Information management system and method based on artificial intelligence

By introducing artificial intelligence and natural language processing technology into the human resources information management system, semantic coding of job requirements and resumes is solved, and the intelligent improvement of automated resume screening and recruitment information management is achieved.

CN118503431BActive Publication Date: 2024-12-03ZHEJIANG HAIERSHI TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410802681.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-06-20
Publication Date
2024-12-03
Estimated Expiration
2044-06-20

AI Technical Summary

Technical Problem

The traditional human resources information management system has low automation degree and low efficiency when screening recruitment information, and is prone to introducing human errors and subjective factors. The automation system has limited capabilities in data processing and analysis functions, which limits the scientificity and accuracy of recruitment decisions. sex.

Method used

An information management system based on artificial intelligence and natural language processing technology is adopted to obtain job requirements descriptions and resume texts from the database, perform word-grained semantic coding, calculate semantic matching coefficients, judge the matching degree between candidates and positions, and realize automated resume screening.

Benefits of technology

It has improved the intelligence of recruitment information management and realized the automated resume screening of the human resources recruitment process, helping enterprises better carry out human resources management and talent recruitment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118503431B_ABST
    Figure CN118503431B_ABST
Patent Text Reader

Abstract

The present application discloses an information management system and method based on artificial intelligence, which obtains the job requirement description from the database and extracts the first candidate resume from the resume database, and then introduces a data processing and semantic understanding algorithm based on artificial intelligence and natural language processing technology at the back end to perform text semantic encoding of the job requirement description and the first candidate resume, so as to capture the word granularity semantic features and interactive semantics in the two, and calculate the semantic matching coefficient between the requirement and the candidate resume, so as to judge the matching degree between the candidate and the position. In this way, the automated resume screening of the human resources recruitment process can be realized, and the intelligent level of recruitment information management is improved, thereby helping enterprises and organizations to better carry out human resources management and talent recruitment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of information management, and more specifically, to an information management system and method based on artificial intelligence. Background Art

[0002] An information management system is a software system used to manage and process information. It is designed to help organizations effectively collect, store, retrieve and analyze data, improve the efficiency of data management, support decision-making, and optimize business processes. In human resource management, information management systems play a key role, helping organizations efficiently manage employee information, recruitment processes, training records, etc.

[0003] However, traditional human resource information management systems usually rely on manual screening of resumes when screening recruitment information, which is not highly automated, inefficient, and prone to human error and subjective factors. In addition, some existing automated information management systems have limited capabilities in data processing and analysis, and can usually only perform simple resume data processing and keyword matching to screen recruitment resumes, limiting the scientificity and accuracy of recruitment decisions.

[0004] Therefore, an optimized information management system is desired. Summary of the invention

[0005] In order to solve the above technical problems, this application is proposed. The embodiment of the present application provides an information management system and method based on artificial intelligence, which obtains the job requirement description from the database and extracts the first candidate resume from the resume database, and then introduces a data processing and semantic understanding algorithm based on artificial intelligence and natural language processing technology at the back end to perform text semantic encoding of the job requirement description and the first candidate resume, so as to capture the word granularity semantic features and interactive semantics in the two, and calculate the semantic matching coefficient between the requirements and the candidate resumes, so as to judge the match between the candidate and the position. In this way, it is possible to realize the automated resume screening of the human resources recruitment process, improve the intelligence level of recruitment information management, and thus help enterprises and organizations better manage human resources and recruit talents.

[0006] According to one aspect of the present application, there is provided an information management system based on artificial intelligence, comprising:

[0007] Position requirement text collection module, used to obtain position requirement descriptions from the database;

[0008] An alternative resume extraction module is used to extract a first alternative resume from a resume database, and extract a text portion of the first alternative resume to obtain a text description of the first alternative resume;

[0009] A word granularity semantic encoding module, used for performing word granularity-based semantic encoding processing on the job requirement description and the first candidate resume text description to obtain a sequence of job requirement word granularity semantic encoding vectors and a sequence of first candidate resume word granularity semantic encoding vectors;

[0010] A semantic enhancement module, used for inputting the sequence of the position requirement word granular semantic coding vectors and the sequence of the first candidate resume word granular semantic coding vectors into a semantic enhancer based on semantic relevance and semantic distance respectively to obtain a sequence of enhanced position requirement word granular semantic coding vectors and a sequence of enhanced first candidate resume word granular semantic coding vectors;

[0011] A word granularity sequence matching measurement module is used to perform a sequence matching measurement on the sequence of the enhanced position requirement word granularity semantic encoding vectors and the sequence of the enhanced first candidate resume word granularity semantic encoding vectors to obtain a feature sequence matching coefficient;

[0012] A matching degree judgment module is used to determine whether the matching degree between the first candidate resume and the job requirement description exceeds a predetermined standard based on the matching coefficient between the feature sequences.

