Post recommendation and learning path generation method based on skill level entity extraction

Abstract

The invention provides a post recommendation and learning path generation method based on skill level entity extraction, and relates to the technical field of person and post matching, and the method comprises the steps: obtaining job seeker data and post data; extracting skills and skill levels of job seekers and posts from the data by using a large language model (LLM), and confirming the extracted skill data through an ESCO classification method; on the basis of the extracted skill data, according to the defined similarity constraint and calculation formula of the job seekers and the posts, similarity calculation is carried out on the job seekers and the posts, and post recommendation is carried out on the basis of the similarity; and analyzing the extracted skill data of the job seekers and the posts to form a visual learning path diagram. By the adoption of the scheme, accurate matching and recommendation of the job seeker and the post are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of person-job matching, and in particular to a method, system and device for job recommendation and learning path generation based on skill level entity extraction. Background Art

[0002] There is a phenomenon of difficulty in finding employment in the current job market. Behind the severe employment situation is the problem of the disconnection between the talent training model and the industry demand. The research on student employment recommendation is helpful for the connection between school and enterprise and the delivery of talents, which can alleviate the employment "dilemma" to a certain extent. The dynamic and rapid development of the contemporary job market requires learners to continuously improve their personal skills in a targeted manner to maintain industry relevance and their own competitiveness. This trend guides learners to choose educational resources with skill orientation to improve their professional knowledge and achieve their career goals in line with the needs of the job market.

[0003] In current research related to student employment recommendations, since students do not have interactive information with positions, there is a cold start problem. Most studies use data such as student interests and on-campus behaviors, combined with collaborative filtering and other methods to make recommendations. These studies do not consider the match between student skill levels and job recruitment requirements. In fact, companies are more concerned about whether students' skill levels meet job requirements. Or by conducting cognitive diagnosis of learners based on answering questions combined with knowledge tracking models, or completing the assessment of learners' prior skill levels through questionnaires, there are also problems of subjective evaluation and lack of objectivity. Summary of the invention

[0004] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0005] To this end, the first purpose of this application is to propose a job recommendation and learning path generation method based on skill level entity extraction, which achieves accurate job matching and recommendation.

[0006] The second objective of this application is to propose a job recommendation and learning path generation system based on skill level entity extraction.

[0007] The third objective of the present application is to provide a computer device.

[0008] A fourth object of the present application is to provide a non-transitory computer-readable storage medium.

[0009] A fifth object of the present application is to provide a computer program product.

[0010] To achieve the above objectives, the first embodiment of the present application proposes a method for job recommendation and learning path generation based on skill level entity extraction, including:

[0011] Obtain job seeker data and job position data;

[0012] Use the large language model LLM to extract the skills and skill levels of job seekers and positions from the data, and confirm the extracted skill data through the ESCO classification method;

[0013] Based on the extracted skill data, calculate the similarity between each job seeker and each position according to the defined similarity constraints and calculation formula for job seekers and positions, and make position recommendations based on the similarity;

[0014] Analyze the extracted skill data of job seekers and positions to form a visual learning path map.

[0015] Optionally, in an embodiment of the present application, the extracted skill levels include beginner, intermediate, expert, and unknown. Before calculating the similarity, preprocess the extracted skill data, including:

[0016] Set the skill level of unknown for job seekers to beginner, and set the skill level of unknown for positions to advanced.

[0017] Optionally, in an embodiment of the present application, define the similarity constraints for job seekers and positions, including:

[0018] Set that the number of skills matching between job seekers and positions is positively correlated with the similarity;

[0019] Set that the level of skills matching between job seekers and positions is positively correlated with the similarity;

[0020] If job seekers and positions match all skills and skill levels, the similarity between job seekers and positions is the highest;

[0021] Define the similarity calculation formula for job seekers and positions as:

[0022]

[0023] Where sim(u,j) is the similarity between job seeker u and position j, J is the skill set of position j, |J| is the size of the skill set of position j, sl su is the proficiency of job seeker in skill s, sl sj is the proficiency of position in skill s, sim(sl su ,sl sj ) represents the proficiency similarity between sl su and sl sj , and the calculation method is:

[0024]

[0025] Where l i 、l tFor two objects calculating proficiency similarity, min(l i ,l j ) represents the smaller value of the two proficiencies.

