Occupational evaluation method and system based on AI large model

Abstract

The invention discloses an AI large model-based occupational evaluation method and system. The method comprises the following steps: capturing network recruitment data by utilizing a search engine to capture a current recruitment hotspot trend and post talent portrait labels, training a bottom layer model by utilizing structured resume data uploaded by a user, and obtaining a user occupational development model under a multi-factor dimension; secondly, evaluating the user based on a traditional character evaluation model, and determining a basic character type of the user; and finally inputting the character type and the personal resume data of the user into the trained model, and outputting a personalized occupational evaluation result in combination with a recruitment hotspot trend and a talent portrait label. In addition, the evaluation result of the user serves as incremental data feedback and is used for further training and optimizing the model. According to the method, the accuracy, timeliness and model iteration capability of occupational evaluation are improved, and a scientific basis is provided for personal occupational planning and enterprise talent selection.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a career assessment method and system based on an AI big model. Background Art

[0002] With the development of artificial intelligence technology, especially the application of large-scale AI models, new solutions have been provided for the field of career assessment. These models can process and analyze large amounts of data, including personal resumes, personality assessment results, and career market trends, thereby providing more accurate and timely career assessment results.

[0003] Traditional career assessment methods often rely on static databases and limited data sources. These methods cannot effectively capture the dynamic changes of individuals during their growth, nor can they timely reflect new trends and changes in the career market. The conclusions of traditional career assessments are limited by the times, and the career development suggestions given are limited. In addition, the existing career assessment models lack iterative optimization based on large-scale data, and cannot continuously improve the timeliness and accuracy of the returned data. Summary of the invention

[0004] Based on this, the embodiment of the present application provides a career assessment method and system based on an AI big model. This method can comprehensively utilize search engine data, resume data and personality assessment results to provide more accurate and real-time career assessment services.

[0005] In the first aspect, a career assessment method based on an AI big model is provided, the method comprising:

[0006] Capturing online recruitment data with preset conditions through a search engine, and obtaining a resume data set in a resume database, and training an underlying model based on the online recruitment data and the resume data set to obtain a trained career assessment model;

[0007] Evaluate the target users based on the traditional personality assessment model to determine their basic personality types;

[0008] The personal resume data of the target user and the basic personality type are input into the career assessment model to obtain the career assessment result of the target user.

[0009] Optionally, the method further comprises:

[0010] After the target user completes the career assessment, the target user's assessment data is collected as incremental training data; wherein the assessment data includes the target user's career assessment result and user feedback data.

[0011] Use incremental training data to incrementally learn the career assessment model;

[0012] After incremental training, the model is evaluated to check whether the performance of the model has improved and whether further optimization is needed;

[0013] When the model performance is improved, the updated model is used as the new career assessment model for subsequent user evaluations; if the performance has not improved or needs further optimization, the model is adjusted and the incremental training and evaluation process is repeated.

[0014] Optionally, in crawling online recruitment data with preset conditions through a search engine, the preset conditions at least include:

[0015] The demand for popular positions in the current time period, positions guided by regional policies, positions that have been eliminated due to overcapacity, high-frequency search keywords on the Internet, keywords related to positions and word frequency information.

[0016] Optionally, obtaining resume datasets uploaded by different users, and training an underlying model based on the online recruitment data and the resume datasets, including:

[0017] Use OCR technology to perform text recognition on resume images and convert the text in the images into electronic text;

[0018] Using information extraction technology to identify entity information from the text; wherein, the information extraction technology includes named entity recognition, and the entity information includes at least name, date of birth, and telephone number;

[0019] By analyzing the layout and context information of the resume document, the identified text information is divided into corresponding information blocks according to the structure of the resume;

[0020] The information in the block is further extracted into structured data in the form of key-value pairs, realizing the conversion from unstructured resume documents to structured information.

[0021] Optionally, the underlying model is trained based on the online recruitment data and the resume data set to obtain a trained career assessment model, further comprising:

[0022] Handle missing values, outliers and duplicate data in the data, and standardize and normalize the data;

[0023] For the text data in the resume, we use technologies including text cleaning, standardization, bag-of-words model, TF-IDF and word embedding to convert the text into numerical vectors;

[0024] The data is divided into training set, validation set and test set to evaluate the performance of the model on different data.

