System and method for automatically matching person and post

Abstract

The invention discloses an automatic person and post matching system and method, and relates to the technical field of post recommendation, and the system comprises an information analysis module which is used for obtaining post information, carrying out analysis clustering to generate a post micro-task graph, collecting user information, and carrying out analysis to generate a user capability graph; the man-post matching module is used for carrying out man-post matching according to the generated post micro-task atlas and the user capability atlas and generating a post matching result; the development prediction module is used for predicting future capability development of the user, updating a user capability graph and predicting a future matching result based on the updated user capability graph; and the display storage module is used for displaying the post matching result and the future matching result and storing the post matching result and the future matching result in a database. According to the method, the accuracy and intuition of post matching are improved, the matching efficiency and the user experience are improved, and meanwhile, the user is effectively helped to perform post selection and self-promotion.

Description

Technical Field

[0001] The present invention relates to the technical field of job recommendation, and in particular to a system and method for automatic matching of people with jobs. Background Art

[0002] With the rapid development of information technology and the widespread application of big data analysis methods, job matching technology has received increasing attention in modern human resource management. Traditional job matching methods usually rely on manual screening and experience judgment, and judge the matching degree between job seekers and positions through resume screening, interview evaluation, etc. However, this method is often subjective and inefficient, and cannot accurately quantify the difference between job seekers' actual abilities and job requirements. In addition, with the increasing complexity of job functions and working environments, the skills and tasks required for jobs have gradually become more refined, and a single skill matching can no longer meet actual needs. Therefore, current research has gradually turned to more refined and data-driven matching methods. Through comprehensive analysis and modeling of job information and job seekers' capabilities, with the help of natural language processing (NLP), machine learning, knowledge graphs and other technologies, we can gradually achieve multi-dimensional analysis of job tasks and personal capabilities, and build a more accurate matching model. However, the existing job matching technology still has many shortcomings. Many matching algorithms do not fully consider the complexity of job micro-tasks in the matching process, and usually use a single or a few core skills as the basis for matching. This simple matching method is difficult to cover the full picture of the job, resulting in insufficient accuracy and intuitiveness of the matching results, and ignoring the dynamic evolution and improvement space of user capabilities, and cannot dynamically match users' future jobs. Summary of the invention

[0003] In view of the problems existing in the above-mentioned existing systems and methods for automatic person-job matching, the present invention is proposed.

[0004] Therefore, the problem to be solved by the present invention is that the accuracy and intuitiveness of the matching results are insufficient, and the dynamic evolution and improvement space of user capabilities are ignored.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: a system for automatic matching of people and positions, which includes: an information analysis module, which is used to obtain position information, perform analysis and clustering to generate a position micro-task map, and collect user information, and analyze and generate a user capability map; a person-position matching module, which is used to match people and positions according to the generated position micro-task map and user capability map, and generate a position matching result; a development prediction module, which is used to predict the future capability development of the user and update the user capability map, and predict future matching results based on the updated user capability map; a display and storage module, which is used to display the position matching results and future matching results, and store them in a database.

[0006] As a preferred solution of the system for automatic matching of people and positions of the present invention, wherein: the acquisition of position information, analysis and clustering to generate a position micro-task graph refers to acquiring position information through the network, processing the position information using NLP technology, extracting keywords from the position information using the TD-IDF algorithm, and generating a position keyword vector according to the keywords and TD-IDF values; Randomly select K initial cluster centers and use the K-means clustering algorithm to cluster the job keyword vectors; Treat each cluster as a job micro-task, calculate the average distance between all job keyword vectors in each cluster and the cluster center as the weight of each job micro-task, and simultaneously calculate the distance between cluster centers of different clusters; Each job microtask is regarded as a node, and the two job microtasks with the shortest distance between cluster centers are regarded as connections to add connecting edges. The mean of the connected job microtask weights is calculated as the connecting edge weight to construct a job microtask graph.