[0026] Optionally, in an embodiment of the present application, calculating the similarity between a job seeker and a position includes:

[0027] Matching the skills of the job seeker and the position, and calculating through a similarity calculation formula. When calculating, for skills not matched in the job seeker or the position, set their proficiency in this skill to 0. For skills matched in the job seeker or the position, determine their proficiency in this skill based on the skill level, and obtain the similarity between the job seeker and the position.

[0028] Optionally, in an embodiment of the present application, forming a visual learning path map includes:

[0029] Preprocessing the extracted skill data of the job seeker and the position to align the skill points of the two;

[0030] Setting prompt words, and using LLM and Mermaid to generate a visual personalized learning path map.

[0031] Optionally, in an embodiment of the present application, the method further includes:

[0032] Establishing an index for each skill and linking the positions that have this skill;

[0033] Caching the data that has completed matching in units of users.

[0034] To achieve the above object, an embodiment of the second aspect of the present invention proposes a job recommendation and learning path generation system based on skill level entity extraction, including:

[0035] A data acquisition module for acquiring job seeker data and position data;

[0036] A skill extraction module for using the large language model LLM to extract the skills and skill levels of job seekers and positions from the data, and confirming the extracted skill data through the ESCO classification method;

[0037] A job recommendation module for calculating the similarity between a job seeker and each position based on the extracted skill data according to the defined similarity constraints and calculation formula of job seekers and positions, and recommending positions based on the similarity;

[0038] A skill learning path generation module for analyzing the extracted skill data of job seekers and positions to form a visual learning path map.

[0039] To achieve the above object, an embodiment of the third aspect of the present invention provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the above-mentioned method for generating job recommendations and learning paths based on skill level entity extraction is implemented.

[0040] To achieve the above object, an embodiment of the fourth aspect of the present invention provides a non-transitory computer-readable storage medium. When the instructions in the storage medium are executed by a processor, the method for generating job recommendations and learning paths based on skill level entity extraction can be executed.

[0041] To achieve the above object, an embodiment of the fifth aspect of the present invention provides a computer program product. When the instructions in the computer program product are executed by a processor, the above-mentioned method for generating job recommendations and learning paths based on skill level entity extraction is executed.

[0042] The method, system, and device for generating job recommendations and learning paths based on skill level entity extraction according to the embodiments of the present application extract skills and levels from employment recruitment information and learner resume information based on LLM, and match them with the ESCO classification method to ensure that the correct skill entities that conform to the current employment reality are extracted; and based on the idea of calculating the similarity between the skills and their mastery levels of the job and the user, the calculation formula of the similarity is designed according to the constraint definition of assigning higher scores to people with more work skills, higher proficiency, and more complete matching in sequence; and based on the skill data of the two that have been extracted above, the jobs with scores in the top 5 are recommended by calculating the similarity; an inverted index and a cache mechanism are added to save computing resources and improve computing efficiency.

[0043] The additional aspects and advantages of the present application will be partially given in the following description, partially become obvious from the following description, or be understood through the practice of the present application. Description of the Drawings

[0044] The above and / or additional aspects and advantages of the present application will become obvious and easy to understand from the following description of the embodiments in conjunction with the drawings, where:

[0045] Figure 1 It is a schematic flowchart of a method for generating job recommendations and learning paths based on skill level entity extraction provided by Embodiment 1 of the present application;

[0046] Figure 2 It is a flowchart of skill and proficiency level entity extraction according to an embodiment of the present application;

[0047] Figure 3 It is a schematic structural diagram of a system for generating job recommendations and learning paths based on skill level entity extraction provided by an embodiment of the present application. Specific Embodiment

[0048] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present application and should not be construed as limiting the present application.

[0049] The method, system, and device for job recommendation and learning path generation based on skill level entity extraction according to the embodiments of the present application will be described below with reference to the accompanying drawings.

[0050] Figure 1 It is a flowchart of a method for job recommendation and learning path generation based on skill level entity extraction provided in the first embodiment of the present application.

[0051] As Figure 1 shown, the method for job recommendation and learning path generation based on skill level entity extraction includes the following steps:

[0052] Step 101, obtain job seeker data and job data;

[0053] In this embodiment, after obtaining the data, preprocess the learner resume data (work experience / professional skill description) and employment position recruitment data. Perform OCR on the original data in pdf format to obtain text format data, perform data text segmentation on the description text, decompose each document into separate sentences, and combine them into one or two groups.

