Human resources data management method and system based on big data

Abstract

The present disclosure relates to a human resources data management method and system based on big data, and relates to the technical field of human resources data management. The method includes: semantically encoding the resume data of the resumes of the employees marked as successful employees to obtain a set of semantically encoded feature vectors of the resume data of successful employees; performing autocorrelation resume data saliency characterization on the set of semantically encoded feature vectors of the resume data of successful employees to obtain a semantically fused feature vector of the commonality of the features of the resumes of successful employees; semantically encoding the resumes of the objects to be evaluated to obtain a semantically encoded feature vector of the resumes of the objects to be evaluated; calculating the hash similarity between the semantically encoded feature vector of the resumes of the objects to be evaluated and the semantically fused feature vector of the commonality of the features of the resumes of successful employees to determine whether to filter out the resumes of the objects to be evaluated. In this way, intelligent talent recruitment for human resources data management can be realized, thereby improving management efficiency and quality, and meeting the talent recruitment needs of modern enterprises.

Description

Technical Field

[0001] The present disclosure relates to the technical field of human resource data management, and in particular, to a human resource data management method and system based on big data. Background Art

[0002] Human resource data management refers to the use of data science, technology, and methods to manage and optimize a company's human resource activities, including recruitment, training, performance evaluation, and employee benefits management. Traditional human resource data management relies primarily on manual processing and simple database records, which has some obvious shortcomings.

[0003] When it comes to talent recruitment within human resources data management, traditional recruitment methods often rely on interviewers' subjective judgment and intuition, which are susceptible to personal bias, resulting in less objective and fair hiring decisions. Furthermore, traditional recruitment methods require significant manpower and time, potentially requiring numerous interviews, and the intensive resume screening process hinders managers' efficiency. Furthermore, traditional recruitment methods struggle to accurately predict a candidate's future performance and development potential, which can easily lead to talent mismatches and loss.

[0004] Therefore, a human resources data management solution based on big data is desired. Summary of the Invention

[0005] This summary is provided to briefly introduce concepts that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0006] In a first aspect, the present disclosure provides a human resources data management method based on big data, the method comprising:

[0007] Get a collection of resume data of employees marked as successful;

[0008] Obtain the resume of the person to be evaluated;

[0009] Performing semantic coding on each piece of resume data marked as successful employees in the set of resume data marked as successful employees to obtain a set of semantic coding feature vectors of the resume data of successful employees;

[0010] Performing autocorrelation resume data saliency characterization on the set of semantically encoded feature vectors of the successful employee resume data to obtain a semantically fused feature vector of commonality of successful employee resume features;

[0011] Performing semantic coding on the resume of the subject to be evaluated to obtain a semantic coding feature vector of the resume of the subject to be evaluated;

[0012] Calculate the hash similarity between the semantic encoding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience of the feature commonality of the resume of the successful employee, and determine whether to filter out the resume of the object to be evaluated based on the hash similarity.

[0013] Optionally, the set of semantically encoded feature vectors of the successful employee resume data is represented by autocorrelated resume data saliency to obtain a semantically fused feature vector of commonality saliency of successful employee resume features, including: passing the set of semantically encoded feature vectors of the successful employee resume data through an autocorrelated resume data saliency fusion network to obtain a semantically fused feature vector of commonality saliency of successful employee resume features.

[0014] Optionally, the set of semantically encoded feature vectors of the successful employee resume data is passed through an autocorrelation resume data saliency fusion network to obtain the commonality saliency semantic fusion feature vector of the successful employee resume features, including: passing the set of semantically encoded feature vectors of the successful employee resume data through the autocorrelation resume data saliency fusion network and processing them using the following autocorrelation saliency formula to obtain the commonality saliency semantic fusion feature vector of the successful employee resume features; wherein the autocorrelation saliency formula is:

[0015]

[0016]

[0017]

[0018] Among them, h i is the i-th successful employee resume data semantic encoding feature vector in the set of successful employee resume data semantic encoding feature vectors, and W i Represent the weight coefficient vector and weight coefficient matrix respectively, B i is the offset vector, Selu(·) represents the Selu function, e i is the attention score value of the semantic encoding feature vector of the i-th successful employee resume data, λ and α are both hyperparameters, softmax(·) represents the softmax function, t is the number of vectors in the set of semantic encoding feature vectors of the successful employee resume data, and V is the semantic fusion feature vector of the commonality of the successful employee resume features.

[0019] Optionally, the hash similarity between the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality of the feature salience of the resume of the successful employee is calculated, and based on the hash similarity, it is determined whether to filter out the resume of the object to be evaluated, including: performing feature optimization on the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality of the feature salience of the resume of the successful employee to obtain an optimized semantic coding feature vector of the resume of the object to be evaluated and an optimized semantic fusion feature vector of the commonality of the feature salience of the resume of the successful employee; calculating the hash similarity between the optimized semantic coding feature vector of the resume of the object to be evaluated and the optimized semantic fusion feature vector of the commonality of the feature salience of the resume of the successful employee; and determining whether to filter out the resume of the object to be evaluated based on a comparison between the hash similarity and a predetermined threshold.

