Big data analysis talent feature extraction method and system based on attachment resume

Abstract

The invention is suitable for the technical field of resume analysis, and provides a big data analysis talent feature extraction method and system based on attachment resumes. The method comprises the following steps: establishing a collection interface with a plurality of recruitment channels and a talent database, and carrying out primary processing to obtain a plurality of resume texts; processing and identifying the plurality of resume texts, and extracting a plurality of pieces of key information; importing the plurality of pieces of key information into a preset talent feature model for feature extraction to obtain a plurality of specific features; performing statistics and modeling on the plurality of specific features to obtain feature statistical data, and establishing a talent feature prediction model; and carrying out visual display on the plurality of specific features, and carrying out recruitment matching processing. The problems that an existing talent feature extraction method is low in accuracy, incomplete in feature and poor in format adaptability are solved, comprehensive talent features can be efficiently and accurately extracted from attachment resumes of various formats, and powerful support is provided for talent recruitment and management of enterprises.

Description

Technical Field

[0001] The present invention belongs to the technical field of resume analysis, and in particular to a talent feature extraction method and system based on big data analysis of attached resumes. Background Art

[0002] Companies' demands for talent are becoming increasingly diversified and precise. Traditional talent screening methods mainly rely on manual reading of resumes, which is inefficient and prone to subjective bias. They have the following main defects: (1) They rely on manual reading of resumes, which is inefficient and prone to subjective bias; (2) The extracted features are not comprehensive enough and cannot adapt to resumes of different formats; (3) When processing massive resume data, the accuracy is not high. Summary of the invention

[0003] The purpose of the embodiments of the present invention is to provide a method and system for extracting talent features through big data analysis based on attached resumes, aiming to solve the technical problems existing in the prior art mentioned in the background technology.

[0004] The embodiment of the present invention is implemented as follows:

[0005] A method for extracting talent features from big data analysis based on attached resumes, the method specifically comprising the following steps:

[0006] Establishing a collection interface with multiple recruitment channels and talent databases, automatically collecting multiple resume attachments, and preliminarily processing the multiple resume attachments to obtain multiple resume texts;

[0007] Based on natural language processing technology, multiple resume texts are processed and recognized to extract multiple key information;

[0008] Importing the plurality of key information into a preset talent feature model for feature extraction to obtain a plurality of specific features;

[0009] Using big data analysis technology, statistics and modeling are performed on the multiple specific characteristics to obtain characteristic statistical data and establish a talent characteristic prediction model;

[0010] Based on the feature statistical data, a plurality of the specific features are visualized and recruitment matching is performed.

[0011] As a further limitation of the technical solution of the embodiment of the present invention, the establishment of a collection interface with multiple recruitment channels and talent databases, automatically collecting multiple attached resumes, and preliminarily processing the multiple attached resumes to obtain multiple resume texts specifically includes the following steps:

[0012] Establish collection interfaces with multiple recruitment channels and talent databases;

[0013] Automatically collect multiple attached resumes through multiple collection interfaces;

[0014] The multiple resume attachments are formatted and cleaned to remove irrelevant information and format errors, thereby obtaining multiple resume texts.

[0015] As a further limitation of the technical solution of the embodiment of the present invention, the resume formats of the multiple attached resumes include: PDF, Word and TXT.

[0016] As a further limitation of the technical solution of the embodiment of the present invention, the processing and recognition of the multiple resume texts based on natural language processing technology and the extraction of multiple key information specifically include the following steps:

[0017] Based on natural language processing technology, multiple resume texts are segmented, POS tagged, and named entity processed to obtain multiple optimized texts;

[0018] Key identification is performed on the multiple optimized texts to extract multiple key information.

[0019] As a further limitation of the technical solution of the embodiment of the present invention, the multiple key information includes: basic personal information, work experience, educational background and skill list.