[0013] According to another aspect of the present application, there is provided an information management method based on artificial intelligence, which comprises:

[0014] Get job requirement description from database;

[0015] Extracting a first candidate resume from a resume database, and extracting a text portion of the first candidate resume to obtain a first candidate resume text description;

[0016] Performing word-granularity-based semantic coding processing on the job requirement description and the first candidate resume text description to obtain a sequence of job requirement word-granularity semantic coding vectors and a sequence of first candidate resume word-granularity semantic coding vectors;

[0017] Inputting the sequence of the position requirement word granular semantic coding vectors and the sequence of the first candidate resume word granular semantic coding vectors into a semantic enhancer based on semantic relevance and semantic distance respectively to obtain a sequence of enhanced position requirement word granular semantic coding vectors and a sequence of enhanced first candidate resume word granular semantic coding vectors;

[0018] Performing inter-sequence matching measurement on the sequence of the enhanced position requirement word granular semantic coding vectors and the sequence of the enhanced first candidate resume word granular semantic coding vectors to obtain a feature sequence matching coefficient;

[0019] Based on the matching coefficient between the feature sequences, it is determined whether the matching degree between the first candidate resume and the job requirement description exceeds a predetermined standard.

[0020] Compared with the prior art, the information management system and method based on artificial intelligence provided by the present application obtains the job requirement description from the database and extracts the first candidate resume from the resume database. Then, a data processing and semantic understanding algorithm based on artificial intelligence and natural language processing technology is introduced at the back end to perform text semantic encoding of the job requirement description and the first candidate resume, so as to capture the word granularity semantic features and interactive semantics in the two, and calculate the semantic matching coefficient between the requirement and the candidate resume, so as to judge the matching degree between the candidate and the position. In this way, the automated resume screening of the human resources recruitment process can be realized, and the intelligent level of recruitment information management is improved, thereby helping enterprises and organizations to better manage human resources and recruit talents. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] 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.

[0022] Figure 1 is a block diagram of an information management system based on artificial intelligence according to an embodiment of the present application;

[0023] Figure 2 A system architecture diagram of an artificial intelligence-based information management system according to an embodiment of the present application;

[0024] Figure 3 Flow chart of an information management method based on artificial intelligence according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0026] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0027] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0028] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0029] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0030] Traditional human resource information management systems usually rely on manual screening of resumes when screening recruitment information, which is not highly automated, inefficient, and easily influenced by human errors and subjective factors. In addition, some existing automated information management systems have limited data processing and analysis capabilities, and can usually only perform simple resume data processing and keyword matching to screen recruitment resumes, limiting the scientificity and accuracy of recruitment decisions. Therefore, an optimized information management system is desired.

[0031] In the technical solution of the present application, an information management system based on artificial intelligence is proposed. Figure 1 It is a block diagram of an information management system based on artificial intelligence according to an embodiment of the present application. Figure 2 : is a system architecture diagram of an information management system based on artificial intelligence according to an embodiment of the present application. Figure 1 and Figure 2As shown, according to the embodiment of the present application, the information management system 300 based on artificial intelligence includes: a position requirement text acquisition module 310, which is used to obtain the position requirement description from the database; an alternative resume extraction module 320, which is used to extract the first alternative resume from the resume database, and extract the text part of the first alternative resume to obtain the first alternative resume text description; a word granularity semantic encoding module 330, which is used to perform word granularity-based semantic encoding processing on the position requirement description and the first alternative resume text description to obtain a sequence of position requirement word granularity semantic encoding vectors and a sequence of first alternative resume word granularity semantic encoding vectors; a semantic enhancement module 340, which is used to encode the position requirement word granularity semantic encoding vectors. The sequence of code vectors and the sequence of the first candidate resume word granularity semantic coding vectors are respectively input into the semantic enhancer based on semantic relevance and semantic distance to obtain the sequence of enhanced job requirement word granularity semantic coding vectors and the sequence of enhanced first candidate resume word granularity semantic coding vectors; the word granularity sequence matching measurement module 350 is used to perform sequence matching measurement on the sequence of enhanced job requirement word granularity semantic coding vectors and the sequence of enhanced first candidate resume word granularity semantic coding vectors to obtain the feature sequence matching coefficient; the matching degree judgment module 360 ​​is used to determine whether the matching degree between the first candidate resume and the job requirement description exceeds a predetermined standard based on the feature sequence matching coefficient.

[0032] In particular, the position requirement text collection module 310 and the candidate resume extraction module 320 are used to obtain the position requirement description from the database; and to extract the first candidate resume from the resume database, and extract the text portion of the first candidate resume to obtain the first candidate resume text description. Among them, the position requirement description refers to the specific requirements and expectations of the company for a certain position during the recruitment process. It should be understood that in the technical solution of the present application, by comparing the word granularity semantic features and interactive semantic matching of the two, a semantic comparison analysis is performed on the resume and the position requirement description to determine the matching degree between the candidate and the position.