[0025] Optionally, the target user is evaluated based on a traditional personality evaluation model to determine the basic personality type of the target user, specifically including:

[0026] Design a questionnaire based on a classic personality assessment model; wherein the questionnaire covers questions in multiple dimensions to assess the user's personality characteristics in terms of energy acquisition, information processing, and decision-making. The classic personality assessment model includes at least MBTI, Holland personality assessment, Enneagram personality assessment, Carter personality assessment, and DiS assessment;

[0027] The score of each dimension is calculated based on the user's answers, and the user's basic personality type is determined by comparing the scores.

[0028] In the second aspect, a career assessment system based on an AI big model is provided, which includes:

[0029] A model training module is used to crawl online recruitment data with preset conditions through a search engine, and obtain a resume data set in a resume database, and train the underlying model based on the online recruitment data and the resume data set to obtain a trained career assessment model;

[0030] The personality determination module is used to evaluate the target user based on the traditional personality evaluation model and determine the basic personality type of the target user;

[0031] The assessment optimization module is used to input the personal resume data of the target user and the basic personality type into the career assessment model to obtain the career assessment result of the target user.

[0032] In a third aspect, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the career assessment method described in any one of the first aspects is implemented.

[0033] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the career assessment method described in any one of the first aspects is implemented.

[0034] In a fifth aspect, a computer program product is provided, comprising a computer program / instruction, which, when executed by a processor, implements any of the career assessment methods described in the first aspect.

[0035] The beneficial effects brought by the technical solution provided by the embodiment of the present application include at least:

[0036] More accurate: Traditional career assessments are based on static databases, but talents will undergo dynamic changes during their growth process. Changes in the variables of each factor (growth experience, learning experience) will affect the accuracy of career assessments. The new assessment model can dynamically learn and capture changes, making it more accurate.

[0037] High timeliness: The conclusions of traditional career assessments are limited by the times, and the career development suggestions given are limited. As the industry changes, new careers emerge, old careers disappear, and the supply relationship in the career market continues to change. The current model, combined with search engine technology, can capture the latest career market dynamics and give more timely and practical suggestions.

[0038] Strong model iteration: In addition to drawing on traditional career assessment theories, the model is trained and iterated based on millions of resume data, analyzing the real correlation between different career development paths, and then continuously iterating and optimizing the underlying model to continuously improve the timeliness and accuracy of returned data. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0040] Figure 1 A flowchart of a career assessment method based on an AI big model provided in an embodiment of the present application;

[0041] Figure 2 This is a personality assessment diagram in the embodiment of this application;

[0042] Figure 3 This is a schematic diagram of the personality assessment results in the embodiment of this application;

[0043] Figure 4 A block diagram of a career assessment system based on an AI big model provided in an embodiment of the present application;

[0044] Figure 5 A schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application 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 application and are not used to limit the present application.

[0046] In the description of the present invention, the terms "comprises", "has" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may also include other steps or units that are not explicitly listed but are inherent to these processes, methods, products or apparatuses, or steps or units added based on further optimization schemes conceived by the present invention.

[0047] The purpose of this application is to optimize the basis of traditional personality assessment by training AI models on resume data and combining it with search engine technology. Users can form a personalized career planning system and talent development report by answering certain questions and combining their own structured and parsed resume data.

[0048] Please refer to Figure 1 , which shows a flow chart of a career assessment method based on an AI big model provided in an embodiment of the present application, which may include the following steps:

[0049] S1, crawling the online recruitment data with preset conditions through the search engine, and obtaining the resume data set in the resume database, training the underlying model based on the online recruitment data and the resume data set to obtain the trained career assessment model.

[0050] In this step, first, search engines are used to crawl online recruitment data to capture current recruitment hot trends and job talent portrait tags, and structured resume data uploaded by users. Among them, the preset conditions at least include the demand for popular positions in the current time period, positions guided by regional policies, positions eliminated due to overcapacity, keywords with high frequency searches on the Internet, keywords associated with positions and word frequency information. Among them, online recruitment data and resume datasets are used as the input of the model, and manually annotated career assessment results are used as the output of the model.

[0051] The resume database is a data set consisting of a large number of resumes obtained in advance through websites or other channels. There is no restriction on the resume format, PDF, picture, word are all acceptable, and it is imported and parsed through mature OCR technology. All resume data exists in the form of structured and decomposed vector databases. Educational data includes school, major, education, graduation time, etc. Work experience includes industry, position, skill labels, years of work, etc. Data is stored in categories and is closely related. If personal data is updated, it will affect personal modeling results. If the macro employment environment changes, it will also affect the model foundation.

