Unemployee post recommendation method and system

Abstract

The invention discloses an unemployee post recommendation method and system, and belongs to the technical field of big data analysis, post recommendation is carried out on unemployees by using a simbert algorithm in a deep neural network, and the method comprises the following steps: collecting background information of the unemployees, and collecting post demand data; cleaning and standardizing the collected data; performing semantic analysis and feature extraction on the preprocessed background information and post requirements by using an SIMBERT algorithm; according to the SIMBERT algorithm, a text is encoded through a bidirectional encoder, and high-dimensional semantic vector representation is generated; constructing a matching model according to the semantic vector of the background information of the unemployee and the semantic vector of the post demand; calculating the semantic similarity between the unemployees and the posts, and quantifying the semantic similarity; and generating a recommendation result and performing feedback optimization. According to the invention, an unemployment person can be helped to find proper work more quickly, and the quality and efficiency of employment service are significantly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis, and in particular to a method and system for recommending positions for unemployed persons. Background Art

[0002] The current employment service system still faces many challenges in actual operation. Traditional job recommendation methods mostly rely on manual screening and simple keyword matching, which have problems such as information asymmetry and low matching, resulting in a long job search cycle and poor recommendation results. Especially for those who have been unemployed for a long time or have special skills, the existing recommendation system is difficult to fully play its role and cannot efficiently match them with suitable jobs.

[0003] In addition, with the development of big data and artificial intelligence technology, many new technical means have achieved remarkable results in different fields, but their application in job recommendation is still relatively limited. At present, some systems that attempt to introduce intelligent recommendation algorithms are mainly based on traditional machine learning models, and fail to make full use of the latest natural language processing technology and deep learning models, thus failing to achieve accurate and efficient job recommendations.

[0004] In order to improve the reemployment efficiency of unemployed people and solve the problems of low matching degree and poor recommendation effect in existing technologies, it is necessary to develop a job recommendation method based on advanced algorithms. Summary of the invention

[0005] The technical task of the present invention is to address the above deficiencies and provide a method and system for recommending jobs for unemployed persons, which can help unemployed persons find suitable jobs more quickly and significantly improve the quality and efficiency of employment services in practical applications.

[0006] The technical solution adopted by the present invention to solve its technical problem is:

[0007] A method for recommending jobs to unemployed persons uses the Simbert algorithm in a deep neural network to recommend jobs to unemployed persons. The implementation of the method includes:

[0008] 1) Data collection: Collect background information of unemployed persons and job demand data;

[0009] 2) Data preprocessing: Clean and standardize the collected data to ensure data consistency and integrity;

[0010] 3)Simbert algorithm processing: Use the SIMBERT algorithm to perform semantic analysis and feature extraction on the pre-processed background information and job requirements; the SIMBERT algorithm encodes the text through a bidirectional encoder to generate a high-dimensional semantic vector representation;

[0011] 4) Matching model construction: Construct a matching model based on the semantic vector of the unemployed person’s background information and the semantic vector of the job requirements; calculate the semantic similarity between the unemployed person and the job, and quantify it;

[0012] 5) Recommendation result generation: Sort the positions according to semantic similarity, generate a recommendation list, and display the recommendation results to the unemployed;

[0013] 6) Feedback optimization: Continuously optimize the recommendation model by collecting feedback from unemployed people on the recommendation results.

[0014] This method realizes job recommendation for unemployed people based on Simbert algorithm, and realizes accurate and efficient job recommendation through deep semantic analysis and big data processing technology. Through natural language preprocessing of collected unemployed people and job information, combined with pre-trained large language model, Simbert algorithm is used to build a matching model between unemployed people information and jobs, and job recommendation is carried out, which ultimately improves the matching probability and shortens the job search cycle to support the government's employment policy.

[0015] Furthermore, the background information of the unemployed person includes but is not limited to resume, work experience, skills, education, job-seeking intentions, etc.

[0016] Furthermore, the job requirement data includes job responsibilities, requirements, company information, etc.

[0017] Furthermore, the data preprocessing includes: performing natural language processing preprocessing operations such as word segmentation and stop word removal on the text data.

[0018] Furthermore, the matching model is constructed to quantify the semantic similarity between unemployed persons and positions, using methods such as cosine similarity and Euclidean distance.