[0033] In particular, the word granularity semantic encoding module 330 is used to perform word granularity-based semantic encoding processing on the job requirement description and the first candidate resume text description to obtain a sequence of job requirement word granularity semantic encoding vectors and a sequence of first candidate resume word granularity semantic encoding vectors. It should be understood that in order to be able to perform semantic analysis and understanding on the job requirement and the first candidate resume respectively, so as to provide data basis for subsequent semantic association matching and recruitment information management, in the technical solution of the present application, the job requirement description and the first candidate resume text description are processed by word segmentation and then passed through a semantic encoder including a word embedding layer to obtain a sequence of job requirement word granularity semantic encoding vectors and a sequence of first candidate resume word granularity semantic encoding vectors. It should be understood that word segmentation is the first step in text processing and semantic understanding. It can divide continuous text strings into meaningful word granularity units, usually words or phrases, which helps to analyze the semantic features of job requirements and the first candidate resume text more comprehensively and meticulously. Word embedding is a technology that converts words into vectors, which can capture the semantic information of words. Through word embedding, similar words are close to each other in the vector space, which helps the machine learning model understand the relationship between words. The semantic encoder is not only able to use word embedding to represent words, but also generates richer and deeper semantic representations by learning the context of the text, which enables the model to understand the deep meaning of the text.

[0034] In a specific example of the present application, after word segmentation processing is performed on the job requirement description and the first candidate resume text description, a sequence of word-granular semantic coding vectors of the job requirement word and a sequence of word-granular semantic coding vectors of the first candidate resume word are obtained through a semantic encoder including a word embedding layer, including: word segmentation processing is performed on the job requirement description and the first candidate resume text description respectively to convert the requirement description and the first candidate resume text description into word sequences composed of multiple words respectively; the embedding layer of the semantic encoder including the word embedding layer is used to map each word in the word sequence to a word embedding vector respectively to obtain a sequence of word embedding vectors; and the converter of the semantic encoder including the word embedding layer is used to perform global context semantic encoding on the sequence of word embedding vectors based on the converter idea to obtain a sequence of word-granular semantic coding vectors of the job requirement word and a sequence of word-granular semantic coding vectors of the first candidate resume word.

[0035] In particular, the semantic enhancement module 340 is used to input the sequence of the position requirement word granularity semantic coding vectors and the sequence of the first candidate resume word granularity semantic coding vectors into the semantic enhancer based on semantic relevance and semantic distance respectively to obtain a sequence of enhanced position requirement word granularity semantic coding vectors and a sequence of enhanced first candidate resume word granularity semantic coding vectors. Considering that in the actual process of semantic analysis and encoding of the position requirements and the first candidate resume, each word therein does not exist independently, and has semantic relevance and importance in the context, and this relationship of relevance and importance is related to the semantic association and distance span between each word. Based on this, in order to improve the ability to understand the semantics of text data, so as to more accurately match and analyze information, in the technical solution of the present application, the sequence of the position requirement word granularity semantic coding vectors and the sequence of the first candidate resume word granularity semantic coding vectors are further input into the semantic enhancer based on semantic relevance and semantic distance respectively to obtain a sequence of enhanced position requirement word granularity semantic coding vectors and a sequence of enhanced first candidate resume word granularity semantic coding vectors. Through the processing of the semantic enhancer based on semantic relevance and semantic distance, the word semantic relevance relationship and word distance span information of the position requirement word granularity semantic features and the first candidate resume word granularity semantic features in the context can be automatically learned respectively, and the expression of the text semantic features of the two can be enhanced by this, which is very important for understanding complex position requirements and candidate qualifications. In other words, by applying the semantic enhancer based on semantic relevance and semantic distance, the keywords or features related to the candidate resume in the position requirement description can be further emphasized, so that the system can more accurately identify the correlation between the position requirement and the resume, and improve the accuracy of subsequent matching and resume screening.

