Human resource matching system based on big data

Abstract

The embodiment of the invention provides a human resource matching system based on big data, and the system comprises a construction module which is used for carrying out the entity recognition of a target text block through a rule base, and obtaining an initial entity; performing entity recognition on the target text block by using a first machine learning model, and adjusting the recognition process of the first machine learning model by using the initial entity to obtain a target entity; constructing a graph database according to the target entity; the target text block comprises a text block obtained by partitioning the job application text and a text block obtained by partitioning the recruitment text. And the search module is used for generating search graph data according to the user input operation and the graph data corresponding to the user. And the matching module is used for calculating the similarity between the search graph data and the graph data in the graph database, and selecting matched graph data from the graph database according to the similarity. In this way, fusion of entity recognition based on rules and in combination with context information is achieved, and the accuracy of entity recognition of a machine learning model can be improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a human resource matching system based on big data. Background Art

[0002] In recent years, with the application of advanced technologies such as big data analysis and artificial intelligence, the field of human resource management has ushered in revolutionary changes. In particular, by building an intelligent matching system, algorithms are used to automatically analyze the matching degree between job seekers' abilities and experience and the requirements of vacant positions, thus achieving accurate and efficient talent recommendations.

[0003] However, in the prior art, a large amount of training data is needed to train the algorithm model in order to improve the accuracy of the data processing of the algorithm model. However, it is difficult to obtain a large amount of labeled training data, which leads to low accuracy of data processing by the existing algorithm model. Summary of the invention

[0004] The embodiment of the present application provides a human resources matching system based on big data to achieve the effect of improving the accuracy of the algorithm model.

[0005] Some embodiments of the present application provide a human resource matching system based on big data, characterized in that the human resource matching system includes a backend server and a front-end application end, and the backend server includes:

[0006] A construction module is used to perform entity recognition on a target text block using a rule library to obtain an initial entity; perform entity recognition on the target text block using a first machine learning model, and use the initial entity to adjust an intermediate recognition result during the recognition process of the first machine learning model to obtain a target entity; and construct a graph database according to the target entity; wherein the target text block includes a text block after job search text is segmented and a text block after recruitment text is segmented;

[0007] A search module, used to generate search graph data based on the focus words input by the user and the graph data corresponding to the user;

[0008] The matching module is used to calculate the similarity between the search graph data and the graph data to be selected in the graph database, and select the matching graph data from the graph database based on the similarity.

[0009] In the above technical solution, the human resources matching system includes a construction module, a search module and a matching module. The construction module obtains a graph database by processing the target text block, the search module is used to generate search graph data, and the matching module is used to select graph data that best matches the search graph data from the graph database. Since job application texts and recruitment texts usually use more specialized terms and have relatively simple sentence structures, the construction module can first perform initial recognition of the target text block using rules to obtain initial entities; then, the target text block is input into the first machine learning model for recognition, and the ability of the first machine learning model to recognize information in combination with contextual information is used to recognize the target text block, and the recognition process of the first machine learning model is adjusted using the initial entity to achieve a fusion of entity recognition based on rules and in combination with contextual information, which can improve the accuracy of entity recognition by the first machine learning model, especially in the case of insufficient training data, the accuracy of entity recognition by the first machine learning model can still be guaranteed.

[0010] In some possible implementations, the first machine learning model includes a model input layer, a model encoding layer, a first fusion layer, a modified input layer, a modified encoding layer, and a model decoding layer;

[0011] Building blocks are used to:

[0012] Use the model input layer to vectorize the target text block to obtain the main vector; use the multi-layer model encoding layer to encode the main vector multiple times and then output it;

[0013] The initial entity is vectorized using the correction input layer to obtain a correction vector; the correction vector is encoded using the correction encoding layer and then output;

[0014] Using the first fusion layer to fuse the data output by the multi-layer model encoding layer and the data output by the correction encoding layer;

[0015] The multi-layer model decoding layer is used to perform multiple decoding processes on the data output by the first fusion layer to obtain the target entity.

[0016] In the above technical scheme, the correction input layer is used to vectorize the initial entity, the correction encoding layer encodes the vectorized initial entity so as to merge it with the data of the target text block after vectorization and encoding, thereby correcting the encoded data, and the decoding layer decodes the corrected encoded data and outputs the target entity, thereby improving the accuracy of entity recognition by the first machine learning model.

[0017] In some possible implementations, the first machine learning model further includes at least one second fusion layer, and the building module is used to:

[0018] Use the i-th second fusion layer to perform weighted average processing on the output data of the corrected coding layer of the i+1-th layer and the output data of the model coding layer of the i+1-th layer;

[0019] The model encoding layer of the i-th last layer is used to encode the data output by the i-th second fusion layer and then output; wherein the weighting coefficient of the second fusion layer is adjustable.

[0020] In the above technical scheme, in order to further improve the initial entity's ability to correct the first machine learning model, the first machine learning model is also provided with multiple second fusion layers. The second fusion layer is used to fuse the data output by the model coding layer and the data output by the correction coding layer and output them to the next model coding layer. The weighting coefficient of the second fusion layer is adjustable. By adjusting the size of the weighting coefficient, the initial entity's ability to correct the first machine learning model can be adjusted, thereby further improving the accuracy of data processing.

[0021] In some possible implementations, the human resource matching system includes multiple graph databases, each graph database corresponding to an industry;

[0022] The search module is used to receive the attention word input by the user, obtain the graph database corresponding to the user, use the attention word to modify the weight of the graph data corresponding to the user, and generate search graph data;

[0023] The matching module is used to determine the search industry corresponding to the search graph data, and calculate the similarity of each node between the search graph data and the graph data to be selected in the graph database corresponding to the search industry to determine the similarity of the graph data.

[0024] In the above technical solution, the focus word is determined according to the focus word input by the user, and the focus word is used to correct the weight in the graph data corresponding to the user. In this way, when calculating the similarity between the search graph data and the graph data in the graph database, the similarity of the graph data matching the focus word is increased, ensuring that the graph data selected from the graph database has the highest match with the focus word, thereby improving the matching accuracy.

[0025] In some possible implementations, the backend server receives an initial screening instruction sent by the frontend application, the initial screening instruction includes an initial screening keyword, generates a recommended keyword according to the initial screening keyword, and sends the recommended keyword to the frontend application;

[0026] The backend server receives a progressive screening instruction sent by the frontend application, the progressive screening instruction includes a progressive keyword, and generates a focus word according to the initial screening keyword and the progressive keyword.

[0027] In the above technical solution, recommended keywords are generated based on the keywords input by the user for the first time, and the user is guided to input again to obtain more filtering information from the user. In this way, the graph data in the graph database can be matched based on more filtering information, so that the matched graph data can be more in line with the user's filtering needs, thereby improving the human resources matching system's ability to match needs.

[0028] In some possible implementations, the building blocks are specifically used to:

[0029] Use the second machine learning model to extract the current year's project plan from the enterprise development report, generate a talent recruitment plan based on the current year's project plan and the existing talent pool, and update the user's corresponding graph data based on the talent recruitment plan;

[0030] The search module generates search graph data according to the focus words input by the user and the updated graph data.

[0031] In the above technical solution, after obtaining the enterprise development report, the machine learning model is triggered to extract the current year's project plan from the enterprise development report, and then a talent recruitment plan is generated based on the current year's project plan and the existing talent pool. This can automatically update the user's corresponding graph data based on the talent recruitment plan, and then trigger the search module to update the search graph data, and obtain the graph data of job seekers that match the end-of-year project plan from the job search graph database, thereby improving data matching efficiency.