[0054] Step 102, use the large language model LLM to extract the skills and skill levels of job seekers and jobs from the data, and confirm the extracted skill data through the ESCO classification method;

[0055] Figure 2 As shown in the flowchart of skill and proficiency level entity extraction, as Figure 2 shown, extract skills and levels from employment position recruitment information and learner resume information based on the LLM, and match them with the ESCO classification method to ensure that the correct skill entities that conform to the current employment reality are extracted.

[0056] In this embodiment, for each description text, first, each document is decomposed into individual sentences and combined into one or two groups in sequence for the LLM to process, providing some context for the LLM and solving the limitations related to the document length. The LLM is instructed to repeat the given recruitment information excerpt and mark the skills with $$ and ## around the skills to make a response. For the mastery level, the LLM is instructed to infer its skill mastery level and classify it into one of the categories "beginner", "intermediate", "expert", and "unkown". To ensure effective extraction, this embodiment sets 6 types of samples as examples for model learning, including positive and negative examples: sentences with skills and sentences without skills; multiple answers and single answers: a sentence may contain multiple skills or only one skill; hard skills and soft skills: hard skills usually refer to specific and quantifiable skills, such as programming ability, and soft skills refer to more abstract skills, such as teamwork ability. Finally, the content of the LLM's answer is extracted as the skill entity and its level respectively and converted into json for output. The Prompt and learning examples are shown in Table 1.

[0057] Table 1 Examples of prompts and learning styles for implementing skill and level entity extraction based on LLM

[0058]

[0059]

[0060] b. Prompts and answer examples in the matching session

[0061]

[0062] In this embodiment, candidate skills are selected from the ESCO taxonomy according to the name and definition using a rule-based method. This method can find exact or approximate matches of the extracted skills in the ESCO taxonomy through string matching. If the string of the extracted skill appears in the name or definition of the skill in the taxonomy, it is considered a good match candidate. When no exact match is found, the token_set_ratio method in the The Fuzz fuzzy matching in the python library is used to select the top four skill terms in terms of similarity.

[0063] In this embodiment, the extracted skills are matched with the selected candidate skills. Similarly, the LLM is used to select the best match from the candidate skills. The extracted skills are provided to the LLM, and the formatted ESCO candidate skills are provided as options. Similar to a sorting task, the large model is required to give the most appropriate match. The LLM outputs the most appropriate option as the matched skill. If no matched skill is found, none is provided.

[0064] In this embodiment, the extracted skill entity data is optimized. On the one hand, the extraction of skills and their proficiency levels in the recruitment information of job positions demanded by the employment market has been completed. For example, the skill requirements for a data analysis engineer position can be expressed as j: {["python", "beginner"], ["SQL", "Intermediate"]}, and on the other hand, the extraction of skills and their proficiency levels in the learner resume information. For example, the skills of a junior data science major student can be expressed as u: {["python", "Intermediate"], ["machine - learning", "beginner"]}. In the job matching task, in the part of data pre - processing, starting from a conservative approach and to be closer to the actual situation and improve the model effect, the following optimizations are made to the processed data: For the data with the recognized skill proficiency of "unkown" in the learner resume, it is default set to "beginner", and for the data with the recognized skill proficiency of "unkown" in the job recruitment information, it is default set to "expert" (expert level).

[0065] Step 103: Based on the extracted skill data, according to the defined similarity constraints and calculation formulas for job seekers and positions, calculate the similarity between each job seeker and each position, and make job recommendations based on the similarity.

[0066] In this embodiment, the learner - position similarity constraints and similarity calculation formulas are defined. Based on the idea of calculating the similarity between the skills and their mastery levels of the position and the user, the similarity calculation formula is designed by defining constraints that assign higher scores to those with more work skills, higher proficiency, and more complete matches in turn. It is defined that whether the skills of user u meet the skill requirements of the job recruitment information is calculated through a learner - position similarity function (as shown in Formulas 1 and 2 below). The following constraint definitions are for describing learner - position similarity:

[0067] ① Assign higher scores to users who match more work skills;

[0068] ② Assign higher or equal scores to users with a higher proficiency level in the skills required for the job;

[0069] ③ Assign the highest scores to users who meet all the skills required for the job and reach the required proficiency level.

