A method, system and platform for intelligent matching of labor services for vocational and skilled personnel

Abstract

The present invention provides a method, system and platform for intelligent matching of labor services for vocational and skilled personnel, and relates to the field of intelligent labor matching technology, including: receiving labor demand information, and analyzing the labor category and demand complexity; retrieving multiple idle workers according to the labor category, performing skill matching according to multiple vocational skill information and labor demand information, and obtaining multiple skill matching degrees; performing service strain analysis on multiple idle workers, and obtaining multiple service strains; configuring weights according to demand complexity, weighting demand complexity, multiple service strains and multiple skill matching degrees to obtain multiple talent matching degrees, and performing sorting and matching display. The present invention can solve the technical problem that the existing method cannot accurately match skilled personnel according to labor demand due to failure to fully consider the complexity of tasks and the flexible adaptability of skilled personnel, and can significantly improve the talent matching efficiency and matching quality through multi-dimensional comprehensive evaluation.

Description

Technical Field

[0001] The present invention relates to the field of intelligent labor matching technology, and in particular to a method, system and platform for intelligent matching of labor employment for vocational talents. Background Art

[0002] With the continuous development of the labor market, the diversification and complexity of employment needs are increasing. In the traditional labor matching process, the matching system usually only performs simple skill matching based on the basic information of the workers (such as years of work, skill level, industry experience, etc.). However, with the increase in task complexity, many jobs require workers not only to have basic professional skills, but also to be able to flexibly respond to various emergencies or handle complex tasks. This makes the matching method that relies solely on basic information show obvious limitations in complex employment scenarios.

[0003] Traditional matching methods often ignore the complexity of tasks and the adaptability of skilled personnel. For example, when faced with complex maintenance tasks or emergency troubleshooting, workers' adaptability, historical service performance, and understanding and communication skills of complex tasks become important factors in determining whether the task can be successfully completed. However, existing matching systems usually lack assessments of these key capabilities, resulting in the system being unable to accurately match suitable talents when faced with difficult or urgent tasks, which in turn affects the efficiency of task completion and service quality.

[0004] In summary, the existing labor matching methods fail to fully consider the complexity of tasks and the flexible adaptability of skilled talents, resulting in the inability to accurately match skilled talents in complex or urgent labor demand scenarios, affecting the overall matching quality and task completion results. Summary of the invention

[0005] The purpose of the present invention is to provide a method, system and platform for intelligent matching of vocational skilled personnel for labor employment, so as to solve the technical problem that the existing labor employment matching methods cannot accurately match skilled personnel according to employment needs due to failure to fully consider the complexity of the tasks and the flexible adaptability of skilled personnel.

[0006] In view of the above problems, the present invention provides a method, system and platform for intelligent matching of labor employment for vocational skills talents.

[0007] In the first aspect, the present invention provides a method for intelligent matching of labor services for vocational skilled personnel, which is implemented through an intelligent matching system for labor services for vocational skilled personnel, including: receiving user's employment demand information, and analyzing the employment category and demand complexity of the employment demand information; according to the employment category, retrieving multiple idle workers to be matched, and performing skill matching analysis based on multiple occupational skill information of the multiple idle workers and in combination with the employment demand information to obtain multiple skill matching degrees; retrieving multiple historical service data sequences of the multiple idle workers, and performing service strain degree analysis on the multiple idle workers respectively to obtain multiple service strain degrees; according to the demand complexity, configuring weights, performing weighted calculation on the demand complexity, multiple service strain degrees and multiple skill matching degrees, obtaining multiple talent matching degrees, and performing sorting and matching display.

[0008] In the second aspect, the present invention also provides an intelligent matching system for labor employment of professional skilled talents, which is used to execute an intelligent matching method for labor employment of professional skilled talents as described in the first aspect, including: a labor demand analysis module, which is used to receive the labor demand information of the user and analyze the labor category and demand complexity of the labor demand information; a skill matching analysis module, which is used to retrieve multiple idle workers to be matched according to the labor category, and perform skill matching analysis based on multiple professional skill information of the multiple idle workers and in combination with the labor demand information to obtain multiple skill matching degrees; a service strain degree analysis module, which is used to retrieve multiple historical service data sequences of the multiple idle workers, and perform service strain degree analysis of the multiple idle workers respectively to obtain multiple service strain degrees; a talent matching degree calculation module, which is used to configure weights according to the demand complexity, perform weighted calculation on the demand complexity, multiple service strain degrees and multiple skill matching degrees, obtain multiple talent matching degrees, and perform sorting and matching display.

[0009] In the third aspect, the present invention also provides an intelligent matching platform for vocational skills talents and labor employment, and the platform includes the intelligent matching system for vocational skills talents and labor employment described in the second aspect.

[0010] In a fourth aspect, the present invention also provides an electronic device comprising: at least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of a method for intelligent matching of vocational skills talents and labor employment in the above-mentioned first aspect.

