Resume screening system and method
By integrating data collection, preprocessing, feature extraction, model training and user interface modules, the problems of low efficiency and insufficient accuracy in the recruitment process in the existing technology are solved, efficient and accurate resume screening and personalized adjustment are achieved, and the quality of the company's recruitment process is improved.
Patent Information
- Application Number
- CN202510444246.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-10
- Publication Date
- 2025-07-18
AI Technical Summary
The prior art has problems such as inefficiency, inconsistent screening standards and difficulty in meeting personalized needs in the recruitment process, especially inadequate accuracy when processing multi-source resume data.
The data acquisition module is used to collect resumes from multiple sources, clean and unify the format through the data preprocessing module, and the feature extraction module is used to extract key information using natural language processing technology, and the model training module is used to build a resume screening model using machine learning algorithms, and finally provide visual adjustment screening conditions in the user interface module.
It realizes efficient automatic analysis and evaluation of candidate resumes, improves the accuracy and consistency of screening results, meets the personalized needs of the company, and significantly improves the efficiency and quality of the recruitment process.
Smart Images
Figure CN120338739A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of human resource management, and specifically refers to a resume screening system and method. Background Art
[0002] In the field of modern human resource management, especially during the recruitment process, enterprises face the challenge of processing a large number of candidate resumes. The traditional human resource management mode relies on manual resume review, which is not only inefficient, consuming a large amount of time and energy of HR staff, but also difficult to ensure the consistency and objectivity of screening criteria. Although existing technical solutions attempt to simplify this process through automated tools, most systems are limited to collecting resume data from a single source and lack the ability to effectively integrate multi-source data; at the same time, these systems usually use simple keyword matching methods for screening and fail to deeply understand the complex information in resume content, such as work experience, skill sets, and educational backgrounds, resulting in insufficient accuracy and consistency of screening results. In addition, existing technologies often ignore the function of providing flexible adjustment of screening conditions and cannot meet the personalized needs of different enterprises. Therefore, there are obvious defects in existing technologies in terms of improving the efficiency of the recruitment process, ensuring screening quality, and supporting customization requirements. Summary of the Invention
[0003] I. Technical Problems to be Solved
[0004] The technical problems to be solved by the present invention are the various problems mentioned in the above background art, and a resume screening system and method are provided.
[0005] II. Technical Solutions
[0006] To solve the above technical problems, the technical solutions provided by the present invention are as follows: A resume screening system, comprising:
[0007] A data collection module for collecting electronic resumes from multiple sources;
[0008] A data preprocessing module configured to clean and uniformly format the electronic resumes;
[0009] A feature extraction module that uses natural language processing technology to parse and extract key information from the electronic resumes;
[0010] A model training module that trains a resume screening model using machine learning algorithms based on historical recruitment data provided by enterprises;
[0011] A screening execution module that inputs the resume data after feature extraction into the trained model to obtain the scores or rankings of candidates;
[0012] The user interface module provides a visual operation interface to display the screening results and allows users to manually adjust the screening conditions.
[0013] As an improvement, the data acquisition module can support obtaining resumes from multiple sources such as online recruitment platforms, emails, and enterprise internal databases.
[0014] As an improvement, the data preprocessing module can remove text noise, standardize the date format, and unify the keyword expressions.
[0015] As an improvement, the feature extraction module can identify work experience, skill sets, educational background, and project experience information in the resume.
[0016] As an improvement, the machine learning algorithms used in the model training module include decision trees and random forests. By analyzing the relationship between the characteristics of candidates and whether they are hired in historical recruitment data, a decision tree model is constructed, and the calculation formula is as follows:
[0017]
[0018] Where Pi represents the probability of belonging to category i; a large number of decision trees are generated using historical data and combined to form a random forest model. The specific formula is as follows:
[0019]
[0020] Here ht(x) is the prediction of the t-th tree for the input x, and T is the number of trees in the forest. For each new resume, the random forest will calculate the prediction results of all decision trees for this resume and then comprehensively obtain the final evaluation score or category.