[0019] Furthermore, the recommendation results are generated and displayed to the unemployed persons, providing detailed job information and matching scores.

[0020] Furthermore, the feedback optimization uses feedback data to perform big data analysis, adjust matching algorithm parameters, and improve the accuracy and effectiveness of recommendations.

[0021] The present invention also claims protection for a job recommendation system for unemployed persons, comprising:

[0022] Data collection module, used to collect background information of unemployed persons and job demand data;

[0023] Data preprocessing is used to clean and standardize the collected data to ensure data consistency and integrity;

[0024] The Simbert algorithm processing module uses the SIMBERT algorithm to perform semantic analysis and feature extraction on the preprocessed background information and job requirements. The SIMBERT algorithm encodes the text through a bidirectional encoder to generate a high-dimensional semantic vector representation.

[0025] The matching model building module is used to build a matching model based on the semantic vector of the background information of the unemployed and the semantic vector of the job requirements; calculate the semantic similarity between the unemployed and the job, and quantify it;

[0026] The recommendation result generation module is used to sort the positions according to semantic similarity, generate a recommendation list, and display the recommendation results to the unemployed;

[0027] Feedback optimization module, which continuously optimizes the recommendation model by collecting feedback from unemployed people on the recommendation results;

[0028] The system achieves job recommendations for unemployed people through the above method.

[0029] The present invention also claims protection for a job recommendation device for unemployed persons, comprising: at least one memory and at least one processor;

[0030] The at least one memory is used to store a machine-readable program;

[0031] The at least one processor is used to call the machine-readable program to implement the above method.

[0032] The present invention also claims protection for a computer-readable medium having computer instructions stored thereon, which, when executed by a processor, causes the processor to perform the above method.

[0033] Compared with the prior art, the method and system for recommending positions for unemployed persons of the present invention have the following beneficial effects:

[0034] The present invention realizes job recommendation for unemployed persons based on Simbert algorithm, and realizes accurate and efficient job recommendation through deep semantic analysis and big data processing technology, which has the following beneficial effects:

[0035] 1. Improve matching and recommendation accuracy: The Simbert algorithm is used to conduct in-depth semantic analysis of the background information and job requirements of unemployed people, which can accurately understand and match text information. Compared with the traditional keyword matching method, the recommended positions are more in line with the skills and experience of unemployed people, thus significantly improving the matching and recommendation accuracy.

[0036] 2. Shorten the job search cycle: Through accurate job recommendations, unemployed people can quickly find jobs that meet their requirements and expectations, reducing the time of blindly submitting resumes and waiting, and significantly shortening the job search cycle.

[0037] 3. Provide personalized recommendation services: Using big data analysis technology, we provide personalized job recommendation services based on the personal background, job search intentions and historical feedback of unemployed people. The system can continuously optimize the recommendation model based on user feedback to improve the personalization and satisfaction of recommendation results.

[0038] 4. Enhance the public employment service system: The present invention improves the intelligence level of the public employment service platform by introducing an intelligent recommendation algorithm, which helps to improve the employment support system for key groups, especially providing more effective employment assistance to groups who have been unemployed for a long time or have special skills, thereby enhancing the overall effect of public employment services.

[0039] 5. Optimize the allocation of employment resources: Through efficient job matching and recommendation, it helps companies find the most suitable employees and improves the efficiency of human resource utilization. Companies can quickly find job seekers who meet job requirements through the system, reduce recruitment cycles and costs, and improve recruitment efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a flowchart of a method for recommending jobs for unemployed persons provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0042] The embodiment of the present invention provides a method for recommending positions for unemployed persons, which uses the Simbert algorithm in a deep neural network to recommend positions for unemployed persons. The implementation of the method includes:

[0043] 1. Data collection:

[0044] Collect background information of unemployed persons, including resume, work experience, skills, education, job search intentions, etc.; collect job demand data, including job responsibilities, requirements, company information, etc.

[0045] 2. Data preprocessing:

[0046] Clean and standardize the collected data to ensure data consistency and integrity. Perform natural language processing preprocessing operations such as word segmentation and stop word removal on text data.