[0011] One or more technical solutions provided in the present invention have at least the following technical effects or advantages:

[0012] By receiving the employment demand information of the user, and analyzing the employment category and demand complexity of the employment demand information; then, according to the employment category, multiple idle workers to be matched are retrieved, and multiple professional skill information of the multiple idle workers is obtained, and further skill matching analysis is performed based on the multiple professional skill information and employment demand information to obtain multiple skill matching degrees; on the other hand, multiple historical service data sequences of the multiple idle workers are retrieved, and service strain degree analysis of the multiple idle workers is performed respectively according to the multiple historical service data sequences to obtain multiple service strain degrees; then, weights are configured according to the demand complexity, and weighted calculations are performed on the demand complexity, multiple service strain degrees and multiple skill matching degrees to obtain multiple talent matching degrees, and talent sorting and matching display are performed based on the multiple talent matching degrees; that is, through multi-dimensional data analysis and comprehensive evaluation, the complexity of the task, the professional skills and adaptability of the workers can be fully considered, the precision and comprehensiveness of talent matching can be improved, the technical goal of accurately matching skilled talents based on employment needs can be achieved, and the efficiency and quality of talent matching can be significantly improved, thereby improving the task success rate and service quality.

[0013] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0015] Figure 1 A flowchart of a method for intelligently matching vocational skills personnel with labor services of the present invention;

[0016] Figure 2 This is a structural schematic diagram of an intelligent matching system for vocational skills personnel and labor employment of the present invention;

[0017] Figure 3 The figure is a schematic diagram of the structure of the electronic device provided by the present invention.

[0018] Description of reference numerals:

[0019] Employment demand analysis module 11, skill matching analysis module 12, service adaptability analysis module 13, talent matching calculation module 14, electronic device 500, memory 510, processor 520, first computer program 511. DETAILED DESCRIPTION

[0020] The present invention provides a method, system and platform for intelligent matching of vocational skilled personnel and labor employment, which solves the technical problem that the existing labor employment matching methods cannot accurately match skilled personnel according to employment needs due to failure to fully consider the complexity of tasks and the flexible adaptability of skilled personnel. Through multi-dimensional comprehensive analysis and evaluation, the precision and comprehensiveness of talent matching can be improved, the technical goal of accurately matching skilled personnel based on employment needs can be achieved, and the efficiency and quality of talent matching can be significantly improved, thereby improving the success rate of tasks and service quality.

[0021] Below, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should also be noted that, for the convenience of description, only the parts related to the present invention are shown in the accompanying drawings, rather than all of them.

[0022] For example, please refer to the attached Figure 1 The present invention provides a method for intelligent matching of labor services for vocational and skilled personnel, which is applied to an intelligent matching system for labor services for vocational and skilled personnel, and specifically comprises the following steps:

[0023] S100: receiving the user's employment demand information, and analyzing the employment category and demand complexity of the employment demand information.

[0024] In one embodiment, step S100 of the present invention further includes:

[0025] S110: receiving labor demand information input by a user; S120: inputting the labor demand information into a pre-trained labor demand parser, performing labor demand parsing, and outputting a labor category, wherein the labor demand parser is trained with a sample labor demand information set and a sample labor category set until convergence; S130: calculating and analyzing the demand complexity of the labor demand information based on similar labor demand information of the labor category.

[0026] Specifically, the labor demand information posted by users on the platform is received. The labor demand information is a description of the recorded tasks, including the specific type of task, fault condition and urgency, etc. For example, the kitchen water pipe needs to be urgently repaired due to leakage and unstable water pressure.

[0027] A labor demand parser is constructed based on random decision forest, wherein random decision forest is an integrated learning method, which improves the overall accuracy and stability of the model by constructing multiple decision trees and integrating the prediction results of each tree; the labor demand parser includes an input layer, multiple random forest layers and an output layer, wherein the input data of the input layer is the labor demand information, and the output data of the output layer is the labor category. The random forest layer is composed of multiple decision trees and is the core part of the random decision forest model. Each decision tree is independently trained on randomly sampled training data and features to ensure the diversity of the tree, and the output of the tree will predict the labor category based on different feature combinations.

[0028] Then, the historical employment records of the labor employment platform are queried to collect and obtain sample employment demand information sets and sample employment category sets. The sample employment demand information sets contain a large number of different types of employment demand text descriptions, covering various task details, such as task type, fault description, urgency, etc., aiming to fully reflect the actual employment demand scenarios. For example, the air conditioner does not cool and needs deep cleaning and repair; the electrical circuit is short-circuited, causing some equipment to be unable to work normally, etc. The sample employment category set is the category label corresponding to the demand information, which is used to represent different employment types. For example, according to the demand information description, the category label can be air conditioning repair, electrical repair, etc. Then, the sample labor demand information is used as input and the sample labor category is used as output. The sample labor demand information set and the sample labor category set are used to supervise the labor demand parser. First, randomly sample from the training set samples, extract some sample data and randomly select some features as the training data of a decision tree; then use the sampled data to train the decision tree, and recursively make classification decisions by splitting nodes until the set tree depth or number of node samples is reached, wherein each tree learns to predict the output category from the input feature vector separately, and the node splitting of the tree is based on indicators such as information gain to maximize the classification effect. Through multiple rounds of decision tree generation, the trees in the forest learn diverse decision rules on different sampled data to form different classification paths; when increasing the number of decision trees does not significantly improve the overall accuracy of the model, that is, the model reaches convergence on the validation set, the training process ends, and a trained labor demand parser is obtained. By using a set of sample labor demand information and a set of labor categories to conduct supervised training on the random decision forest, the labor demand parser can accurately parse new demand information and identify the most suitable labor category, thereby improving the accuracy and stability of labor category identification and being able to adapt to different labor demand scenarios.

