Personnel screening method and system based on large model technology

Abstract

The invention particularly relates to a personnel screening method and system based on a large model technology. According to the personnel screening method based on the large model technology, a personnel screening interface is defined, text extraction is carried out on a process file to be uploaded by a user, the process file is preprocessed and then converted into a format customized and specified by a system, and uploading is carried out, so that the analysis accuracy is ensured; analyzing the extracted process text by using a pre-trained large model GPT or BERT, identifying condition information related to personnel, and structuring the extracted condition information; combining the extracted condition information with information of a personnel screening interface, providing input for a large model, and generating an interface calling method; and calling a personnel screening interface, and returning response data. According to the personnel screening method and system based on the large model technology, manual intervention is remarkably reduced, the information processing efficiency is improved, human errors are greatly reduced, real-time response is achieved, and high flexibility and adaptability are achieved.

Description

Technical Field

[0001] The present invention relates to the field of data governance technology, and in particular to a personnel screening method and system based on big model technology. Background Art

[0002] In modern society, the execution and management of processes have put forward higher requirements for the selection and screening of personnel. Process documents usually contain a large number of terms and conditions, involving requirements for the qualifications, capabilities, experience, etc. of specific people. Traditional methods rely on manual reading and analysis of process documents, which is time-consuming and error-prone. In addition, existing personnel screening interfaces often lack intelligent integration with process texts, resulting in low information retrieval efficiency. Therefore, there is an urgent need for an intelligent solution that can automatically parse process documents and seamlessly connect with the personnel screening system.

[0003] Based on the above problems, the present invention proposes a personnel screening method and system based on large model technology. Summary of the invention

[0004] In order to make up for the defects of the prior art, the present invention provides a simple and efficient personnel screening method and system based on large model technology.

[0005] The present invention is achieved through the following technical solutions:

[0006] A personnel screening method based on large model technology, characterized in that it includes the following steps:

[0007] Step S1: Define the personnel screening interface

[0008] The personnel screening interface is responsible for receiving request parameters and returning response data based on the request parameters;

[0009] The request parameters are screening conditions, including age, qualification certificate, work experience, education level and city;

[0010] The response data includes a list of people who meet the screening criteria and the resume information of each person;

[0011] In step S1, the personnel screening interface filters historical data according to the user's input information, generates optimal selection conditions according to the filtering information, and predicts and intelligently prompts the screening conditions input by the user.

[0012] Step S2: Upload process files

[0013] Extract text from the process files to be uploaded by the user, convert them into the system-defined format after preprocessing, and upload them to ensure the accuracy of the analysis;

[0014] Supported file formats include PDF, Word, and TXT.

[0015] In step S2, preprocessing the process file to be uploaded includes the following steps:

[0016] Step S2.1, clear irrelevant information, including page numbers and watermarks;

[0017] Step S2.2: format verification, converting the file into a plain text format that can be analyzed;

[0018] Step S2.3, error detection and optimization of the text, automatic detection of parsing error areas in the file, and prompting the user to correct them.

[0019] Step S3: Large model analysis

[0020] Use the pre-trained large model GPT or BERT to parse the extracted process text, identify the condition information related to personnel, including qualification requirements and restrictions, and structure the extracted condition information for subsequent processing;

[0021] In step S3, the extracted process text is first parsed using the pre-trained large model GPT or BERT, and the steps are as follows:

[0022] Step S3.1, data cleaning, removing irrelevant text, including watermarks and repeated information;

[0023] Step S3.2: Segment and classify text according to the language model.

[0024] Step S3.3, identify the invisible correlations in the documents through the large model, including the invisible mean dimension between personnel qualifications and job requirements, to improve the analysis accuracy and positive application space.

[0025] Step S4: Generate interface call information

[0026] Combine the extracted condition information with the information of the personnel screening interface to provide input for the large model and generate the interface calling method;

[0027] In step S4, the implementation process is as follows:

[0028] Step S4.1, formatting and processing the extracted condition information according to the request parameters of the personnel screening interface;

[0029] Step S4.2, custom design the optimal input format according to the large model description;

[0030] Step S4.3: Automatically implement debugging and error return to ensure the accuracy and pass rate of calling the interface and improve user experience.