[0047] 3.Simbert algorithm processing:

[0048] The SIMBERT algorithm is used to perform semantic analysis and feature extraction on the preprocessed background information and job requirements; the SIMBERT algorithm encodes the text through a bidirectional encoder to generate a high-dimensional semantic vector representation.

[0049] 4. Matching model construction:

[0050] A matching model is constructed based on the semantic vector of the background information of unemployed persons and the semantic vector of job requirements. The semantic similarity between unemployed persons and jobs is calculated and quantified using methods such as cosine similarity and Euclidean distance.

[0051] 5. Recommendation result generation:

[0052] The positions are sorted according to semantic similarity, a recommendation list is generated, and the recommendation results are displayed to the unemployed, providing detailed position information and matching scores.

[0053] 6. Feedback optimization:

[0054] By collecting feedback from unemployed people on recommendation results, the recommendation model is continuously optimized. The feedback data is used for big data analysis to adjust matching algorithm parameters and improve the accuracy and effectiveness of recommendations.

[0055] The Simbert algorithm is an emerging natural language processing model that can better understand and process semantic information and is suitable for accurate analysis and matching of text. The job recommendation method based on the Simbert algorithm can accurately match suitable jobs by performing in-depth semantic analysis on the background information and job requirements of unemployed persons, thereby greatly improving the accuracy and effectiveness of recommendations. This method uses the Simbert algorithm and combines big data analysis technology to propose an efficient and accurate job recommendation method for unemployed persons, solving the problems of low matching and poor recommendation effect in existing technologies. By utilizing advanced natural language processing technology and big data analysis technology, unemployed persons and job requirements can be matched more accurately, achieving the following specific goals: improving the matching degree and accuracy of job recommendations, shortening the job search cycle, providing personalized recommendation services, and supporting government employment policies.

[0056] The embodiment of the present invention also provides a job recommendation system for unemployed persons, which implements job recommendation for unemployed persons through the job recommendation method for unemployed persons described in the above embodiment.

[0057] The system includes:

[0058] 1. Data collection module, used to collect background information of unemployed persons and job demand data.

[0059] Collect background information of unemployed persons, including resume, work experience, skills, education, job search intentions, etc.; collect job demand data, including job responsibilities, requirements, company information, etc.

[0060] 2. Data preprocessing is used to clean and standardize the collected data to ensure data consistency and integrity; perform natural language processing preprocessing operations such as word segmentation and stop word removal on text data.

[0061] 3. The Simbert algorithm processing module uses the SIMBERT algorithm to perform semantic analysis and feature extraction on the pre-processed background information and job requirements. The SIMBERT algorithm encodes the text through a bidirectional encoder to generate a high-dimensional semantic vector representation.

[0062] 4. A matching model building module is used to build a matching model based on the semantic vector of the background information of unemployed persons and the semantic vector of job requirements; calculate the semantic similarity between unemployed persons and jobs, and quantify it using methods such as cosine similarity and Euclidean distance.

[0063] 5. The recommendation result generation module is used to sort the positions according to semantic similarity, generate a recommendation list, display the recommendation results to the unemployed, and provide detailed position information and matching scores.

[0064] 6. Feedback optimization module: By collecting feedback from unemployed people on the recommendation results, the recommendation model is continuously optimized; feedback data is used for big data analysis, matching algorithm parameters are adjusted, and the accuracy and effectiveness of recommendations are improved.

[0065] The embodiment of the present invention also provides a job recommendation device for unemployed persons, comprising: at least one memory and at least one processor;

[0066] The at least one memory is used to store a machine-readable program;

[0067] The at least one processor is used to call the machine-readable program to implement the job recommendation method for unemployed persons described in the above embodiment.

[0068] The embodiment of the present invention further provides a computer-readable medium, on which computer instructions are stored, and when the computer instructions are executed by a processor, the processor executes the job recommendation method for unemployed persons described in the above embodiment. Specifically, a system or device equipped with a storage medium can be provided, on which software program codes for implementing the functions of any of the above embodiments are stored, and a computer (or CPU or MPU) of the system or device reads and executes the program code stored in the storage medium.

[0069] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.

[0070] The storage medium embodiments for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a non-volatile memory card, and a ROM. Alternatively, the program code can be downloaded from a server computer by a communication network.