[0032] In some possible implementations, the existing talent pool includes at least one piece of existing talent information, and each piece of existing talent information includes mastered skills and project experience;

[0033] The search module is specifically used for:

[0034] Use the second machine learning model to extract talent demand information from the current year's project plan and generate a talent demand database. The talent demand information includes skill requirements and project requirements.

[0035] For each required talent information, match the required talent information with the existing talent information in the existing talent pool, determine the talent gap information based on the matching results; and use the talent gap information as a recruitment plan.

[0036] In the above technical solution, the second machine learning model is used to extract the required talent information from this year's project plan, and the required talent information is matched with the existing talent information, and a recruitment plan is generated based on the matching results. This ensures that the recruited talents can meet this year's project plan and improves the human resources matching system's ability to match demand.

[0037] This embodiment provides a human resources matching method based on big data, including:

[0038] Using a rule library to perform entity recognition on a target text block to obtain an initial entity; using a first machine learning model to perform entity recognition on the target text block, and using the initial entity to adjust an intermediate recognition result during the recognition process of the first machine learning model to obtain a target entity; constructing a graph database according to the target entity; wherein the target text block includes a text block after job search text is segmented and a text block after recruitment text is segmented;

[0039] Generate search graph data based on the focus word input by the user and the graph data corresponding to the user;

[0040] The similarity between the search graph data and the graph data to be selected in the graph database is calculated, and matching graph data is selected from the graph database according to the similarity.

[0041] The embodiment of the present application provides a backend server, including: a memory, a processor;

[0042] Memory stores computer-executable instructions;

[0043] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the implementation methods involved in the above embodiments.

[0044] An embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the implementation methods involved in the above embodiments.

[0045] An embodiment of the present application provides a computer program product, including a computer program, which implements the implementation methods involved in the above embodiments when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0047] Figure 1 A structural block diagram of a human resources matching system based on big data provided in some embodiments of the present application;

[0048] Figure 2 A schematic diagram of job search graph data provided for some embodiments of the present application;

[0049] Figure 3 A schematic diagram of recruitment graph data provided for some embodiments of the present application;

[0050] Figure 4 A schematic diagram of the architecture of a first machine learning model provided for some embodiments of the present application;

[0051] Figure 5 A schematic diagram of the architecture of a first machine learning model provided for some embodiments of the present application;

[0052] Figure 6 A schematic diagram of the architecture of a backend server provided for some embodiments of the present application.

[0053] Reference numerals:

[0054] 100, backend server; 110, construction module; 120, search module; 130, matching module; 200, front-end application terminal.

[0055] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0056] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0057] In recent years, with the application of advanced technologies such as big data analysis and artificial intelligence, the field of human resource management has ushered in revolutionary changes. In particular, by building an intelligent matching system, algorithms are used to automatically analyze the matching degree between job seekers' abilities and experience and the requirements of vacant positions, thus achieving accurate and efficient talent recommendations.

[0058] In the prior art, a large amount of training data is needed to train the algorithm model in order to improve the accuracy of the data processing of the algorithm model. However, it is difficult to obtain a large amount of labeled training data, which leads to low accuracy of data processing by the existing algorithm model.

[0059] This application provides a human resources matching system based on big data. Due to the large number of specialized terms and single sentence structures in job application texts and recruitment texts, some corpora are suitable for entity recognition using rule bases. In view of this, by integrating the entity recognition of machine learning models with the entity recognition of rule bases, entity recognition based on rules and combined with contextual information can be achieved. In the case of insufficient training data, the accuracy of entity recognition by machine learning models can be improved.

[0060] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0061] Figure 1 This is a structural block diagram of a human resources matching system based on big data provided by some embodiments of the present application. Figure 1 As shown, the human resource matching system includes a backend server 100 and a frontend application terminal 200 , and the backend server 100 includes a construction module 110 , a search module 120 and a matching module 130 .

[0062] The construction module 110 is used to perform entity recognition on the target text block using the rule library to obtain the initial entity. The target text block is recognized using the first machine learning model, and the initial entity is used to adjust the intermediate recognition result in the recognition process of the first machine learning model to obtain the target entity. A graph database is constructed according to the target entity. The target text block includes a text block after the job application text is segmented and a text block after the recruitment text is segmented.

[0063] The search module 120 is used to generate search graph data according to the focus words input by the user and the graph data corresponding to the user.

[0064] The matching module 130 is used to calculate the similarity between the search graph data and each candidate graph data in the graph database, and select the matching graph data from the graph database according to the similarity.

[0065] More specifically, the construction module 110 is used to collect resume information and pre-process the resume information to obtain a job application text. In some examples, the construction module 110 obtains the resume information submitted by the user, removes irrelevant information in the resume information, such as headers, footers, etc., and converts the resume information to obtain a job application text.

[0066] Subsequently, the construction module 110 divides the job application text into text blocks corresponding to personal basic information, text blocks corresponding to educational background, text blocks corresponding to work experience, text blocks corresponding to skill certificates, text blocks corresponding to job application information, and text blocks corresponding to project experience.

[0067] For each of the above text blocks, the rule library is used to identify the text block to obtain the initial entity. For example, the corpus in the text block is segmented, and the segmented corpus is matched with the words in the dictionary library to obtain the initial entity. The first machine learning model is used to perform entity recognition on the text block, and the initial entity is used to adjust the intermediate recognition result in the recognition process of the first machine learning model to obtain the target entity.

[0068] The job search entity includes personal basic information, job search information, education background, work experience, project experience, and skill certificates. Among them, personal basic information includes name, gender, age, and contact information. Job search information includes job title, work location, and salary range. Education background includes school name, major, education, and graduation time. Work experience includes company name, position, working hours, and work content. Project experience includes project name and project content. Skill certificates include skills mastered, certificates obtained, etc.

[0069] The construction module 110 generates job-seeking graph data based on the extracted job-seeking entities. Figure 2 A schematic diagram of job search graph data provided in some embodiments of the present application, such as Figure 2 As shown, the job search node includes personal information, job search information, education background, work experience, project experience, and skill certificates. Each job search node is connected to the job search graph data identifier by an edge. Each edge is set with a weight value, and the weight value of each edge can be a default value or can be modified according to requirements.

[0070] Name, gender, age and contact information are used as attributes of the personal basic information node. Job title, work location and salary range are used as attributes of the job search information node. School name, major, education and graduation time are used as attributes of the education background node. Company name, position, working hours and work content are used as attributes of the work experience node. Project name and project content are used as attributes of the project experience node. Skills acquired and certificates obtained are used as attributes of the skill certificate node.

[0071] The construction module 110 is specifically used to collect recruitment information and pre-process the recruitment information to obtain recruitment text. More specifically, the construction module 110 collects recruitment information from recruitment websites and corporate official websites. Removes redundant and irrelevant information in the recruitment information, such as advertisements, etc. Converts the recruitment information into a format to obtain recruitment text.

[0072] The construction module 110 uses the rule library to identify the job text and obtain the initial entity. For example, the corpus in the job text is segmented, and the segmented corpus is matched with the words in the dictionary library to obtain the initial entity. The first machine learning model is used to perform entity recognition on the job text, and the initial entity is used to adjust the intermediate recognition result during the recognition process of the first machine learning model to obtain the target entity.