[0020] Optionally, feature optimization is performed on the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience of the resume features of the successful employee to obtain an optimized semantic coding feature vector of the resume of the object to be evaluated and an optimized semantic fusion feature vector of the commonality salience of the resume features of the successful employee, including: respectively calculating the weighting coefficients of the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience of the resume features of the successful employee to obtain a first weighting coefficient and a second weighting coefficient; using the first weighting coefficient and the second weighting coefficient as weighting factors, weighted optimization is performed on the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience of the resume features of the successful employee to obtain the optimized semantic coding feature vector of the resume of the object to be evaluated and the optimized semantic fusion feature vector of the commonality salience of the resume features of the successful employee to obtain.

[0021] Optionally, in response to the hash similarity being less than the predetermined threshold, it is determined to filter out the resume of the subject to be evaluated.

[0022] In a second aspect, the present disclosure provides a human resources data management system based on big data, the system comprising:

[0023] A resume data acquisition module is used to obtain a collection of resume data of employees marked as successful;

[0024] A resume acquisition module for the subject to be evaluated, used to obtain the resume of the subject to be evaluated;

[0025] A first semantic encoding module is used to perform semantic encoding on each resume data marked as a successful employee in the set of resume data marked as successful employees to obtain a set of semantic encoding feature vectors of the resume data of successful employees;

[0026] An autocorrelated resume data saliency representation module is used to perform autocorrelated resume data saliency representation on the set of semantic encoding feature vectors of the successful employee resume data to obtain a common saliency semantic fusion feature vector of the successful employee resume features;

[0027] A second semantic coding module is used to semantically code the resume of the subject to be evaluated to obtain a semantic coding feature vector of the resume of the subject to be evaluated;

[0028] The resume judgment module for filtering out the object to be evaluated is used to calculate the hash similarity between the semantic encoding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience of the feature commonality of the resume of the successful employee, and determine whether to filter out the resume of the object to be evaluated based on the hash similarity.

[0029] Optionally, the autocorrelation resume data saliency representation module is used to: pass the set of semantically encoded feature vectors of the successful employee resume data through the autocorrelation resume data saliency fusion network to obtain the commonality saliency semantic fusion feature vector of the successful employee resume features.

[0030] Optionally, the autocorrelation resume data saliency representation module is used to: process the set of semantically encoded feature vectors of the successful employee resume data through the autocorrelation resume data saliency fusion network using the following autocorrelation saliency formula to obtain the commonality saliency semantic fusion feature vector of the successful employee resume features; wherein the autocorrelation saliency formula is:

[0031]

[0032]

[0033]

[0034] Among them, h i is the i-th successful employee resume data semantic encoding feature vector in the set of successful employee resume data semantic encoding feature vectors, and W i Represent the weight coefficient vector and weight coefficient matrix respectively, B i is the offset vector, Selu(·) represents the Selu function, e i is the attention score value of the semantic encoding feature vector of the i-th successful employee resume data, λ and α are both hyperparameters, softmax(·) represents the softmax function, t is the number of vectors in the set of semantic encoding feature vectors of the successful employee resume data, and V is the semantic fusion feature vector of the commonality of the successful employee resume features.

[0035] Optionally, the resume judgment module for filtering out the object to be evaluated includes: a feature optimization unit, used to perform feature optimization on the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salient features of the resume of a successful employee to obtain an optimized semantic coding feature vector of the resume of the object to be evaluated and an optimized semantic fusion feature vector of the commonality salient features of the resume of a successful employee; a hash similarity calculation unit, used to calculate the hash similarity between the optimized semantic coding feature vector of the resume of the object to be evaluated and the optimized semantic fusion feature vector of the commonality salient features of the resume of a successful employee; a resume filtering judgment unit, used to determine whether to filter out the resume of the object to be evaluated based on a comparison between the hash similarity and a predetermined threshold.

[0036] Using the above technical solution, the obtained resume data marked as successful employees is semantically encoded to obtain a set of semantically encoded feature vectors of the successful employee resume data; the set of semantically encoded feature vectors of the successful employee resume data is autocorrelatedly represented to obtain a semantically fused feature vector of the commonality of the successful employee resume features; the obtained resume of the subject to be evaluated is semantically encoded to obtain a semantically encoded feature vector of the subject to be evaluated resume; and the hash similarity between the semantically encoded feature vector of the subject to be evaluated resume and the semantically fused feature vector of the commonality of the successful employee resume features is calculated to determine whether to filter out the subject's resume. This enables intelligent talent recruitment for human resources data management, thereby improving management efficiency and quality and meeting the talent recruitment needs of modern enterprises.

[0037] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The above and other features, advantages and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale. In the drawings:

[0039] Figure 1 The figure is a flowchart showing a method for managing human resources data based on big data according to an exemplary embodiment.

[0040] Figure 2 It is a block diagram showing a human resources data management system based on big data according to an exemplary embodiment.

[0041] Figure 3 It is a block diagram of an electronic device according to an exemplary embodiment.

[0042] Figure 4This is an application scenario diagram of a human resources data management method based on big data according to an exemplary embodiment. DETAILED DESCRIPTION

[0043] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0044] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0045] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0046] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0047] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0048] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0049] First, in today's information age, big data technology has become an indispensable component of corporate management. Particularly in the field of human resources management, the application of big data can help companies make more accurate decisions in key areas such as talent recruitment, performance evaluation, and compensation management. Human resources data management methods based on big data analysis have become a key trend in corporate talent recruitment and management. With the development of big data technology, companies can leverage massive amounts of data and advanced algorithms to optimize recruitment processes, improve employee matching, and thus better identify and attract the right talent.