[0029] The labor demand information is then input into a trained labor demand parser for labor demand analysis, and the labor category is output. Further, multiple similar labor demand information is retrieved according to the labor category, and a similarity comparison is performed between multiple similar labor demand information and the labor demand information to calculate the demand complexity.

[0030] In one embodiment, step S130 of the present invention further includes:

[0031] S131: According to the employment category, retrieve the M most recent employment demand information of the same employment category, where M is an integer greater than 1; S132: Calculate the similarity between the M pieces of similar employment demand information and the employment demand information, and calculate the average to obtain the demand similarity; S133: Subtract the demand similarity from 1 to obtain the demand complexity.

[0032] Specifically, after determining the category of the current labor demand, the M most recent labor demand information under the category is retrieved from the database according to the labor category, where the most recent refers to the historical labor demand information within a short period of time from the current time node. For example, historical labor demand information with the same category as the current demand is screened out in the database, and these labor demand information of the same type are sorted in descending order by submission time to ensure that the demand data closest to the current time is retrieved; then the most recent M pieces of demand information are extracted from the sorted data, where M is an integer greater than 1 and can be flexibly set according to the application scenario, such as 5, 10 or 20 pieces.

[0033] Then, the similarities between the M pieces of similar labor demand information and the labor demand information are calculated respectively to obtain multiple similarities. For example, the similarity is calculated based on the text repetition ratio between the similar labor demand information and the labor demand information. First, for each piece of similar labor demand information, the number of identical characters between it and the current demand information is found. The identical number of characters indicates the number of characters or words that overlap in the two demand descriptions. Then, the number of identical characters in each piece of similar labor demand information is divided by the total number of characters in the current demand information to obtain the text repetition ratio, i.e., the similarity. The formula for calculating the demand similarity between the labor demand information and the M pieces of similar labor demand information is: , where S is the demand similarity, M is the number of similar employment demand information, and K i is the number of repeated words between the i-th similar employment demand information and the current employment demand information, K xis the number of words in the current employment demand information; for example, if the current demand information description has 30 words, and the number of words in common with a similar demand information is 15, then the similarity of this demand is 50%. Then the multiple similarities are averaged, and the average calculation result is used as the demand similarity. Further, 1 is subtracted from the demand similarity to obtain the demand complexity. The calculation formula for demand complexity is: Z=1-S, Z is the demand complexity, S is the demand similarity. For example, if the average demand similarity is 70%, then 1-70%=30%, and the demand complexity is 30%; the smaller the demand similarity, the greater the demand complexity. By calculating the demand complexity, the complexity of the current demand can be accurately judged, providing an accurate basis for subsequent matching. For example, a high complexity score indicates that the demand is more special or unique, and the subsequent matching process can give priority to more adaptable and highly skilled workers.

[0034] S200: According to the employment category, a plurality of idle workers to be matched are retrieved, and skill matching analysis is performed based on a plurality of professional skill information of the plurality of idle workers and in combination with the employment demand information to obtain a plurality of skill matching degrees.

[0035] In one embodiment, step S200 of the present invention further includes:

[0036] S210: According to the employment category, retrieve multiple idle workers that are currently idle and match the employment category; S220: Retrieve multiple professional skill information of the multiple idle workers, respectively combine the employment demand information and input it into a pre-trained skill matching analyzer, and output multiple skill matching degrees.

[0037] Specifically, the labor database is accessed for information query based on the employment category, only the laborers matching the current employment category are retained, and the laborers who are currently idle and have the skills required for the category are screened out. For example, for plumbing repair needs, the system will screen out all idle plumbers. By retrieving the current idle labor information matching the employment category, the system can perform skill matching analysis more accurately and provide efficient support for subsequent task allocation.

[0038] Then, multiple professional skill information of the multiple idle workers is called, wherein the professional skill information corresponds to the idle workers one by one, and the professional skill information includes skill level, work experience, certificate and qualification, etc. Then, the multiple professional skill information is respectively combined with the employment demand information to form specific combination input data, and multiple combination input data are obtained. The multiple combination input data are further input into the trained skill matching analyzer to obtain multiple skill matching degrees, wherein the skill matching analyzer is a machine learning model built based on a machine learning algorithm.

[0039] In one embodiment, step S220 of the present invention further includes:

[0040] S221: Based on the labor matching data in the historical period, collect sample employment demand information sets and sample occupational skill information sets, and annotate and obtain sample skill matching degree sets based on the average employment evaluation data under different sample employment demand information and sample occupational skill information; S222: Use the sample employment demand information sets, sample occupational skill information sets and sample skill matching degree sets as supervised training data and verification data, use machine learning algorithms to train the skill matching analyzer and verify that the convergence requirements are met.