[0073] Recruitment entities include job information, skill requirements, work experience requirements, project experience requirements, and education requirements. Job information includes job title, job category, work location, salary range, job content, job responsibilities, team introduction, company name, industry, size, geographic location, etc. Skill requirements include required skills and certificate requirements. Work experience requirements include the company and required years of work experience. Project experience requirements include required projects. Education requirements include undergraduate and postgraduate degrees.

[0074] The construction module 110 generates recruitment graph data based on the extracted recruitment entities. Figure 3 A schematic diagram of a recruitment graph data provided in some embodiments of the present application, such as Figure 3 As shown, the recruitment node includes position information, skill requirements, work experience requirements, project experience requirements, and education requirements. Each recruitment node is connected to the recruitment graph data identifier by an edge. Each edge is set with a weight value, and the weight value of each edge can be the default value or can be modified according to requirements.

[0075] Position name, position category, work location, salary range, work content, job responsibilities, team introduction, company name, industry, size, and geographic location are attributes of the position information node. Required skills and certificate requirements are attributes of the skill requirements node. Work company and required years of work are attributes of the work experience requirements node. Project name and project content are attributes of the project experience requirements node. Bachelor's degree and postgraduate degree are attributes of the education requirements node.

[0076] The search module 120 is used to receive the focus word input by the user, obtain the graph data corresponding to the user, use the focus word to modify the nodes in the graph data corresponding to the user, and obtain the search graph data.

[0077] The matching module 130 is used to traverse the image data to be selected in the image database and calculate the similarity between the search image data and the image data to be selected in the image database. In some examples, the image data to be selected whose similarity is greater than a preset similarity threshold is selected as the matched image data output. In other examples, the image data to be selected with a higher similarity ranking is selected as the matched image data output.

[0078] In the above technical solution, the human resources matching system includes a construction module 110, a search module 120 and a matching module 130. The construction module 110 obtains a graph database by processing the target text block, the search module 120 is used to generate search graph data, and the matching module 130 is used to select graph data that best matches the search graph data from the graph database. Since job application texts and recruitment texts usually use more specialized terms and have relatively simple sentence structures, the construction module 110 can first perform initial recognition of the target text block by using rules to obtain initial entities; then, the target text block is input into the first machine learning model for recognition, and the ability of the first machine learning model to perform information recognition in combination with contextual information is used to recognize the target text block. The initial entity is used for adjustment during the recognition process of the first machine learning model to achieve a fusion of rule-based and contextual information recognition technology, which can improve the accuracy of entity recognition by the first machine learning model in the case of insufficient training data.

[0079] Specifically, the target text block is initially identified through the rule base, and the recognition process of the machine learning model is adjusted using the initial entity, thus achieving fusion recognition based on rules and context information. This method is particularly suitable for job search and recruitment texts with rich terms and single sentences, which effectively improves the accuracy of entity recognition and maintains a high recognition accuracy even when there is insufficient training data.

[0080] The system can build a structured graph database based on the identified target entities, where each entity is a node in the graph and the relationship between entities is an edge. This structured data representation facilitates subsequent efficient retrieval and matching operations.

[0081] The search module can generate personalized search graph data based on the user's input focus words and the corresponding graph data. By adjusting the weights of relevant nodes in the user's graph data, the system can more accurately reflect the user's search intent, thereby improving the personalization and relevance of the match.

[0082] The matching module can quickly filter out the options that best match the user's needs by calculating the similarity between the search graph data and the candidate graph data in the graph database. This method not only improves the matching efficiency, but also ensures the accuracy and relevance of the matching results, providing users with more accurate job or talent recommendations.

[0083] The system supports dynamic updating of the graph database based on enterprise development reports to ensure the timeliness and accuracy of the data. At the same time, the system can also continuously expand the content of the graph database based on new recruitment needs and job search information, improving the scalability and practicality of the system.

[0084] Through precise matching and recommendation functions, the system can help companies quickly find suitable talents and reduce recruitment costs and time. At the same time, the system can also provide functions such as talent gap analysis to provide strong support for the company's human resource planning and optimize the recruitment process and decision-making process.

[0085] In addition, by providing personalized search and matching services, the system can significantly improve the user experience of job seekers and recruiters. Job seekers can find positions that meet their expectations more quickly, while companies can more easily find talents with the required skills and experience, thereby improving the satisfaction and cooperation efficiency of both parties.

[0086] In some possible implementations, the human resources matching system further includes a rule base, which includes multiple dictionaries, one dictionary corresponding to one industry, and the construction module 110 is further used to obtain the dictionary of the industry to which the target text block belongs. The corpus in the target text block is segmented, and the segmented corpus is matched with the words in the dictionary of the industry to which the target text block belongs to obtain the initial entity.

[0087] Among them, when obtaining job-seeking information, the company where the applicant has worked is extracted from the job-seeking information, and the industry to which the job-seeking information belongs is determined based on the industry to which the company where the applicant has worked belongs, thereby obtaining the industry to which the job-seeking text corresponds. Construction module 110 processes the job-seeking text in blocks to obtain text blocks corresponding to personal basic information, text blocks corresponding to educational background, text blocks corresponding to work experience, text blocks corresponding to skill certificates, text blocks corresponding to job-seeking information, and text blocks corresponding to project experience. For each of the above text blocks, the corpus in each text block is segmented, and the segmentation results are matched with the words in the dictionary library of the industry to which the text block belongs. If they match, the matching segmentation results are used as the initial entity. For example: the text block corresponding to the skill certificate is segmented to obtain one of the segmentation results as Java, and Java is the same as the word in the dictionary library of the computer industry, so Java is used as an initial entity.

[0088] In the above technical solution, by classifying the dictionaries in the rule library according to the industry, the construction module 110 obtains the industry corresponding to the target text block when using the rule library to identify the target text block, and then focuses on the dictionary of the corresponding industry. Using the dictionary of the corresponding industry for identification can reduce the amount of data processing and improve data processing efficiency.

[0089] In some possible implementations, the human resources matching system includes multiple graph databases, each corresponding to an industry. The search module 120 is used to receive the focus word input by the user, obtain the graph database corresponding to the user, modify the weight of the graph data corresponding to the user using the focus word, and generate search graph data.

[0090] The matching module 130 is used to determine the industry corresponding to the search graph data, take the industry corresponding to the search graph data as the search industry, traverse the graph data to be selected in the graph database corresponding to the search industry, calculate the similarity of corresponding nodes between the search graph data and the graph data to be selected in the graph database of the search industry, and calculate the graph data similarity according to the first formula;

[0091] The first formula specifically includes:

[0092]

[0093] Among them, x1 represents the similarity of the first node, w 11 Represents the weight of the first node in the search graph data, w 21 represents the weight of the first node of the selected graph data; x2 represents the similarity of the first node, w 12 Represents the weight of the second node in the search graph data, w 22 Indicates the weight of the second node of the graph data to be selected.

[0094] It is worth noting that the first formula above calculates the similarity of each node between the search graph data and the candidate graph data in the graph database, and weighted averages these similarities to obtain the similarity of the overall graph data. The first formula comprehensively considers the matching of multiple nodes, and compared with the matching of a single node, it can better reflect the overall matching degree of the graph data, thereby improving the accuracy of the matching.

