of the job vacancies and the number of the job applicants. The post demand evaluation unit, the post treatment evaluation unit and the target recruitment data group obtain a quantitative post node set, including: Receiving a post demand evaluation instruction from the post demand evaluation unit and a post treatment evaluation instruction from the post treatment evaluation unit respectively, and analyzing the post demand evaluation instruction and the post treatment evaluation instruction respectively to obtain a post demand evaluation index set and a post treatment evaluation index set; Performing the following operations on each target recruitment data in the target recruitment data group: Retrieving a target treatment evaluation index set from the post treatment evaluation index set by using the publishing unit address corresponding to the target recruitment data, and obtaining a post evaluation value and a treatment evaluation value by using the post demand evaluation index set, the target treatment evaluation index set, the post demand text corresponding to the target recruitment data, the post treatment text corresponding to the target recruitment data, a pre-constructed analytic hierarchy process and a pre-constructed data analysis method; The post evaluation value and the treatment evaluation value are obtained by using the post demand evaluation index set, the target treatment evaluation index set, the post demand text corresponding to the target recruitment data, the post treatment text corresponding to the target recruitment data, a pre-constructed analytic hierarchy process and a pre-constructed data analysis method. The post treatment scale value set is obtained by using the pre-constructed scale method and the post treatment text, and the post evaluation weight value set is obtained based on the analytic hierarchy process, the target treatment evaluation index set and the post treatment text, wherein the post treatment scale value set includes one or more post treatment scale values, the post evaluation weight value set includes one or more post evaluation weight values, and the post treatment scale value is a scale value obtained by scaling the post treatment text for representing different treatments by using the scale method. The post analysis weight value set is obtained according to the data analysis method and the post treatment text, wherein the post analysis weight value set includes one or more post analysis weight values, and the post treatment scale value, the post evaluation weight value and the post analysis weight value correspond to each other. The post evaluation node set is obtained based on the post treatment scale value set, the post evaluation weight value set and the post analysis weight value set, wherein the post evaluation node set includes a plurality of post evaluation nodes, and the post evaluation node is as follows: in, Indicates the first stage of the job evaluation process. Each job evaluation stage This indicates the first position in the set of job evaluation weight values. Each job evaluation weight value This indicates the first value in the set of job analysis weight values. Analyze the weight values ​​for each job position. This indicates the first value in the set of job compensation scale values. Salary scale value for each position; The treatment evaluation value is calculated based on the post evaluation node in the post evaluation node set, and the calculation formula is as follows: wherein, represents a treatment evaluation value, represents a post evaluation node commonly shared in a set of post evaluation nodes a post evaluation node; The post evaluation value is obtained based on the scale method, the post demand text, the post demand evaluation index set, the analytic hierarchy process and the data analysis method. The quantitative post node is obtained by associating the post evaluation value and the treatment evaluation value, and the quantitative post node set is obtained by collecting the quantitative post node.

6. The method of claim 5, wherein the method further comprises: determining the number of the candidates who have applied for the job opening; and determining the number of the candidates who have been selected for the job opening. The plurality of post shortage evaluation values are obtained by using the plurality of reference post nodes and the plurality of quantitative post node sets, including: The plurality of reference post nodes are divided according to the published post and the published industry to obtain one or more target search node sets, wherein the target search node set includes a plurality of target search nodes, and the published post and the published industry corresponding to the target search node are the same; The following operations are performed on each target search node set in the one or more target search node sets: The target post node set is searched from the plurality of quantitative post node sets by using the published post and the published industry corresponding to the target search node set; The following operations are performed on each target search node in the target search node set: The optimized search node is obtained based on the target search node and the reference recruitment data corresponding to the target search node, wherein the optimized search node is as follows: wherein, represents an optimized search node, represents a publishing unit address corresponding to the reference recruitment data, wherein, respectively represent longitude and latitude, respectively represent a reference job evaluation value and a reference treatment evaluation value corresponding to the target search node; The optimized post node set is obtained by using the target post node set, and the search post node set is obtained by collecting the optimized search node and the optimized post node set, and the search post node set is clustered to obtain one or more optimized search node sets, and the judgment search node set is confirmed in the one or more optimized search node sets, wherein the judgment search node set is the optimized search node set including the optimized search node; The post shortage evaluation value is obtained based on the judgment search node set, and the plurality of post shortage evaluation values are obtained by collecting the post shortage evaluation values.

