Talent information analysis management method and system based on big data

Abstract

The present application discloses a talent information analysis management method and system based on big data, which obtains the recruitment requirements issued by the enterprise, extracts the description information of the first candidate talent from the talent database, and uses the data processing and analysis algorithm based on big data and artificial intelligence to perform semantic analysis and context encoding of the recruitment requirements and the description information of the first candidate talent, so as to intelligently obtain the analysis result of whether the first candidate talent is compatible with the recruitment requirements based on the interactive matching characteristics between the recruitment requirements and the talent information. In this way, qualified candidates can be quickly screened out from a large number of candidates, the automation of the recruitment process can be realized, and the matching quality between candidates and positions can be improved, and the recruitment success rate can be increased.

Description

Technical Field

[0001] The present application relates to the field of intelligent management, and more specifically, to a talent information analysis and management method and system based on big data. Background Art

[0002] In modern enterprise management, in order to achieve the optimal allocation and utilization of talent resources, talent data needs to be systematically collected, analyzed and managed. Talent information analysis management is a systematic approach that involves collecting, analyzing and utilizing data on talent recruitment to support human resource planning, decision-making and strategic implementation. By analyzing recruitment data, companies can more accurately locate and attract suitable talents, while improving the efficiency and effectiveness of the recruitment process, laying a solid talent foundation for the long-term development of the company.

[0003] However, the traditional recruitment process may take a lot of time to screen candidates, especially when the number of candidates is large, manual screening can be very time-consuming. In addition, in traditional recruitment, due to the lack of effective analytical tools, recruitment resources may not be optimally allocated, resulting in the recruitment needs of some positions not being met in a timely manner.

[0004] Therefore, a talent information analysis and management method based on big data is desired. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a talent information analysis management method and system based on big data, which obtains the recruitment needs issued by the enterprise, extracts the description information of the first candidate talent from the talent database, and uses data processing and analysis algorithms based on big data and artificial intelligence to perform semantic analysis and context encoding of the recruitment needs and the description information of the first candidate talent, so as to intelligently obtain the analysis result of whether the first candidate talent is compatible with the recruitment needs based on the interactive matching characteristics between the recruitment needs and the talent information. In this way, qualified candidates can be quickly screened out from a large number of candidates, and the automation of the recruitment process can be realized, while improving the matching quality of candidates and positions and increasing the success rate of recruitment.

[0006] According to one aspect of the present application, a talent information analysis and management method based on big data is provided, which includes:

[0007] Obtain recruitment requirements posted by enterprises;

[0008] Extracting description information of the first candidate talent from the talent database;

[0009] Semantically encoding the recruitment requirements published by the enterprise to obtain a recruitment requirements semantic encoding vector;

[0010] After performing sentence processing on the description information of the first candidate talent, inter-sentence context semantic coding is performed to obtain a sequence of context first candidate talent description information sentence granularity semantic coding vectors;

[0011] Based on the sequence of the granular semantic coding vectors of the first candidate talent description information sentence in the context, performing one-way interactive matching on the recruitment demand semantic coding vector to obtain a recruitment demand-talent information interactive matching vector as a recruitment demand-talent information interactive matching feature;

[0012] Based on the recruitment demand-talent information interactive matching characteristics, an analysis result is obtained.

[0013] In the above-mentioned talent information analysis and management method based on big data, semantic encoding is performed on the recruitment needs published by the enterprise to obtain a recruitment need semantic encoding vector, including: performing word segmentation processing on the recruitment needs published by the enterprise and then inputting the word segmentation processing into a recruitment need semantic encoder based on a converter model to obtain the recruitment need semantic encoding vector.

[0014] In the above-mentioned talent information analysis and management method based on big data, the description information of the first candidate talent is processed into sentences and then inter-sentence context semantic encoding is performed to obtain a sequence of sentence-granularity semantic encoding vectors of the contextual first candidate talent description information, including: the description information of the first candidate talent is processed into sentences and then an inter-sentence context semantic encoder including a sentence encoder is used to obtain a sequence of sentence-granularity semantic encoding vectors of the contextual first candidate talent description information.

[0015] In the above-mentioned talent information analysis and management method based on big data, based on the sequence of granularity semantic coding vectors of the first candidate talent description information sentence in the context, the recruitment demand semantic coding vector is unidirectionally interactively matched to obtain a recruitment demand-talent information interactive matching vector as a recruitment demand-talent information interactive matching feature, including: calculating the semantic association feature information between the sequence of granularity semantic coding vectors of the first candidate talent description information sentence in the context and the recruitment demand semantic coding vector to obtain a recruitment information guide-talent information description semantic coding vector; and, cascading the recruitment information guide-talent information description semantic coding vector and the recruitment demand semantic coding vector to obtain the recruitment demand-talent information interactive matching vector.

[0016] In the above-mentioned talent information analysis and management method based on big data, the semantic association feature information between the sequence of granular semantic coding vectors of the context first candidate talent description information sentence and the recruitment demand semantic coding vector is calculated to obtain the recruitment information guidance-talent information description semantic coding vector, including: calculating the semantic association between each context first candidate talent description information sentence granular semantic coding vector in the sequence of granular semantic coding vectors of the context first candidate talent description information sentence and the recruitment demand semantic coding vector to obtain a sequence of candidate talent-recruitment demand semantic associations; and, using the sequence of candidate talent-recruitment demand semantic associations as weights, calculating the vector weighted sum of the sequence of granular semantic coding vectors of the context first candidate talent description information sentence to obtain the recruitment information guidance-talent information description semantic coding vector.

