Job matching method, device, equipment and storage medium

By obtaining resume and evaluation information, using the collaborative filtering and weighted average units of the job matching model for multi-dimensional matching processing, the problem of low resume screening accuracy in the existing technology is solved, and higher job matching accuracy and reference value are achieved. .

CN114742520BActive Publication Date: 2024-11-19ONECONNECT TECH SERVICES CO LTD SHENZHEN
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202210284416.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-03-22
Publication Date
2024-11-19
Estimated Expiration
2042-03-22

AI Technical Summary

Technical Problem

In the prior art, screening is performed based on resumes only. Due to the matching relationship or matching conditions that are too single, the accuracy of job matching is low, and the results are not of reference value.

Method used

By obtaining job seeker data containing resume information and evaluation information, the collaborative filtering unit and weighted average unit in the trained job matching model are used for initial and secondary job matching processing, and the weighted average results are combined with the weighted average, and the matching results of multiple dimensions are used to improve Match accuracy.

Benefits of technology

The accuracy of job matching is improved, and the reference value and accuracy of matching results are enhanced through the weighted average of multi-dimensional matching results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114742520B_ABST
    Figure CN114742520B_ABST
Patent Text Reader

Abstract

The present application relates to the field of artificial intelligence technology, and discloses a job matching method, device, equipment and storage medium, which obtains job-seeking information of job seekers including a resume information set and an assessment information feature set; converts the resume information set into a corresponding resume information feature set, and uses a collaborative filtering unit in a job matching model to perform a primary job matching process on the resume information feature set, thereby obtaining a primary job matching result; then uses a weighted average unit in the job matching model to perform a secondary job matching process on the assessment information feature set, thereby obtaining a secondary job matching result; performs a secondary weighted average based on the primary job matching result and the secondary job matching result, thereby obtaining a job matching result, performs job matching through multiple dimensions, and combines the job matching results of multiple dimensions, thereby improving the accuracy of job matching.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a job matching method, apparatus, computer equipment, and storage medium. Background Art

[0002] With the continuous development of internet technology, more and more companies are posting jobs online. Job seekers seeking these positions are also uploading their resumes online to apply for these positions. Recruiters review and screen the received resumes to identify those that match the posted positions. To improve recruitment efficiency, algorithms are being used to perform preliminary screening of applicants' resumes, identifying those with a high degree of match. However, screening based solely on resumes can result in low matching accuracy and unreliable results due to overly simplistic matching relationships or conditions. Summary of the Invention

[0003] The present application provides a job matching method, apparatus, computer equipment and storage medium, which solves the problem in the prior art of poor matching accuracy due to overly simple matching relationships or matching conditions when screening is performed only based on resumes.

[0004] In a first aspect, an embodiment of the present application provides a job matching method, comprising:

[0005] Obtaining job-seeking information of a job seeker including a resume information set and an assessment information feature set, and converting multiple resume information in the resume information set to obtain a resume information feature set;

[0006] Using the collaborative filtering unit in the trained job matching model, perform initial job matching processing based on the resume information feature set to obtain an initial job matching result;

[0007] Using the weighted average unit in the trained job matching model, a secondary job matching process is performed according to the evaluation information feature set to obtain a secondary job matching result;

[0008] A secondary weighted average is performed based on the initial job matching result and the secondary job matching result to obtain a job matching result.

[0009] In a second aspect, the present application also provides a job matching method and apparatus, including:

[0010] An acquisition module acquires job-seeking information of a job seeker including a resume information set and an evaluation information feature set, and converts multiple resume information in the resume information set to obtain a resume information feature set;

[0011] The initial job matching module utilizes the collaborative filtering unit in the trained job matching model to perform initial job matching processing based on the resume information feature set to obtain the initial job matching result;

[0012] A secondary job matching module, utilizing the weighted average unit in the trained job matching model to perform secondary job matching processing according to the evaluation information feature set, to obtain a secondary job matching result;

[0013] The job matching result module performs a secondary weighted average based on the initial job matching result and the secondary job matching result to obtain a job matching result.

[0014] In a third aspect, an embodiment of the present application further provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned job matching method when executing the computer program.

[0015] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned job matching method are implemented.