[0020] As a further limitation of the technical solution of the embodiment of the present invention, the step of importing the plurality of key information into a preset talent feature model for feature extraction to obtain a plurality of specific features specifically comprises the following steps:

[0021] Importing a plurality of the key information into a preset talent characteristic model;

[0022] Extracting quantitative features from a plurality of the key information through the talent feature model;

[0023] Using preset text analysis and machine learning algorithms to evaluate and extract evaluation features from a plurality of the key information;

[0024] A plurality of the quantitative features and a plurality of the evaluation features are integrated to obtain a plurality of specific features.

[0025] As a further limitation of the technical solution of the embodiment of the present invention, the multiple quantitative characteristics include: years of work experience, number of projects and degree of skill mastery; the multiple evaluation characteristics include: communication skills and teamwork skills.

[0026] As a further limitation of the technical solution of the embodiment of the present invention, the use of big data analysis technology to perform statistics and modeling on the multiple specific features to obtain feature statistical data and establish a talent feature prediction model specifically includes the following steps:

[0027] Using big data analysis technology, statistics are collected on the multiple specific features, the correlation between different specific features, and the distribution of specific features in different industries are analyzed to obtain feature statistical data;

[0028] A talent characteristic prediction model is established based on the characteristic statistical data.

[0029] As a further limitation of the technical solution of the embodiment of the present invention, the visual display of the multiple specific features based on the feature statistical data and the recruitment matching process specifically include the following steps:

[0030] Visually displaying the plurality of specific features according to the feature statistical data, wherein the visual display includes a table and an icon;

[0031] According to the statistical data of the characteristics, accurate matching of recruitment needs is carried out;

[0032] Different training plans are customized according to the characteristic statistics.

[0033] A big data analysis talent feature extraction system based on attached resume, the system includes a resume data collection unit, a natural language processing unit, a feature extraction unit, a big data analysis modeling unit and a visualization display application unit, wherein:

[0034] A resume data collection unit is used to establish a collection interface with multiple recruitment channels and talent databases, automatically collect multiple attached resumes, and perform preliminary processing on the multiple attached resumes to obtain multiple resume texts;

[0035] A natural language processing unit, used to process and identify the multiple resume texts based on natural language processing technology, and extract multiple key information;

[0036] A feature extraction unit, used for importing the plurality of key information into a preset talent feature model to perform feature extraction and obtain a plurality of specific features;

[0037] A big data analysis and modeling unit, used to use big data analysis technology to perform statistics and modeling on the multiple specific features, obtain feature statistical data, and establish a talent feature prediction model;

[0038] A visualization application unit is used to visualize the multiple specific features according to the feature statistical data and perform recruitment matching processing.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] (1) It can accurately extract key information and deep features from resumes and reduce errors caused by manual intervention;

[0041] (2) It can extract talent characteristics from multiple dimensions, including quantifiable characteristics and soft skill characteristics that are difficult to directly quantify, to provide enterprises with comprehensive talent assessment;

[0042] (3) Supports a variety of common resume formats and can automatically process resumes in different formats to improve the efficiency and coverage of data collection;

[0043] (4) The extracted talent characteristics can be applied to multiple fields such as talent recruitment, talent management, and career development planning, providing strong support for the human resource management of enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A flow chart of a method for extracting talent features through big data analysis based on attached resumes provided by an embodiment of the present invention is shown;

[0045] Figure 2 The application architecture diagram of the talent feature extraction system based on attached resumes and big data analysis provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0047] It is understandable that companies’ demands for talent are becoming increasingly diversified and precise. Traditional talent screening methods mainly rely on manual reading of resumes, which is inefficient and prone to subjective bias. They have the following main defects: (1) They rely on manual reading of resumes, which is inefficient and prone to subjective bias; (2) The extracted features are not comprehensive enough and cannot adapt to resumes of different formats; (3) When processing massive resume data, the accuracy is not high.