[0036] In a specific example of the present application, the sequence of the position requirement word granularity semantic coding vectors and the sequence of the first candidate resume word granularity semantic coding vectors are respectively input into a semantic enhancer based on semantic relevance and semantic distance to obtain a sequence of enhanced position requirement word granularity semantic coding vectors and a sequence of enhanced first candidate resume word granularity semantic coding vectors, including: extracting a predetermined position requirement word granularity semantic coding vector from the sequence of position requirement word granularity semantic coding vectors; calculating the semantic association between the predetermined position requirement word granularity semantic coding vector and all other position requirement word granularity semantic coding vectors to obtain a sequence of position requirement word granularity semantic associations; calculating the global mean of the sequence of position requirement word granularity semantic associations to obtain the global average association of position requirement word granularity semantics; using the global average association of position requirement word granularity semantics as a weight, weightedly enhancing the predetermined position requirement word granularity semantic coding vector to obtain an enhanced position requirement word granularity semantic coding vector corresponding to the predetermined position requirement word granularity semantic coding vector. Among them, calculating the semantic association between the predetermined position requirement word granularity semantic coding vector and the granularity semantic coding vectors of all other position requirement words to obtain a sequence of position requirement word granularity semantic associations, including: calculating the semantic similarity between the predetermined position requirement word granularity semantic coding vector and the granularity semantic coding vectors of all other position requirement words to obtain a sequence of position requirement word granularity semantic similarities; calculating the number of feature vectors between the predetermined position requirement word granularity semantic coding vector and the granularity semantic coding vectors of all other position requirement words to obtain a sequence of word granularity distance meter quantities; dividing the sequence of position requirement word granularity semantic similarities by the sequence of word granularity distance meter quantities by position to obtain a sequence of position requirement word granularity semantic associations. More specifically, the sequence of the position requirement word granularity semantic coding vectors and the sequence of the first candidate resume word granularity semantic coding vectors are respectively input into the semantic enhancer based on semantic relevance and semantic distance to obtain a sequence of enhanced position requirement word granularity semantic coding vectors and a sequence of enhanced first candidate resume word granularity semantic coding vectors, further including: extracting a predetermined first candidate resume word granularity semantic coding vector from the sequence of the first candidate resume word granularity semantic coding vectors; calculating the semantic association between the first candidate resume word granularity semantic coding vector and all other first candidate resume word granularity semantic coding vectors to obtain a sequence of resume information word granularity semantic associations; calculating the global mean of the sequence of resume information word granularity semantic associations to obtain the global average association of resume information word granularity semantics; using the global average association of resume information word granularity semantics as a weight, weightedly enhancing the predetermined first candidate resume word granularity semantic coding vector to obtain the enhanced first candidate resume word granularity semantic coding vector corresponding to the predetermined first candidate resume word granularity semantic coding vector.

[0037] In summary, the sequence of the position requirement word granular semantic coding vectors and the sequence of the first candidate resume word granular semantic coding vectors are respectively input into the semantic enhancer based on semantic relevance and semantic distance to obtain a sequence of enhanced position requirement word granular semantic coding vectors and a sequence of enhanced first candidate resume word granular semantic coding vectors, including: inputting the sequence of the position requirement word granular semantic coding vectors into the semantic enhancer based on semantic relevance and semantic distance and processing them with the following semantic enhancement formula to obtain the sequence of enhanced position requirement word granular semantic coding vectors; wherein the semantic enhancement formula is: ;in, and Respectively represent the first and The granular semantic encoding vector of job requirement words, express and The number of eigenvectors between express and The similarity between The total number of feature vectors in the sequence representing the granular semantic encoding vector of the job requirement word minus one, and The values ​​of are equal, The first in the sequence of the granular semantic encoding vectors of the enhanced job requirement words Strengthen the granular semantic encoding vector of job requirement words.

[0038] In particular, the word-granularity sequence matching measurement module 350 is used to perform sequence matching measurement on the sequence of the word-granularity semantic coding vectors of the enhanced job requirements and the sequence of the word-granularity semantic coding vectors of the enhanced first candidate resume to obtain a feature sequence matching coefficient. Considering that after the semantic enhancement expression of the word-granularity semantic coding features of the job requirements and the word-granularity semantic coding features of the first candidate resume, respectively, in order to be able to match the semantics of the two in a more fine-grained manner, thereby providing more accurate candidate recommendations for human resource decision makers, in the technical solution of the present application, the sequence of the word-granularity semantic coding vectors of the enhanced job requirements and the sequence of the word-granularity semantic coding vectors of the enhanced first candidate resume are further input into the feature sequence matching measurement network to obtain a feature sequence matching coefficient. Through the processing of the feature sequence matching metric network, the word-granularity-based correlation relationship and interactive feature information between the job requirements and the first candidate resume can be automatically learned and captured, so as to compare the correlation degree and difference information between the word-granularity semantic features in the sequence of the enhanced job requirements word-granularity semantic coding vectors and the sequence of the enhanced first candidate resume word-granularity semantic coding vectors, thereby achieving fine-grained semantic matching between the job requirements and the first candidate resume based on word granularity, which helps to more comprehensively identify the parts and semantic matching features related to the job requirements in the candidate resume, and provide a reliable basis for recruitment decisions. In a specific example of the present application, the sequence of the enhanced job requirements word-granularity semantic coding vectors and the sequence of the enhanced first candidate resume word-granularity semantic coding vectors are subjected to sequence matching measurement to obtain the feature sequence matching coefficient, including: the sequence of the enhanced job requirements word-granularity semantic coding vectors and the sequence of the enhanced first candidate resume word-granularity semantic coding vectors are input into the feature sequence matching metric network and processed with the following sequence matching metric formula to obtain the feature sequence matching coefficient;