[0017] In the above-mentioned talent information analysis and management method based on big data, the semantic association between each context first candidate talent description information sentence granularity semantic coding vector in the sequence of the context first candidate talent description information sentence granularity semantic coding vector and the recruitment demand semantic coding vector is calculated to obtain a sequence of candidate talent-recruitment demand semantic associations, including: calculating the position-based logarithmic function value with base 2 of each context first candidate talent description information sentence granularity semantic coding vector in the sequence of the context first candidate talent description information sentence granularity semantic coding vector to obtain the context first candidate talent description. The method comprises the following steps: calculating a sequence of the granularity logarithmic function value vectors of the information sentence; calculating the positional point multiplication between each context first candidate talent description information sentence granularity logarithmic function value vector in the sequence of the context first candidate talent description information sentence granularity logarithmic function value vector and the recruitment demand semantic encoding vector to obtain a sequence of recruitment information-talent description semantic interaction feature vectors; and calculating the global mean between the feature values ​​of each position of each recruitment information-talent description semantic interaction feature vector in the sequence of recruitment information-talent description semantic interaction feature vectors to obtain a sequence of candidate talent-recruitment demand semantic associations.

[0018] In the above-mentioned talent information analysis and management method based on big data, an analysis result is obtained based on the recruitment demand-talent information interaction matching characteristics, including: the recruitment demand-talent information interaction matching vector is passed through a classifier-based analysis result generation module to obtain an analysis result, and the analysis result is used to indicate whether the first candidate talent is compatible with the recruitment demand.

[0019] In the above-mentioned talent information analysis and management method based on big data, the recruitment demand-talent information interaction matching vector is passed through a classifier-based analysis result generation module to obtain an analysis result, and the analysis result is used to indicate whether the first candidate talent is compatible with the recruitment demand, including: using the fully connected layer of the classifier-based analysis result generation module to fully connect the recruitment demand-talent information interaction matching vector to obtain a recruitment demand-talent information interaction matching coding classification feature vector; and, passing the recruitment demand-talent information interaction matching coding classification feature vector through the Softmax classification function of the classifier-based analysis result generation module to obtain the classification result.

[0020] According to another aspect of the present application, a talent information analysis and management system based on big data is provided, which includes:

[0021] Recruitment demand acquisition module, used to obtain recruitment needs published by enterprises;

[0022] A candidate talent description information extraction module is used to extract the description information of the first candidate talent from the talent database;

[0023] A recruitment demand semantic coding module, used for semantically coding the recruitment demand published by the enterprise to obtain a recruitment demand semantic coding vector;

[0024] An inter-sentence context semantic coding module, used for performing sentence processing on the description information of the first candidate talent and then performing inter-sentence context semantic coding to obtain a sequence of sentence granularity semantic coding vectors of the contextual first candidate talent description information;

[0025] A one-way interactive matching module, configured to perform one-way interactive matching on the recruitment demand semantic encoding vector based on the sequence of the granular semantic encoding vectors of the first candidate talent description information sentence in the context to obtain a recruitment demand-talent information interactive matching vector as a recruitment demand-talent information interactive matching feature;

[0026] The analysis result generation module is used to obtain the analysis result based on the recruitment demand-talent information interaction matching characteristics.

[0027] In the above-mentioned talent information analysis and management system based on big data, the inter-sentence context semantic coding module is used to: after sentence processing of the description information of the first candidate talent, pass it through the inter-sentence context semantic encoder including the sentence encoder to obtain a sequence of sentence-granularity semantic coding vectors of the context first candidate talent description information.

[0028] Compared with the prior art, the talent information analysis management method and system provided by the present application based on big data obtains the recruitment requirements issued by the enterprise, extracts the description information of the first candidate talent from the talent database, and uses the data processing and analysis algorithm based on big data and artificial intelligence to perform semantic analysis and context encoding of the recruitment requirements and the description information of the first candidate talent, so as to intelligently obtain the analysis result of whether the first candidate talent is compatible with the recruitment requirements based on the interactive matching characteristics between the recruitment requirements and the talent information. In this way, qualified candidates can be quickly screened out from a large number of candidates, the automation of the recruitment process can be realized, and at the same time, the matching quality between candidates and positions can be improved, and the recruitment success rate can be increased. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0030] Figure 1 The present invention is a flowchart of a talent information analysis and management method based on big data according to an embodiment of the present application.

[0031] Figure 2 Schematic diagram of the architecture of the talent information analysis and management method based on big data according to an embodiment of the present application.

[0032] Figure 3 This is a flowchart of performing one-way interactive matching on the recruitment demand semantic coding vector based on the sequence of granularity semantic coding vectors of the first candidate talent description information sentence in the context in the talent information analysis and management method based on big data according to an embodiment of the present application to obtain a recruitment demand-talent information interactive matching vector as a recruitment demand-talent information interactive matching feature.

[0033] Figure 4 A flowchart for calculating the semantic association feature information between the sequence of the granularity semantic coding vectors of the first candidate talent description information sentence in the context and the recruitment demand semantic coding vector in the talent information analysis and management method based on big data according to an embodiment of the present application to obtain a recruitment information guidance-talent information description semantic coding vector.