[0048] To solve the above problems, the embodiment of the present invention discloses a talent feature extraction method and system based on big data analysis of attached resumes. By establishing a collection interface with multiple recruitment channels and talent databases, multiple attached resumes are automatically collected, and multiple attached resumes are preliminarily processed to obtain multiple resume texts; based on natural language processing technology, multiple resume texts are processed and identified to extract multiple key information; multiple key information is imported into a preset talent feature model for feature extraction to obtain multiple specific features; using big data analysis technology, multiple specific features are counted and modeled to obtain feature statistical data, and a talent feature prediction model is established; based on the feature statistical data, multiple specific features are visualized and recruitment matching is performed. The problem of low accuracy, incomplete features and poor format adaptability existing in the existing talent feature extraction method is solved, and comprehensive talent features can be extracted from attached resumes of various formats efficiently and accurately, providing strong support for the talent recruitment and management of enterprises.

[0049] Specifically, Figure 1 A flow chart of a talent feature extraction method based on attached resumes and big data analysis provided by an embodiment of the present invention is shown.

[0050] In a preferred embodiment of the present invention, a method for extracting talent characteristics based on big data analysis of attached resumes specifically comprises the following steps:

[0051] Step S101, establish a collection interface with multiple recruitment channels and talent databases, automatically collect multiple attached resumes, and preliminarily process the multiple attached resumes to obtain multiple resume texts.

[0052] In an embodiment of the present invention, a collection interface is established with multiple recruitment channels and talent databases, and then through multiple collection interfaces, attached resumes in different resume formats are automatically collected, including: PDF, Word and TXT, etc., and then the multiple attached resumes are format converted and cleaned up to remove irrelevant information and format errors, ensure the availability of information, and obtain multiple resume texts.

[0053] Step S102: Based on natural language processing technology, the multiple resume texts are processed and recognized to extract multiple key information.

[0054] In an embodiment of the present invention, natural language processing technologies including NLTK, Spacy, etc. are used to perform word segmentation, part-of-speech tagging and named entity processing on multiple resume texts to obtain multiple optimized texts, and then key recognition is performed on the multiple optimized texts to extract multiple key information, analyze the sentence structure and semantics in the resume, and understand the candidate's career development path, project experience and achievements and other deep information. Specifically, the multiple key information includes: basic personal information, work experience, educational background and skill list, etc.

[0055] Step S103: import the plurality of key information into a preset talent feature model to extract features, and obtain a plurality of specific features.

[0056] In an embodiment of the present invention, multiple key information are imported into a preset talent characteristic model, and quantitative features are extracted from the multiple key information through the talent characteristic model, including: years of work experience, number of projects, and degree of skill mastery, etc.; and preset text analysis and machine learning algorithms are used to evaluate and extract evaluation features from multiple key information, including: communication skills and teamwork skills, etc., and then the multiple quantitative features and the multiple evaluation features are combined to obtain multiple specific features.

[0057] Step S104: Utilize big data analysis technology to perform statistics and modeling on the multiple specific features, obtain feature statistical data, and establish a talent feature prediction model.

[0058] In the embodiment of the present invention, big data analysis technology is used to perform statistics on multiple specific features, analyze the correlation between different specific features, and the distribution of specific features in different industries to obtain feature statistical data. Based on the feature statistical data, a talent feature prediction model is established to predict unknown features based on known features, thereby improving the completeness and accuracy of feature extraction. Among them, big data analysis technology can use Hive, Spark, etc.

[0059] Step S105: Based on the feature statistical data, multiple specific features are visualized and recruitment matching is performed.

[0060] In an embodiment of the present invention, based on feature statistical data, multiple specific features are visualized in the form of tables and icons, and recruitment needs are accurately matched based on the feature statistical data. In the training process after the recruitment is completed, different training plans are customized based on the feature statistical data. Specifically, the visualization tool may be Tableau, PowerBI, etc.

[0061] Furthermore, Figure 2 The application architecture diagram of the talent feature extraction system based on attached resumes and big data analysis provided by an embodiment of the present invention is shown.