[0039] The sequence matching metric formula is: ;in, is the first in the sequence of the granular semantic encoding vectors of the enhanced job requirement words Strengthen the job requirement word granular semantic encoding vector, is the first candidate resume word in the sequence of granular semantic encoding vectors. A reinforced first candidate resume word granularity semantic encoding vector, represents the Frobenius norm of a vector, Represents the eigenvalues ​​of each position in the semantic cosine similarity matrix of work order-candidate maintenance technicians, yes , is the number of feature vectors in the sequence of the granular semantic encoding vectors of the enhanced job requirement words, is the eigenvalue of each position in the job requirements-alternative resume semantic attention matrix, is the number of feature vectors in the sequence of the enhanced first candidate resume word granularity semantic encoding vector, is the number of vectors in the sequence of the granular semantic encoding vectors of the enhanced job requirement words, is the eigenvalue of each position in the candidate resume-job requirement semantic attention matrix, It is The attention weight value corresponding to the granular semantic encoding vector of the enhanced job requirement word contains the granular semantic encoding feature of the enhanced first candidate resume word, Indicates the first candidate word in the sequence of granular semantic encoding vectors. Focus on strengthening the first candidate resume word granular semantic encoding vector, yes The inverse temperature coefficient of the function, Indicates The attention weight value corresponding to the enhanced first candidate resume word granular semantic encoding vector containing the enhanced job requirement word granular semantic encoding feature, Indicates the first Focus on strengthening the granular semantic encoding vector of job requirements, represents the eigenvalues ​​of each position in the semantic cosine similarity matrix of enhanced job requirements and candidate resumes, represents the eigenvalues ​​of each position in the enhanced candidate resume-job requirement semantic cosine similarity matrix, is a hyperparameter, represents the matching coefficient between the feature sequences, Expressed as a natural constant An exponential function with base .

[0040] Considering that the sequence of the enhanced job requirement word granularity semantic coding vectors and the sequence of the enhanced first candidate resume word granularity semantic coding vectors respectively express the semantic association enhancement features of the word segmentation embedding encoding semantic features of the job requirement description and the first candidate resume text description, when performing matching calculations between feature sequences, due to the difference in source semantic distribution between the job requirement description and the first candidate resume text description, the semantic correlation and semantic distance of the encoded semantic features will have more significant differences, resulting in significant local overflow in the sequence of the enhanced job requirement word granularity semantic coding vectors and the sequence of the enhanced first candidate resume word granularity semantic coding vectors as a whole Features, thereby affecting the mapping consistency to the common semantic feature matching domain, reducing the calculation accuracy of the feature sequence matching coefficient between the sequence of the enhanced job requirement word granular semantic coding vector and the sequence of the enhanced first candidate resume word granular semantic coding vector. Therefore, before the applicant inputs the sequence of the enhanced job requirement word granular semantic coding vector and the sequence of the enhanced first candidate resume word granular semantic coding vector into the feature sequence matching metric network, the applicant preferably performs a joint correction on the sequence of the enhanced job requirement word granular semantic coding vector and the sequence of the enhanced first candidate resume word granular semantic coding vector, including:

[0041] Concatenate the sequence of the enhanced job requirement word granular semantic coding vectors and the sequence of the enhanced first candidate resume word granular semantic coding vectors into an enhanced job requirement-first candidate resume word granular semantic joint coding vector;

[0042] Calculate the enhanced job requirements-first candidate resume word granular semantic joint encoding and representation matrix of the enhanced job requirements-first candidate resume word granular semantic joint encoding vector and the enhanced job requirements-first candidate resume word granular semantic joint encoding difference representation matrix, wherein the enhanced job requirements-first candidate resume word granular semantic joint encoding and representation matrix The value of the position is the first position of the semantic joint encoding vector of the enhanced job requirements-first candidate resume word granularity and The mean of the feature values ​​of the position, and the first candidate resume word granularity semantic joint encoding difference representation matrix The value of the position is the first position of the semantic joint encoding vector of the enhanced job requirements-first candidate resume word granularity and The absolute value of the difference between the eigenvalues ​​of the positions;

[0043] Perform matrix multiplication of the transpose vector of the reinforced job requirement-first candidate resume word granularity semantic joint coding vector with the reinforced job requirement-first candidate resume word granularity semantic joint coding and representation matrix to obtain the reinforced job requirement-first candidate resume word granularity semantic joint coding and representation vector, and perform matrix multiplication of the reinforced job requirement-first candidate resume word granularity semantic joint coding difference representation matrix with the reinforced job requirement-first candidate resume word granularity semantic joint coding vector to obtain the reinforced job requirement-first candidate resume word granularity semantic joint coding difference representation vector, wherein the reinforced job requirement-first candidate resume word granularity semantic joint coding vector is a column vector;