[0016] The present application provides a job matching method, apparatus, computer equipment and storage medium, wherein a job matching method is provided, wherein the method obtains job application information of a job seeker including a resume information set and an evaluation information feature set; converts the resume information set into a corresponding resume information feature set, performs a primary job matching process on the resume information feature set using a collaborative filtering unit in a job matching model, performs a primary job matching test using the resume experience of the job seeker, and thereby obtains a primary job matching result; then performs a secondary job matching process on the evaluation information feature set using a weighted average unit in the job matching model, performs a primary job matching test using the job seeker's job evaluation result, and obtains a secondary job matching result; performs a secondary weighted average based on the primary job matching result and the secondary job matching result to obtain a job matching result, performs job matching through multiple dimensions, and combines the job matching results of multiple dimensions, thereby improving the accuracy of job matching. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1This is a schematic diagram of an application environment of a job matching method provided in one embodiment of the present application;

[0019] Figure 2 This is a flowchart of an implementation method of a job matching method provided in one embodiment of the present application;

[0020] Figure 3 This is a flowchart of step S20 in a job matching method provided in one embodiment of the present application;

[0021] Figure 4 This is a structural diagram of a job matching method and apparatus provided in one embodiment of the present application;

[0022] Figure 5 Schematic diagram of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0024] The job matching method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Figure 1 As shown, a client (computer device) communicates with a server via a network. The client (computer device) includes, but is not limited to, various personal computers, laptops, smartphones, tablets, cameras, and portable wearable devices. The server can be a standalone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0025] The job matching method provided in this embodiment can be executed by the server. For example, the client sends the job application information to the server. The server executes the job matching method provided in this embodiment based on the job application information, and then obtains the job matching result after job matching processing, and finally sends the job matching result to the client.

[0026] exist Figure 1In some other scenarios, the job matching method can also be executed by the client, directly based on the client's job search information, by executing the job matching method provided in this embodiment to obtain the job matching result after job matching processing, and then send the job matching result to the server for storage.

[0027] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0028] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0029] In one embodiment, the present application discloses a job matching method, which is based on big data processing technology, mines user information of job seekers for big data analysis, matches jobs through information in multiple dimensions, and combines job matching results in multiple dimensions to improve the accuracy of job matching.

[0030] Figure 2 FIG1 shows a flowchart of a job matching method according to an embodiment of the present application. Figure 2 As shown, a job matching method is provided, and its technical solution mainly includes the following steps S10-S40:

[0031] Step S10: obtaining job-seeking information of a job seeker including a resume information set and an assessment information feature set, and converting multiple resume information in the resume information set to obtain a resume information feature set;

[0032] In step S10, based on the job recruitment requirements, the job application information of participating job seekers is collected and analyzed to serve as a data basis for job matching calculation. This information is collected from multiple dimensions, including but not limited to multiple resume information and test information such as the results of various ability tests obtained by providing job tests.

[0033] In one embodiment, since the resume information set corresponding to the resume is generally information, it is necessary to convert multiple resume information in the resume information set into corresponding discrete values ​​or character vectors to obtain the corresponding resume information feature set for subsequent analysis.

[0034] In one embodiment, job seekers need to refine their information based on their actual information for the job they are applying for. In this embodiment, the analysis is primarily conducted through two dimensions: resume information and assessment information. The resume information set can be collected using a resume template provided by a recruitment website, or a resume template required for a job matching application can be provided to obtain a resume and a corresponding resume information set. Resumes typically include multiple pieces of information such as professional background, industry, years of work experience, major, educational background, previous location, work experience, professional experience, and professional skills.

[0035] The assessment test is sent to the job seeker for improvement; the assessment test is used to test the job seeker's quality, and the assessment information is mainly the quality test provided according to the recruitment position. Usually the quality test includes IQ, EQ, experience quotient, adversity quotient, attitude quotient, resource quotient, and TEL mainly refers to thinking, doing things, and leading a team, thereby forming multiple quantitative quality data as a set of assessment information.

[0036] In one embodiment, resume information is converted one by one into corresponding discrete values ​​using a one-hot algorithm to obtain a resume information feature set. An example of converting resume information into resume information features is as follows: a resume information item is "education information," which typically includes ["high school," "vocational school," "junior college," "undergraduate," and "graduate student"]. According to the principle of encoding N states using an N-bit state register, this element has only two states, so N = 5. After processing, the values ​​are as follows: (high school → 10000), (vocational school → 01000), (junior college → 00100), (undergraduate → 00010), (graduate student → 00001); It also includes ["full-time", "part-time"]. According to the principle of encoding N states using an N-bit status register, this element has only two states, so N=2. After processing, it is as follows: (full-time→10), (part-time→01). When an "education information" is ["full-time graduate student"], the project information characteristics of the complete discretization result are: [1, 0, 0, 0, 0, 0, 1], which corresponds to the combined encoding of full-time (10) and graduate student (00001).