7. The method of claim 6, wherein the method further comprises: determining the number of the candidates who have applied for the job opening; and determining the number of the candidates who have been selected for the job opening. The job shortage degree evaluation value is obtained based on the evaluation search node set, and the job shortage degree evaluation value comprises: The maximum recruitment time, the job evaluation range and the treatment evaluation range are searched in the evaluation search node set; The evaluation time mean is obtained by using the optimized job node set corresponding to the evaluation search node set, the reference job evaluation value and the reference treatment evaluation value corresponding to the optimized search node are normalized by using the job evaluation range and the treatment evaluation range, the normalized job evaluation value and the normalized treatment evaluation value are obtained, the job evaluation recruitment time is calculated by using the normalized job evaluation value, the normalized treatment evaluation value and the evaluation time mean, if the job evaluation recruitment time is greater than the maximum recruitment time, the absolute difference value between the maximum recruitment time and the job evaluation recruitment time is calculated, and the job shortage degree evaluation value is obtained.

8. The method of claim 7, wherein the method further comprises: determining the number of the job vacancies based on the number of the job vacancies and the number of the job applicants; and determining the number of the job vacancies based on the number of the job vacancies and the number of the job applicants. The job evaluation recruitment time is calculated by using the normalized job evaluation value, the normalized treatment evaluation value and the evaluation time mean, and the calculation formula is as follows: wherein, represents the post evaluation recruitment time, represents a preset coefficient, respectively represent the normalized post evaluation value and the normalized treatment evaluation value, represents the evaluation time average.

9. A dynamic analysis system for job shortage based on an evaluation model, characterized in that, The system comprises: A job analysis preparation module is configured to receive a job analysis instruction and confirm a job analysis system based on the job analysis instruction, wherein the job analysis system comprises a recruitment data collection unit, a recruitment data cleaning unit, a job demand evaluation unit, a job treatment evaluation unit, a job analysis unit and a result feedback unit. An initial job data integration module is configured to obtain an initial recruitment data set by using the recruitment data collection unit based on a preset collection time interval, wherein the initial recruitment data set comprises a plurality of initial recruitment data, and the initial recruitment data comprises a publishing unit, a publishing unit address, a published position, a published industry, a job publishing time, a recruitment time interval, a job demand text and a job treatment text. The initial recruitment data set is integrated by using the recruitment data cleaning unit to obtain a plurality of target recruitment data groups. The data cleaning instruction from the recruitment data cleaning unit is confirmed, the data cleaning instruction is analyzed to obtain a classification time gradient set, wherein the classification time gradient set comprises a plurality of classification time gradients, and a classification time range group is obtained by using the classification time gradient set and the collection time interval, wherein the classification time range group comprises a plurality of classification time ranges. The following operations are performed on each classification time range in the plurality of classification time ranges: The initial recruitment data in the initial recruitment data set is summarized based on the classification time range, the published industry and the published position to obtain a classification recruitment data set sequence, wherein the classification recruitment data set sequence comprises a plurality of classification recruitment data sets, and each classification recruitment data set in the plurality of classification recruitment data sets comprises a plurality of classification recruitment data, and the job publishing time corresponding to the classification recruitment data is located in the classification time range. The following operations are performed on each classification recruitment data set in the classification recruitment data set sequence: The number of classification recruitment data in the classification recruitment data set is counted to obtain a classification recruitment number, and one or more target recruitment time interval sets are obtained by clustering the recruitment time interval set in the classification recruitment data set. The following operations are performed on each of the one or more target recruitment time interval sets: The number of target recruitment time intervals in the target recruitment time interval set is counted to obtain a target recruitment number, a ratio of the target recruitment number to the classified recruitment number is calculated to obtain an initial recruitment ratio, the initial recruitment ratio is compared with a preset reference recruitment ratio, and if the initial recruitment ratio is less than or equal to the reference recruitment ratio, the target recruitment time interval set is removed from the one or more target recruitment time interval sets; The retained target recruitment time interval sets are aggregated to obtain one or more classified recruitment time interval sets, and the one or more classified recruitment time interval sets are used to obtain a plurality of target recruitment data groups; The following operations are performed on each of the plurality of target recruitment data groups: A quantitative post node set is obtained based on a post demand evaluation unit, a post treatment evaluation unit, and the target recruitment data group, the quantitative post node set is aggregated to obtain a plurality of quantitative post node sets, the quantitative post node set includes a plurality of quantitative post nodes, the quantitative post node includes a post evaluation value and a treatment evaluation value, and the quantitative post node corresponds to the target recruitment data in the target recruitment data group in a one-to-one manner; A post data evaluation confirmation module is configured to confirm a post analysis instruction received from a post analysis unit, analyze the post analysis instruction to obtain a plurality of reference recruitment data, and obtain a plurality of reference post nodes based on the plurality of reference recruitment data, wherein the reference post nodes are obtained in the same manner as the quantitative post nodes. A post shortage analysis module is configured to obtain a plurality of post shortage evaluation values using the plurality of reference post nodes and the plurality of quantitative post node sets, confirm a shortage post sequence group based on the plurality of post shortage evaluation values, and send the shortage post sequence group to an initiating end of a post analysis instruction using a result feedback unit to realize dynamic analysis of the recruitment post shortage.

Images