[0034] Figure 5 It is a block diagram of a talent information analysis and management system based on big data according to an embodiment of the present application. DETAILED DESCRIPTION

[0035] The embodiments of the present disclosure will be described in more detail below 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 being limited to the embodiments described herein, but rather these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0036] 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.

[0037] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0038] It should be noted that the modifications of "one" and "plurality" 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, it should be understood as "one or more".

[0039] In modern enterprise management, in order to achieve the optimal allocation and utilization of talent resources, talent data needs to be systematically collected, analyzed and managed. Talent information analysis management is a systematic approach that involves collecting, analyzing and utilizing data on talent recruitment to support human resource planning, decision-making and strategic implementation. By analyzing recruitment data, companies can more accurately locate and attract suitable talents, while improving the efficiency and effectiveness of the recruitment process, laying a solid talent foundation for the long-term development of the company.

[0040] However, the traditional recruitment process may take a lot of time to screen candidates, especially when the number of candidates is large, manual screening can be very time-consuming. In addition, in traditional recruitment, due to the lack of effective analytical tools, recruitment resources may not be optimally allocated, resulting in the recruitment needs of some positions not being met in a timely manner.

[0041] It should be understood that big data refers to a large amount of diversified data that emerges at a high speed. Its characteristics can be simply summarized as 3V: volume, velocity, and variety. In short, big data refers to very large and complex data sets, especially data sets from new data sources, whose scale makes traditional data processing software helpless. With the development of big data, cloud computing and storage technology, it is possible to process and analyze large-scale data sets, providing technical support for talent information analysis and management. For example, analyzing a large amount of resumes and professional social platform data can help companies quickly identify and screen suitable candidates; by analyzing industry data, recruitment data and social media data, predicting talent demand and supply trends, etc. These applications can help companies make more scientific and reasonable decisions in talent management and improve the efficiency and effectiveness of human resource management.

[0042] Based on this, I propose a talent information analysis and management method based on big data, which obtains the recruitment needs released by the enterprise, extracts the description information of the first candidate talent from the talent database, and uses data processing and analysis algorithms based on big data and artificial intelligence to perform semantic analysis and context encoding of the recruitment needs and the description information of the first candidate talent, so as to intelligently obtain the analysis result of whether the first candidate talent is compatible with the recruitment needs based on the interactive matching characteristics between the recruitment needs and talent information. In this way, qualified candidates can be quickly screened out from a large number of candidates, realizing the automation of the recruitment process, while improving the matching quality between candidates and positions and increasing the recruitment success rate.

[0043] Figure 1 The present invention is a flowchart of a talent information analysis and management method based on big data according to an embodiment of the present application. Figure 2 FIG. 1 is a schematic diagram of the architecture of a talent information analysis and management method based on big data according to an embodiment of the present application. Figure 1 and Figure 2As shown, according to the embodiment of the present application, the talent information analysis and management method based on big data includes: S110, obtaining recruitment needs released by an enterprise; S120, extracting description information of the first candidate talent from the talent database; S130, semantically encoding the recruitment needs released by the enterprise to obtain a recruitment need semantic coding vector; S140, performing sentence processing on the description information of the first candidate talent and then performing inter-sentence context semantic coding to obtain a sequence of context first candidate talent description information sentence granularity semantic coding vectors; S150, based on the sequence of context first candidate talent description information sentence granularity semantic coding vectors, performing one-way interactive matching on the recruitment need semantic coding vector to obtain a recruitment need-talent information interactive matching vector as a recruitment need-talent information interactive matching feature; and, S160, based on the recruitment need-talent information interactive matching feature, obtaining an analysis result.

[0044] In step S110, the recruitment demand issued by the enterprise is obtained. In step S120, the description information of the first candidate talent is extracted from the talent database. It should be understood that the recruitment demand issued by the enterprise and the description information of the first candidate talent are two key data sets in the talent information analysis and management, which represent the specific requirements of the enterprise for talents and the qualification profile of potential candidates respectively. In detail, the recruitment demand issued by the enterprise usually includes information such as job description, required skills and experience, educational background, job responsibilities, and qualifications, which clarifies the type and standard of talents sought by the enterprise in the recruitment process. The description information of the first candidate talent includes the candidate's educational background, work experience, skill certificates, professional achievements, personal statements, etc., which help evaluate whether the candidate meets the recruitment needs of the enterprise. Based on this, in the technical solution of the present application, the recruitment demand issued by the enterprise is obtained, and the description information of the first candidate talent is extracted from the talent database, and the description information of the first candidate talent is analyzed and semantically processed, so that the most suitable candidate can be quickly identified and matched, ensuring that the recruitment process is more efficient and systematic, and reducing unnecessary waste of time and resources.