[0044] Calculate the matrix product of the enhanced job requirements-first candidate resume word granularity semantic joint coding and representation matrix and the enhanced job requirements-first candidate resume word granularity semantic joint coding difference representation matrix, and after matrix multiplication of the transposed vector of the enhanced job requirements-first candidate resume word granularity semantic joint coding vector and the matrix product, perform dot addition with the enhanced job requirements-first candidate resume word granularity semantic joint coding and representation vector and the enhanced job requirements-first candidate resume word granularity semantic joint coding difference representation vector to obtain a corrected enhanced job requirements-first candidate resume word granularity semantic joint coding vector;

[0045] The corrected enhanced job requirement-first alternative resume word granularity semantic joint coding vector is split into a sequence of corrected enhanced job requirement word granularity semantic coding vectors and a sequence of corrected enhanced first alternative resume word granularity semantic coding vectors according to the cascade of the sequence of enhanced job requirement word granularity semantic coding vectors and the sequence of enhanced first alternative resume word granularity semantic coding vectors.

[0046] That is, the sum representation matrix and the difference representation matrix of the group aggregation statistical evaluation of the feature value granularity local distribution of the joint semantic representation of the sequence of the enhanced job requirement words granularity semantic coding vectors and the sequence of the enhanced first candidate resume words granularity semantic coding vectors are used as the retrieval and response distribution enhancement of the sequence of the enhanced job requirement words granularity semantic coding vectors and the sequence of the enhanced first candidate resume words granularity semantic coding vectors, and a reference-free analysis of the open domain of the sum-difference feature distribution of the sequence of the enhanced job requirement words granularity semantic coding vectors and the sequence of the enhanced first candidate resume words granularity semantic coding vectors based on group aggregation is constructed. The search-based response framework is used to avoid the distribution response redundancy caused by the local overflow characteristics of the sequence of the granular semantic coding vectors of the enhanced job requirement words and the sequence of the granular semantic coding vectors of the enhanced first candidate resume words through response superposition, so as to realize the faithfulness constraint of the self-aggregation statistics correlation of the response sequence of the granular semantic coding vectors of the enhanced job requirement words and the sequence of the granular semantic coding vectors of the enhanced first candidate resume words to the target common semantic matching regression domain, and improve the calculation accuracy of the feature sequence matching coefficient between the sequence of the granular semantic coding vectors of the enhanced job requirement words and the sequence of the granular semantic coding vectors of the enhanced first candidate resume words. In this way, the matching degree between candidates and positions can be judged more accurately, thereby realizing the automated resume accurate screening in the human resources recruitment process, and helping enterprises and organizations to better manage human resources and recruit talents.

[0047] In particular, the matching degree judgment module 360 ​​is used to determine whether the matching degree between the first candidate resume and the job requirement description exceeds a predetermined standard based on the matching coefficient between the feature sequences. That is, in the technical solution of the present application, based on the comparison between the matching coefficient between the feature sequences and the predetermined threshold, it is determined whether the matching degree between the first candidate resume and the job requirement description exceeds the predetermined standard. In particular, in response to the matching coefficient between the feature sequences being greater than the predetermined threshold, it is determined that the matching degree between the first candidate resume and the job requirement description exceeds the predetermined standard. In this way, automated resume screening of the human resource recruitment process can be achieved, and the intelligence level of recruitment information management is improved, thereby helping enterprises and organizations to better conduct human resource management and talent recruitment.

[0048] As described above, the information management system 300 based on artificial intelligence according to the embodiment of the present application can be implemented in various wireless terminals, such as a server with an information management algorithm based on artificial intelligence. In one possible implementation, the information management system 300 based on artificial intelligence according to the embodiment of the present application can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the information management system 300 based on artificial intelligence can be a software module in the operating system of the wireless terminal, or it can be an application developed for the wireless terminal; of course, the information management system 300 based on artificial intelligence can also be one of the many hardware modules of the wireless terminal.

[0049] Alternatively, in another example, the artificial intelligence-based information management system 300 and the wireless terminal may also be separate devices, and the artificial intelligence-based information management system 300 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.

[0050] Furthermore, an information management method based on artificial intelligence is also provided.