[0062] Among them, in another preferred embodiment provided by the present invention, a talent feature extraction system based on big data analysis of attached resumes includes:

[0063] The resume data collection unit 101 is used to establish a collection interface with multiple recruitment channels and talent databases, automatically collect multiple attached resumes, and perform preliminary processing on the multiple attached resumes to obtain multiple resume texts.

[0064] In an embodiment of the present invention, the resume data collection unit 101 establishes a collection interface with multiple recruitment channels and talent databases, and then automatically collects attached resumes in different resume formats through multiple collection interfaces, including: PDF, Word and TXT, etc., and then converts and cleans up the multiple attached resumes to remove irrelevant information and format errors, ensure the availability of information, and obtain multiple resume texts.

[0065] The natural language processing unit 102 is used to process and recognize the multiple resume texts based on natural language processing technology to extract multiple key information.

[0066] In an embodiment of the present invention, the natural language processing unit 102 uses natural language processing technologies including NLTK, Spacy, etc. to perform word segmentation, part-of-speech tagging and named entity processing on multiple resume texts to obtain multiple optimized texts, and then performs key recognition on the multiple optimized texts to extract multiple key information, analyze the sentence structure and semantics in the resume, and understand the candidate's career development path, project experience and achievements and other deep information. Specifically, the multiple key information includes: basic personal information, work experience, educational background and skill list, etc.

[0067] The feature extraction unit 103 is used to import the plurality of key information into a preset talent feature model to perform feature extraction to obtain a plurality of specific features.

[0068] In an embodiment of the present invention, the feature extraction unit 103 imports multiple key information into a preset talent feature model, and extracts quantitative features from the multiple key information through the talent feature model, including: years of work experience, number of projects, and degree of skill mastery, etc.; and uses a preset text analysis and machine learning algorithm to evaluate and extract evaluation features from multiple key information, including: communication skills and teamwork skills, etc., and then combines multiple quantitative features and multiple evaluation features to obtain multiple specific features.

[0069] The big data analysis and modeling unit 104 is used to utilize big data analysis technology to perform statistics and modeling on the multiple specific features, obtain feature statistical data, and establish a talent feature prediction model.

[0070] In the embodiment of the present invention, the big data analysis modeling unit 104 uses big data analysis technology to perform statistics on multiple specific features, analyze the correlation between different specific features, and the distribution of specific features in different industries, obtain feature statistical data, and then establish a talent feature prediction model based on the feature statistical data, so as to predict unknown features based on known features and improve the completeness and accuracy of feature extraction. Among them, big data analysis technology can use Hive, Spark, etc.

[0071] The visualization application unit 105 is used to visualize the multiple specific features according to the feature statistical data and perform recruitment matching processing.

[0072] In an embodiment of the present invention, the visualization application unit 105 visualizes multiple specific features in the form of tables and icons based on feature statistical data, accurately matches recruitment needs based on the feature statistical data, and customizes different training plans based on the feature statistical data during the training process after the recruitment is completed. Specifically, the visualization tool may be Tableau, PowerBI, etc.

[0073] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0074] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0075] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for extracting talent features based on big data analysis of attached resumes, characterized in that: The method specifically comprises the following steps: Establishing a collection interface with multiple recruitment channels and talent databases, automatically collecting multiple attached resumes, and preliminarily processing the multiple attached resumes to obtain multiple resume texts; Based on natural language processing technology, multiple resume texts are processed and recognized to extract multiple key information; Importing the plurality of key information into a preset talent feature model to extract features and obtain a plurality of specific features; Using big data analysis technology, statistics and modeling are performed on the multiple specific characteristics to obtain characteristic statistical data and establish a talent characteristic prediction model; Based on the feature statistical data, a plurality of the specific features are visualized and recruitment matching is performed.