[0007] As a preferred solution of the system for automatic matching of people and positions of the present invention, wherein: the collecting of user information and analyzing and generating a user capability map refers to collecting user information through the network, using the Word2Vec model for word segmentation and word vector representation, converting the user information into a user embedding vector and mapping it to a feature node in the map, for the user embedding vector of each feature node, querying its time node according to the user information, integrating the time nodes of all feature nodes to form a time series, and calculating the feature node weight based on the time node of each feature node using time decay weighting: ; in is the weight of the i-th feature node, is the time node of the feature node, is the current time, is the time decay rate, is the time node of the characteristic node in the time series and ≠ , G is the time series; Select the CART algorithm to build a decision tree, and set the decision tree classification target as relevance; The user embedding vectors of two feature nodes are input into the decision tree to determine the correlation of the feature nodes. If the decision tree output is correlated, a connecting edge is generated between the feature nodes, the cosine similarity of the user embedding vectors in the connected feature nodes is calculated, and the angle between the connected feature nodes is obtained based on the cosine similarity; Calculate the weight of the jth feature node connected to the i-th feature node , based on the weights of two connected feature nodes and The mean of , and calculate the angle similarity based on the angle between the connected feature nodes : ; in and is the user embedding vector of the connected feature node i and feature node j, is the angle between feature node i and feature node j; Adjust the initial weight of the connecting edge according to the angle similarity Get the connection edge adjustment weight : ; Adjust the weight of the connecting edge Assign connection edges and combine feature nodes to build a user capability graph.

[0008] As a preferred solution of the system for automatic job matching of the present invention, the job matching based on the generated job microtask map and user capability map and generating the job matching result refers to obtaining the job microtask map and the user capability map, forming a job microtask map matching list for all job microtask nodes, and calculating the cosine similarity between any feature node in the user capability map and all job microtask nodes in the job microtask map, and selecting the job microtask node with the highest cosine similarity as the matching node, and calculating the matching node matching degree: ; in Nodes in the job microtask graph and feature nodes in the user capability graph The matching degree between Nodes in the job microtask graph and feature nodes in the user capability graph The cosine similarity of Nodes in the job microtask graph The weight of Characteristic nodes in the user capability graph The weight of After obtaining the matching nodes, remove the job microtask nodes in the matching nodes from the job microtask graph matching list, select feature nodes from the user capability graph in turn, select matching nodes from the job microtask graph matching list, and record the matching degree of each pair of matching nodes. The matching degrees of all matching nodes are combined as the matching degree between the user and the job; Calculate the matching degree between users and different positions and sort them from high to low, and generate a person-position matching list as the position matching result.

[0009] As a preferred solution of the system for automatic matching of people and positions described in the present invention, wherein: the prediction of the user's future capability development and updating of the user's capability map, and the prediction of future matching results based on the updated user capability map refer to constructing a long-term and short-term LSTM model, inputting the collected user information into the long-term and short-term LSTM model to obtain future user information, and constructing a future user capability map based on the future user information to update the current user capability map, and calculating the matching degree between the user and different positions based on the user's future capability map, and generating future matching results.

[0010] As a preferred solution of the system for automatic matching of people and jobs described in the present invention, displaying the job matching results and future matching results means obtaining the user capability map and the future user capability map respectively after obtaining the job matching results and the future matching results, displaying the job matching results and the user capability map in correspondence, and marking and displaying the differences between the user capability map and the future user capability map.

[0011] As a preferred solution of the system for automatic matching of people and positions described in the present invention, the storage in the database refers to storing the user capability map, position matching results, future user capability map, future matching results and user information in the database, and classifying and storing them according to the user information. The database synchronizes the stored data to the cloud for backup.

[0012] Another object of the present invention is to provide a method for automatic matching of people and positions, which comprises: Obtain job information, analyze and cluster to generate job micro-task maps, and collect user information, analyze and generate user capability maps; Perform job matching based on the generated job micro-task map and user capability map, and generate job matching results; Predict the user's future capability development and update the user's capability map, and predict future matching results based on the updated user capability map; The job matching results and future matching results are displayed and stored in the database.

[0013] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of the above-mentioned method for automatic person-job matching when executing the computer program.

[0014] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for automatic person-job matching.