[0095] The weight items in the first formula (such as the weight of the first node in the search graph data, the weight of the first node in the candidate graph data, etc.) allow the system to flexibly adjust the importance of each node according to actual needs. For example, when the user pays special attention to a certain node (such as work location, salary range, etc.), the weight of the node can be increased to make the matching results more in line with the user's expectations.

[0096] In addition, human resource matching often involves information of multiple dimensions, such as personal information, educational background, work experience, skill requirements, etc. The first formula achieves a comprehensive evaluation of these multi-dimensional information by calculating the weighted average of the similarities of each node, thereby being able to more comprehensively reflect the matching situation between job seekers and recruiters, and improve the comprehensiveness and accuracy of matching.

[0097] Moreover, by calculating the similarity between graph data, the system can quickly filter out the candidate graph data that best matches the search graph data. This method avoids the traditional traversal search method, reduces the amount of calculation, and improves the search efficiency. At the same time, due to the high matching accuracy, the system can find matching results that meet user needs more quickly.

[0098] In the following, the user is a job seeker user. The user graph data including personal information, job search information, educational background, work experience and skill certificates are obtained from the job seeker graph database. If the user is concerned about the work location in the job search information, the weight of the job search information in the user graph data is increased, and the search graph data is generated. The graph data to be selected is the recruitment graph data, which includes position information, skill requirements, work experience requirements and educational requirements.

[0099] The job search information nodes in the search graph data correspond to the position information nodes in the candidate graph data. Calculate the position similarity between the job search information in the search graph data and the position information in the candidate graph data. The skill certificate nodes in the search graph data correspond to the skill requirement nodes in the candidate graph data, and calculate the skill similarity between the skill certificate in the search graph data and the skill requirement in the candidate graph data. The work experience nodes in the search graph data correspond to the work experience requirement nodes in the candidate graph data, and calculate the experience similarity between the work experience in the search graph data and the work experience requirement in the candidate graph data. The education background nodes in the search graph data correspond to the education requirement nodes in the candidate graph data, and calculate the education similarity between the education background in the search graph data and the education requirement in the candidate graph data.

[0100] Calculate the average weight of the job search information node in the user graph data and the weight of the position information node in the recruitment graph data As the weight of job similarity. Calculate the average weight of the skill certificate node in the user graph data and the weight of the skill requirement node in the recruitment graph data As the weight of skill similarity. Calculate the average weight of the work experience node in the user graph data and the weight of the work experience requirement node in the recruitment graph data As the weight of experience similarity. Calculate the average weight of the education requirement node in the recruitment graph data and the weight of the education background node in the search graph data As the weight of the educational background similarity, the weighted average of the similarities of the above four nodes is calculated to obtain the similarity between the search graph data and the candidate graph data.

[0101] In the above technical solution, the focus word is determined according to the focus word input by the user, and the focus word is used to correct the weight in the graph data corresponding to the user. In this way, when calculating the similarity between the search graph data and the graph data to be selected in the graph database, the similarity of the graph data matching the focus word is increased, ensuring that the graph data selected from the graph database has the highest match with the focus word, thereby improving the matching accuracy.

[0102] Specifically, the system can establish multiple graph databases based on industry divisions. This segmentation strategy enables each graph database to focus more on the human resources data of a specific industry, thereby improving the pertinence and accuracy of matching. When a user searches, the system can quickly locate the graph database related to the user's industry, laying a solid foundation for the subsequent matching process.

[0103] The search module can receive the user's input of the focus words and modify the weights of the nodes in the user's corresponding graph data based on these focus words. This mechanism allows nodes that are highly related to the user's focus words to obtain higher weights in the graph data, thereby highlighting the contribution of these nodes when calculating similarity. This weight correction strategy significantly enhances the relevance of matching results to user needs.

[0104] The matching module calculates the similarity between the search graph data and the candidate graph data through the first formula. This formula takes into account the similarity of each node and the weight of the corresponding node, and comprehensively evaluates the similarity between the graph data by weighted average. This refined calculation method can more accurately reflect the actual differences and similarities between the graph data, thereby improving the accuracy of matching.

[0105] Furthermore, since the revision of focus words and weights is based on real-time information input by users, the system has strong dynamic adjustment capabilities. No matter how the user's needs change, the system can respond quickly and adjust the matching strategy to ensure that users are provided with the human resources matching results that best meet their needs.

[0106] Through the implementation of the above technical solutions, the system can provide users with more personalized and accurate human resource matching services, which not only improves the user's search efficiency, but also greatly enhances the user's satisfaction and trust in the system's matching results.

[0107] In addition, the introduction of multiple graph databases and segmentation strategies enable the system to manage and allocate resources more effectively. During the search and matching process, the system can quickly locate the relevant graph database, avoiding unnecessary waste of resources and computing overhead. This optimization strategy improves the overall efficiency and response speed of the system.

[0108] In some possible implementations, the matching module is used to:

[0109] Generate an education conversion database based on the education information of existing talents in the existing talent database, and use the education conversion database to train a vector conversion model so that each education information in the education conversion database is converted into the same vector;

[0110] Generate a work experience conversion library based on the work experience information of existing talents in the existing talent pool, and use the work experience conversion library to train a vector conversion model so that each work experience information in the work experience conversion library is converted into the same vector;

[0111] The search graph data is converted into a search vector using a vector conversion model, and the candidate graph data is converted into a candidate vector using a vector conversion model;

[0112] The Euclidean distance between the search vector and the candidate vector is calculated to obtain the similarity between the search graph data and the candidate graph data.

[0113] Among them, for each enterprise user, obtain the enterprise user's existing talent information, such as: the school where the existing talent graduated, the existing talent's previous work experience, and add the existing talent's school where the existing talent graduated to the enterprise user's academic degree conversion library. Use the academic degree conversion library to train the vector conversion model so that each graduating school in the academic degree conversion library is mapped to the same vector. In this way, when calculating the similarity between the education background nodes in two graph data, the similarity between any two graduating schools in the academic degree conversion library is relatively high.

[0114] Add the company where the existing talent works to the work experience conversion library of the company user. Use the work experience conversion library to train the vector conversion model so that each work company in the work experience conversion library is mapped to the same vector. In this way, when calculating the similarity between work experience nodes in two graph data, the similarity between any two work companies in the work experience conversion library is high.

[0115] The job search information nodes in the search graph data correspond to the job information nodes in the candidate graph data. The vector conversion model is used to convert the job search information nodes in the search graph data into job search vectors, and the vector conversion model is used to convert the job information nodes in the candidate graph data into job candidate vectors. The Euclidean distance between the job search vector and the job candidate vector is calculated as the job similarity.

[0116] The skill certificate nodes in the search graph data correspond to the skill requirement nodes in the candidate graph data. The skill certificate nodes in the search graph data are converted into skill search vectors using a vector conversion model. The skill requirement nodes in the candidate graph data are converted into skill candidate vectors using a vector conversion model. The Euclidean distance between the skill search vector and the skill candidate vector is calculated as the skill similarity.

[0117] The work experience nodes in the search graph data correspond to the work experience requirement nodes in the candidate graph data. The vector conversion model is used to convert the work experience nodes in the search graph data into experience search vectors. The vector conversion model is used to convert the work experience requirement nodes in the candidate graph data into experience candidate vectors. The Euclidean distance between the experience search vector and the experience candidate vector is calculated as the experience similarity.

[0118] The education requirement nodes in the candidate graph data correspond to the education background nodes in the search graph data. The vector conversion model is used to convert the education background nodes in the search graph data into education search vectors. The vector conversion model is used to convert the education requirement nodes in the candidate graph data into education candidate vectors. The Euclidean distance between the education search vector and the education candidate vector is calculated as the education similarity.