[0050] Based on this, the technical concept of this application is that during the talent recruitment process, enterprises use big data technology and artificial intelligence technology to analyze the resume data of successful employees and compare it with the resumes of candidates to be evaluated. Based on the semantic similarity between the common characteristics of the successful employee's resume and the resume of the candidate to be evaluated, the enterprise determines whether to filter out the resume of the candidate to be evaluated, thereby conducting efficient and objective human resources recruitment. This can realize intelligent talent recruitment based on human resources data management, thereby improving management efficiency and quality, and meeting the talent recruitment needs of modern enterprises.

[0051] In order to solve the above problems, the present disclosure provides a human resources data management method and system based on big data, which performs semantic encoding on the resume data of the obtained employees marked as successful employees to obtain a set of semantic encoding feature vectors of the resume data of successful employees; performs autocorrelation resume data saliency representation on the set of semantic encoding feature vectors of the resume data of successful employees to obtain a semantic fusion feature vector of the common saliency of the resume features of successful employees; performs semantic encoding on the resume of the obtained object to be evaluated to obtain a semantic encoding feature vector of the resume of the object to be evaluated; calculates the hash similarity between the semantic encoding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the common saliency of the resume features of successful employees to determine whether to filter out the resume of the object to be evaluated. In this way, intelligent talent recruitment for human resources data management can be realized, thereby improving management efficiency and quality, and meeting the talent recruitment needs of modern enterprises.

[0052] The specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0053] Figure 1 is a flowchart of a human resources data management method based on big data according to an exemplary embodiment. Figure 1 As shown, the method includes:

[0054] Step 101: Obtain a collection of resume data of employees marked as successful employees;

[0055] Step 102: Obtain the resume of the person to be evaluated;

[0056] Step 103: semantically encode each resume data marked as a successful employee in the set of resume data marked as successful employees to obtain a set of semantically encoded feature vectors of the resume data of successful employees;

[0057] Step 104: performing autocorrelation resume data saliency characterization on the set of semantically encoded feature vectors of the successful employee resume data to obtain a semantically fused feature vector of commonality of successful employee resume features;

[0058] Step 105: semantically encode the resume of the subject to be evaluated to obtain a semantic encoding feature vector of the resume of the subject to be evaluated;

[0059] Step 106: Calculate the hash similarity between the semantic encoding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience feature of the resume of the successful employee, and determine whether to filter out the resume of the object to be evaluated based on the hash similarity.

[0060] Specifically, in the technical solution of the present application, first, a collection of resume data of employees marked as successful is obtained, and the resume of the subject to be evaluated is obtained. Then, in order to be able to perform semantic analysis and understanding on each resume data of employees marked as successful in the collection of resume data of employees marked as successful, so as to capture the semantics of the resumes of employees marked as successful, thereby facilitating the subsequent identification of the commonalities between the semantic features of the resumes of successful employees, in the technical solution of the present application, it is necessary to perform semantic encoding on each resume data of employees marked as successful in the collection of resume data of employees marked as successful, so as to extract the semantic encoding feature information of each resume data of employees marked as successful, thereby obtaining a collection of semantic encoding feature vectors of the resume data of successful employees.

[0061] It should be understood that since there is a common semantic correlation relationship between the semantic features of the resume data of each of the employees marked as successful, and when capturing the common features between the semantic features of the resumes of each successful employee, since the contribution of the semantic features of each employee's resume to the common semantics is different, it is necessary to perform a correlation weighted analysis based on the semantic importance of different successful employee resumes, so as to more fully and accurately characterize the common semantic feature information of these successful employee resumes. Based on this, in the technical solution of the present application, the set of semantic encoding feature vectors of the successful employee resume data is further passed through the autocorrelation resume data saliency fusion network to obtain a common saliency semantic fusion feature vector of the successful employee resume features. By processing through the autocorrelation resume data saliency fusion network, the semantic features of the resume of each successful employee can be combined, so as to better capture the common semantic features of the resume data of these successful employees, which helps to more comprehensively understand the common features and patterns between successful employees. In particular, the fusion network can also help reduce noise and individual differences in the data, highlight the common features of successful employees' resume data, and thus better distinguish the differences between successful employees and unsuccessful employees, making the obtained semantic fusion feature vector of the common significant features of the successful employees' resume features more representative and discriminative, which helps to improve the subsequent resume semantic similarity judgment and recruitment resume screening work.

[0062] In one embodiment of the present disclosure, the set of semantically encoded feature vectors of the successful employee resume data is characterized by autocorrelation resume data saliency to obtain a commonality saliency semantic fusion feature vector of the successful employee resume features, including: passing the set of semantically encoded feature vectors of the successful employee resume data through an autocorrelation resume data saliency fusion network to obtain a commonality saliency semantic fusion feature vector of the successful employee resume features.