[0045] In step S130, the recruitment needs published by the enterprise are semantically encoded to obtain a recruitment needs semantic encoding vector. Specifically, in an embodiment of the present application, the recruitment needs published by the enterprise are semantically encoded to obtain a recruitment needs semantic encoding vector, including: performing word segmentation processing on the recruitment needs published by the enterprise and inputting the word segmentation processing into a recruitment needs semantic encoder based on a converter model to obtain the recruitment needs semantic encoding vector. Accordingly, considering that the recruitment needs contain a large amount of semantic information, such as job titles, job responsibilities, skill requirements, etc., these semantic information can be used for subsequent matching of recruitment needs and talent descriptions. Based on this, in order to be able to understand the keywords and concepts in the recruitment needs, in the technical solution of the present application, the recruitment needs published by the enterprise are semantically encoded to obtain a recruitment needs semantic encoding vector. In particular, in a specific embodiment of the present application, the recruitment needs semantic encoding vector can be obtained by performing word segmentation processing on the recruitment needs published by the enterprise and inputting the word segmentation processing into a recruitment needs semantic encoder based on a converter model. That is, by segmenting an entire recruitment demand, the entire text can be divided into multiple word sequences of recruitment demands composed of words or phrases, which can enable the model to better understand the meaning and requirements of the recruitment needs. Then, the multiple word sequences after word segmentation are input into the recruitment demand semantic encoder based on the converter model to accurately capture the key information and requirements in the recruitment needs, including skill requirements, experience requirements, educational background, etc., so as to obtain a recruitment demand semantic encoding vector containing rich recruitment semantic information, which provides more effective feature representation for subsequent matching and analysis, thereby helping companies find talents that match their needs more quickly.

[0046] In step S140, the description information of the first candidate talent is processed by sentence segmentation and then inter-sentence context semantic coding is performed to obtain a sequence of sentence-granularity semantic coding vectors of the context first candidate talent description information. Specifically, in an embodiment of the present application, the description information of the first candidate talent is processed by sentence segmentation and then inter-sentence context semantic coding is performed to obtain a sequence of sentence-granularity semantic coding vectors of the context first candidate talent description information, including: the description information of the first candidate talent is processed by sentence segmentation and then an inter-sentence context semantic encoder including a sentence encoder is used to obtain a sequence of sentence-granularity semantic coding vectors of the context first candidate talent description information. It should be understood that, considering that the description information of the first candidate talent contains a wealth of description sentences, and there may be contextual semantic relationships between different candidate talent description information sentences, that is, the meaning of one description information sentence may be affected by the previous and next description information sentences. Therefore, in order to better capture the semantic associations and dependencies between the various candidate talent description information sentences, so as to more accurately understand the meaning of the entire candidate talent description information, in the technical solution of the present application, the description information of the first candidate talent is processed by sentence segmentation, and then the inter-sentence context semantic encoder including the sentence encoder is used to obtain a sequence of context first candidate talent description information sentence granularity semantic coding vectors. Specifically, after the description information of the first candidate talent is processed by sentence segmentation, the candidate talent description information expressed in each sentence can be fully understood and analyzed more deeply, and each candidate talent description information sentence is encoded by the inter-sentence context semantic encoder including the sentence encoder, so that the important semantic features and meanings implied in each sentence can be better extracted, so as to better reflect the semantic structure and logical relationship of the entire candidate talent description information, thereby improving the understanding and expression ability of the first candidate talent description information.

[0047] In step S150, based on the sequence of the granular semantic coding vectors of the first candidate talent description information sentence in the context, the recruitment demand semantic coding vector is subjected to one-way interactive matching to obtain a recruitment demand-talent information interactive matching vector as a recruitment demand-talent information interactive matching feature. Accordingly, considering that each context first candidate talent description information sentence granular semantic coding vector in the sequence of the first candidate talent description information sentence granular semantic coding vector describes the semantic features of the candidate talent's personal ability, work experience or educational background and other aspects of information. The recruitment demand semantic coding vector describes the characteristic expression of the overall semantics of the recruitment demand. Therefore, in order to extract the semantic association features between the recruitment demand and each description information of the candidate talent, so as to better evaluate the matching degree between the recruitment demand and the first candidate talent description information, in the technical solution of the present application, based on the sequence of the granular semantic coding vectors of the first candidate talent description information sentence in the context, the recruitment demand semantic coding vector is subjected to one-way interactive matching to obtain a recruitment demand-talent information interactive matching vector. In detail, first, the semantic correlation between each context first candidate talent description information sentence granularity semantic coding vector and the recruitment demand semantic coding vector in the sequence of the context first candidate talent description information sentence granularity semantic coding vector is calculated to help extract the key features between the candidate talent description information sentence granularity semantic features and the recruitment demand semantic features, including common keywords, themes or semantic information. Then, each semantic correlation is weighted and summed for each context first candidate talent description information sentence granularity semantic coding vector to focus on and highlight those semantic features that are more critical to job matching, ensuring that these features occupy a larger proportion in the final evaluation. Finally, the weighted features are cascaded with the recruitment demand semantic coding features, so as to more accurately and comprehensively evaluate the degree of match between candidates and positions and improve the accuracy of matching results.

[0048] Figure 3 The present invention is a flowchart of performing one-way interactive matching on the recruitment demand semantic coding vector based on the sequence of the first candidate talent description information sentence granularity semantic coding vector in the context in the talent information analysis and management method based on big data according to the embodiment of the present application to obtain the recruitment demand-talent information interactive matching vector as the recruitment demand-talent information interactive matching feature. Specifically, in the embodiment of the present application, if Figure 3As shown, based on the sequence of granularity semantic coding vectors of the first candidate talent description information sentence in the context, the recruitment demand semantic coding vector is unidirectionally interactively matched to obtain a recruitment demand-talent information interactive matching vector as a recruitment demand-talent information interactive matching feature, including: S210, calculating the semantic association feature information between the sequence of granularity semantic coding vectors of the first candidate talent description information sentence in the context and the recruitment demand semantic coding vector to obtain a recruitment information guide-talent information description semantic coding vector; and, S220, cascading the recruitment information guide-talent information description semantic coding vector and the recruitment demand semantic coding vector to obtain the recruitment demand-talent information interactive matching vector.