[0021] As an improvement, a resume screening method based on the system described in claim 1 includes the following steps:
[0022] S1. Collect electronic resumes from multiple sources;
[0023] S2. Clean and unify the format of the electronic resumes;
[0024] S3. Use natural language processing technology to parse and extract key information in the electronic resumes;
[0025] S4. Train a resume screening model using historical recruitment data provided by the enterprise;
[0026] S5. Input the resume data after feature extraction into the trained model to obtain the score or ranking of the candidate;
[0027] S6. Connect an external visual interface to display the screening results and allow users to manually adjust the screening conditions.
[0028] As an improvement, the feature extraction step further includes quantifying the extracted key information for facilitating the combined use with the screening model.
[0029] III. Beneficial Effects
[0030] The advantages of the present invention compared with the prior art are as follows:
[0031] The resume screening system and method proposed by the present invention integrate multiple modules such as data collection, preprocessing, feature extraction, model training, and screening execution, realizing efficient automatic analysis and evaluation of candidate resumes. The system can automatically collect electronic resumes from multiple sources, and perform rapid cleaning and format unification processing, greatly saving the time cost of the human resources department in the preliminary screening stage; using advanced natural language processing technology to accurately identify and extract key information in the resume, and constructing a precise resume screening model through machine learning algorithms, effectively improving the accuracy and consistency of the screening results; the system provides a user-friendly visual interface, which not only displays the screening results, but also allows HR personnel to manually adjust the screening conditions according to specific needs, ensuring that the screening process is more in line with the actual employment needs of the enterprise. In summary, the resume screening system and method provide a comprehensive, efficient and flexible solution for enterprises, significantly improving the overall efficiency and quality of the recruitment process, and having important significance for enhancing the competitiveness of enterprises. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] Figure 1 is a structural diagram of a resume screening system of the present invention.
[0033] Figure 2 is a flowchart of a screening method of a resume screening system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0034] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments; based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0035] Embodiment 1
[0036] As Figure 1 — Figure 2 shown, a resume screening system includes:
[0037] A data collection module, which can support obtaining resumes from various sources such as online recruitment platforms, emails, and enterprise internal databases;
[0038] A data preprocessing module, which can remove text noise, standardize the date format, and unify the keyword expressions;
[0039] A feature extraction module, which can identify work experience, skill sets, educational background, and project experience information in resumes;
[0040] A model training module, which trains a resume screening model using machine learning algorithms based on historical recruitment data provided by enterprises;
[0041] A screening execution module, which inputs the resume data after feature extraction into the trained model to obtain the scores or rankings of candidates;
[0042] A user interface module, which provides a visual operation interface to display the screening results and allows users to manually adjust the screening conditions.
[0043] The machine learning algorithms used by the model training module include decision trees and random forests. By analyzing the relationship between the characteristics of candidates in historical recruitment data and whether they are hired, a decision tree model is constructed. The calculation formula is as follows:
[0044]
[0045] where Pi represents the probability of belonging to category i; a large number of decision trees are generated using historical data and combined to form a random forest model. The specific formula is as follows:
[0046]
[0047] Here, ht(x) is the prediction of the t-th tree for the input x, and T is the number of trees in the forest. For each new resume, the random forest will calculate the prediction results of all decision trees for this resume and then comprehensively obtain the final evaluation score or category.
[0048] A resume screening method based on the system described in claim 1, including the following steps:
[0049] S1. Collect electronic resumes from multiple sources;
[0050] S2. Clean and unify the format of the electronic resumes;
[0051] S3. Use natural language processing technology to parse and extract key information from the electronic resumes;
[0052] S4. Train a resume screening model using historical recruitment data provided by enterprises;
[0053] S5. Input the resume data after feature extraction into the trained model to obtain the scores or rankings of candidates;
[0054] S6. An external visual interface displays the screening results and allows users to manually adjust the screening conditions.
[0055] The feature extraction step further includes quantifying the extracted key information for use in combination with the screening model.
[0056] The working principle of the present invention:
[0057] First, the data collection module automatically collects electronic resumes from multiple sources (such as online recruitment platforms, emails, and enterprise internal databases). These sources provide rich and diverse candidate information, ensuring the comprehensiveness and extensiveness of the data.
[0058] Next, the data preprocessing module cleans and standardizes the collected electronic resumes. This includes removing noise (such as irrelevant characters) from the text, standardizing date formats, and unifying keyword expressions, etc., to ensure that subsequent steps can be processed based on consistent data standards.