[0063] Furthermore, the set of semantically encoded feature vectors of the successful employee resume data is passed through an autocorrelation resume data saliency fusion network to obtain the commonality saliency semantic fusion feature vector of the successful employee resume features, including: passing the set of semantically encoded feature vectors of the successful employee resume data through the autocorrelation resume data saliency fusion network and processing them using the following autocorrelation saliency formula to obtain the commonality saliency semantic fusion feature vector of the successful employee resume features; wherein the autocorrelation saliency formula is:

[0064]

[0065]

[0066]

[0067] Among them, h iis the i-th successful employee resume data semantic encoding feature vector in the set of successful employee resume data semantic encoding feature vectors, and W i Represent the weight coefficient vector and weight coefficient matrix respectively, B i is the offset vector, Selu(·) represents the Selu function, e i is the attention score value of the semantic encoding feature vector of the i-th successful employee resume data, λ and α are both hyperparameters, softmax(·) represents the softmax function, t is the number of vectors in the set of semantic encoding feature vectors of the successful employee resume data, and V is the semantic fusion feature vector of the commonality of the successful employee resume features.

[0068] Next, the candidate's resume is semantically encoded to capture its semantically encoded features, thereby generating a semantically encoded feature vector. Semantic encoding helps extract key features and semantic information from the candidate's resume and converts them into a semantically encoded feature vector. This allows for a more comprehensive representation of the candidate's resume semantics, facilitating subsequent semantic similarity comparison and screening.

[0069] Furthermore, in order to quantify the degree of similarity between the semantic features of the resume of the object to be evaluated and the common semantic features of the resumes of successful employees, so as to determine the semantic matching degree of the resumes between the object to be evaluated and the successful employee, and provide an objective basis for recruitment decisions, in the technical solution of the present application, the hash similarity between the semantic coding feature vector of the resume of the object to be evaluated and the common significant semantic fusion feature vector of the resume features of the successful employee is further calculated. By calculating the hash similarity, the semantic coding features of the resume of the object to be evaluated and the common semantic features of the resume of the successful employee can be mapped into a common hash space, and the similarity analysis and comparison of the semantic features of the resumes can be performed in the hash space to determine whether the semantics of the resume of the object to be evaluated match the common semantics of the resumes of successful employees. Furthermore, based on the comparison between the hash similarity and the predetermined threshold, it is determined whether to filter out the resume of the object to be evaluated.

[0070] In one embodiment of the present disclosure, the hash similarity between the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salient features of the resume of a successful employee is calculated, and based on the hash similarity, it is determined whether to filter out the resume of the object to be evaluated, including: performing feature optimization on the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salient features of the resume of a successful employee to obtain an optimized semantic coding feature vector of the resume of the object to be evaluated and an optimized semantic fusion feature vector of the commonality salient features of the resume of a successful employee; calculating the hash similarity between the optimized semantic coding feature vector of the resume of the object to be evaluated and the optimized semantic fusion feature vector of the commonality salient features of the resume of a successful employee; and determining whether to filter out the resume of the object to be evaluated based on a comparison between the hash similarity and a predetermined threshold.

[0071] Furthermore, feature optimization is performed on the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality of the feature significance of the resume of the successful employee to obtain an optimized semantic coding feature vector of the resume of the object to be evaluated and an optimized semantic fusion feature vector of the commonality of the feature significance of the resume of the successful employee, including: respectively calculating the weighting coefficients of the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality of the feature significance of the resume of the successful employee to obtain a first weighting coefficient and a second weighting coefficient; using the first weighting coefficient and the second weighting coefficient as weighting factors, weighted optimization is performed on the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality of the feature significance of the resume of the successful employee to obtain the optimized semantic coding feature vector of the resume of the object to be evaluated and the optimized semantic fusion feature vector of the commonality of the feature significance of the resume of the successful employee to obtain.

[0072] In the technical solution described above, each semantic coding feature vector of successful employee resume data in the set of semantic coding feature vectors of successful employee resume data expresses the encoded text semantic features of the successful employee resume data. Thus, after the set of semantic coding feature vectors of successful employee resume data passes through the autocorrelation resume data saliency fusion network, the commonality saliency semantic fusion feature vector of the successful employee resume feature can obtain the fused text semantic feature representation of the successful employee resume data set based on the importance of the text semantic feature distribution of each successful employee resume data, thereby having semantic feature expression distinctiveness from the encoded text semantic feature representation of the resume of the object to be evaluated of the semantic coding feature vector of the resume of the object to be evaluated.

[0073] In this way, when calculating the hash similarity between the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality of the feature of the resume of the successful employee, and thus mapping the hash similarity probability space of the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality of the feature of the resume of the successful employee respectively, it is expected to improve the probability mapping certainty of the distinguishable feature distribution of the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality of the feature of the resume of the successful employee, so as to improve the calculation accuracy of the hash similarity.

[0074] Based on this, the applicant of this application respectively calculates the weighted coefficients of the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salient features of the resume of the successful employee, which is expressed as follows: the weighted coefficients of the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salient features of the resume of the successful employee are respectively calculated using the following optimization formula to obtain the first weighted coefficient and the second weighted coefficient; wherein, the optimization formula is:

[0075]

[0076]

[0077] Among them, v 1-max and v 2-max are the maximum eigenvalues ​​of the semantic encoding feature vector V1 of the resume of the object to be evaluated and the semantic fusion feature vector V2 of the commonality salient feature of the resume of the successful employee, v 1-j and v 2-j is the j-th eigenvalue of the semantic encoding feature vector V1 of the resume of the object to be evaluated and the semantic fusion feature vector V2 of the commonality salience of the resume features of the successful employee, L is the length of the feature vector, log represents the logarithmic function with base 2, and α is the weight hyperparameter, ω1 is the first weighting coefficient, ω2 is the second weighting coefficient, and exp(·) represents the calculation of the natural exponential function value with a numerical value as the power.