[0041] Specifically, based on the labor matching data in historical time, we collect and construct sample labor demand information sets and sample occupational skill information sets. The sample labor demand information sets include descriptions of various types of labor demand that have actually been completed in history. These demand information covers a variety of labor categories and complexities, such as electrical maintenance, emergency tasks, and quick response requirements; air conditioning cleaning, those with professional qualifications are preferred; the sample occupational skill information set includes the actual occupational skill data of workers who are assigned to complete tasks corresponding to the labor demand. The skill information of the actual matching workers for each task can be extracted from the historical task completion records. Each sample contains key occupational skill information such as the worker's skill level, years of work experience, relevant qualifications, and task completion rate.

[0042] Then, multiple employment evaluation data under different sample employment demand information and sample occupational skill information are obtained, where the employment evaluation data is the feedback score of the user to the worker after the task is completed, usually expressed as a percentage score or a 5-star score. The user evaluation data of each task can be extracted from the historical task record. These evaluations include scores for task completion quality, response speed, skill professionalism, etc., such as 0-100% scores. Then, the average of multiple employment evaluation data is calculated to obtain the average employment evaluation data, and the average employment evaluation data is set as the sample skill matching degree, where the sample skill matching degree is expressed in percentage. The higher the score, the higher the user's satisfaction with the service, and the greater the skill matching degree. For example, a skill matching degree greater than 95% indicates that it is very consistent with user needs; a skill matching degree less than or equal to 95% and greater than 85% indicates that it meets the needs, but there is room for improvement; a sample skill matching degree set is obtained, where the sample skill matching degree corresponds to the sample employment demand information and the sample occupational skill information.

[0043] A skill matching analyzer is constructed based on a machine learning algorithm, such as a random forest regression model, a neural network model, etc. In the present invention, a BP neural network is taken as an example. First, a skill matching analyzer is constructed based on a BP neural network. The skill matching analyzer is a BP neural network model that can be iteratively optimized in machine learning. It is obtained by iterative training of a sample data set, and includes an input layer, multiple hidden layers, and an output layer. The input data of the input layer is the employment demand information and the occupational skill information, and the output data of the output layer is the skill matching degree. Then, the sample labor demand information set, the sample occupational skill information set and the sample skill matching degree set are used as sample data sets, and the sample data sets are divided into a sample training set and a sample verification set according to a preset ratio, such as the sample training set accounts for 85% and the sample verification set accounts for 15%; then, the sample labor demand information and the sample occupational skill information are used as input, and the sample skill matching degree is used as output, and the sample training set is used to supervise the training of the skill matching analyzer. First, the labor demand information and occupational skill information in the sample training set are input into the input layer of the BP neural network, and the input data is weighted summed and activated by each hidden layer. The input data is passed forward to the output layer layer by layer, and the output layer generates a prediction value, that is, the prediction result of the skill matching degree; then, the loss function is used to calculate the error between the model prediction value and the actual skill matching degree, and the back propagation algorithm is used to calculate the gradient of each parameter (weight and bias) to minimize the loss function, that is, starting from the output layer, the error of the loss function is propagated backward layer by layer, the gradient of the weight and bias of each hidden layer is calculated, and the weight and bias are updated, and the gradient descent method is applied to update each parameter to reduce the prediction error. Repeat the process of forward propagation, loss calculation and back propagation. The model continuously optimizes parameters in each iteration until the predetermined number of iterations is met. Then the skill matching analyzer is verified and trained using the sample validation set. According to the evaluation results of the validation set, the model structure or training parameters are adjusted. Through multiple iterations, it is ensured that the model performs stably on the validation set and the skill matching prediction is close to the true value.

[0044] Through supervised training and verification training, the BP neural network skill matching analyzer is gradually optimized, so that the model can output accurate skill matching under the actual employment needs and occupational skill information input. This method improves the prediction accuracy and robustness of the model and ensures its applicability in different employment scenarios.

[0045] S300: Retrieving a plurality of historical service data sequences of the plurality of idle workers, respectively performing service susceptibility analysis on the plurality of idle workers, and obtaining a plurality of service susceptibility.

[0046] In one embodiment, step S300 of the present invention further includes:

[0047] S310: Retrieve multiple historical service data sequences of the multiple idle workers, and extract historical labor demand information within the multiple historical service data sequences to obtain multiple historical labor demand information sequences; S320: Calculate the similarity between each historical labor demand information within the multiple historical labor demand information sequences and the labor demand information to obtain multiple historical labor demand similarity sequences; S330: Randomly extract a number of first historical labor demand similarities within the first historical labor demand similarity sequence of the first idle worker, calculate the difference amplitude with the mean of the first historical labor demand similarity sequence, and calculate the mean of the several difference amplitudes to obtain a first service strain degree; S340: Continue to calculate and obtain multiple service strain degrees based on the multiple historical labor demand similarity sequences.