[0070] Formula 1:

[0071]

[0072] Formula 2:

[0073]

[0074] Formula 1 traverses all skills s required for job j (corresponding to Constraint ①, the more skills matched, the greater the contribution), and calculates the proficiency sl of the user in skill s su and the proficiency sl required for the job in skill s sj between them, and sums up these similarities with weights. The weight is the reciprocal of the size of the skill set of job j, ensuring that the contribution of each skill to the overall similarity is balanced. If a relevant skill is not involved in the user or the job, the corresponding sl su or sl sj is recorded as 0. Formula 2 calculates the similarity between two proficiencies sl su or sl sj between them, min(l i , l j ) represents the smaller value of the two proficiencies, and the denominator is the proficiency required for the job. This ratio measures the proportion of the user's proficiency in a certain skill relative to the proficiency required for the job (corresponding to Constraint ②, if the user's proficiency in this skill fully meets or exceeds the job requirements, the score is higher) (in this embodiment, l i , l j are the proficiency of a certain skill of the user and the proficiency of a certain required skill of the job respectively). If the user's proficiency is equal to or higher than the job requirements, this ratio will be close to or equal to 1; if the user's proficiency is lower than the job requirements, this ratio will be less than 1. If all skills are matched, for each skill, the similarity will be the highest value 1, and the highest score will be obtained (corresponding to Constraint ③).

[0075] In this embodiment, based on the skill data of the two that have been extracted above, the similarity between each user and each position is calculated, and the positions with scores in the top 5 are recommended.

[0076] In this embodiment, it also includes:

[0077] For the large-scale job information and user data in the actual situation, each time |j|×|u| similarity calculations are performed, and an inverted index mechanism and a caching mechanism are added to improve the calculation performance. Inverted index mechanism: An index is established for each skill, followed by the positions and corresponding proficiencies that have this skill. When matching users and positions, directly query the list of positions corresponding to the user's skills without having to traverse all positions; Caching mechanism: Use OrderedDict to implement a cache dictionary with LRU (Least Recently Used) characteristics to store the similarity calculation results of users and positions, which can reduce repeated calculations when learners update their resumes in an online employment system or an online learning system.

[0078] Step 104: Analyze the extracted skill data of job seekers and positions to form a visualized learning path map.

[0079] In this embodiment, an LLM + Mermaid grammar is used to generate a visualized personalized skill learning path map. Specifically:

[0080] Preprocess the json data formed based on the extraction of entities of skills and proficiency levels from the user's resume and the recruitment information of the target position to align the skill points of the two. The preprocessing process includes: deleting skills where the user's proficiency level is higher than the required proficiency level of the position; deleting skills that the user has mastered but the position does not require.

[0081] Set predefined prompt words. The backend system calls the language model (LLM) to generate Mermaid grammar code based on the preprocessed data. The frontend system calls the Mermaid API to render the generated Mermaid code into a visualized personalized skill learning path map. Table 2 shows an example of the predefined prompt words.

[0082] Table 2 Generative path map prompt words

[0083]

[0084]

[0085] The method for job recommendation and learning path generation based on skill level entity extraction in the embodiments of the present application extracts skills and levels from employment position recruitment information and learner resume information based on the LLM, matches them with the ESCO classification method to ensure the correct extraction of skill entities that conform to the current employment reality; and designs a similarity calculation formula based on the idea of calculating the similarity between the skills and their mastery levels of the position and the user, and sequentially assigns higher scores to those with more job skills, higher proficiency, and more complete matching; and based on the skill data of the two that have been extracted above, recommends the positions with scores in the top 5 by calculating the similarity; adds an inverted index and a caching mechanism to save computing resources and improve computing efficiency.

[0086] To implement the above embodiments, the present application also proposes a job recommendation and learning path generation system based on skill level entity extraction.

[0087] Figure 3 It is a schematic structural diagram of a job recommendation and learning path generation system based on skill level entity extraction provided by the embodiments of the present application.

[0088] As Figure 3 shown, the job recommendation and learning path generation system based on skill level entity extraction includes:

[0089] A data acquisition module for acquiring job seeker data and job data;

[0090] A skill extraction module for using a large language model (LLM) to extract the skills and skill levels of job seekers and jobs from the data, and confirming the extracted skill data through the ESCO classification method;

[0091] A job recommendation module for calculating the similarity between job seekers and each job based on the extracted skill data according to the defined similarity constraints and calculation formulas for job seekers and jobs, and making job recommendations based on the similarity;

[0092] A skill learning path generation module for analyzing the extracted skill data of job seekers and jobs to form a visual learning path map.

[0093] It should be noted that the foregoing explanations of the embodiments of the job recommendation and learning path generation method based on skill level entity extraction also apply to the job recommendation and learning path generation system based on skill level entity extraction of this embodiment, and will not be elaborated here.

[0094] To implement the above embodiments, the present invention also provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the method described in the above embodiments is implemented.