[0078] Specifically, the majority vote (majority) of the text semantic features of the semantic encoding feature vector V1 of the resume of the object to be evaluated and the common significant semantic fusion feature vector V2 of the resume of the successful employee are respectively used to represent the text semantics in the form of text semantic crowdsourcing. Voting) mechanism is used to seek the maximization of the individual information expectation of the semantic coding feature vector V1 of the resume of the object to be evaluated and the semantic fusion feature vector V2 of the commonality of the feature of the successful employee's resume relative to the distribution subordinate probability model of the feature vector V1. In this way, the semantic coding feature vector V1 of the resume of the object to be evaluated and the semantic fusion feature vector V2 of the commonality of the feature of the successful employee's resume are weighted by coefficients ω1 and ω1 to optimize the semantic coding feature vector V1 of the resume of the object to be evaluated and the semantic fusion feature vector V2 of the commonality of the feature of the successful employee's resume. Based on the average information confidence of the eigenvalues ​​of the semantic coding feature vector V1 of the resume of the object to be evaluated and the semantic fusion feature vector V2 of the commonality of the feature of the successful employee's resume, a joint distribution estimation relative to the hash similarity probability space can be performed to maintain the distinguishability of the feature distribution of the semantic coding feature vector V1 of the resume of the object to be evaluated and the semantic fusion feature vector V2 of the commonality of the feature of the successful employee's resume, while improving the certainty of their probability mapping to the hash similarity probability space, so as to improve the calculation accuracy of the hash similarity. In this way, during the recruitment process, it is possible to determine whether to filter out the resume of the person to be evaluated based on the similarity between the common semantic features of the resume of a successful employee and the semantics of the resume of the person to be evaluated, thereby conducting efficient and objective human resource recruitment and realizing intelligent talent recruitment based on human resource data management, so as to improve employee matching, and enhance management efficiency and quality, thereby helping companies better identify and attract suitable talents.

[0079] Based on the calculation results of hash similarity, recruiters can more accurately judge the degree of match between the person to be evaluated and the successful employee, thereby making more informed recruitment decisions, improving the recruitment success rate, and optimizing the efficiency and quality of human resources data management to meet the talent recruitment needs of modern enterprises.

[0080] In one embodiment of the present disclosure, in response to the hash similarity being less than the predetermined threshold, it is determined to filter out the resume of the subject to be evaluated.

[0081] In summary, the above solution allows enterprises to leverage big data and AI technologies during the recruitment process to analyze the resumes of successful employees and compare them with the resumes of candidates to be evaluated. Based on the semantic similarity between the common features of the successful employee's resume and the semantic similarity between the candidate's resume and the candidate's resume, enterprises can determine whether to filter out the candidate's resume, thereby achieving efficient and objective human resources recruitment. This enables intelligent recruitment through human resources data management, improving management efficiency and quality, and meeting the talent recruitment needs of modern enterprises.

[0082] Figure 2 FIG is a block diagram of a human resources data management system based on big data according to an exemplary embodiment. Figure 2 As shown, the system 200 includes:

[0083] A resume data acquisition module 201 is used to acquire a collection of resume data of employees marked as successful employees;

[0084] A resume acquisition module 202 for the subject to be evaluated is used to acquire the resume of the subject to be evaluated;

[0085] A first semantic encoding module 203 is configured to semantically encode each resume data marked as a successful employee in the set of resume data marked as successful employees to obtain a set of semantic encoding feature vectors of the resume data of successful employees;

[0086] The autocorrelation resume data saliency characterization module 204 is used to perform autocorrelation resume data saliency characterization on the set of semantic encoding feature vectors of the successful employee resume data to obtain a common saliency semantic fusion feature vector of the successful employee resume features;

[0087] A second semantic coding module 205 is configured to perform semantic coding on the resume of the subject to be evaluated to obtain a semantic coding feature vector of the resume of the subject to be evaluated;

[0088] The resume judgment module 206 for filtering out the object to be evaluated is used to calculate the hash similarity between the semantic encoding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience of the feature commonality of the resume of the successful employee, and determine whether to filter out the resume of the object to be evaluated based on the hash similarity.

[0089] In one embodiment of the present disclosure, the autocorrelated resume data saliency representation module is used to: pass the set of semantically encoded feature vectors of the successful employee resume data through the autocorrelated resume data saliency fusion network to obtain the commonality saliency semantic fusion feature vector of the successful employee resume features.

[0090] In one embodiment of the present disclosure, the autocorrelation resume data saliency representation module is used to: process the set of semantically encoded feature vectors of the successful employee resume data through the autocorrelation resume data saliency fusion network using the following autocorrelation saliency formula to obtain the commonality saliency semantic fusion feature vector of the successful employee resume features; wherein the autocorrelation saliency formula is:

[0091]

[0092]

[0093]

[0094] Among them, h i is the i-th successful employee resume data semantic encoding feature vector in the set of successful employee resume data semantic encoding feature vectors, and W i Represent the weight coefficient vector and weight coefficient matrix respectively, B i is the offset vector, Selu(·) represents the Selu function, e i is the attention score value of the semantic encoding feature vector of the i-th successful employee resume data, λ and α are both hyperparameters, softmax(·) represents the softmax function, t is the number of vectors in the set of semantic encoding feature vectors of the successful employee resume data, and V is the semantic fusion feature vector of the commonality of the successful employee resume features.