[0119] The weighted average of the similarities of the above four nodes is calculated to obtain the similarity between the search graph data and the candidate graph data.

[0120] In the above technical scheme, by collecting educational information from the existing talent pool, determining the schools that the company tends to recruit, collecting work experience from the existing talent pool, determining the companies that the company tends to recruit, and using the above information to train the vector conversion model, when calculating the similarity between the search graph data and the selected graph data, that is, calculating the corresponding graph data of the job seeker and the corresponding graph data of the recruiter, if the job seeker's educational experience is the same as the school that the recruiter prefers to recruit, the converted vectors of the job seeker's corresponding graph data and the recruiter's corresponding graph data are the same, the Euclidean distance between the two is also the smallest, and the similarity is the highest. In this way, the best job seeker can be matched for the company, and the matching accuracy of the human resources matching system is improved.

[0121] Specifically, the system collects the education information and work experience information from the existing talent pool to generate an education conversion library and a work experience conversion library. The use of these two conversion libraries enables the originally complex and diverse education and work experience information to be uniformly converted into vector form. This unified data representation method not only simplifies the data processing process, but also greatly improves the matching efficiency, because the comparison and calculation between vectors are more efficient than raw text or structured data.

[0122] The construction of the education conversion database and work experience conversion database is based on the actual data in the existing talent pool. This means that these conversion databases can accurately reflect the recruitment preferences of enterprises, such as the schools and enterprises they prefer to recruit. By training the vector conversion model, the system can learn these preferences and use them in the subsequent matching process, so as to more accurately recommend job seekers who meet the requirements of enterprises.

[0123] When calculating the similarity between the search graph data and the candidate graph data, the system uses the Euclidean distance as a measurement standard. Since the education and work experience information have been converted into vectors in the same vector space through the vector conversion model, the Euclidean distance can accurately reflect the similarity between these vectors. When the job seeker's education experience is the same as the school that the recruiter prefers to recruit, or the work experience is consistent with the company that the recruiter prefers to recruit, their corresponding vectors will be very close, with the smallest Euclidean distance and the highest similarity. This matching method significantly improves the accuracy of the human resources matching system.

[0124] In addition, the introduction of the vector transformation model makes the system more adaptable and scalable. As the recruitment needs of enterprises change and the talent pool is constantly updated, the system can adapt to the new data environment by retraining or adjusting the vector transformation model. This flexibility enables the system to maintain efficient and accurate matching capabilities.

[0125] Through the implementation of the above technical solutions, the system can provide enterprises with more accurate job seeker recommendations that better meet their needs. This not only improves the recruitment efficiency of enterprises, but also reduces recruitment costs. At the same time, for job seekers, they can also find suitable job opportunities more quickly.

[0126] In some possible implementations, the first machine learning model includes a model input layer, a model encoding layer, a first fusion layer, a modified input layer, a modified encoding layer, and a model decoding layer. Construction module 110 is used to:

[0127] Use the model input layer to vectorize the target text block to obtain the main vector; use the multi-layer model encoding layer to encode the main vector multiple times and then output it;

[0128] Using a correction input layer to vectorize the initial entity to obtain a correction vector; using at least one correction encoding layer to encode the correction vector and then output it;

[0129] Using a first fusion layer to fuse data output by a multi-layer model encoding layer and data output by at least one layer of correction encoding layer;

[0130] The multi-layer model decoding layer is used to perform multiple decoding processes on the data output by the first fusion layer to obtain the target entity.

[0131] More specifically, Figure 4 A schematic diagram of the architecture of a first machine learning model provided in some embodiments of the present application, such as Figure 4 As shown, the model input layer receives the target text block, and the model input layer vectorizes the target text block and converts it into a first vector. The model encoding layer of the first layer receives the model input layer output vector, encodes the model input layer output vector, and then outputs it to the second model encoding layer. The second model encoding layer encodes the data received at its input end and then outputs it, and so on. The last model encoding layer encodes the data received at its input end and then outputs it.

[0132] The target text block is subjected to entity recognition using the rule base to obtain the initial entity. The initial entity is received by the correction input layer, which is vectorized and output to the first correction coding layer. The first correction coding layer encodes the data received at its input end and outputs it to the second correction coding layer. The second correction coding layer encodes the data received at its input end and outputs it to the third correction coding layer, until the last correction coding layer encodes the data received at its input end and outputs it.

[0133] The first fusion layer receives the data output by the last model encoding layer, and also receives the data output by the last modified encoding layer. The first fusion layer fuses the data output by the last model encoding layer and the data output by the last modified encoding layer, and then outputs the data to the first model decoding layer. The second model decoding layer receives the data output by the first model decoding layer, decodes the data output by the second model decoding layer, and then outputs the data, until the last model decoding layer decodes the data output by the second to last model decoding layer, and then outputs the data.

[0134] Each model encoding layer has the same structure, each modified encoding layer has the same structure, and the model encoding layer and modified encoding layer have the same structure, both including a multi-head self-attention mechanism and a feedforward neural network. The model decoding layer includes an encoder-decoder attention mechanism and a feedforward neural network. The first fusion layer outputs the last model encoding layer output data and the modified encoding layer output data by weighted averaging.

[0135] In the above technical scheme, the correction input layer is used to vectorize the initial entity, the correction encoding layer encodes the vectorized initial entity so as to merge it with the data of the target text block after vectorization and encoding, thereby correcting the encoded data, and the decoding layer decodes the corrected encoded data and outputs the target entity, thereby realizing the fusion of rule-based and contextual information recognition technology, thereby improving the accuracy of entity recognition by the machine learning model.

[0136] Specifically, the model input layer first converts the target text block into a vectorized representation (main vector), and then deeply encodes the main vector through a multi-layer model encoding layer. This process can capture the deep semantic information in the text and provide rich feature representation for subsequent entity recognition.

[0137] The correction input layer vectorizes the initial entity to obtain a correction vector, which is then encoded by the correction encoding layer. The introduction of the correction vector provides the model with additional context or domain knowledge, which helps the model to strengthen these key information during the encoding process, thereby improving the accuracy of entity recognition.

[0138] The first fusion layer fuses the data output by the multi-layer model encoding layer with the data output by the correction encoding layer. This fusion strategy combines the global features automatically learned by the model with the local features obtained through the rule base, realizing the complementary advantages of two different recognition paths. By adjusting the fusion weights, the recognition performance of the model can be further optimized, especially when processing domain texts with specific patterns or terms.

[0139] The fused data is decoded through the multi-layer model decoding layer to gradually restore the specific form of the target entity. The multi-layer decoding structure can not only improve the accuracy of decoding, but also enhance the robustness and generalization ability of the model. Even when faced with unseen entities or new text patterns, the model can effectively handle them through its powerful encoding and decoding capabilities.

[0140] In addition, the first machine learning model adopts a modular design, so that each layer can be trained and optimized independently. This design reduces the complexity of the model and improves the training efficiency. At the same time, by adjusting the parameters and structure of each layer, the model can be flexibly tuned to adapt to different application scenarios and needs.

[0141] Moreover, by combining the rule base and the machine learning model, the system can achieve better recognition results with limited training data. This hybrid approach not only takes advantage of the accuracy and stability of the rule base, but also takes advantage of the adaptability and generalization capabilities of the machine learning model.