[0037] In another embodiment, a word segmenter is used to process the resume information in the resume information set into corresponding character vectors, and the character vectors are used as corresponding project information features. Wherein, word segmenters include but are not limited to Ansj, word2vec, ICTCLAS and HanLP. In this embodiment, the word2vec algorithm is used as a word segmenter. The word2vec algorithm is an algorithm for converting words into word embedding vectors. Each character or word in the project information text is vector-converted, and the character embedding vector and the word embedding vector after vector conversion are spliced ​​to obtain vector text as the corresponding project information feature. Wherein, the vector conversion includes the conversion process of converting characters into character embedding vectors and converting words into word embedding vectors, and the vector text is a vector array including character embedding vectors and / or word embedding vectors.

[0038] Understandably, the one-hot algorithm, also known as one-hot encoding, primarily uses an N-bit state register to encode N states. Each state is represented by its own register bit, and only one bit is active at any given time. For each feature, if it has m possible values, then after one-hot encoding, it becomes m binary features. Furthermore, these features are mutually exclusive, with only one active at a time.

[0039] Step S20: using the collaborative filtering unit in the trained job matching model to perform initial job matching processing based on the resume information feature set to obtain an initial job matching result;

[0040] In step S20, the trained job matching model performs multiple job matching operations based on multiple dimensions of the job seeker's job application information, thereby improving the accuracy of the resulting job matching results. The collaborative filtering unit within the trained job matching model performs an initial job matching operation on the resume information feature set, and the dimensions of this resume information feature set serve as the initial job matching result. However, the matching operations for each dimension do not need to be performed in a specific order and can be performed in parallel.

[0041] In one embodiment, the job matching model is constructed by a collaborative filtering algorithm unit and a weighted average algorithm unit. The collaborative filtering algorithm unit is used to process the resume information features in the project information feature set, and the weighted average algorithm unit is used to process the evaluation information features in the project information feature set, and the corresponding initial job matching results and secondary job matching results are obtained, and finally the job matching results are obtained.

[0042] Understandably, collaborative filtering, as a classic recommendation algorithm, is based on finding similarities (between users or between objects) through group behavior, and using this similarity to make decisions and recommendations for users. The core of collaborative filtering is to calculate the similarity between objects and the similarity between users. Generally, there are m items and m users' data. Only some users and some data have rating data, while the rest of the ratings are blank. In this case, we need to use the existing sparse data to predict the rating relationship between those blank items and data, find the highest-rated items and recommend them to users. In this embodiment, it is mainly used to recommend job seekers who may be suitable for the position based on the sample resume information characteristics of current employees using collaborative filtering.

[0043] like Figure 3 As shown, the specific implementation process of step S20 of this embodiment is as follows: using the collaborative filtering unit in the trained job matching model to perform initial job matching processing based on the resume information feature set to obtain the initial job matching result. As an example, step S20 includes:

[0044] Step S201: using the collaborative filtering unit to match each resume information feature with a corresponding resume information feature score;

[0045] Step S202: Acquire multiple sample resume information features and corresponding sample resume information feature scores in the collaborative filtering unit;

[0046] Step S203: constructing a collaborative matrix based on the resume information features, the resume information feature scores, the sample resume information features, and the sample resume information feature scores;

[0047] Step S204: Calculate the similarity score between the resume information features and the sample resume information features according to the collaboration matrix as the initial job matching result.

[0048] In step S201, the collaborative filtering unit in the trained job matching model recommends candidates potentially suitable for the position based on a set of sample resume information features from current employees. First, by matching resume information features to corresponding resume information feature scores, the trained collaborative filtering unit has quantified the content range of each resume information feature. For ease of understanding, a simple example is provided. A higher score indicates a more robust information feature. For ease of identification, let's assume the resume information corresponding to the "full-time" feature is a good choice. The content range of the corresponding resume information includes both full-time and part-time. A score of 2 is assigned to "full-time" and a score of 1 is assigned to "part-time." Full-time applicants have a better quantitative score than part-time applicants. If the resume information corresponding to the "graduate student" feature is a good choice, the content range includes associate's, undergraduate's, graduate's, and doctoral degrees. The scores are 1, 2, 3, and 4, respectively. This score is 3, indicating that graduate students have a better quantitative score than both associate's and undergraduate degrees.