[0071] In addition, it should be clear that the functions of any of the above embodiments can be implemented not only by executing the program code read by the computer, but also by enabling an operating system operating on the computer to complete part or all of the actual operations based on instructions from the program code.

[0072] In addition, it can be understood that the program code read from the storage medium is written to a memory provided in an expansion board inserted into the computer or written to a memory provided in an expansion unit connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or the expansion unit is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above-mentioned embodiments.

[0073] The present invention is shown and described in detail above through the accompanying drawings and preferred embodiments. However, the present invention is not limited to these disclosed embodiments. Based on the above multiple embodiments, those skilled in the art can know that the code review methods in the above different embodiments can be combined to obtain more embodiments of the present invention, and these embodiments are also within the protection scope of the present invention.

Claims

1. A method for recommending jobs for unemployed persons, characterized in that: The Simbert algorithm in the deep neural network is used to recommend jobs to unemployed people. The implementation of this method includes: 1) Data collection: Collect background information of unemployed persons and job demand data; 2) Data preprocessing: Clean and standardize the collected data to ensure data consistency and integrity; 3)Simbert algorithm processing: Use the SIMBERT algorithm to perform semantic analysis and feature extraction on the pre-processed background information and job requirements; the SIMBERT algorithm encodes the text through a bidirectional encoder to generate a high-dimensional semantic vector representation; 4) Matching model construction: Construct a matching model based on the semantic vector of the unemployed person’s background information and the semantic vector of the job requirements; calculate the semantic similarity between the unemployed person and the job, and quantify it; 5) Recommendation result generation: Sort the positions according to semantic similarity, generate a recommendation list, and display the recommendation results to the unemployed; 6) Feedback optimization: Continuously optimize the recommendation model by collecting feedback from unemployed people on the recommendation results.

2. A method for recommending jobs for unemployed persons according to claim 1, characterized in that: The background information of the unemployed person includes resume, work experience, skills, education, and job-seeking intention information.

3. A method for recommending jobs for unemployed persons according to claim 1 or 2, characterized in that: The job requirement data includes job responsibilities, requirements, company information, etc.

4. A method for recommending jobs for unemployed persons according to claim 1, characterized in that: The data preprocessing includes: performing word segmentation and stop word removal operations on the text data.

5. A method for recommending positions for unemployed persons according to claim 1, characterized in that: The matching model is constructed to quantify the semantic similarity between unemployed persons and positions, and the methods used include cosine similarity and Euclidean distance methods.

6. A method for recommending jobs for unemployed persons according to claim 1, characterized in that: The recommendation results are generated and displayed to the unemployed persons, providing detailed job information and matching scores.

7. A method for recommending positions for unemployed persons according to claim 1, characterized in that: The feedback optimization uses feedback data to perform big data analysis, adjust matching algorithm parameters, and improve the accuracy and effectiveness of recommendations.

8. A job recommendation system for unemployed persons, characterized in that: include: Data collection module, used to collect background information of unemployed persons and job demand data; Data preprocessing is used to clean and standardize the collected data to ensure data consistency and integrity; The Simbert algorithm processing module uses the SIMBERT algorithm to perform semantic analysis and feature extraction on the preprocessed background information and job requirements. The SIMBERT algorithm encodes the text through a bidirectional encoder to generate a high-dimensional semantic vector representation. A matching model building module is used to build a matching model based on the semantic vector of the background information of the unemployed and the semantic vector of the job requirements; Calculate and quantify the semantic similarity between unemployed persons and positions; The recommendation result generation module is used to sort the positions according to semantic similarity, generate a recommendation list, and display the recommendation results to the unemployed; Feedback optimization module, which continuously optimizes the recommendation model by collecting feedback from unemployed people on the recommendation results; The system realizes job recommendation for unemployed persons through the method described in any one of claims 1 to 7.

9. A job recommendation device for unemployed persons, characterized in that: include: at least one memory and at least one processor; The at least one memory is used to store a machine-readable program; The at least one processor is used to call the machine-readable program to implement the method described in any one of claims 1 to 7.

10. A computer-readable medium, characterized in that The computer readable medium stores computer instructions, which, when executed by a processor, cause the processor to execute the method according to any one of claims 1 to 7.

Images