[0031] Step S5: Calling the personnel screening interface

[0032] The user customizes the specified filtering conditions, and according to the call information provided by the large model, the personnel screening interface is automatically called to obtain the information of qualified personnel, and the response data is returned as the result and displayed to the user.

[0033] In step S5, the user is allowed to define the screening conditions and perform secondary screening on the response data;

[0034] By displaying the association between files and screening results, such as through process file nodes matched by personnel, users can improve their understanding of the results and seamless involvement.

[0035] A personnel screening system based on big model technology, including a personnel screening interface, a process file uploading module, a big model parsing module and an interface calling generation module;

[0036] The process file upload module is responsible for extracting text from the process file to be uploaded by the user, converting it into a system-defined format after preprocessing, and uploading it;

[0037] The large model parsing module is responsible for parsing the extracted process text using the pre-trained large model GPT or BERT, identifying the condition information related to personnel, including qualification requirements and restrictions, and structuring the extracted condition information for subsequent processing;

[0038] The interface call generation module is responsible for combining the extracted condition information with the information of the personnel screening interface, providing input for the large model, and generating an interface call method;

[0039] The personnel screening interface is responsible for receiving request parameters and returning response data according to the request parameters;

[0040] The request parameters are screening conditions, including age, qualification certificate, work experience, education level and city;

[0041] The response data includes a list of people who meet the screening criteria and the resume information of each person.

[0042] A personnel screening device based on large model technology, characterized in that it includes a memory and a processor; the memory is used to store a computer program, and the processor is used to implement the above method steps when executing the computer program.

[0043] A readable storage medium, characterized in that: a computer program is stored on the readable storage medium, and the computer program implements the above method steps when executed by a processor.

[0044] The beneficial effects of the present invention are: the personnel screening method and system based on large model technology significantly reduce human intervention, improve information processing efficiency, greatly reduce human errors, achieve real-time response, and have strong flexibility and adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Attached Figure 1 Schematic diagram of the personnel screening method based on large model technology of the present invention. DETAILED DESCRIPTION

[0047] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0048] Large Language Model (LLM), also known as Large Language Model, is an artificial intelligence model designed to understand and generate human language. They are trained on large amounts of text data and can perform a wide range of tasks, including text summarization, translation, sentiment analysis, and more. LLMs are characterized by their large size and contain billions of parameters, which help them learn complex patterns in language data. These models are often based on deep learning architectures such as transformers, which helps them achieve impressive performance on various NLP tasks.

[0049] The personnel screening method based on the large model technology comprises the following steps:

[0050] Step S1: Define the personnel screening interface

[0051] The personnel screening interface is responsible for receiving request parameters and returning response data based on the request parameters;

[0052] The request parameters are screening conditions, including age, qualification certificate, work experience, education level and city;

[0053] The response data includes a list of people who meet the screening criteria and the resume information of each person;

[0054] The following are examples of request parameters:

[0055] Age: Specify an age range, such as "25-40".

[0056] Qualifications: including professional certificates, such as "PMP" and "Medical Qualification Certificate".

[0057] Work experience: Specify the number of years of work experience, such as “not less than 5 years”.

[0058] Other conditions: may also include city, university degree, etc.

[0059] The following is an example of the response data:

[0060] Personnel list: screening results, including basic information such as name, age, and professional qualifications.

[0061] Detailed information: Detailed information of each person, including educational background, work history, contact information, etc.

[0062] In step S1, the personnel screening interface filters historical data according to the user's input information, generates optimal selection conditions according to the filtering information, and predicts and intelligently prompts the screening conditions input by the user.

[0063] Step S2: Upload process files

[0064] Extract text from the process files to be uploaded by the user, convert them into the system-defined format after preprocessing, and upload them to ensure the accuracy of the analysis;

[0065] Supported file formats include PDF, Word, and TXT.