[0059] Subsequently, the feature extraction module uses natural language processing technology to deeply analyze each resume, identify and extract key information such as work experience, skill set, educational background, and project experience. This process is not limited to surface information extraction, but also includes quantifying this information and converting it into a data form suitable for model training.
[0060] On this basis, the model training module uses historical recruitment data provided by the enterprise, through machine learning algorithms (such as decision trees and random forests), to analyze the relationship between candidate characteristics and whether they are hired, and constructs an accurate resume screening model. The decision tree model determines the best split point by calculating the probability Pi belonging to different classes; while the random forest determines the final evaluation score or class based on the average output of all trees by integrating the prediction results ht(x) of multiple decision trees.
[0061] Then, the screening execution module inputs the resume data after feature extraction into the trained model, and the model generates a score or ranking for each candidate, thereby helping the HR to quickly locate the most suitable candidates.
[0062] Finally, the user interface module provides a visual operation interface for displaying the screening results and allows HR personnel to manually adjust the screening conditions according to specific needs, such as modifying weights or adding specific requirements, to ensure that the screening process better meets the actual employment needs of the enterprise.
[0063] The entire process integrates a variety of advanced technologies to achieve efficient automatic analysis and evaluation of candidates' resumes, significantly improving the overall efficiency and quality of the recruitment process, providing a comprehensive, efficient and flexible solution for enterprises, and helping to enhance the competitive advantage of enterprises in the fierce market competition.
[0064] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.
[0065] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.
[0066] The above describes the present invention and its implementation manners. Such description is not restrictive. What is shown in the drawings is only one of the implementation manners of the present invention, and the actual structure is not limited thereto. Generally speaking, if those of ordinary skill in the art are inspired by it and design similar structural manners and embodiments without creative efforts without departing from the purpose of the present invention, they shall fall within the protection scope of the present invention.
Claims
1. A resume screening system, characterized in that, Including: A data collection module for collecting electronic resumes from multiple sources; A data preprocessing module configured to clean and unify the format of the electronic resumes; A feature extraction module that uses natural language processing technology to parse and extract key information from the electronic resumes; A model training module that trains a resume screening model using machine learning algorithms based on historical recruitment data provided by enterprises; A screening execution module that inputs the resume data after feature extraction into the trained model to obtain the scores or rankings of candidates; A user interface module that provides a visual operation interface to display the screening results and allows users to manually adjust the screening conditions.
2. The resume screening system according to claim 1, wherein The data collection module can support obtaining resumes from multiple sources such as online recruitment platforms, emails, and enterprise internal databases.
3. The resume screening system according to claim 1, wherein The data preprocessing module can remove text noise, standardize the date format, and unify the keyword expressions.
4. A resume screening system according to claim 1, characterized in that, The feature extraction module can identify work experience, skill sets, educational background, and project experience information in the resumes.
5. A resume screening system according to claim 1, characterized in that, The machine learning algorithms used by the model training module include decision trees and random forests. By analyzing the relationship between the characteristics of candidates in historical recruitment data and whether they are hired, a decision tree model is constructed, and the calculation formula is as follows: Where Pi represents the probability of belonging to category i; a large number of decision trees are generated using historical data and combined to form a random forest model. The specific formula is as follows: Here ht(x) is the prediction of the t-th tree for the input x, and T is the number of trees in the forest. For each new resume, the random forest will calculate the prediction results of all decision trees for this resume and then comprehensively obtain the final evaluation score or category.
6. A resume screening method based on the system described in claim 1, characterized in that, Including the following steps: S1. Collect electronic resumes from multiple sources; S2. Clean and unify the format of the electronic resumes; S3. Use natural language processing technology to parse and extract key information from the electronic resumes; S4. Train a resume screening model using historical recruitment data provided by enterprises; S5. Input the resume data after feature extraction into the trained model to obtain the scores or rankings of candidates; S6. Connect to a visual interface to display the screening results and allow users to manually adjust the screening conditions.
7. The resume screening method of the system according to claim 6, characterized in that The feature extraction step further includes quantifying the extracted key information for use in combination with the screening model.