[0049] Figure 4 The present invention is a flowchart of calculating the semantic association feature information between the sequence of the first candidate talent description information sentence granularity semantic coding vector and the recruitment demand semantic coding vector in the talent information analysis and management method based on big data according to the embodiment of the present application to obtain the recruitment information guide-talent information description semantic coding vector. Specifically, in the embodiment of the present application, if Figure 4 As shown, the semantic association feature information between the sequence of granular semantic coding vectors of the context first candidate talent description information sentence and the recruitment demand semantic coding vector is calculated to obtain the recruitment information guidance-talent information description semantic coding vector, including: S310, calculating the semantic association between each context first candidate talent description information sentence granular semantic coding vector in the sequence of granular semantic coding vectors of the context first candidate talent description information sentence and the recruitment demand semantic coding vector to obtain a sequence of candidate talent-recruitment demand semantic associations; and, S320, using the sequence of candidate talent-recruitment demand semantic associations as weights, calculating the vector weighted sum of the sequence of granular semantic coding vectors of the context first candidate talent description information sentence to obtain the recruitment information guidance-talent information description semantic coding vector.

[0050] More specifically, in an embodiment of the present application, the semantic association between each context first candidate talent description information sentence granularity semantic coding vector in the sequence of the context first candidate talent description information sentence granularity semantic coding vector and the recruitment demand semantic coding vector is calculated to obtain a sequence of candidate talent-recruitment demand semantic associations, including: calculating the position-based logarithmic function value with base 2 of each context first candidate talent description information sentence granularity semantic coding vector in the sequence of the context first candidate talent description information sentence granularity semantic coding vector to obtain a sequence of context first candidate talent description information sentence granularity logarithmic function value vectors; calculating the position-based point multiplication between each context first candidate talent description information sentence granularity logarithmic function value vector in the sequence of the context first candidate talent description information sentence granularity logarithmic function value vector and the recruitment demand semantic coding vector to obtain a sequence of recruitment information-talent description semantic interaction feature vectors; and calculating the global mean between the feature values ​​of each position of each recruitment information-talent description semantic interaction feature vector in the sequence of the recruitment information-talent description semantic interaction feature vectors to obtain the sequence of candidate talent-recruitment demand semantic associations.

[0051] In the embodiment of the present application, specifically, calculating the semantic association between each contextual first candidate talent description information sentence granularity semantic coding vector in the sequence of the contextual first candidate talent description information sentence granularity semantic coding vector and the recruitment demand semantic coding vector to obtain a sequence of candidate talent-recruitment demand semantic associations, including: calculating the semantic association between each contextual first candidate talent description information sentence granularity semantic coding vector in the sequence of the contextual first candidate talent description information sentence granularity semantic coding vector and the recruitment demand semantic coding vector using the following association formula to obtain the sequence of candidate talent-recruitment demand semantic associations; wherein the association formula is:

[0052]

[0053] in, and are the values ​​of each position of the semantic encoding vector of the recruitment demand and the granularity semantic encoding vector of each of the first candidate talent description information sentences in the context, L is the scale of the semantic encoding vector of the recruitment demand and the granularity semantic encoding vector of each of the first candidate talent description information sentences in the context, r ij It represents the semantic association degree between candidate talents and recruitment needs at each position in the sequence of semantic association degrees between candidate talents and recruitment needs, and log represents the logarithmic function value with 2 as the base.

[0054] In step S160, based on the recruitment demand-talent information interactive matching feature, an analysis result is obtained. Specifically, in an embodiment of the present application, based on the recruitment demand-talent information interactive matching feature, an analysis result is obtained, including: the recruitment demand-talent information interactive matching vector is passed through a classifier-based analysis result generation module to obtain an analysis result, and the analysis result is used to indicate whether the first candidate talent is compatible with the recruitment demand. That is, the recruitment demand-talent information interactive matching obtained by interactively matching the sequence of the contextual first candidate talent description information sentence granularity semantic coding vector and the recruitment demand semantic coding vector is classified and processed, so as to intelligently obtain the analysis result of whether the first candidate talent is compatible with the recruitment demand. In this way, qualified candidates can be quickly screened out from a large number of candidates, the automation of the recruitment process can be realized, and at the same time, the matching quality of candidates and positions can be improved, and the recruitment success rate can be increased.

[0055] More specifically, in an embodiment of the present application, the recruitment demand-talent information interaction matching vector is passed through a classifier-based analysis result generation module to obtain an analysis result, and the analysis result is used to indicate whether the first candidate talent is compatible with the recruitment demand, including: using the fully connected layer of the classifier-based analysis result generation module to fully connect encode the recruitment demand-talent information interaction matching vector to obtain a recruitment demand-talent information interaction matching encoding classification feature vector; and, passing the recruitment demand-talent information interaction matching encoding classification feature vector through the Softmax classification function of the classifier-based analysis result generation module to obtain the classification result.