[0049] In step S202, a sample resume information feature set from the trained collaborative filtering unit and sample resume information feature scores corresponding to multiple sample resume information features in the sample resume information feature set are obtained. After training based on the resume information features of multiple staff members in the position, a score with a high degree of similarity in quantifying the quality of the position personnel is obtained. This sample resume information feature score is used as the sample resume information feature. This sample resume information feature score is then evaluated as a template standard for the position to ensure that the position matching model recommends job seekers who are more suitable for the position. For ease of understanding, a simple example is provided. For example, if the "personality" sample resume information feature score in the sample resume information feature is 7, corresponding to "outgoing," and the "personality" resume information feature score in the resume information feature of the job seeker to be matched is 3, corresponding to "relatively introverted," then the similarity between the resume information features of the job seeker and the sample resume information features is likely low, making the job seeker unsuitable for the position.

[0050] In step S203, based on the resume information feature set and the resume information feature scores corresponding to the multiple resume information features and the resume information feature scores corresponding to the multiple sample resume information features and the sample resume information feature scores corresponding to the sample resume information features in the sample resume information feature set, the resume information feature set and the sample resume information feature set are sorted according to the type of each resume information feature, and a collaborative matrix is ​​constructed for similarity calculation.

[0051] In step S204, different similarity calculation functions can be used to perform similarity calculation on the collaboration matrix according to different environments. The similarity calculation function can be a sim function, which uses the sample resume information feature set as the basis to calculate the similarity between the sample resume information features of each same type and the resume information features. After the similarity calculation corresponding to each sample resume information feature is completed, the similarity score is summed up to obtain the similarity score as the initial job matching result.

[0052] In one embodiment, collaborative filtering recommendation is divided into three types: the first is user-based collaborative filtering, the second is item-based collaborative filtering, and the third is model-based collaborative filtering.

[0053] Step S30: using the weighted average unit in the trained job matching model to perform secondary job matching processing according to the evaluation information feature set to obtain a secondary job matching result;

[0054] In step S30, since there are multiple evaluation results obtained through the evaluation test, the evaluation results are used as evaluation information features. According to the requirements of the position, the weighted average unit in the trained position matching model is used to perform a weighted average on each evaluation information feature to obtain a secondary position matching result. The weighted average unit matches the evaluation information feature weight values ​​corresponding to each evaluation information feature, and the evaluation information features are weighted averaged according to the weight values ​​of each evaluation information feature to obtain the weighted average of the evaluation information as the secondary position matching result.

[0055] In one embodiment, the assessment tests corresponding to the assessment information features are quantitatively evaluated to assess the applicant's competence. For ease of understanding, a simple example is used to test the applicant's IQ, EQ, and professional knowledge using a series of test questions designed to assess different types of knowledge. These scores are then calculated, respectively, to determine their IQ, EQ, and professional knowledge scores. Based on the job requirements, positions requiring higher IQ scores are assigned a higher weight. The specific weights are calculated and determined based on the sample assessment information feature set.

[0056] Step S40: performing a secondary weighted average based on the initial job matching result and the secondary job matching result to obtain a job matching result;

[0057] In step S40, the job matching results obtained twice are weighted averaged according to the weight values ​​of the initial job matching result and the secondary job matching result, and the final result is used as the job matching result, thereby improving the preliminary screening of the career matching degree of the recruited job seekers, thereby improving the accuracy of screening job seekers corresponding to the positions.

[0058] In another embodiment, the screening for job matching results can be multiple times. According to different needs and environments, multiple job matching processes can be performed based on the dimensions of the job search information of specific job seekers. Based on the results of multiple job matching processes, a final match is performed, thereby obtaining a more accurate job search accuracy.