[0048] Specifically, the historical service records of each idle worker are retrieved from the database. Each record contains information about the tasks that the worker has completed before, including the task category, complexity, urgency, skill requirements, etc. Then, multiple historical service data sequences of the multiple idle workers are retrieved based on the historical service records, that is, the historical service data of each worker is arranged in chronological order to form a time series, so as to observe the changes in the types and requirements of the workers. Then, the historical labor demand information in the multiple historical service data sequences is extracted, that is, the information related to the task requirements is extracted from each historical service record, and multiple historical labor demand information sequences are obtained.

[0049] Then, similarity calculation is performed on each historical labor demand information and the labor demand information in the multiple historical labor demand information sequences, wherein similarity calculation refers to calculating the text repetition ratio between the historical labor demand information and the labor demand information, and the text repetition ratio is the ratio of the number of overlapping characters to the total number of characters in the current labor demand information, which represents the degree of similarity between the two texts, and the text repetition ratio is set as the similarity. The similarity calculation formula for each historical labor demand information and the current labor demand information is: Similarity = number of identical characters / number of characters in historical labor demand information. For example, if the historical labor demand information description has 50 characters and the number of identical characters with the labor demand information is 30, then the similarity of the demand is 60%; based on the similarity calculation results, multiple historical labor demand similarity sequences of multiple idle workers are obtained.

[0050] Randomly select any idle worker from multiple idle workers as the first idle worker, and obtain the first historical labor demand similarity sequence of the first idle worker; then randomly extract a number of first historical labor demand similarities in the first historical labor demand similarity sequence, that is, randomly extract a number of similarity values ​​from the historical similarity sequence, these values ​​are used to calculate the difference amplitude with the mean to evaluate the fluctuation of the similarity, wherein the number of the several values ​​can be set according to the data volume of the similarity in the first historical labor demand similarity sequence, for example, set the several values ​​to 10% of the data volume, if the data volume of the similarity is 50, then the several values ​​are 5. Further calculate the first service strain degree of the first idle worker, the calculation formula of the first service strain degree is:

[0051] , where Y1 is the first service strain, N is the number of similarities of several first historical labor demand randomly selected, S j is the similarity of the jth historical labor demand randomly selected, S 1均 It is the first similarity sequence mean of the first historical labor demand similarity sequence.

[0052] Among them, the first historical labor demand similarity sequence is averaged to obtain the first similarity sequence average; the absolute values ​​of the differences between several first historical labor demand similarities and the first similarity sequence average are further calculated to obtain several difference amplitudes; finally, the average of the several difference amplitudes is calculated, and the average calculation result is set as the first service strain degree. For example, assuming that the mean of the first similarity sequence is 0.6, and the similarities of several first historical labor demands are 0.7, 0.75, 0.55, 0.5 and 0.65 respectively, then substituting the difference amplitudes into the formula to obtain several difference amplitudes of 0.1, 0.15, 0.05, 0.1 and 0.05, then the mean of the several difference amplitudes is 0.09, and the first service strain is 9%. Among them, the larger the difference amplitude, the greater the degree of change in the historical labor demand information of the service provided by the laborer in the historical time, and the greater the service strain. The service strain represents the ability of the laborer to quickly adapt and flexibly handle tasks of different types and difficulties. The larger the service strain, the better the strain capacity, that is, the laborer can efficiently adapt to various complex and changeable task requirements, and can be assigned to complex and more changing tasks in priority to ensure service quality and efficiency.

[0053] Then, the same calculation and processing method as in the above content is used to continue to calculate the service strain degree according to the multiple historical labor demand similarity sequences, and obtain multiple service strain degrees of multiple idle workers. By calculating the service strain degree, the worker's resilience can be quantified. The larger the service strain degree, the more complex the changes in labor demand handled by the worker in the historical time, the stronger the worker's resilience and communication ability, and the more complex the work that can be handled. At the same time, a more detailed evaluation of the workers can be carried out from the dimension of resilience, and the matching effect between the workers and the tasks can be optimized, thereby improving the service efficiency and quality in a complex and changing task environment.

[0054] S400: According to the complexity of the demand, weights are configured, and weighted calculations are performed on the complexity of the demand, multiple service adaptability and multiple skill matching degrees to obtain multiple talent matching degrees, and then sort and display the talent matching degrees.

[0055] In one embodiment, step S400 of the present invention further includes:

[0056] S410: Calculate and obtain the average demand complexity based on the employment demand information in historical time; S420: According to the ratio of the demand complexity and the average demand complexity, modify and calculate the preset complexity weight to obtain the complexity weight, and subtract the complexity weight from 1 to obtain the skill weight, wherein the preset complexity weight is 0.5; S430: Calculate the ratio of the multiple service strain degrees to the demand complexity respectively to obtain multiple strain matching degrees; S440: According to the complexity weight and skill weight, perform weighted calculation on the multiple strain matching degrees and the multiple skill matching degrees to obtain multiple talent matching degrees; S450: Sorting and matching display according to the multiple talent matching degrees.