[0142] Moreover, in different fields or application scenarios, the trained model parameters can be transferred to new tasks through methods such as transfer learning, thereby realizing the rapid transfer and sharing of knowledge. This greatly reduces the development cost and time cost of new tasks.

[0143] In some possible implementations, the construction module 110 is used to:

[0144] Use the i-th second fusion layer to perform weighted average processing on the output data of the corrected coding layer of the i+1-th layer and the output data of the model coding layer of the i+1-th layer;

[0145] The model encoding layer of the i-th last layer is used to encode the data output by the i-th second fusion layer and then output; wherein the weighting coefficient of the second fusion layer is adjustable.

[0146] More specifically, Figure 5 A schematic diagram of the architecture of a machine learning model provided in some embodiments of the present application, and Figure 4The difference is that the machine learning model also includes at least one second fusion layer, and each second fusion layer is used to fuse a correction coding layer output data and a model coding layer output data. The number of second fusion layers and the number of correction coding layers differ by one, and the number of second fusion layers is less than half of the number of model coding layers. For example: There are two second fusion layers, and the second-to-last second fusion layer performs weighted averaging processing on the correction coding layer output data of the third-to-last layer and the model coding layer output data of the third-to-last layer, and outputs it to the model coding layer of the second-to-last layer. The first-to-last second fusion layer performs weighted averaging processing on the correction coding layer output data of the second-to-last layer and the model coding layer output data of the second-to-last layer, and outputs it to the model coding layer of the first-to-last layer.

[0147] Among them, the weight coefficient of the second fusion layer has a value range of [0,1], and the weight coefficient of the second fusion layer includes the weight coefficient of the model coding layer and the weight coefficient of the correction coding layer. When the weight coefficient of the correction coding layer is relatively small, the correction effect of the initial entity on the processing process of the model coding layer is reduced. When the weight coefficient of the correction coding layer is relatively large, the correction effect of the initial entity on the processing process of the model coding layer is increased. The correction effect of the initial entity on the processing process of the machine learning model can be adjusted by adjusting the weight coefficient of the second fusion layer.

[0148] In the above technical solution, in order to further improve the correction ability of the initial entity to the machine learning model, the machine learning model is also provided with multiple second fusion layers, and the second fusion layer is used to fuse the data output by the model coding layer and the data output by the correction coding layer and output them to the next model coding layer. The weight coefficient of the second fusion layer has a value range of [0,1]. The correction ability of the initial entity to the machine learning model can be adjusted by adjusting the size of the weight coefficient, thereby further improving the accuracy of data processing. By making the number of second fusion layers and the number of correction coding layers differ by one, and the number of second fusion layers is less than half of the number of model coding layers, the correction effect of the initial entity on the processing process of the machine learning model can be reduced to avoid excessive correction effect and reduce the accuracy of data recognition.

[0149] Specifically, by adding a second fusion layer, the system can more carefully and flexibly fuse the output data of the model encoding layer and the correction encoding layer. These fusion layers not only promote the deep fusion between the features automatically learned by the model and the initial entity features provided by the rule base, but also further optimize the fusion process through weighted average processing, so that the model can more accurately capture and utilize the key information in the text.

[0150] In addition, the weight coefficient of the second fusion layer is adjustable, which means that the system can dynamically adjust the strength of the initial entity's correction of the model according to actual needs and performance. When a stronger correction capability is needed, the weight of the output data of the correction coding layer can be increased; otherwise, its weight can be reduced. This flexibility enables the model to better adapt to different application scenarios and data characteristics.

[0151] The adoption of a multi-layer fusion strategy (including the first fusion layer and the second fusion layer) can also enhance the robustness and generalization of the model. By performing data fusion and feature extraction at different levels, the model can understand the text content more comprehensively and reduce recognition errors caused by data bias or noise. At the same time, this design also improves the model's ability to handle new data or unseen entities.

[0152] The second fusion layer passes the output data of the correction encoding layer back to the model encoding layer, forming a closed loop of knowledge transfer. This design promotes knowledge sharing and deep learning between different levels of the model, allowing the model to more effectively use the context or domain knowledge provided by the initial entity to optimize the recognition results. The adjustable weighting coefficients provide more degrees of freedom for model training. During the training process, these coefficients can be adjusted to optimize the performance of the model, such as accuracy, recall, etc. In addition, the multi-layer fusion structure also enables the model to converge to the optimal solution more stably during training. Through multiple fusion and encoding processes, the model can more accurately identify entities in the text. This multi-level and multi-stage processing method helps to eliminate ambiguity and misjudgment in the recognition process, thereby improving the accuracy and reliability of data processing.

[0153] In some possible implementations, the construction module 110 is specifically used to:

[0154] Use the second machine learning model to extract this year's project plan from the corporate development report, generate a talent recruitment plan based on this year's project plan and the existing talent pool, and update the user's corresponding graph data based on the talent recruitment plan.

[0155] Among them, the architecture of the first machine learning model is the same as that of the second machine learning model. The backend server 100 trains the second machine learning model so that the geothermal machine learning model can extract the project plan for the end of this year from the enterprise development report. After the front-end application end 200 removes the sensitive information in the enterprise development report, it uploads the enterprise development report to the backend server 100. The backend server 100 uses the trained second machine learning model to extract the project plan for this year from the enterprise development report.

[0156] The enterprise development report is preprocessed on the backend server 100 to delete irrelevant information. Subsequently, the preprocessed enterprise development report is segmented into text blocks to obtain multiple target text blocks. The target text blocks are identified using a second machine learning model to obtain the year-end project plan.

[0157] Correspondingly, after determining to update the graph data corresponding to the user, the search module generates search graph data according to the focus word input by the user and the graph data corresponding to the user.

[0158] In the above solution, the system can automatically trigger the second machine learning model to conduct in-depth analysis of the enterprise development report and accurately extract the project plan for the current year. This automated process not only reduces the workload of the human resources department, but also avoids the errors and delays that may be caused by manual analysis, ensuring the accuracy and timeliness of project plan information.

[0159] Based on the extracted information of this year's project plan and the existing talent pool, the system can intelligently generate a talent recruitment plan. This plan fully considers the company's current and future project needs, as well as the skills and experience of existing talents, thus ensuring the pertinence and practicality of the recruitment plan.

[0160] The generation of a talent recruitment plan will trigger the system to automatically update the user's corresponding graph data. This dynamic update mechanism ensures that the user graph data is always consistent with the company's current project plan and recruitment needs, providing an accurate data foundation for subsequent search and matching processes.

[0161] The search module can quickly generate search graph data based on the user-entered focus words and updated graph data. Since the graph data has been updated according to the latest recruitment plan, the search process can more accurately locate the graph data of job seekers that match the year-end project plan. This precise matching not only improves search efficiency, but also reduces the possibility of invalid searches and wrong matches.

[0162] Through mechanisms such as automated extraction, intelligent generation and dynamic updating, the system can quickly respond to changes in corporate development reports and adjust recruitment plans and search strategies in a timely manner. This ability to respond quickly and flexibly enables the system to better adapt to the changing needs of enterprises and provide more efficient and accurate human resource matching services.

[0163] Subsequently, the backend server 100 matches the talents required in the current year's project plan with the talents in the existing talent pool, and generates a talent recruitment plan based on the matching results. The talent recruitment plan includes recruitment information for multiple recruitment positions. The first machine learning model is used to identify the recruitment information for multiple recruitment positions to obtain a target entity, and the graph data corresponding to the user is updated based on the target entity.