[0059] The embodiment shown below differs in that, before the step S20 in which the collaborative filtering unit in the trained job matching model is used to perform initial job matching processing based on the resume information feature set to obtain the initial job matching result, the embodiment further includes the step of constructing the job matching model by a collaborative filtering algorithm unit and a weighted average algorithm unit, and processing the resume information features in the project information feature set using the collaborative filtering algorithm unit respectively. Specifically, steps S51-S53:

[0060] Step S51: Use the hierarchical analysis method to compare the information features of each employee's resume in pairs; quantify the importance of each employee's resume information feature according to the rating level, and obtain a quantitative standard that matches the resume information feature score with the resume information feature score.

[0061] In step S51, since resume information features are usually discrete values, they cannot be directly used in the collaborative filtering unit to calculate job matching results. In advance, training is performed using employee resume information features to derive quantitative standards for establishing information feature scores corresponding to each resume information feature.

[0062] In one embodiment, quantification of resume information features is primarily performed using a pairwise comparison matrix within the Analytic Hierarchy Process (AHP). This approach is illustrated by way of example. A pairwise comparison matrix is ​​established based on multiple employee resume information features using the AHP method. Pairwise comparisons are then made between employee resume information features for the same project. The use of relative scales reduces the difficulty of comparing factors of varying nature, thereby improving accuracy. A pairwise comparison matrix is ​​formed based on importance ratings, and corresponding quantification is performed based on the comparison results for several pairs of employee resume information features, thereby obtaining a quantitative standard for matching resume information feature scores to corresponding resume information feature scores.

[0063] Understandably, the Analytic Hierarchy Process (AHP) is a systematic, hierarchical analytical method that combines qualitative and quantitative analysis. This method is characterized by using less quantitative information to mathematically analyze the decision-making process based on an in-depth study of the nature, influencing factors, and internal relationships of complex decision-making problems. This provides a simple decision-making method for complex decision-making problems with multiple objectives, multiple criteria, or unstructured characteristics. Based on the nature of the problem and the overall goal to be achieved, the AHP breaks the problem down into its various components. It then clusters and combines the factors at different levels according to their interrelationships and affiliations, forming a multi-level analytical structure model. Ultimately, the problem is reduced to determining the relative importance of the lowest level relative to the highest level, or ranking the relative merits.

[0064] Step S52: Input multiple employee resume information into the collaborative filtering unit to construct an employee collaborative matrix; the employee resume information set includes employee resume information features and corresponding employee resume information feature scores; filter out the employee resume information feature scores corresponding to the employee resume information features with high similarity between the employee resume information sets, and use them as the sample resume information feature scores corresponding to each sample resume information feature in the sample resume information feature set.

[0065] In step S52, in order to improve the accuracy of the collaborative filtering unit in matching recruitment positions, the employee resume information feature set is used as a training sample to predict the score characteristics of each resume information feature of the position employee, and the similarity recommendation feature of the collaborative filtering unit is used to perform accurate position matching.

[0066] In one embodiment, a plurality of employee resume information sets including employee resume information features and corresponding employee resume information feature scores for the position are input into the collaborative filtering unit, and after being sorted according to each, an employee collaborative matrix is ​​established to calculate similarity. The commonalities between the employee resume information feature scores in each employee resume information feature among the plurality of employee resume information are screened out, that is, the employee resume information feature with the most similar scores is used as the characteristics of the employee in the position. The employee resume information feature scores corresponding to the employee resume information features with high similarity are retained as the sample resume information feature scores corresponding to each sample resume information feature in the sample resume information feature set, for use in subsequent job matching processing.

[0067] Step S53: Calculate the weight value of the evaluation information feature according to multiple sample evaluation information feature sets using the entropy weight method; standardize each sample evaluation information feature in the sample evaluation information feature set to obtain a normalized sample evaluation information feature set; calculate the weight value of the multiple normalized sample evaluation information sets using the information entropy formula to obtain the weight value of the sample evaluation information feature as the evaluation information feature weight value.

[0068] In step S53, an assessment test is sent to the employee in the position, and the completed assessment test results are used as a sample assessment information feature set as a training sample, which is input into the weighted averaging unit for training. The entropy weight method is used to calculate the assessment information feature weights based on multiple sample assessment information feature sets. The weight values ​​corresponding to each assessment information feature are calculated and used to calculate the weighted average of the assessment information feature set.