2. The method for extracting talent characteristics based on big data analysis of attached resumes according to claim 1 is characterized in that: The establishment of a collection interface with multiple recruitment channels and talent databases, automatically collecting multiple attached resumes, and preliminarily processing the multiple attached resumes to obtain multiple resume texts specifically includes the following steps: Establish collection interfaces with multiple recruitment channels and talent databases; Automatically collect multiple attached resumes through multiple collection interfaces; The multiple resume attachments are formatted and cleaned to remove irrelevant information and format errors, thereby obtaining multiple resume texts.

3. The method for extracting talent characteristics based on big data analysis of attached resumes according to claim 2 is characterized in that: The resume formats of the multiple attached resumes include: PDF, Word and TXT.

4. The method for extracting talent characteristics based on big data analysis of attached resumes according to claim 1 is characterized in that: The process of processing and identifying the multiple resume texts based on natural language processing technology and extracting multiple key information specifically includes the following steps: Based on natural language processing technology, multiple resume texts are segmented, POS tagged, and named entity processed to obtain multiple optimized texts; Key identification is performed on the multiple optimized texts to extract multiple key information.

5. The method for extracting talent characteristics based on big data analysis of attached resumes according to claim 4 is characterized in that: The key information includes: basic personal information, work experience, educational background and skill list.

6. The method for extracting talent characteristics based on big data analysis of attached resumes according to claim 1 is characterized in that: The step of importing the plurality of key information into a preset talent feature model to extract features and obtain a plurality of specific features specifically comprises the following steps: Importing a plurality of the key information into a preset talent characteristic model; Extracting quantitative features from a plurality of the key information through the talent feature model; Using preset text analysis and machine learning algorithms to evaluate and extract evaluation features from a plurality of the key information; A plurality of the quantitative features and a plurality of the evaluation features are integrated to obtain a plurality of specific features.

7. The method for extracting talent characteristics based on big data analysis of attached resumes according to claim 6 is characterized in that: The multiple quantitative characteristics include: years of work experience, number of projects and degree of skill mastery; the multiple evaluation characteristics include: communication skills and teamwork skills.

8. The method for extracting talent characteristics based on big data analysis of attached resumes according to claim 1 is characterized in that: The use of big data analysis technology to perform statistics and modeling on the multiple specific features to obtain feature statistical data and establish a talent feature prediction model specifically includes the following steps: Using big data analysis technology, statistics are collected on the multiple specific features, the correlation between different specific features, and the distribution of specific features in different industries are analyzed to obtain feature statistical data; A talent characteristic prediction model is established based on the characteristic statistical data.

9. The method for extracting talent characteristics based on big data analysis of attached resumes according to claim 1 is characterized in that: The step of visually displaying the plurality of specific features based on the feature statistical data and performing recruitment matching processing specifically includes the following steps: Visually displaying the plurality of specific features according to the feature statistical data, wherein the visual display includes a table and an icon; According to the statistical data of the characteristics, accurate matching of recruitment needs is carried out; Different training plans are customized according to the characteristic statistics.

10. A big data analysis talent feature extraction system based on attached resumes, characterized in that: The system includes a resume data collection unit, a natural language processing unit, a feature extraction unit, a big data analysis modeling unit and a visualization display application unit, wherein: A resume data collection unit is used to establish a collection interface with multiple recruitment channels and talent databases, automatically collect multiple attached resumes, and perform preliminary processing on the multiple attached resumes to obtain multiple resume texts; A natural language processing unit, used to process and identify the multiple resume texts based on natural language processing technology, and extract multiple key information; A feature extraction unit, used for importing the plurality of key information into a preset talent feature model to perform feature extraction and obtain a plurality of specific features; A big data analysis and modeling unit, used to use big data analysis technology to perform statistics and modeling on the multiple specific features, obtain feature statistical data, and establish a talent feature prediction model; A visualization application unit is used to visualize the multiple specific features according to the feature statistical data and perform recruitment matching processing.

Images