[0164] In the above technical solution, after obtaining the enterprise development report, the second machine learning model is triggered to extract this year's project plan from the enterprise development report, and then a talent recruitment plan is generated based on this year's project plan and the existing talent pool. This can automatically update the user's corresponding graph data based on the talent recruitment plan, and then trigger the search module to update the search graph data, and obtain the graph data of job seekers that match the end-of-year project plan from the job search graph database, thereby improving data matching efficiency.

[0165] In some possible implementations, the existing talent pool includes at least one existing talent information, and each existing talent information includes mastered skills and project experience. The search module is specifically used to:

[0166] Use the second machine learning model to extract talent demand information from the current year's project plan and generate a talent demand database. The talent demand information includes skill requirements and project requirements.

[0167] For each required talent information, match the required talent information with the existing talent information in the existing talent pool, determine the talent gap information based on the matching results; and use the talent gap information as a recruitment plan.

[0168] Among them, matching includes the matching of skills and project experience, as well as the matching of the number of required talents and the number of existing talents, and talent gap information is generated based on the matching results.

[0169] For example: Use the second machine learning model to extract the talent pool from this year's project plan. This year's projects include Project A, which requires two types of talents. The first type of talent needs to be able to use hardware development software and have experience in hardware development projects. There are two talents in the first type. The second type of talent needs to master Java development skills and have experience in Java development projects. There are three talents in the second type. The talent pool includes two talents in the first type and three talents in the second type.

[0170] By extracting the skills and project experience of existing employees of the enterprise, an existing talent pool is obtained. For example, the existing talent pool includes 20 categories of existing talents. Category A existing talents match Category 1 required talents, and the number of Category A existing talents is 3. Category B existing talents match Category 2 required talents, and the number of Category B existing talents is 2. Then the talent gap information is that there is a lack of 1 Category 2 required talent. It is necessary to recruit 1 Category 2 required talent, and the Category 2 required talent information is used as recruitment information.

[0171] In the above technical solution, the second machine learning model is used to extract the required talent information from this year's project plan, match the required talent information with the existing talent information, and generate a recruitment plan based on the matching results. This ensures that the recruited talents can meet this year's project plan and improves the human resources matching system's ability to match demand.

[0172] Specifically, the system uses the second machine learning model to deeply analyze the project plan for the current year, accurately identify and extract the skill requirements and project requirements required for the project, and form a talent pool of demand. This step ensures that the recruitment plan is formulated based on actual project needs, avoiding blind recruitment and waste of resources.

[0173] The search module can conduct a comprehensive search and match in the existing talent pool for each required talent information. By comparing the skills and project experience of existing talents with the skill requirements and project requirements in the required talent information, the system can quickly locate talents that meet or are close to the requirements, providing strong support for subsequent recruitment plans.

[0174] Through the matching process, the system can clearly identify the unmet needs in the existing talent pool, namely the talent gap information. This information is crucial for formulating targeted recruitment plans, and it directly guides the company on what skills and experience talents need to be recruited, as well as the number and priority of recruitment.

[0175] Based on accurate talent demand information and talent gap information, the system can generate a highly targeted recruitment plan. This plan not only clarifies the recruitment goals and priorities, but also optimizes the allocation of recruitment resources and improves the efficiency and success rate of recruitment.

[0176] In some possible implementations, the search module 120 is specifically configured to:

[0177] Calculate the skill similarity between the skill requirements of the talent in demand and the skills mastered by the existing talents; calculate the project similarity between the project requirements of the talent in demand and the project experience of the existing talents;

[0178] Take a weighted average of skill similarity and project similarity to obtain the talent matching degree between the required talents and the existing talents;

[0179] If the talent matching degree is greater than the preset threshold, it is determined that there is a match between the required talents and the existing talents. If the number of required talents is less than or equal to the number of existing talents, it is determined that there is no gap in this type of required talents. If the number of required talents is greater than the number of existing talents, the gap information of this type of required talents is generated.

[0180] Among them, for each type of required talent, traverse each existing talent information in the existing talent database, convert the required talent information into a required vector, convert the existing talent information into an existing vector, calculate the Euclidean distance between the required vector and the existing vector, obtain the talent matching degree between the required talent and the existing talent, and achieve matching in the skill and project experience dimensions.

[0181] After the required talents are matched with the existing talents in terms of skills and projects, we will continue to judge whether the number of existing talents meets the required talents. If so, there is no gap in this type of talent. If not, the gap information of this type of required talents will be generated.

[0182] In the above technical solution, we first determine whether the existing talents and required talents match each other in terms of skills and project experience. If they do match, we confirm whether the number of existing talents can meet the number of required talents. Considering these two dimensions, we generate corresponding gap information to ensure that the recruited talents can meet the annual project plan and improve the ability of the human resources matching system to match demand.

[0183] Specifically, the system can accurately calculate the skill similarity between the skill requirements and the skills mastered by existing talents for each type of talent in demand, and simultaneously calculate the project similarity between the project requirements and the project experience of existing talents. This dual matching mechanism ensures a comprehensive assessment of the matching degree of talents from the two core dimensions of skills and project experience, and improves the accuracy and reliability of matching.

[0184] By taking a weighted average of skill similarity and project similarity, the system can derive a comprehensive talent matching index. This index takes into account the similarity of skills and project experience, provides a scientific basis for judging whether existing talents meet the requirements of needed talents, and avoids the one-sidedness of single-dimensional evaluation.

[0185] The system can intelligently identify talent gaps based on the talent matching degree and the comparison between the number of required talents and existing talents. When the talent matching degree is greater than the preset threshold, the system determines it as a match; further, if the number of required talents is less than or equal to the number of existing talents, it is confirmed that there is no gap in the required talents of this type; otherwise, gap information is generated. This process ensures the accuracy and timeliness of gap information and provides strong support for the formulation of recruitment plans.

[0186] Accurate gap information enables companies to clearly understand what types of talent are in short supply, so that they can adjust recruitment strategies and resource allocation in a targeted manner. This helps avoid waste of resources and blind recruitment, and improves recruitment efficiency and effectiveness.

[0187] It can be seen that by deeply matching from the two dimensions of skills and project experience, and combining quantity comparison to generate gap information, the system has significantly improved its demand matching capabilities in human resource matching. This improvement in capabilities enables the system to better meet the actual needs of enterprises and provide more accurate and effective support for the human resource management of enterprises.

[0188] In some possible implementations, the backend server 100 is used to receive an initial screening instruction sent by the front-end application end 200, the initial screening instruction including an initial screening keyword, generate a recommended keyword according to the initial screening keyword, and send the recommended keyword to the front-end application end 200;

[0189] The backend server 100 receives the progressive screening instruction sent by the frontend application 200, the progressive screening instruction includes a progressive keyword, and generates a focus word according to the initial screening keyword and the progressive keyword.

[0190] The front-end application receives the keyword input by the user, generates an initial screening instruction according to the keyword input by the user, and sends the initial screening instruction to the back-end server 100. After the back-end server 100 extracts the initial screening keyword from the initial screening instruction, it inputs the initial screening instruction into the existing recommendation model, so that the existing recommendation model generates a recommended keyword, and sends the recommended keyword to the front-end application 200.

[0191] The recommended keywords are displayed on the front-end application terminal 200, and the user input is received again. A progressive filtering instruction is generated according to the user input, and the progressive filtering instruction is sent to the back-end server, and a focus word is generated according to the initial filtering keyword and the progressive keyword.