[0095] In one embodiment of the present disclosure, the resume judgment module for filtering out the object to be evaluated includes: a feature optimization unit, used to perform feature optimization on the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salient features of the resume of a successful employee to obtain an optimized semantic coding feature vector of the resume of the object to be evaluated and an optimized semantic fusion feature vector of the commonality salient features of the resume of a successful employee; a hash similarity calculation unit, used to calculate the hash similarity between the optimized semantic coding feature vector of the resume of the object to be evaluated and the optimized semantic fusion feature vector of the commonality salient features of the resume of a successful employee; a resume filtering judgment unit, used to determine whether to filter out the resume of the object to be evaluated based on a comparison between the hash similarity and a predetermined threshold.

[0096] Reference below Figure 3, which shows a schematic structural diagram of an electronic device 600 suitable for implementing the embodiments of the present disclosure. The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 3 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0097] like Figure 3 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the electronic device 600 are also stored in the RAM 603. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0098] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0099] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0100] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0101] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0102] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0103] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0104] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0105] The modules described in the embodiments of the present disclosure may be implemented in software or hardware. In some cases, the name of a module does not necessarily limit the module itself. For example, a test parameter acquisition module may also be described as a "module for acquiring device test parameters corresponding to a target device."

[0106] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0107] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0108] According to one or more embodiments of the present disclosure, Example 1 provides a human resources data management method based on big data, the method comprising:

[0109] Get a collection of resume data of employees marked as successful;

[0110] Obtain the resume of the person to be evaluated;

[0111] Performing semantic coding on each piece of resume data marked as successful employees in the set of resume data marked as successful employees to obtain a set of semantic coding feature vectors of the resume data of successful employees;

[0112] Performing autocorrelation resume data saliency characterization on the set of semantically encoded feature vectors of the successful employee resume data to obtain a semantically fused feature vector of commonality of successful employee resume features;

[0113] Performing semantic coding on the resume of the subject to be evaluated to obtain a semantic coding feature vector of the resume of the subject to be evaluated;

[0114] Calculate the hash similarity between the semantic encoding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience of the feature commonality of the resume of the successful employee, and determine whether to filter out the resume of the object to be evaluated based on the hash similarity.

[0115] According to one or more embodiments of the present disclosure, Example 2 provides the method of Example 1, performing autocorrelated resume data saliency characterization on the set of semantically encoded feature vectors of the successful employee resume data to obtain a semantic fusion feature vector of commonality saliency of the successful employee resume features, including: passing the set of semantically encoded feature vectors of the successful employee resume data through an autocorrelated resume data saliency fusion network to obtain a semantic fusion feature vector of commonality saliency of the successful employee resume features.

[0116] According to one or more embodiments of the present disclosure, Example 3 provides the method of Example 2, wherein the set of semantically encoded feature vectors of the successful employee resume data is processed through an autocorrelation resume data saliency fusion network to obtain the commonality saliency semantic fusion feature vector of the successful employee resume features, including: processing the set of semantically encoded feature vectors of the successful employee resume data through the autocorrelation resume data saliency fusion network using the following autocorrelation saliency formula to obtain the commonality saliency semantic fusion feature vector of the successful employee resume features;

[0117] The autocorrelation significant formula is:

[0118]

[0119]

[0120]

[0121] Among them, h i is the i-th successful employee resume data semantic encoding feature vector in the set of successful employee resume data semantic encoding feature vectors, and W i Represent the weight coefficient vector and weight coefficient matrix respectively, B i is the offset vector, Selu(·) represents the Selu function, e i is the attention score value of the semantic encoding feature vector of the i-th successful employee resume data, λ and α are both hyperparameters, softmax(·) represents the softmax function, t is the number of vectors in the set of semantic encoding feature vectors of the successful employee resume data, and V is the semantic fusion feature vector of the commonality of the successful employee resume features.

[0122] According to one or more embodiments of the present disclosure, Example 4 provides the method of Example 3, calculating the hash similarity between the semantic encoding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience feature of the resume of the successful employee, and determining whether to filter out the resume of the object to be evaluated based on the hash similarity, including:

[0123] Performing feature optimization on the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience of the resume of the successful employee to obtain an optimized semantic coding feature vector of the resume of the object to be evaluated and an optimized semantic fusion feature vector of the commonality salience of the resume of the successful employee;

[0124] Calculating the hash similarity between the semantic encoding feature vector of the optimized resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience of the optimized resume of the successful employee;

[0125] Based on the comparison between the hash similarity and a predetermined threshold, it is determined whether to filter out the resume of the object to be evaluated.