[0057] Specifically, multiple labor demand information within a preset historical time period is obtained, and the historical time period can be customized, for example, within the last month; then the calculation formula and calculation method of demand similarity and demand complexity in the aforementioned content are used to calculate the demand complexity of multiple labor demand information within the preset historical time period, and multiple demand complexities are obtained and averaged to obtain the average demand complexity.

[0058] Then calculate the ratio of the demand complexity to the average demand complexity. For example, if the demand complexity is 60% and the average demand complexity is 50%, the ratio is 1.2. Then, the preset complex weight is modified and calculated according to the ratio, where the preset complex weight is 0.5, that is, the ratio is used as the weight, and the preset complex weight is weighted to obtain the complex weight, that is, the complex weight is equal to 1.2 times 0.5, which is 0.6. Further, 1 is subtracted from the complex weight, and the difference between the two is used as the skill weight, that is, the skill weight is 1 minus 0.6, which is 0.4.

[0059] According to the complex weight and skill weight, the talent matching degree of multiple idle workers is calculated. The talent matching degree calculation formula is:

[0060] , where P is the talent matching degree, w f and w j are complexity weight and skill weight respectively, Y is service adaptability, Z is demand complexity, and J is skill matching.

[0061] Then, according to the calculation formula, the ratios of the multiple service strains and the demand complexity are calculated respectively, and the ratios are set as strain matching degrees to obtain multiple strain matching degrees. For example, if the service strain is 10% and the demand complexity is 40%, then the strain matching degree is 25%. The greater the service strain and the smaller the demand complexity, the greater the strain matching degree, indicating that the worker performs better in coping with changes in complex tasks, and therefore can be given priority in being assigned to complex or changeable tasks.

[0062] Further, according to the calculation formula, the multiple strain matching degrees and the multiple skill matching degrees are weightedly calculated according to the complex weight and the skill weight to obtain multiple talent matching degrees. For example, assuming that the complex weight is 0.6, the skill weight is 0.4, the strain matching degree is 25%, and the skill matching degree is 60%, then the talent matching degree is 39%. Finally, the multiple talent matching degrees are arranged from large to small to obtain a talent matching degree sequence, and talent matching is displayed according to the talent matching degree sequence, that is, laborers with large talent matching degrees are displayed first, and further, idle laborers with the largest talent matching degrees can be selected for recommendation.

[0063] By comprehensively considering complexity weight and skill weight, the matching degree of workers can be quantified more accurately, especially in high-complexity tasks, workers with strong adaptability can be given priority, while in tasks with high skill requirements, more attention is paid to skill matching. This flexible weighting method makes the system more intelligent and adaptable in matching; by sorting and displaying according to talent matching, it is possible to quickly find the workers who best meet the task requirements and achieve efficient matching, while ensuring that complex or high-demand tasks are given priority to suitable workers, thereby improving the overall service quality.

[0064] In summary, the intelligent matching method for vocational skilled personnel and labor employment provided by the present invention has the following technical effects:

[0065] By receiving the employment demand information of the user, and analyzing the employment category and demand complexity of the employment demand information; then, according to the employment category, multiple idle workers to be matched are retrieved, and multiple professional skill information of the multiple idle workers is obtained, and further skill matching analysis is performed based on the multiple professional skill information and employment demand information to obtain multiple skill matching degrees; on the other hand, multiple historical service data sequences of the multiple idle workers are retrieved, and service strain degree analysis of the multiple idle workers is performed respectively according to the multiple historical service data sequences to obtain multiple service strain degrees; then, weights are configured according to the demand complexity, and weighted calculations are performed on the demand complexity, multiple service strain degrees and multiple skill matching degrees to obtain multiple talent matching degrees, and talent sorting and matching display are performed based on the multiple talent matching degrees; that is, through multi-dimensional data analysis and comprehensive evaluation, the complexity of the task, the professional skills and adaptability of the workers can be fully considered, the precision and comprehensiveness of talent matching can be improved, the technical goal of accurately matching skilled talents based on employment needs can be achieved, and the efficiency and quality of talent matching can be significantly improved, thereby improving the task success rate and service quality.

[0066] Embodiment 2: Based on the same inventive concept as the intelligent matching method for labor service of vocational skilled personnel in the aforementioned embodiment, the present invention also provides an intelligent matching system for labor service of vocational skilled personnel, please refer to the attached Figure 2 ,include:

[0067] The labor demand analysis module 11 is used to receive the labor demand information of the user and analyze the labor category and demand complexity of the labor demand information; the skill matching analysis module 12 is used to retrieve multiple idle workers to be matched according to the labor category, and perform skill matching analysis based on multiple professional skill information of the multiple idle workers in combination with the labor demand information to obtain multiple skill matching degrees; the service strain analysis module 13 is used to retrieve multiple historical service data sequences of the multiple idle workers, perform service strain analysis on the multiple idle workers respectively, and obtain multiple service strains; the talent matching calculation module 14 is used to configure weights according to the demand complexity, perform weighted calculation on the demand complexity, multiple service strains and multiple skill matching degrees, obtain multiple talent matching degrees, and perform sorting and matching display.