[0095] To implement the above embodiments, the present invention also provides a non - transitory computer - readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in the above embodiments is implemented.

[0096] To implement the above embodiments, the present invention also provides a computer program product. When the instruction processor in the computer program product executes, the method described in the above embodiments is implemented.

[0097] In the description of this specification, the descriptions with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0098] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the technical features indicated. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "a plurality of" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0099] Any process or method description represented in a flowchart or otherwise described herein can be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a customized logical function or process. The scope of the preferred embodiments of the present application includes additional implementations, where functions may be executed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed, which should be understood by those skilled in the technical field to which the embodiments of the present application pertain.

[0100] Logic and / or steps represented in a flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing a logical function, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in conjunction with such instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection portion having one or more wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, a computer-readable medium can even be paper or other suitable media on which the program can be printed, as the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then stored in a computer memory.

[0101] It should be understood that each part of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits with logic gate circuits for implementing logical functions on data signals, application specific integrated circuits with appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.

[0102] Those of ordinary skill in the art can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing relevant hardware through a program. The said program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0103] In addition, in each of the embodiments of the present application, each functional unit can be integrated in a processing module, or each unit can exist physically alone, or two or more units can be integrated in a module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. When the above integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0104] The above-mentioned storage medium can be a read-only memory, a magnetic disk, an optical disc, or the like. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for job recommendation and learning path generation based on skill level entity extraction, characterized in that: include: Obtain job seeker data and job position data; Use the Large Language Model (LLM) to extract the skills and skill levels of job seekers and positions from the data, and confirm the extracted skill data using the ESCO classification method; Based on the extracted skill data, the similarity between the job seeker and each position is calculated according to the defined similarity constraints and calculation formula, and the position recommendation is made based on the similarity; Analyze the skill data of the extracted job seekers and positions to form a visual learning path map.

2. The method according to claim 1, characterized in that The extracted skill levels include entry-level, intermediate, expert, and unknown. Before similarity calculation, the extracted skill data is preprocessed, including: Set job seekers with unknown skill levels to entry-level, and set positions with unknown skill levels to senior.

3. The method according to claim 1, characterized in that Define similarity constraints between job seekers and positions, including: The number of skills that set a job seeker and a job match is positively correlated with similarity; The level of skills that set the match between job seekers and jobs is positively correlated with similarity; If the job seeker and the job position match all skills and skill levels, the similarity between the job seeker and the job position is the highest; The similarity calculation formula between job seekers and positions is defined as: Among them, sim(u,j) is the similarity between job seeker u and position j, J is the skill set of position j, |J| is the size of the skill set of position j, and sl su is the job seeker's proficiency in skill s, sl sj is the proficiency of the position in skill s, sim(sl su ,sl sj ) means sl su and sl sj The similarity of proficiency is calculated as: Among them, l i , l j To calculate the proficiency similarity of two objects, min(l i ,l j ) represents the smaller of the two proficiency levels.

4. The method according to claim 3, characterized in that Calculate similarity between job seekers and positions, including: The skills of job seekers and positions are matched and calculated using a similarity calculation formula. During the calculation, for skills that are not matched in job seekers or positions, their proficiency in the skill is set to 0. For skills that are matched in job seekers or positions, their proficiency in the skill is determined based on the skill level to obtain the similarity between the job seekers and positions.

5. The method according to claim 1, characterized in that Form a visual learning path map, including: Pre-process the extracted skill data of job seekers and positions to align their skill points; Set prompt words and use LLM and Mermaid to generate a visual personalized learning path map.

6. The method according to claim 1, characterized in that The method further comprises: Create an index for each skill and link it to the positions that have that skill; Cache the data of completed matches on a user-by-user basis.

7. A job recommendation and learning path generation system based on skill level entity extraction, characterized in that: include: Data acquisition module, used to obtain job seeker data and job position data; The skill extraction module is used to extract the skills and skill levels of job seekers and positions from the data using the large language model (LLM), and confirm the extracted skill data using the ESCO classification method; The job recommendation module is used to calculate the similarity between job seekers and each job based on the extracted skill data, according to the defined similarity constraints and calculation formulas between job seekers and jobs, and recommend jobs based on the similarity; The skill learning path generation module is used to analyze the extracted skill data of job seekers and positions to form a visual learning path diagram.

8. A computer device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

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

10. A computer program product, when instructions in the computer program product are executed by a processor, implements the method according to any one of claims 1 to 6.

Images