[0126] According to one or more embodiments of the present disclosure, Example 5 provides the method of Example 4, which performs feature optimization on the semantic encoding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salient feature of the resume of the successful employee to obtain an optimized semantic encoding feature vector of the resume of the object to be evaluated and an optimized semantic fusion feature vector of the commonality salient feature of the resume of the successful employee, including:

[0127] Calculating weighting coefficients of the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience of the feature commonality of the resume of the successful employee to obtain a first weighting coefficient and a second weighting coefficient respectively;

[0128] The semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience of the resume of the successful employee are weightedly optimized using the first weighting coefficient and the second weighting coefficient as weighting factors to obtain the optimized semantic coding feature vector of the resume of the object to be evaluated and the optimized semantic fusion feature vector of the commonality salience of the resume of the successful employee.

[0129] According to one or more embodiments of the present disclosure, Example 6 provides the method of Example 5, wherein, in response to the hash similarity being less than the predetermined threshold, it is determined to filter out the resume of the subject to be evaluated.

[0130] According to one or more embodiments of the present disclosure, Example 7 provides a human resources data management system based on big data, the system comprising:

[0131] A resume data acquisition module is used to obtain a collection of resume data of employees marked as successful;

[0132] A resume acquisition module for the subject to be evaluated, used to obtain the resume of the subject to be evaluated;

[0133] A first semantic encoding module is used to perform semantic encoding on each resume data marked as a successful employee in the set of resume data marked as successful employees to obtain a set of semantic encoding feature vectors of the resume data of successful employees;

[0134] An autocorrelated resume data saliency representation module is used to perform autocorrelated resume data saliency representation on the set of semantic encoding feature vectors of the successful employee resume data to obtain a common saliency semantic fusion feature vector of the successful employee resume features;

[0135] A second semantic coding module is used to semantically code the resume of the subject to be evaluated to obtain a semantic coding feature vector of the resume of the subject to be evaluated;

[0136] The resume judgment module for filtering out the object to be evaluated is used to calculate the hash similarity between the semantic encoding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience of the feature commonality of the resume of the successful employee, and determine whether to filter out the resume of the object to be evaluated based on the hash similarity.

[0137] According to one or more embodiments of the present disclosure, Example 8 provides the system of Example 7, wherein the autocorrelated resume data saliency representation module is used to: pass the set of semantically encoded feature vectors of the successful employee resume data through the autocorrelated resume data saliency fusion network to obtain the commonality saliency semantic fusion feature vector of the successful employee resume features.

[0138] According to one or more embodiments of the present disclosure, Example 9 provides the system of Example 8, wherein the autocorrelation resume data saliency representation module is configured to: process the set of semantically encoded feature vectors of the successful employee resume data through the autocorrelation resume data saliency fusion network using the following autocorrelation saliency formula to obtain a semantically fused feature vector of commonality saliency of the successful employee resume features;

[0139] The autocorrelation significant formula is:

[0140]

[0141]

[0142]

[0143] Among them, h i is the i-th successful employee resume data semantic encoding feature vector in the set of successful employee resume data semantic encoding feature vectors, and W i Represent the weight coefficient vector and weight coefficient matrix respectively, B i is the offset vector, Selu(·) represents the Selu function, e i is the attention score value of the semantic encoding feature vector of the i-th successful employee resume data, λ and α are both hyperparameters, softmax(·) represents the softmax function, t is the number of vectors in the set of semantic encoding feature vectors of the successful employee resume data, and V is the semantic fusion feature vector of the commonality of the successful employee resume features.

[0144] According to one or more embodiments of the present disclosure, Example 10 provides the system of Example 9, wherein the resume determination module for filtering out the subject to be evaluated includes:

[0145] A feature optimization unit is used to optimize the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience of the resume of the successful employee to obtain an optimized semantic coding feature vector of the resume of the object to be evaluated and an optimized semantic fusion feature vector of the commonality salience of the resume of the successful employee;

[0146] A hash similarity calculation unit is used to calculate the hash similarity between the semantic encoding feature vector of the optimized resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience of the optimized successful employee resume;

[0147] The resume filtering judgment unit is used to determine whether to filter out the resume of the object to be evaluated based on the comparison between the hash similarity and a predetermined threshold.

[0148] Figure 4 FIG. 1 is an application scenario diagram of a human resource data management method based on big data according to an exemplary embodiment. Figure 4 As shown, in this application scenario, first, a collection of resume data of employees marked as successful is obtained (for example, Figure 4 C1 in the figure); obtain the resume of the person to be evaluated (for example, Figure 4 Then, the obtained resume data of the successful employee and the resume of the evaluation object are input into a server (for example, Figure 4 In S) shown in , the server is capable of processing the resume data of the successful employee and the resume of the evaluation object based on the human resources data management algorithm of big data to determine whether to filter out the resume of the object to be evaluated based on the hash similarity.

[0149] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0150] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0151] Although the subject matter has been described using language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims. Regarding the apparatus in the above-described embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method and will not be elaborated upon here.