[0068] Furthermore, the intelligent matching system for vocational skills talent and labor employment is also used for:

[0069] Receive labor demand information input by a user; input the labor demand information into a pre-trained labor demand parser, perform labor demand parsing, and output a labor category, wherein the labor demand parser is trained using a sample labor demand information set and a sample labor category set until convergence; calculate and analyze the demand complexity of the labor demand information based on similar labor demand information of the labor category.

[0070] Furthermore, the intelligent matching system for vocational skills talent and labor employment is also used for:

[0071] According to the employment category, retrieve the M most recent employment demand information of the same employment category, where M is an integer greater than 1; calculate the similarity between the M pieces of similar employment demand information and the employment demand information, and calculate the average to obtain the demand similarity; subtract the demand similarity from 1 to obtain the demand complexity.

[0072] Furthermore, the intelligent matching system for vocational skills talent and labor employment is also used for:

[0073] According to the employment category, multiple idle workers that are currently idle and match the employment category are retrieved; multiple professional skill information of the multiple idle workers is called, and the employment demand information is respectively combined and input into a pre-trained skill matching analyzer, and multiple skill matching degrees are obtained as output.

[0074] Furthermore, the intelligent matching system for vocational skills talent and labor employment is also used for:

[0075] According to the labor matching data in historical time, sample employment demand information sets and sample occupational skill information sets are collected, and according to the average employment evaluation data under different sample employment demand information and sample occupational skill information, the sample skill matching degree sets are labeled; the sample employment demand information sets, sample occupational skill information sets and sample skill matching degree sets are used as supervised training data and verification data, and a machine learning algorithm is used to train a skill matching analyzer and verify that the convergence requirements are met.

[0076] Furthermore, the intelligent matching system for vocational skills talent and labor employment is also used for:

[0077] Retrieve multiple historical service data sequences of the multiple idle workers, and extract historical labor demand information within the multiple historical service data sequences to obtain multiple historical labor demand information sequences; respectively calculate the similarity between each historical labor demand information within the multiple historical labor demand information sequences and the labor demand information to obtain multiple historical labor demand similarity sequences; randomly extract a number of first historical labor demand similarities within the first historical labor demand similarity sequence of the first idle worker, respectively calculate the difference amplitudes with the mean of the first historical labor demand similarity sequence, and calculate the mean of the several difference amplitudes to obtain a first service strain degree; continue to calculate and obtain multiple service strain degrees based on the multiple historical labor demand similarity sequences.

[0078] Furthermore, the intelligent matching system for vocational skills talent and labor employment is also used for:

[0079] According to the employment demand information in historical time, the average demand complexity is calculated; according to the ratio of the demand complexity and the average demand complexity, the preset complexity weight is corrected and calculated to obtain the complexity weight, and the skill weight is obtained by subtracting the complexity weight from 1, wherein the preset complexity weight is 0.5; the ratios of the multiple service strain degrees to the demand complexity are calculated respectively to obtain multiple strain matching degrees; according to the complexity weight and the skill weight, the multiple strain matching degrees and the multiple skill matching degrees are weightedly calculated to obtain multiple talent matching degrees; according to the multiple talent matching degrees, they are sorted and matched and displayed.

[0080] Embodiment three, based on the same inventive concept as the intelligent matching system for labor employment of professional skilled personnel in the aforementioned embodiment, the present invention also provides an intelligent matching platform for labor employment of professional skilled personnel, which includes the intelligent matching system for labor employment of professional skilled personnel in Embodiment two, and is used to perform corresponding functions.

[0081] Example 4, please refer to Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a first computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the first computer program 511, the following steps are implemented: receiving the user's employment demand information, and analyzing the employment category and demand complexity of the employment demand information; according to the employment category, retrieving multiple idle workers to be matched at present, and performing skill matching analysis based on multiple professional skill information of the multiple idle workers and combining the employment demand information to obtain multiple skill matching degrees; retrieving multiple historical service data sequences of the multiple idle workers, and performing service strain degree analysis on the multiple idle workers respectively to obtain multiple service strain degrees; according to the demand complexity, configuring weights, performing weighted calculation on the demand complexity, multiple service strain degrees and multiple skill matching degrees, obtaining multiple talent matching degrees, and performing sorting and matching display.