[0051] Figure 3 Flowchart of the information management method based on artificial intelligence according to an embodiment of the present application. Figure 3 As shown, according to the embodiment of the present application, the information management method based on artificial intelligence includes the following steps: S1, obtaining a job requirement description from a database; S2, extracting a first candidate resume from a resume database, and extracting the text portion of the first candidate resume to obtain a first candidate resume text description; S3, performing word granularity-based semantic encoding processing on the job requirement description and the first candidate resume text description to obtain a sequence of job requirement word granularity semantic encoding vectors and a sequence of first candidate resume word granularity semantic encoding vectors; S4, combining the sequence of job requirement word granularity semantic encoding vectors with the first candidate resume text description; The sequence of candidate resume word granularity semantic coding vectors is respectively input into the semantic enhancer based on semantic relevance and semantic distance to obtain a sequence of enhanced job requirement word granularity semantic coding vectors and a sequence of enhanced first candidate resume word granularity semantic coding vectors; S5, the sequence of enhanced job requirement word granularity semantic coding vectors and the sequence of enhanced first candidate resume word granularity semantic coding vectors are subjected to sequence matching measurement to obtain a feature sequence matching coefficient; S6, based on the feature sequence matching coefficient, it is determined whether the matching degree between the first candidate resume and the job requirement description exceeds a predetermined standard.

[0052] In summary, the information management method based on artificial intelligence according to the embodiment of the present application is explained, which obtains the job requirement description from the database and extracts the first candidate resume from the resume database, and then introduces a data processing and semantic understanding algorithm based on artificial intelligence and natural language processing technology at the back end to perform text semantic encoding of the job requirement description and the first candidate resume, so as to capture the word granularity semantic features and interactive semantics in the two, and calculate the semantic matching coefficient between the requirements and the candidate resumes, so as to judge the matching degree between the candidate and the position. In this way, the automated resume screening of the human resources recruitment process can be realized, and the intelligence level of recruitment information management is improved, thereby helping enterprises and organizations to better manage human resources and recruit talents.

[0053] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. An information management system based on artificial intelligence, characterized in that: include: Position requirement text collection module, used to obtain position requirement descriptions from the database; An alternative resume extraction module is used to extract a first alternative resume from a resume database, and extract a text portion of the first alternative resume to obtain a text description of the first alternative resume; A word granularity semantic encoding module, used for performing word granularity-based semantic encoding processing on the job requirement description and the first candidate resume text description to obtain a sequence of job requirement word granularity semantic encoding vectors and a sequence of first candidate resume word granularity semantic encoding vectors; A semantic enhancement module, used for inputting the sequence of the position requirement word granular semantic coding vectors and the sequence of the first candidate resume word granular semantic coding vectors into a semantic enhancer based on semantic relevance and semantic distance respectively to obtain a sequence of enhanced position requirement word granular semantic coding vectors and a sequence of enhanced first candidate resume word granular semantic coding vectors; A word granularity sequence matching measurement module is used to perform a sequence matching measurement on the sequence of the enhanced position requirement word granularity semantic encoding vectors and the sequence of the enhanced first candidate resume word granularity semantic encoding vectors to obtain a feature sequence matching coefficient; A matching degree judgment module, used to determine whether the matching degree between the first candidate resume and the job requirement description exceeds a predetermined standard based on the matching coefficient between the feature sequences; Wherein, the semantic enhancement module includes: A first predetermined vector extraction unit, used to extract a predetermined position requirement word granular semantic coding vector from the sequence of position requirement word granular semantic coding vectors; A first semantic relevance calculation unit is used to calculate the semantic relevance between the predetermined position requirement word granularity semantic coding vector and all other position requirement word granularity semantic coding vectors to obtain a sequence of position requirement word granularity semantic relevances; A first global mean value calculation unit is used to calculate the global mean value of the sequence of the granular semantic association of the job requirement words to obtain the global average granular semantic association of the job requirement words; A first weighted optimization unit is used to perform weighted enhancement on the predetermined position requirement word granularity semantic coding vector by taking the global average relevance of the position requirement word granularity semantics as a weight to obtain an enhanced position requirement word granularity semantic coding vector corresponding to the predetermined position requirement word granularity semantic coding vector; Wherein, the first semantic relevance calculation unit is used to: Calculating the semantic similarity between the predetermined position requirement word granularity semantic encoding vector and all other position requirement word granularity semantic encoding vectors to obtain a sequence of position requirement word granularity semantic similarities; Calculate the number of feature vectors between the predetermined position requirement word granularity semantic coding vector and all other position requirement word granularity semantic coding vectors to obtain a sequence of word granularity distance meter quantities; The sequence of the semantic similarity of the job requirement words and the sequence of the word granularity distance counter numbers are divided by position to obtain the sequence of the semantic association of the job requirement words.

2. The information management system based on artificial intelligence according to claim 1, characterized in that: The word-granularity semantic encoding module is used to: perform word segmentation processing on the job requirement description and the first candidate resume text description, and then obtain a sequence of word-granularity semantic encoding vectors of the job requirement and a sequence of word-granularity semantic encoding vectors of the first candidate resume through a semantic encoder including a word embedding layer.