[0056] It should be understood that here, when the recruitment demand semantic coding vector is subjected to one-way interactive matching based on the sequence of the sentence granularity semantic coding vectors of the contextual first candidate talent description information, its essence is to use the attention mechanism to measure the semantic matching degree between the semantic information of each word in the description information of the first candidate talent and the recruitment demand released by the enterprise in the high-dimensional semantic space, and then use the semantic matching degree as the attention factor to adjust the global semantic expression of the description information of the first candidate talent, so as to more accurately represent the semantic implicit association pattern characteristics between the recruitment demand released by the enterprise and the description information of the first candidate talent. However, due to the difference in feature dimension and text semantic granularity between the sentence granularity semantic coding vectors of the contextual first candidate talent description information and the semantic coding vector of the recruitment demand, the local feature overflow of the recruitment demand-talent information interactive matching vector will be caused in the process of one-way interactive matching, thereby affecting the accuracy of the recruitment demand-talent information interactive matching vector when it is classified by the analysis result generation module based on the classifier.

[0057] Based on this, preferably, the recruitment demand-talent information interaction matching vector is passed through a classifier-based analysis result generation module to obtain an analysis result, including the following steps: calculating the self-mean matrix and self-standard deviation matrix of the recruitment demand-talent information interaction matching vector, wherein the value of the (i, j)th position of the self-mean matrix is ​​the mean of the eigenvalue at the i-th position and the eigenvalue at the j-th position of the recruitment demand-talent information interaction matching vector, and the value of the (i, j)th position of the self-standard deviation matrix is ​​the standard deviation of the eigenvalue at the i-th position and the eigenvalue at the j-th position of the recruitment demand-talent information interaction matching vector; performing matrix multiplication on the transposed vector of the recruitment demand-talent information interaction matching vector as a row eigenvector and the self-mean matrix to obtain a first central The method comprises the following steps: calculating an intermediate vector and performing matrix multiplication of the self-standard deviation matrix with the recruitment demand-talent information interaction matching vector to obtain a second intermediate vector; calculating the point sum of the transposed vectors of the first intermediate vector and the second intermediate vector to obtain a third intermediate vector; calculating the matrix product of the self-mean matrix and the self-standard deviation matrix, and performing matrix multiplication of the transposed vector of the recruitment demand-talent information interaction matching vector and the matrix product to obtain a fourth intermediate vector; calculating the point sum of the transposed vectors of the third intermediate vector and the fourth intermediate vector to obtain an optimized recruitment demand-talent information interaction matching vector; and passing the optimized recruitment demand-talent information interaction matching vector through the classifier-based analysis result generation module to obtain the analysis result.

[0058] Based on this, the self-mean matrix and self-standard deviation matrix of the group aggregation statistical evaluation of the local distribution of the characteristic value granularity of the recruitment demand-talent information interaction matching vector are used as the retrieval and response distribution enhancement of the recruitment demand-talent information interaction matching vector, and a reference-free distribution retrieval response framework based on the group aggregation characteristic distribution open domain of the recruitment demand-talent information interaction matching vector is constructed to avoid the distribution response redundancy caused by the local overflow characteristics of the recruitment demand-talent information interaction matching vector through response superposition, so as to realize the faithfulness constraint of the self-aggregation statistics of the response of the optimized recruitment demand-talent information interaction matching vector to the classification target domain, and improve the accuracy of the analysis results obtained by the analysis result generation module based on the classifier of the optimized recruitment demand-talent information interaction matching vector. In this way, qualified candidates can be quickly screened out from a large number of candidates, the automation of the recruitment process can be realized, and the matching quality of candidates and positions can be improved, and the recruitment success rate can be increased.

[0059] In summary, the talent information analysis and management method based on big data according to the embodiment of the present application is explained, which obtains the recruitment needs issued by the enterprise, extracts the description information of the first candidate talent from the talent database, and uses the data processing and analysis algorithm based on big data and artificial intelligence to perform semantic analysis and context encoding of the recruitment needs and the description information of the first candidate talent, so as to intelligently obtain the analysis result of whether the first candidate talent is compatible with the recruitment needs according to the interactive matching characteristics between the recruitment needs and the talent information. In this way, qualified candidates can be quickly screened out from a large number of candidates, and the automation of the recruitment process can be realized, while improving the matching quality between candidates and positions and increasing the recruitment success rate.

[0060] Figure 5 FIG. 1 is a block diagram of a talent information analysis and management system based on big data according to an embodiment of the present application. Figure 5 As shown, according to the embodiment of the present application, the talent information analysis and management system 100 based on big data includes: a recruitment demand acquisition module 110, which is used to obtain the recruitment demand released by the enterprise; a candidate talent description information extraction module 120, which is used to extract the description information of the first candidate talent from the talent database; a recruitment demand semantic encoding module 130, which is used to semantically encode the recruitment demand released by the enterprise to obtain a recruitment demand semantic encoding vector; an inter-sentence context semantic encoding module 140, which is used to perform inter-sentence context semantic encoding on the description information of the first candidate talent after sentence processing to obtain a sequence of context first candidate talent description information sentence granularity semantic encoding vectors; a one-way interactive matching module 150, which is used to perform one-way interactive matching on the recruitment demand semantic encoding vector based on the sequence of context first candidate talent description information sentence granularity semantic encoding vectors to obtain a recruitment demand-talent information interactive matching vector as a recruitment demand-talent information interactive matching feature; and an analysis result generation module 160, which is used to obtain an analysis result based on the recruitment demand-talent information interactive matching feature.

[0061] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned talent information analysis and management system based on big data have been referred to above. Figures 1 to 4 The description of the talent information analysis and management method based on big data has been introduced in detail, and therefore, its repeated description will be omitted.