[0082] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0083] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0084] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0085] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0086] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0087] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0088] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. An intelligent matching method for vocational skills talent labor employment, characterized in that: Methods include: Receive the user's employment demand information, and analyze the employment category and demand complexity of the employment demand information; According to the employment category, multiple idle workers to be matched are retrieved, and skill matching analysis is performed based on multiple professional skill information of the multiple idle workers and the employment demand information to obtain multiple skill matching degrees; Retrieving multiple historical service data sequences of the multiple idle workers, respectively performing service susceptibility analysis on the multiple idle workers, and obtaining multiple service susceptibility; According to the complexity of the demand, weights are configured, and weighted calculations are performed on the complexity of the demand, multiple service adaptability and multiple skill matching degrees to obtain multiple talent matching degrees, and then sort and match them for display; The process of retrieving multiple historical service data sequences of the multiple idle workers and performing service susceptibility analysis on the multiple idle workers to obtain multiple service susceptibility comprises: Retrieving multiple historical service data sequences of the multiple idle workers, and extracting historical labor demand information in the multiple historical service data sequences to obtain multiple historical labor demand information sequences; Respectively calculating the similarity between each piece of historical labor demand information in the plurality of historical labor demand information sequences and the labor demand information to obtain a plurality of historical labor demand similarity sequences; In the first historical labor demand similarity sequence of the first idle worker, a number of first historical labor demand similarities are randomly selected, and the difference amplitudes with the mean of the first historical labor demand similarity sequence are respectively calculated, and the mean of the number of difference amplitudes is calculated to obtain a first service strain degree; Continuing to calculate and obtain multiple service strains according to the multiple historical labor demand similarity sequences; According to the complexity of the demand, weights are configured, and weighted calculations are performed on the complexity of the demand, multiple service adaptability and multiple skill matching degrees to obtain multiple talent matching degrees, which are sorted and matched and displayed, including: Based on the historical labor demand information, calculate and obtain the average demand complexity; According to the ratio of the demand complexity to the average demand complexity, the preset complexity weight is corrected and calculated to obtain the complexity weight, and the skill weight is obtained by subtracting the complexity weight from 1, wherein the preset complexity weight is 0.5; Calculating the ratios of the multiple service strain degrees to the demand complexity respectively to obtain multiple strain matching degrees; According to the complex weight and the skill weight, weighted calculation is performed on the multiple strain matching degrees and the multiple skill matching degrees to obtain multiple talent matching degrees; According to the matching degrees of the multiple talents, the talents are sorted and matched and displayed.

2. The intelligent matching method for vocational skills personnel and labor employment according to claim 1 is characterized in that: Receive the user's employment demand information, and analyze the employment category and demand complexity of the employment demand information, including: Receive labor demand information input by users; Input the labor demand information into a pre-trained labor demand parser, perform labor demand parsing, and output the obtained labor category, wherein the labor demand parser is trained with a sample labor demand information set and a sample labor category set until convergence; Based on similar employment demand information of the employment category, the demand complexity of the employment demand information is calculated and analyzed.

3. The intelligent matching method for vocational skills personnel and labor employment according to claim 2 is characterized in that: According to the same type of employment demand information of the employment category, the demand complexity of the employment demand information is calculated and analyzed, including: According to the employment category, retrieve the M most recent employment demand information of the same employment category, where M is an integer greater than 1; Calculate the similarity between the M pieces of similar employment demand information and the employment demand information, and calculate the average to obtain the demand similarity; The demand complexity is obtained by subtracting the demand similarity from 1.

4. The intelligent matching method for vocational skills personnel and labor employment according to claim 1 is characterized in that: According to the employment category, multiple idle workers to be matched are retrieved, and skill matching analysis is performed based on multiple professional skill information of the multiple idle workers and combined with the employment demand information to obtain multiple skill matching degrees, including: According to the employment category, a plurality of idle workers that are currently idle and match the employment category are retrieved; The multiple professional skill information of the multiple idle workers is called, and the labor demand information is respectively combined and input into a pre-trained skill matching analyzer, and multiple skill matching degrees are obtained by output.

5. The intelligent matching method for vocational skills personnel and labor employment according to claim 4 is characterized in that: The training step of the skill matching analyzer includes: According to the labor matching data in the historical period, a sample labor demand information set and a sample occupational skill information set are collected, and according to the average labor evaluation data under different sample labor demand information and sample occupational skill information, a sample skill matching degree set is obtained by annotation; The sample employment demand information set, sample occupational skill information set and sample skill matching degree set are used as supervised training data and verification data, and a machine learning algorithm is used to train a skill matching analyzer and verify that convergence requirements are met.

6. The intelligent matching system for vocational skills talent and labor employment is characterized by: The steps for implementing the intelligent matching method for vocational skills personnel and labor employment as described in any one of claims 1 to 5 include: A labor demand analysis module, used to receive the labor demand information of the user and analyze the labor category and demand complexity of the labor demand information; A skill matching analysis module is used to retrieve multiple idle workers to be matched according to the employment category, and perform skill matching analysis based on multiple professional skill information of the multiple idle workers and the employment demand information to obtain multiple skill matching degrees; A service contingency analysis module is used to retrieve a plurality of historical service data sequences of the plurality of idle workers, and respectively perform service contingency analysis on the plurality of idle workers to obtain a plurality of service contingencies; The talent matching degree calculation module is used to configure weights according to the demand complexity, perform weighted calculations on the demand complexity, multiple service adaptability and multiple skill matching degrees, obtain multiple talent matching degrees, and perform sorting and matching display.

7. The intelligent matching platform for vocational skills talent and labor employment is characterized by: The platform includes the intelligent matching system for vocational skills talent and labor employment as described in claim 6.

8. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the steps of the method for intelligent matching of vocational skills talents and labor employment as described in any one of claims 1 to 5.

Images