[0052] First, use OCR technology to perform text recognition on the resume image and convert the text in the image into electronic text. Next, use information extraction technology, such as named entity recognition (NER), to identify entities with specific meanings from the text, such as name, date of birth, phone number, etc. Then, by analyzing the layout and context information of the resume document, the recognized text information is divided into corresponding information blocks according to the structure of the resume, such as educational background, work experience, etc. Finally, the information in these blocks is further extracted into structured data in the form of key-value pairs to facilitate subsequent processing and analysis. The conversion from unstructured resume documents to structured information is achieved.

[0053] In an optional embodiment of the present application, data preprocessing is also included:

[0054] Specifically, it includes processing missing values, outliers and duplicate data in the data, and standardizing and normalizing the data;

[0055] For the text data in the resume, we use technologies including text cleaning, standardization, bag-of-words model, TF-IDF and word embedding to convert the text into numerical vectors;

[0056] The data is divided into training set, validation set and test set to evaluate the performance of the model on different data.

[0057] S2, evaluate the target users based on the traditional personality evaluation model to determine the basic personality type of the target users.

[0058] The target user is the user who needs to undergo career assessment. This step obtains the user career development model under multiple factors. The specific implementation details are as follows:

[0059] First, design a set of questionnaires based on classic personality assessment models (such as MBTI, Holland personality assessment, Enneagram personality assessment, Karlter personality assessment, DiS assessment), covering multiple dimensions of questions to assess the user's personality characteristics in terms of energy acquisition, information processing, decision-making, etc. For example, the MBTI model divides individuals into 16 personality types through four dimensions (extroversion / introversion, sensing / intuition, thinking / feeling, and judgment / perception). When users answer these questions, the system will record the score of each dimension.

[0060] Next, the scores of each dimension are calculated based on the user's answers, and the user's basic personality type is determined by comparing the scores. For example, if the score for extroversion is higher than that for introversion, the user is classified as an extrovert.

[0061] S3, inputting the personal resume data and basic personality type of the target user into the career assessment model to obtain the career assessment result of the target user.

[0062] In the embodiment of the present application, the career assessment result of the target user is obtained by combining the recruitment hot trend and the talent portrait tag, and the above method also includes:

[0063] After the target user completes the career assessment, the target user's assessment data is collected as incremental training data; wherein the assessment data includes the target user's career assessment result and user feedback data, and the career assessment model is incrementally learned using the incremental training data;

[0064] After incremental training, the model is evaluated to check whether the performance of the model has improved and whether further optimization is needed;

[0065] When the model performance is improved, the updated model is used as the new career assessment model for subsequent user evaluations; if the performance has not improved or needs further optimization, the model is adjusted and the incremental training and evaluation process is repeated.

[0066] like Figure 2 and Figure 3 A personality assessment diagram and a personality assessment result diagram are provided respectively. In this embodiment, user input is not limited to answering the personality assessment questionnaire. The user needs to provide the content of his resume, including detailed information such as education background, work experience, skill certificates, etc., so as to fully understand his professional experience and ability level. In addition, the user needs to clarify the industry and position he is currently interested in, which helps the system match popular occupations more accurately and provide more targeted suggestions for the user's career planning.

[0067] The method also provides a matching analysis of current popular occupations to help users understand the degree of fit between their personality and abilities and popular occupations. At the same time, based on the preferred industry and job information provided by the user, it generates personalized career planning suggestions, including career development paths, required skill enhancements, career advancement opportunities, etc., to provide users with a clear direction and practical guidance for their career development.

[0068] Through this comprehensive input and output, the present invention can provide users with more accurate, comprehensive and personalized services, help users better understand themselves and plan their career development, and also provide strong support for enterprises' talent selection and training.

[0069] Please refer to Figure 4 , which shows a block diagram of a career assessment system based on an AI big model provided by an embodiment of the present application. Figure 4 As shown, the system may include:

[0070] A model training module is used to crawl online recruitment data with preset conditions through a search engine, and obtain a resume data set in a resume database, and train the underlying model based on the online recruitment data and the resume data set to obtain a trained career assessment model;

[0071] The personality determination module is used to evaluate the target user based on the traditional personality evaluation model and determine the basic personality type of the target user;

[0072] The assessment optimization module is used to input the personal resume data of the target user and the basic personality type into the career assessment model to obtain the career assessment result of the target user.