[0062] As described above, the talent information analysis and management system 100 based on big data according to the embodiment of the present disclosure can be implemented in various wireless terminals, such as a server with a talent information analysis and management algorithm based on big data. In a possible implementation, the talent information analysis and management system 100 based on big data according to the embodiment of the present disclosure can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the talent information analysis and management system 100 based on big data can be a software module in the operating system of the wireless terminal, or can be an application developed for the wireless terminal; of course, the talent information analysis and management system 100 based on big data can also be one of the many hardware modules of the wireless terminal.

[0063] Alternatively, in another example, the big data-based talent information analysis and management system 100 and the wireless terminal may also be separate devices, and the big data-based talent information analysis and management system 100 may be connected to the wireless terminal via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0064] The foregoing is merely an example of the principles of the present disclosure, and various modifications may be made by those skilled in the art without departing from the scope of the present disclosure. The above embodiments are presented for the purpose of illustration and not limitation. The present disclosure may also take many forms other than those explicitly described herein. Therefore, it is emphasized that the present disclosure is not limited to the methods, systems and devices explicitly disclosed, but is intended to include variations and modifications within the spirit and scope of the appended claims.

Claims

1. A talent information analysis and management method based on big data, characterized in that: include: Obtain recruitment requirements posted by enterprises; Extracting description information of the first candidate talent from the talent database; Semantically encoding the recruitment requirements published by the enterprise to obtain a recruitment requirements semantic encoding vector; After performing sentence processing on the description information of the first candidate talent, inter-sentence context semantic coding is performed to obtain a sequence of context first candidate talent description information sentence granularity semantic coding vectors; Based on the sequence of the granular semantic coding vectors of the first candidate talent description information sentence in the context, performing one-way interactive matching on the recruitment demand semantic coding vector to obtain a recruitment demand-talent information interactive matching vector as a recruitment demand-talent information interactive matching feature; Based on the recruitment demand-talent information interaction matching characteristics, an analysis result is obtained; Based on the recruitment demand-talent information interactive matching feature, obtaining an analysis result, including: passing the recruitment demand-talent information interactive matching vector through a classifier-based analysis result generation module to obtain an analysis result, wherein the analysis result is used to indicate whether the first candidate talent is compatible with the recruitment demand; The recruitment demand-talent information interaction matching vector is passed through a classifier-based analysis result generation module to obtain an analysis result, comprising the following steps: calculating a self-mean matrix and a self-standard deviation matrix of the recruitment demand-talent information interaction matching vector, wherein the value of the (i, j)th position of the self-mean matrix is ​​the mean of the eigenvalue at the i-th position and the eigenvalue at the j-th position of the recruitment demand-talent information interaction matching vector, and the value of the (i, j)th position of the self-standard deviation matrix is ​​the standard deviation of the eigenvalue at the i-th position and the eigenvalue at the j-th position of the recruitment demand-talent information interaction matching vector; performing matrix multiplication of the transposed vector of the recruitment demand-talent information interaction matching vector as a row eigenvector with the self-mean matrix to obtain a first intermediate vector And perform matrix multiplication of the self-standard deviation matrix and the recruitment demand-talent information interaction matching vector to obtain a second intermediate vector; calculate the point sum of the transposed vectors of the first intermediate vector and the second intermediate vector to obtain a third intermediate vector; calculate the matrix product of the self-mean matrix and the self-standard deviation matrix, and perform matrix multiplication of the transposed vector of the recruitment demand-talent information interaction matching vector and the matrix product to obtain a fourth intermediate vector; calculate the point sum of the transposed vectors of the third intermediate vector and the fourth intermediate vector to obtain an optimized recruitment demand-talent information interaction matching vector; and, pass the optimized recruitment demand-talent information interaction matching vector through the classifier-based analysis result generation module to obtain the analysis result.

2. The talent information analysis and management method based on big data according to claim 1 is characterized in that: The recruitment requirements published by the enterprise are semantically encoded to obtain a recruitment requirement semantic encoding vector, including: performing word segmentation processing on the recruitment requirements published by the enterprise and then inputting the word segmentation processing into a recruitment requirement semantic encoder based on a converter model to obtain the recruitment requirement semantic encoding vector.

3. The talent information analysis and management method based on big data according to claim 2 is characterized in that: The description information of the first candidate talent is processed into sentences and then inter-sentence context semantic coding is performed to obtain a sequence of sentence-granularity semantic coding vectors of the contextual first candidate talent description information, including: the description information of the first candidate talent is processed into sentences and then an inter-sentence context semantic encoder including a sentence encoder is used to obtain a sequence of sentence-granularity semantic coding vectors of the contextual first candidate talent description information.

4. The talent information analysis and management method based on big data according to claim 3 is characterized in that: Based on the sequence of the granular semantic coding vectors of the first candidate talent description information sentence in the context, one-way interactive matching is performed on the recruitment demand semantic coding vector to obtain a recruitment demand-talent information interactive matching vector as a recruitment demand-talent information interactive matching feature, including: Calculating semantic association feature information between the sequence of the contextual first candidate talent description information sentence granularity semantic coding vector and the recruitment demand semantic coding vector to obtain a recruitment information guide-talent information description semantic coding vector; The recruitment information guidance-talent information description semantic coding vector and the recruitment demand semantic coding vector are cascaded to obtain the recruitment demand-talent information interaction matching vector.