[0069] In one embodiment, the sample evaluation information feature set includes a positive sample evaluation information feature set and a negative sample evaluation information feature set. The so-called positive sample evaluation information feature set represents employees with good work performance, while the negative sample evaluation information feature set represents employees with seriously poor work performance. First, the sample evaluation information features of the positive sample evaluation information feature set and the negative sample evaluation information feature set are pre-processed, that is, the sample evaluation information features are standardized or normalized. For the normalized sample evaluation information after normalization, the proportion of each normalized sample evaluation information in the final score is calculated, and the information entropy of each normalized sample evaluation information is calculated. The entropy is continuously reduced to obtain the weight value corresponding to the sample evaluation information feature, which is used as the evaluation information feature weight value.

[0070] In one embodiment, the weight values ​​of the initial job matching results, the secondary job matching results, and N job matching results of other dimensions that may appear are calculated using the entropy weight method. By utilizing multiple job matching result samples, the entropy weight method is used to continuously select entropy reduction of the multiple job matching result samples, thereby obtaining the corresponding weight value information of the initial job matching results, the secondary job matching results, and N job matching results of other dimensions that may appear.

[0071] In another embodiment, the method of calculating the weight of the user classification model further includes using a linear regression algorithm, a factor analysis method, and a principal component method.

[0072] Understandably, the entropy weight method determines objective weights based on the variability of indicators. A lower information entropy indicates greater variability, more information, and a greater role in comprehensive evaluation, resulting in a higher weight. Conversely, a higher information entropy indicates lower variability, less information, and a smaller role in comprehensive evaluation, resulting in a lower weight.

[0073] In one embodiment, a job matching method and apparatus is provided, which corresponds one-to-one to the job matching method in the above embodiment. Figure 4 As shown, the job matching method and apparatus includes an acquisition module 11, a primary job matching module 12, a secondary job matching module 13, and a job matching result module 14. The functional modules are described in detail as follows:

[0074] An acquisition module 11 acquires job-seeking information of a job seeker including a resume information set and an assessment information feature set, and converts multiple resume information in the resume information set to obtain a resume information feature set;

[0075] The initial job matching module 12 utilizes the collaborative filtering unit in the trained job matching model to perform initial job matching processing based on the resume information feature set to obtain an initial job matching result;

[0076] A secondary job matching module 13 uses the weighted average unit in the trained job matching model to perform secondary job matching processing according to the evaluation information feature set to obtain a secondary job matching result;

[0077] The job matching result module 14 performs a secondary weighted average based on the initial job matching result and the secondary job matching result to obtain a job matching result.

[0078] For the specific definition of the job matching method and apparatus, please refer to the definition of the job matching method above and will not be repeated here. Each module in the above-mentioned job matching method and apparatus can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software so that the processor can call and execute the operations corresponding to each of the above modules.

[0079] In one embodiment, a computer device is provided. The computer device can be a client or a server. The internal structure diagram thereof can be as follows: Figure 5As shown. The computer device includes a processor, memory, network interface, and database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium and an internal memory. The readable storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the readable storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When executed by the processor, the computer program implements a job matching method.

[0080] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the job matching method in the above embodiment is implemented.

[0081] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the job matching method in the above embodiment is implemented.

[0082] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0083] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0084] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A job matching method, characterized in that: include: Acquire job-seeking information of job seekers including a resume information set and an evaluation information feature set, and transform multiple resume information in the resume information set to obtain a resume information feature set; Calculate the weight value of the evaluation information feature according to the multiple sample evaluation information feature sets using the entropy weight method; Normalizing each sample evaluation information feature in the sample evaluation information feature set to obtain a normalized sample evaluation information feature set; Calculating the weight values ​​of the plurality of normalized sample evaluation information sets by using an information entropy formula to obtain the weight values ​​of the sample evaluation information features as the evaluation information feature weight values; Using the collaborative filtering unit in the trained job matching model, perform initial job matching processing according to the resume information feature set to obtain an initial job matching result; Using the weighted average unit in the trained job matching model, a secondary job matching process is performed according to the evaluation information feature set to obtain a secondary job matching result; Perform a secondary weighted average based on the initial job matching result and the secondary job matching result to obtain a job matching result; The collaborative filtering unit in the trained job matching model is used to perform initial job matching processing according to the resume information feature set to obtain the initial job matching result, including: Using the collaborative filtering unit, each of the resume information features is matched to a corresponding resume information feature score; obtaining a plurality of sample resume information features and corresponding sample resume information feature scores in the collaborative filtering unit; constructing a collaborative matrix based on the resume information features, the resume information feature scores, the sample resume information features and the sample resume information feature scores; calculating a similarity score between the resume information features and the sample resume information features based on the collaborative matrix as an initial job matching result; The method of using the weighted average unit in the trained job matching model to perform secondary job matching processing according to the evaluation information feature set to obtain a secondary job matching result includes: The weighted average unit is used to match the assessment information feature weight value corresponding to each assessment information feature; the assessment information features are weighted averaged according to each assessment information feature weight value to obtain the assessment information weighted average value as the secondary job matching result.