[0066] In step S2, preprocessing the process file to be uploaded includes the following steps:

[0067] Step S2.1, clear irrelevant information, including page numbers and watermarks;

[0068] Step S2.2: format verification, converting the file into a plain text format that can be analyzed;

[0069] Step S2.3, error detection and optimization of the text, automatic detection of parsing error areas in the file, and prompting the user to correct them.

[0070] Step S3: Large model analysis

[0071] Use the pre-trained large model GPT or BERT to parse the extracted process text, identify the condition information related to personnel, including qualification requirements and restrictions, and structure the extracted condition information for subsequent processing;

[0072] In step S3, the extracted process text is first parsed using the pre-trained large model GPT or BERT, and the steps are as follows:

[0073] Step S3.1, data cleaning, removing irrelevant text, including watermarks and repeated information;

[0074] Step S3.2: Segment and classify text according to the language model.

[0075] Step S3.3, identify the invisible correlations in the documents through the large model, including the invisible mean dimension between personnel qualifications and job requirements, to improve the analysis accuracy and positive application space.

[0076] Step S4: Generate interface call information

[0077] Combine the extracted condition information with the information of the personnel screening interface to provide input for the large model and generate the interface calling method;

[0078] In step S4, the implementation process is as follows:

[0079] Step S4.1, formatting and processing the extracted condition information according to the request parameters of the personnel screening interface;

[0080] Step S4.2, custom design the optimal input format according to the large model description;

[0081] Step S4.3: Automatically implement debugging and error return to ensure the accuracy and pass rate of calling the interface and improve user experience.

[0082] Step S5: Calling the personnel screening interface

[0083] The user customizes the specified filtering conditions, and according to the call information provided by the large model, the personnel screening interface is automatically called to obtain the information of qualified personnel, and the response data is returned as the result and displayed to the user.

[0084] In step S5, the user is allowed to define the screening conditions and perform secondary screening on the response data;

[0085] By displaying the association between files and screening results, such as through process file nodes matched by personnel, users can improve their understanding of the results and seamless involvement.

[0086] The personnel screening system based on the big model technology includes a personnel screening interface, a process file uploading module, a big model parsing module and an interface calling generation module;

[0087] The process file upload module is responsible for extracting text from the process file to be uploaded by the user, converting it into a system-defined format after preprocessing, and uploading it;

[0088] The large model parsing module is responsible for parsing the extracted process text using the pre-trained large model GPT or BERT, identifying the condition information related to personnel, including qualification requirements and restrictions, and structuring the extracted condition information for subsequent processing;

[0089] The interface call generation module is responsible for combining the extracted condition information with the information of the personnel screening interface, providing input for the large model, and generating an interface call method;

[0090] The personnel screening interface is responsible for receiving request parameters and returning response data according to the request parameters;

[0091] The request parameters are screening conditions, including age, qualification certificate, work experience, education level and city;

[0092] The response data includes a list of people who meet the screening criteria and the resume information of each person.

[0093] The personnel screening device based on the large model technology includes a memory and a processor; the memory is used to store a computer program, and the processor is used to implement the above method steps when executing the computer program.

[0094] The readable storage medium stores a computer program, and when the computer program is executed by a processor, the above method steps are implemented.

[0095] In summary, the personnel screening method and system based on large model technology has the following characteristics:

[0096] Improved efficiency: Automated process analysis and personnel screening processes significantly reduce manual intervention and improve information processing efficiency.

[0097] Improved accuracy: By leveraging the natural language processing capabilities of the big model, the system can more accurately extract personnel conditions related to the process, reducing human errors.

[0098] Real-time response is achieved: after uploading the process file, the user can quickly obtain the information of qualified personnel to meet the real-time needs.

[0099] Strong flexibility and adaptability: The system can process process files in various formats and flexibly adjust screening conditions according to different process contents.

[0100] The embodiment described above is only one specific implementation of the present invention. Common changes and substitutions made by those skilled in the art within the scope of the technical solution of the present invention should be included in the protection scope of the present invention.