5. The talent information analysis and management method based on big data according to claim 4 is characterized in that: Calculating the semantic association feature information between the sequence of the contextual first candidate talent description information sentence granularity semantic coding vector and the recruitment demand semantic coding vector to obtain a recruitment information guide-talent information description semantic coding vector, including: Calculating the semantic association between each contextual first candidate talent description information sentence granularity semantic encoding vector in the sequence of contextual first candidate talent description information sentence granularity semantic encoding vectors and the recruitment demand semantic encoding vector to obtain a sequence of candidate talent-recruitment demand semantic associations; Taking the sequence of candidate talent-recruitment demand semantic associations as weights, the vector weighted sum of the sequence of granular semantic coding vectors of the first candidate talent description information sentence in the context is calculated to obtain the recruitment information guide-talent information description semantic coding vector.

6. The talent information analysis and management method based on big data according to claim 5 is characterized in that: Calculating the semantic association between each context first candidate talent description information sentence granularity semantic encoding vector in the sequence of context first candidate talent description information sentence granularity semantic encoding vectors and the recruitment demand semantic encoding vector to obtain a sequence of candidate talent-recruitment demand semantic associations, including: Calculating the position-based logarithmic function value with base 2 of each contextual first candidate talent description information sentence granularity semantic coding vector in the sequence of contextual first candidate talent description information sentence granularity semantic coding vectors to obtain a sequence of contextual first candidate talent description information sentence granularity logarithmic function value vectors; Calculating the position point multiplication between each context first candidate talent description information sentence granularity logarithmic function value vector in the sequence of context first candidate talent description information sentence granularity logarithmic function value vectors and the recruitment demand semantic encoding vector to obtain a sequence of recruitment information-talent description semantic interaction feature vectors; The global mean between the feature values ​​of each position of each recruitment information-talent description semantic interaction feature vector in the sequence of recruitment information-talent description semantic interaction feature vectors is calculated to obtain the sequence of the semantic association between candidate talents and recruitment needs.

7. The talent information analysis and management method based on big data according to claim 6 is characterized in that: The recruitment demand-talent information interactive matching vector is passed through a classifier-based analysis result generation module to obtain an analysis result, wherein the analysis result is used to indicate whether the first candidate talent is compatible with the recruitment demand, including: Using the fully connected layer of the classifier-based analysis result generation module to perform fully connected encoding on the recruitment demand-talent information interaction matching vector to obtain a recruitment demand-talent information interaction matching encoding classification feature vector; The recruitment demand-talent information interactive matching encoding classification feature vector is passed through the Softmax classification function of the classifier-based analysis result generation module to obtain the analysis result.

8. A talent information analysis and management system based on big data, characterized in that: include: Recruitment demand acquisition module, used to obtain recruitment needs published by enterprises; A candidate talent description information extraction module is used to extract the description information of the first candidate talent from the talent database; A recruitment demand semantic coding module, used for semantically coding the recruitment demand published by the enterprise to obtain a recruitment demand semantic coding vector; An inter-sentence context semantic coding module, used for performing inter-sentence context semantic coding on the description information of the first candidate talent after sentence processing to obtain a sequence of sentence-granularity semantic coding vectors of the description information of the first candidate talent in the context; A one-way interactive matching module, configured to perform one-way interactive matching on the recruitment demand semantic encoding vector based on the sequence of the granular semantic encoding vectors of the first candidate talent description information sentence in the context to obtain a recruitment demand-talent information interactive matching vector as a recruitment demand-talent information interactive matching feature; An analysis result generation module, used to obtain analysis results based on the recruitment demand-talent information interaction matching characteristics; The analysis result generation module is used to: pass the recruitment demand-talent information interaction matching vector through the classifier-based analysis result generation module to obtain an analysis result, wherein the analysis result is used to indicate whether the first candidate talent is compatible with the recruitment demand; The analysis result generating module is used to: calculate the self-mean matrix and self-standard deviation matrix of the recruitment demand-talent information interaction matching vector, wherein the value of the (i, j)th position of the self-mean matrix is ​​the mean of the eigenvalue of the i-th position and the eigenvalue of the j-th position of the recruitment demand-talent information interaction matching vector, and the value of the (i, j)th position of the self-standard deviation matrix is ​​the standard deviation of the eigenvalue of the i-th position and the eigenvalue of the j-th position of the recruitment demand-talent information interaction matching vector; perform matrix multiplication of the transposed vector of the recruitment demand-talent information interaction matching vector as a row eigenvector with the self-mean matrix to obtain a first intermediate vector and perform matrix multiplication of the self-standard deviation matrix with the recruitment demand-talent information interaction matching vector. The information interaction matching vector is matrix multiplied to obtain a second intermediate vector; the dot sum of the transposed vectors of the first intermediate vector and the second intermediate vector is calculated to obtain a third intermediate vector; the matrix product of the self-mean matrix and the self-standard deviation matrix is ​​calculated, and the transposed vector of the recruitment demand-talent information interaction matching vector and the matrix product are matrix multiplied to obtain a fourth intermediate vector; the dot sum of the transposed vectors of the third intermediate vector and the fourth intermediate vector is calculated to obtain an optimized recruitment demand-talent information interaction matching vector; and the optimized recruitment demand-talent information interaction matching vector is passed through the classifier-based analysis result generation module to obtain the analysis result.

9. The talent information analysis and management system based on big data according to claim 8 is characterized in that: The inter-sentence context semantic encoding module is used to: after sentence processing on the description information of the first candidate talent, obtain a sequence of sentence-granularity semantic encoding vectors of the contextual first candidate talent description information through an inter-sentence context semantic encoder including a sentence encoder.

Images