2. The job matching method according to claim 1, characterized in that: The job-seeking information of the job seeker including the resume information set and the assessment information feature set is obtained; Before the step of converting the multiple resume information in the resume information set to obtain the resume information feature set, the method further includes: Sending the assessment test to the job seeker for completion; the assessment test is used to test the quality of the job seeker; Receive the improvement result of the evaluation test and obtain multiple test scores as corresponding evaluation information.

3. The job matching method according to claim 1, characterized in that: Before the step of using the collaborative filtering unit in the trained job matching model to perform initial job matching processing according to the resume information feature set to obtain the initial job matching result, the method further includes: Inputting multiple employee resume information into the collaborative filtering unit to construct an employee collaborative matrix; the employee resume information set includes employee resume information features and corresponding employee resume information feature scores; The employee resume information features and corresponding employee resume information feature scores with high similarity between the employee resume information sets are screened out as the sample resume information feature scores corresponding to each sample resume information feature in the sample resume information feature set.

4. The job matching method according to claim 3, characterized in that: Before the step of inputting the resume information of multiple employees into the collaborative filtering unit to construct the employee collaborative matrix, the step further includes: The hierarchical analysis method is used to compare the information characteristics of the resumes of the employees in pairs; The importance rating of each employee's resume information feature is quantified to obtain a quantitative standard corresponding to the resume information feature score according to the resume information feature score matching.

5. A job matching method and device, characterized in that: include: An acquisition module is used to acquire job-seeking information of job seekers including a resume information set and an evaluation information feature set, and transform multiple resume information in the resume information set to obtain a resume information feature set, and use an entropy weight method to calculate the evaluation information feature weight value according to multiple sample evaluation information feature sets; Standardize each sample evaluation information feature in the sample evaluation information feature set to obtain a normalized sample evaluation information feature set; calculate the weight value of multiple normalized sample evaluation information sets using an information entropy formula to obtain the weight value of the sample evaluation information feature as the evaluation information feature weight value; The initial job matching module is used to use the collaborative filtering unit in the trained job matching model to perform initial job matching processing according to the resume information feature set to obtain the initial job matching result; wherein, the collaborative filtering unit in the trained job matching model is used to perform initial job matching processing according to the resume information feature set to obtain the initial job matching result, including: Using the collaborative filtering unit, each of the resume information features is matched to a corresponding resume information feature score; obtaining a plurality of sample resume information features and corresponding sample resume information feature scores in the collaborative filtering unit; constructing a collaborative matrix based on the resume information features, the resume information feature scores, the sample resume information features and the sample resume information feature scores; calculating a similarity score between the resume information features and the sample resume information features based on the collaborative matrix as an initial job matching result; A secondary job matching module is used to use the weighted average unit in the trained job matching model to perform secondary job matching processing according to the evaluation information feature set to obtain a secondary job matching result; wherein, using the weighted average unit in the trained job matching model to perform secondary job matching processing according to the evaluation information feature set to obtain a secondary job matching result includes: Matching the evaluation information feature weight value corresponding to each evaluation information feature through the weighted average unit; performing weighted average calculation on the evaluation information features according to each evaluation information feature weight value, and obtaining the evaluation information weighted average value as the secondary job matching result; The job matching result module is used to perform a secondary weighted average based on the initial job matching result and the secondary job matching result to obtain a job matching result.

6. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the job matching method according to any one of claims 1 to 4 is implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the job matching method as described in any one of claims 1 to 4 is implemented.

Citation Information

Patent Citations

  • A job and talent matching and recommending method for human resource enterprises

    CN109885761A

  • Campus recruitment management system and method

    CN109978510A

  • Recruitment recommendation method based on talent portraits

    CN110414917A

  • Recruitment method and system for remote self-service evaluation

    CN111062613A