Claims

1. A human resources data management method based on big data, characterized in that: include: Get a collection of resume data of employees marked as successful; Obtain the resume of the person to be evaluated; Performing semantic coding on each piece of resume data marked as successful employees in the set of resume data marked as successful employees to obtain a set of semantic coding feature vectors of the resume data of successful employees; Performing autocorrelation resume data saliency characterization on the set of semantically encoded feature vectors of the successful employee resume data to obtain a semantically fused feature vector of commonality of successful employee resume features; Performing semantic coding on the resume of the subject to be evaluated to obtain a semantic coding feature vector of the resume of the subject to be evaluated; Calculating weighting coefficients of the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience of the feature commonality of the resume of the successful employee to obtain a first weighting coefficient and a second weighting coefficient respectively; Using the first weighting coefficient and the second weighting coefficient as weighting factors, weighted optimization is performed on the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salient feature of the resume of the successful employee to obtain the optimized semantic coding feature vector of the resume of the object to be evaluated and the optimized semantic fusion feature vector of the commonality salient feature of the resume of the successful employee; Calculate the hash similarity between the semantic encoding feature vector of the optimized resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience of the optimized successful employee resume; Based on the comparison between the hash similarity and a predetermined threshold, it is determined whether to filter out the resume of the object to be evaluated.

2. The human resources data management method based on big data according to claim 1, characterized in that: The set of semantically encoded feature vectors of the successful employee resume data is represented by autocorrelated resume data saliency to obtain a common saliency semantic fusion feature vector of the successful employee resume features, including: passing the set of semantically encoded feature vectors of the successful employee resume data through an autocorrelated resume data saliency fusion network to obtain a common saliency semantic fusion feature vector of the successful employee resume features.

3. The human resources data management method based on big data according to claim 2, characterized in that: The method comprises the following steps: passing the set of semantically encoded feature vectors of the successful employee resume data through an autocorrelation resume data saliency fusion network to obtain the commonality saliency semantic fusion feature vector of the successful employee resume feature, and processing the set of semantically encoded feature vectors of the successful employee resume data through the autocorrelation resume data saliency fusion network using the following autocorrelation saliency formula to obtain the commonality saliency semantic fusion feature vector of the successful employee resume feature; The autocorrelation significant formula is: in, The first character in the set of semantic encoding feature vectors of the successful employee resume data Semantic encoding feature vector of successful employee resume data, and Represent the weight coefficient vector and weight coefficient matrix respectively, is the offset vector, express function, For the The attention score of the semantic encoding feature vector of the successful employee resume data, and are all hyperparameters, express function, The number of vectors in the set of semantically encoded feature vectors of the successful employee resume data, A semantic fusion feature vector is generated for salient commonality of the resume features of the successful employee.

4. The human resources data management method based on big data according to claim 3, characterized in that: In response to the hash similarity being less than the predetermined threshold, it is determined to filter out the resume of the subject to be evaluated.

5. A human resources data management system based on big data, used to execute the method according to any one of claims 1 to 4, characterized in that: include: A resume data acquisition module is used to obtain a collection of resume data of employees marked as successful; A resume acquisition module for the subject to be evaluated, used to obtain the resume of the subject to be evaluated; A first semantic encoding module is used to perform semantic encoding on each resume data marked as a successful employee in the set of resume data marked as successful employees to obtain a set of semantic encoding feature vectors of the resume data of successful employees; An autocorrelated resume data saliency representation module is used to perform autocorrelated resume data saliency representation on the set of semantic encoding feature vectors of the successful employee resume data to obtain a common saliency semantic fusion feature vector of the successful employee resume features; A second semantic coding module is used to semantically code the resume of the subject to be evaluated to obtain a semantic coding feature vector of the resume of the subject to be evaluated; The resume judgment module for filtering out the object to be evaluated is used to calculate the hash similarity between the semantic encoding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience of the feature commonality of the resume of the successful employee, and determine whether to filter out the resume of the object to be evaluated based on the hash similarity.

6. The human resources data management system based on big data according to claim 5, characterized in that: The autocorrelation resume data saliency representation module is used to: pass the set of semantic encoding feature vectors of the successful employee resume data through the autocorrelation resume data saliency fusion network to obtain the commonality saliency semantic fusion feature vector of the successful employee resume features.

7. The human resources data management system based on big data according to claim 6, characterized in that: The autocorrelation resume data saliency representation module is used to: process the set of semantic encoding feature vectors of the successful employee resume data through the autocorrelation resume data saliency fusion network using the following autocorrelation saliency formula to obtain the commonality saliency semantic fusion feature vector of the successful employee resume features; The autocorrelation significant formula is: in, The first character in the set of semantic encoding feature vectors of the successful employee resume data Semantic encoding feature vector of successful employee resume data, and Represent the weight coefficient vector and weight coefficient matrix respectively, is the offset vector, express function, For the The attention score of the semantic encoding feature vector of the successful employee resume data, and are all hyperparameters, express function, The number of vectors in the set of semantically encoded feature vectors of the successful employee resume data, A semantic fusion feature vector is generated for salient commonality of the resume features of the successful employee.

8. The human resources data management system based on big data according to claim 7, characterized in that: The resume judgment module for filtering out the subject to be evaluated includes: A feature optimization unit is used to optimize the semantic coding feature vector of the resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience of the resume of the successful employee to obtain an optimized semantic coding feature vector of the resume of the object to be evaluated and an optimized semantic fusion feature vector of the commonality salience of the resume of the successful employee; A hash similarity calculation unit is used to calculate the hash similarity between the semantic encoding feature vector of the optimized resume of the object to be evaluated and the semantic fusion feature vector of the commonality salience of the optimized successful employee resume; The resume filtering judgment unit is used to determine whether to filter out the resume of the object to be evaluated based on the comparison between the hash similarity and a predetermined threshold.

Images