[0192] In the above technical solution, recommended keywords are generated based on the keywords input by the user for the first time, and the user is guided to input again to obtain more filtering information from the user. In this way, the graph data in the graph database can be matched based on more filtering information, so that the matched graph data can be more in line with the user's filtering needs, thereby improving the ability of the human resources matching system to match needs.

[0193] Specifically, the system can receive the initial screening keywords entered by the user for the first time and quickly generate recommended keywords related to them. This instant feedback mechanism not only simplifies the user's input process, but also guides the user to express his or her needs more deeply by providing suggested keywords. This interactive method enhances the user's sense of participation and makes the screening process more intuitive and efficient.

[0194] By introducing progressive filtering instructions, the system encourages users to input multiple times, and each input can be used for more detailed filtering based on the previous one. This progressive filtering method can gradually accumulate the user's filtering information, allowing the system to understand the user's needs more comprehensively and provide a rich information foundation for subsequent graph data matching.

[0195] In addition, the system generates focus words based on the initial screening keywords and progressive keywords. These focus words are a direct reflection of user needs. In the graph database matching process, the system can focus on these focus words, so as to more accurately locate graph data that meets user needs. This precise matching mechanism can improve the accuracy and efficiency of the human resources matching system.

[0196] By gradually accumulating the user's filtering information, the system can more accurately locate the range of graph data that the user is interested in, avoiding unnecessary waste of resources. This optimization strategy enables the system to be more efficient when processing large amounts of data and improves resource utilization.

[0197] Moreover, since the system can more accurately match the needs of users, the user's satisfaction and trust in the process of use will also be improved accordingly. Users can find human resources information that meets their needs more quickly, thus improving the practicality and value of the entire system.

[0198] In addition, by collecting and analyzing users’ screening instructions and focus words, the system can continuously learn and optimize its recommendation algorithm and matching strategy. This iterative optimization process enables the system to better adapt to users’ changing needs and maintain its competitiveness and advancement.

[0199] Figure 6 This is a schematic diagram of the structure of the backend server 100 provided in this application. Figure 6 As shown, the electronic device 100 provided in this embodiment includes: at least one processor 101 and a memory 102. Optionally, the device 100 also includes a communication component 103. The processor 101, the memory 102 and the communication component 103 are connected via a bus 104.

[0200] In a specific implementation process, at least one processor 101 executes the computer-executable instructions stored in the memory 102, so that at least one processor 101 executes the above method.

[0201] The specific implementation process of the processor 101 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0202] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0203] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0204] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0205] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0206] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0207] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0208] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0209] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0210] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0211] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0212] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0213] A person of ordinary skill in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk, etc., various media that can store program codes.

[0214] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed by the present invention, are not limited to the precise structures described above and shown in the drawings, and may be modified and altered in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A human resource matching system based on big data, characterized in that: The human resources matching system includes a backend server and a front-end application end, and the backend server includes: A construction module is used to perform entity recognition on a target text block using a rule library to obtain an initial entity; perform entity recognition on the target text block using a first machine learning model, and use the initial entity to adjust an intermediate recognition result during the recognition process of the first machine learning model to obtain a target entity; and construct a graph database according to the target entity; wherein the target text block includes a text block after job search text is segmented and a text block after recruitment text is segmented; A search module, used to generate search graph data based on the focus words input by the user and the graph data corresponding to the user; A matching module is used to calculate the similarity between the search graph data and the graph data to be selected in the graph database, and select matching graph data from the graph database based on the similarity.

2. The human resources matching system based on big data according to claim 1 is characterized in that: The first machine learning model includes a model input layer, a model encoding layer, a first fusion layer, a modified input layer, a modified encoding layer, and a model decoding layer; The building blocks are used to: Use the model input layer to vectorize the target text block to obtain a main vector; use multiple layers of the model encoding layer to encode the main vector multiple times and then output it; Use the correction input layer to vectorize the initial entity to obtain a correction vector; use the correction encoding layer to encode the correction vector and then output it; Using the first fusion layer to fuse the data output by the multiple layers of the model coding layer and the data output by the correction coding layer; The data output by the first fusion layer is decoded multiple times using multiple layers of the model decoding layers to obtain the target entity.

3. The human resources matching system based on big data according to claim 2 is characterized in that: The first machine learning model further includes at least one second fusion layer, and the building module is used to: Use the i-th second fusion layer to perform weighted average processing on the output data of the corrected coding layer of the i+1-th layer and the output data of the model coding layer of the i+1-th layer; The data output by the i-th second fusion layer is encoded and outputted using the i-th model encoding layer from the bottom; wherein the weighting coefficient of the second fusion layer is adjustable.

4. The human resources matching system based on big data according to any one of claims 1 to 3, characterized in that: The human resources matching system includes a plurality of graph databases, each of which corresponds to an industry; The search module is used to receive a focus word input by a user, obtain a graph database corresponding to the user, use the focus word to modify the weight of the graph data corresponding to the user, and generate the search graph data; The matching module is used to determine the search industry corresponding to the search graph data, and calculate the similarity of each node between the search graph data and the graph data to be selected in the graph database corresponding to the search industry to determine the similarity of the graph data.

5. The human resources matching system based on big data according to claim 4 is characterized in that: The backend server receives an initial screening instruction sent by the front-end application, the initial screening instruction includes an initial screening keyword, generates a recommended keyword according to the initial screening keyword, and sends the recommended keyword to the front-end application; The backend server receives a progressive screening instruction sent by a frontend application, wherein the progressive screening instruction includes a progressive keyword, and generates the focus word according to the initial screening keyword and the progressive keyword.

6. The human resources matching system based on big data according to any one of claims 1 to 3, characterized in that: The building blocks are specifically used for: Using the second machine learning model to extract the current year's project plan from the enterprise development report, generating a talent recruitment plan based on the current year's project plan and the existing talent pool, and updating the graph data corresponding to the user based on the talent recruitment plan; The search module generates the search graph data according to the focus word input by the user and the updated graph data.

7. The human resources matching system based on big data according to claim 6 is characterized in that: The existing talent pool includes at least one piece of existing talent information, and each piece of existing talent information includes mastered skills and project experience; The search module is specifically used for: Using the second machine learning model to extract required talent information from the current year's project plan to generate a required talent database, wherein the required talent information includes skill requirements and project requirements; For each required talent information, the required talent information is matched with each existing talent information in the existing talent database, and talent gap information is determined according to the matching result; and the talent gap information is used as a recruitment plan.

8. A human resource matching method based on big data, characterized in that: include: Use the rule base to perform entity recognition on the target text block to obtain the initial entity; Using a first machine learning model to perform entity recognition on the target text block, and using the initial entity to adjust the intermediate recognition result during the recognition process of the first machine learning model to obtain a target entity; constructing a graph database according to the target entity; wherein the target text block includes a text block after the job application text is segmented and a text block after the recruitment text is segmented; Generate search graph data based on the focus word input by the user and the graph data corresponding to the user; The similarity between the search graph data and the graph data to be selected in the graph database is calculated, and matching graph data is selected from the graph database according to the similarity.

9. A backend server, characterized in that: include: processor; as well as, A memory, configured to store executable instructions of the processor; Wherein, the processor is configured to perform the method of claim 8 by executing the executable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to claim 8 when executed by a processor.

Images