Claims

1. A personnel screening method based on large model technology, characterized in that: The following steps are involved: Step S1: Define the personnel screening interface The personnel screening interface is responsible for receiving request parameters and returning response data based on the request parameters; The request parameters are screening conditions, including age, qualification certificate, work experience, education level and city; The response data includes a list of people who meet the screening criteria and the resume information of each person; Step S2: Upload process files Extract text from the process files to be uploaded by the user, convert them into the system-defined format after preprocessing, and upload them to ensure the accuracy of the analysis; Supported file formats include PDF, Word and TXT; Step S3: Large model analysis Use the pre-trained large model GPT or BERT to parse the extracted process text, identify the condition information related to personnel, including qualification requirements and restrictions, and structure the extracted condition information for subsequent processing; Step S4: Generate interface call information Combine the extracted condition information with the information of the personnel screening interface to provide input for the large model and generate the interface calling method; Step S5: Calling the personnel screening interface The user customizes the specified filtering conditions, and according to the call information provided by the large model, the personnel screening interface is automatically called to obtain the information of qualified personnel, and the response data is returned as the result and displayed to the user.

2. The personnel screening method based on large model technology according to claim 1 is characterized in that: In step S1, the personnel screening interface filters historical data according to the user's input information, generates optimal selection conditions according to the filtering information, and predicts and intelligently prompts the screening conditions input by the user.

3. The personnel screening method based on large model technology according to claim 1 is characterized in that: In step S2, preprocessing the process file to be uploaded includes the following steps: Step S2.1, clear irrelevant information, including page numbers and watermarks; Step S2.2: format verification, converting the file into a plain text format that can be analyzed; Step S2.3, error detection and optimization of the text, automatic detection of parsing error areas in the file, and prompting the user to correct them.

4. The personnel screening method based on large model technology according to claim 1 is characterized in that: In step S3, the extracted process text is first parsed using the pre-trained large model GPT or BERT, and the steps are as follows: Step S3.1, data cleaning, removing irrelevant text, including watermarks and repeated information; Step S3.2: Segment and classify text according to the language model. Step S3.3, identify the invisible correlations in the documents through the large model, including the invisible mean dimension between personnel qualifications and job requirements, to improve the analysis accuracy and positive application space.

5. The personnel screening method based on large model technology according to claim 1 is characterized in that: In step S4, the implementation process is as follows: Step S4.1, formatting and processing the extracted condition information according to the request parameters of the personnel screening interface; Step S4.2, custom design the optimal input format according to the large model description; Step S4.3: Automatically implement debugging and error return to ensure the accuracy and pass rate of calling the interface and improve user experience.

6. The personnel screening method based on large model technology according to claim 2 is characterized in that: In step S5, the user is allowed to define the screening conditions and perform secondary screening on the response data; By displaying the association between files and screening results, such as through process file nodes matched by personnel, users can improve their understanding of the results and seamless involvement.

7. A personnel screening system based on large model technology, characterized in that: Including personnel screening interface, process file upload module, large model parsing module and interface call generation module; The process file upload module is responsible for extracting text from the process file to be uploaded by the user, converting it into a system-defined format after preprocessing, and uploading it; The large model parsing module is responsible for parsing the extracted process text using the pre-trained large model GPT or BERT, identifying the condition information related to personnel, including qualification requirements and restrictions, and structuring the extracted condition information for subsequent processing; The interface call generation module is responsible for combining the extracted condition information with the information of the personnel screening interface, providing input for the large model, and generating an interface call method; The personnel screening interface is responsible for receiving request parameters and returning response data according to the request parameters; The request parameters are screening conditions, including age, qualification certificate, work experience, education level and city; The response data includes a list of people who meet the screening criteria and the resume information of each person.

8. A personnel screening device based on large model technology, characterized in that: The method comprises a memory and a processor; the memory is used to store a computer program, and the processor is used to implement the method according to any one of claims 1 to 7 when executing the computer program.

9. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images