[0073] For the specific limitations of the career assessment system based on the AI ​​big model, please refer to the limitations of the career assessment method based on the AI ​​big model above, which will not be repeated here. Each module in the above-mentioned career assessment system based on the AI ​​big model can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0074] In one embodiment, an electronic device is provided. The electronic device may be a computer, and its internal structure diagram may be as follows: Figure 5 As shown. The electronic device includes a processor, a memory and a network interface connected via a system bus. Among them, the processor of the device is used to provide computing and control capabilities. The memory of the device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used for career assessment data based on the AI ​​big model. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a career assessment method based on the AI ​​big model is implemented.

[0075] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0076] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which involves all or part of the processes in the above-mentioned embodiment method.

[0077] In one embodiment, a computer program product is also provided, including a computer program / instruction, which involves all or part of the process in the above embodiment method.

[0078] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer 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 may 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. By way of illustration and not limitation, RAM is available in M ​​forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SyMchliMk) DRAM (SLDRAM), memory bus (RaMbus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0079] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0080] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent application shall be subject to the attached claims.

Claims

1. A career assessment method based on AI big model, characterized in that: The method comprises: Capturing online recruitment data with preset conditions through a search engine, and obtaining a resume data set in a resume database, and training an underlying model based on the online recruitment data and the resume data set to obtain a trained career assessment model; wherein the online recruitment data and the resume data set serve as inputs to the model, and the manually annotated career assessment results serve as outputs of the model; Evaluate the target users based on the traditional personality assessment model to determine their basic personality types; The personal resume data of the target user and the basic personality type are input into the career assessment model to obtain the career assessment result of the target user.

2. The career assessment method according to claim 1, characterized in that: The method further comprises: After the target user completes the career assessment, the target user's assessment data is collected as incremental training data; wherein the assessment data includes the target user's career assessment results and user feedback data Use incremental training data to incrementally learn the career assessment model; After incremental training, the model is evaluated to check whether the performance of the model has improved and whether further optimization is needed; When the model performance is improved, the updated model is used as the new career assessment model for subsequent user evaluations; if the performance has not improved or needs further optimization, the model is adjusted and the incremental training and evaluation process is repeated.

3. The career assessment method according to claim 1, characterized in that: In the online recruitment data with preset conditions crawled by search engines, the preset conditions at least include: The demand for popular positions in the current time period, positions guided by regional policies, positions that have been eliminated due to overcapacity, high-frequency search keywords on the Internet, keywords related to positions and word frequency information.

4. The career assessment method according to claim 1, characterized in that: Obtaining resume data sets uploaded by different users, and training the underlying model based on the online recruitment data and the resume data sets, including: Use OCR technology to perform text recognition on resume images and convert the text in the images into electronic text; Using information extraction technology to identify entity information from the text; wherein, the information extraction technology includes named entity recognition, and the entity information includes at least name, date of birth, and telephone number; By analyzing the layout and context information of the resume document, the identified text information is divided into corresponding information blocks according to the structure of the resume; The information in the block is further extracted into structured data in the form of key-value pairs, realizing the conversion from unstructured resume documents to structured information.

5. The career assessment method according to claim 1, characterized in that: The underlying model is trained based on the online recruitment data and the resume data set to obtain a trained career assessment model, further comprising: Handle missing values, outliers and duplicate data in the data, and standardize and normalize the data; For the text data in the resume, we use technologies including text cleaning, standardization, bag-of-words model, TF-IDF and word embedding to convert the text into numerical vectors; The data is divided into training set, validation set and test set to evaluate the performance of the model on different data.

6. The career assessment method according to claim 1, characterized in that: Evaluate the target users based on the traditional personality assessment model to determine the basic personality type of the target users, including: Design a questionnaire based on a classic personality assessment model; wherein the questionnaire covers questions in multiple dimensions to assess the user's personality characteristics in terms of energy acquisition, information processing, and decision-making. The classic personality assessment model includes at least MBTI, Holland personality assessment, Enneagram personality assessment, Carter personality assessment, and DiS assessment; The score of each dimension is calculated based on the user's answers, and the user's basic personality type is determined by comparing the scores.

7. A career assessment system based on AI big model, characterized in that: The system comprises: A model training module is used to crawl online recruitment data with preset conditions through a search engine, and obtain a resume data set in a resume database, and train the underlying model based on the online recruitment data and the resume data set to obtain a trained career assessment model; wherein the online recruitment data and the resume data set serve as the input of the model, and the manually annotated career assessment results serve as the output of the model; The personality determination module is used to evaluate the target user based on the traditional personality evaluation model and determine the basic personality type of the target user; The assessment optimization module is used to input the personal resume data of the target user and the basic personality type into the career assessment model to obtain the career assessment result of the target user.

8. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images