3. The information management system based on artificial intelligence according to claim 2 is characterized in that: The word granularity semantic encoding module includes: A word segmentation unit is used to perform word segmentation processing on the job requirement description and the first candidate resume text description respectively to convert the requirement description and the first candidate resume text description into a word sequence consisting of multiple words respectively; A word embedding unit, configured to map each word in the word sequence to a word embedding vector using the embedding layer of the semantic encoder including the word embedding layer to obtain a sequence of word embedding vectors; A context encoding unit is used to use the converter of the semantic encoder including the word embedding layer to perform global context semantic encoding on the sequence of word embedding vectors based on the converter idea to obtain the sequence of the job requirement word granularity semantic encoding vectors and the sequence of the first candidate resume word granularity semantic encoding vectors.

4. The information management system based on artificial intelligence according to claim 3 is characterized in that: The semantic enhancement module further includes: A second predetermined vector extraction unit, used to extract a predetermined first candidate resume word granularity semantic encoding vector from the sequence of the first candidate resume word granularity semantic encoding vectors; A second semantic association calculation unit is used to calculate the semantic association between the first candidate resume word granularity semantic coding vector and all other first candidate resume word granularity semantic coding vectors to obtain a sequence of resume information word granularity semantic associations; A second global mean calculation unit is used to calculate the global mean of the sequence of granular semantic associations of the resume information words to obtain a global average association of the granular semantics of the resume information words; The second weighted optimization unit is used to use the global average correlation of the resume information word granularity semantics as a weight to weightedly enhance the predetermined first candidate resume word granularity semantic coding vector to obtain an enhanced first candidate resume word granularity semantic coding vector corresponding to the predetermined first candidate resume word granularity semantic coding vector.

5. The information management system based on artificial intelligence according to claim 4, characterized in that: The matching degree judgment module is used to determine whether the matching degree between the first candidate resume and the job requirement description exceeds a predetermined standard based on the comparison between the matching coefficient between the feature sequences and a predetermined threshold.

6. The information management system based on artificial intelligence according to claim 5, characterized in that: The matching degree judgment module is used to: in response to the matching coefficient between the feature sequences being greater than the predetermined threshold, determine that the matching degree between the first candidate resume and the job requirement description exceeds a predetermined standard.

7. An information management method based on artificial intelligence, characterized in that: include: Get job requirement description from database; Extracting a first candidate resume from a resume database, and extracting a text portion of the first candidate resume to obtain a first candidate resume text description; Performing word-granularity-based semantic coding processing on the job requirement description and the first candidate resume text description to obtain a sequence of job requirement word-granularity semantic coding vectors and a sequence of first candidate resume word-granularity semantic coding vectors; Inputting the sequence of the position requirement word granular semantic coding vectors and the sequence of the first candidate resume word granular semantic coding vectors into a semantic enhancer based on semantic relevance and semantic distance respectively to obtain a sequence of enhanced position requirement word granular semantic coding vectors and a sequence of enhanced first candidate resume word granular semantic coding vectors; Performing inter-sequence matching measurement on the sequence of the enhanced position requirement word granular semantic coding vectors and the sequence of the enhanced first candidate resume word granular semantic coding vectors to obtain a feature sequence matching coefficient; Based on the matching coefficient between the feature sequences, determining whether the matching degree between the first candidate resume and the job requirement description exceeds a predetermined standard; The sequence of the position requirement word granular semantic coding vectors and the sequence of the first candidate resume word granular semantic coding vectors are respectively input into a semantic enhancer based on semantic relevance and semantic distance to obtain a sequence of enhanced position requirement word granular semantic coding vectors and a sequence of enhanced first candidate resume word granular semantic coding vectors, including: Extracting a predetermined position requirement word granular semantic encoding vector from the sequence of position requirement word granular semantic encoding vectors; Calculating the semantic association between the predetermined position requirement word granularity semantic encoding vector and all other position requirement word granularity semantic encoding vectors to obtain a sequence of position requirement word granularity semantic associations; Calculating the global mean of the sequence of the granular semantic associations of the job requirement words to obtain the global average granular semantic association of the job requirement words; Taking the global average relevance of the position requirement word granular semantics as a weight, weightedly strengthening the predetermined position requirement word granular semantic coding vector to obtain a strengthened position requirement word granular semantic coding vector corresponding to the predetermined position requirement word granular semantic coding vector; The step of calculating the semantic association between the predetermined position requirement word granularity semantic coding vector and all other position requirement word granularity semantic coding vectors to obtain a sequence of position requirement word granularity semantic associations includes: Calculating the semantic similarity between the predetermined position requirement word granularity semantic encoding vector and all other position requirement word granularity semantic encoding vectors to obtain a sequence of position requirement word granularity semantic similarities; Calculate the number of feature vectors between the predetermined position requirement word granularity semantic coding vector and all other position requirement word granularity semantic coding vectors to obtain a sequence of word granularity distance meter quantities; The sequence of the semantic similarity of the job requirement words and the sequence of the word granularity distance counter numbers are divided by position to obtain the sequence of the semantic association of the job requirement words.