[0015] The beneficial effects of the present invention are as follows: the present invention collects job information to construct a job micro-task map, and collects user information to construct a user capability map, and calculates the matching degree between users and jobs based on the job micro-task map and the user capability map, thereby improving the accuracy and intuitiveness of job matching, improving matching efficiency and user experience, and at the same time predicting and constructing future user capability maps, matching future user jobs, and effectively helping users to select jobs and improve themselves. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0017] Figure 1 Schematic diagram of the structure of the system for automatic matching of people and jobs.

[0018] Figure 2 A flowchart of a method for automatically matching people to positions. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0020] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0021] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0022] Example 1 Reference Figure 1 , which is the first embodiment of the present invention, and which provides a system for automatic matching of people and positions, and the system for automatic matching of people and positions includes: S1, information analysis module, used to obtain job information, analyze and cluster to generate job micro-task maps, and collect user information, analyze and generate user capability maps; Specifically, obtaining job information, analyzing and clustering to generate job micro-task graphs refers to obtaining job information through the Internet, processing the job information using NLP technology, extracting keywords from the job information using the TD-IDF algorithm, and generating job keyword vectors based on the keywords and TD-IDF values. The job information includes job title, job description, work location, required skills, education requirements, experience requirements, etc.; NLP technology combined with the TF-IDF algorithm can accurately extract keywords from a large number of job descriptions, reduce the interference of irrelevant information, and improve the accuracy and representativeness of keyword vectors. The construction of keyword vectors provides a data basis for subsequent clustering, which helps to identify and divide the specific micro-tasks of the job. Through the K-means clustering algorithm, complex job responsibilities can be divided into several independent micro-tasks. This refinement and modularization process helps to better understand the core requirements of the job and provide a refined basis for subsequent job matching. Randomly select K initial cluster centers and use the K-means clustering algorithm to cluster the job keyword vectors; The K-means algorithm has high computational efficiency. It can quickly cluster large-scale job information and quickly generate job microtasks, which ensures that the system can efficiently process large amounts of data. Treat each cluster as a job micro-task, calculate the average distance between all job keyword vectors in each cluster and the cluster center as the weight of each job micro-task, and simultaneously calculate the distance between cluster centers of different clusters; Each job microtask is regarded as a node, and the two job microtasks with the shortest distance between cluster centers are regarded as connections to add connecting edges. The mean of the connected job microtask weights is calculated as the connecting edge weight to construct a job microtask graph.

[0023] Through the construction of the job microtask map, the system can clearly display the correlation between different microtasks, which is of great significance for understanding the complexity of job responsibilities. The job microtask map displays the correlation and weight distribution between microtasks in the form of a graph, which not only improves the intuitiveness of the matching system, but also provides users with clearer job analysis results. The construction of the graph structure enables the subsequent matching process to be realized through graph operations, improving the overall matching efficiency of the system.

[0024] Furthermore, collecting user information and analyzing and generating a user capability map refers to collecting user information through the Internet, using the Word2Vec model for word segmentation and word vector representation, and using the Word2Vec model to convert user information in text form into a structured data form, which is helpful for subsequent feature calculation and user map construction. The user information includes personal basic information, educational experience, professional experience, skills, professional preferences, etc. The user information is converted into a user embedding vector and mapped to a feature node in the map. For the user embedding vector of each feature node, its time node is queried according to the user information, and the time nodes of all feature nodes are integrated to form a time series. The feature node weight is calculated based on the time node of each feature node using time decay weighting: ; in is the weight of the i-th feature node, is the time node of the feature node, is the current time, is the time decay rate, set empirically, is the time node of the characteristic node in the time series and ≠ , G is the time series; Through time-decay weighted calculation, the weight of feature nodes can be adjusted according to time, so that the latest user information has a greater weight in the graph, thereby ensuring the dynamic and real-time nature of the graph. By taking time as a weighting factor, the changes in user capabilities over time can be captured, so that the graph can better reflect the dynamic development of user capabilities. Select the CART algorithm to build a decision tree, set the decision tree classification target as relevance, and use the training set to iteratively train the decision tree parameters; The user embedding vectors of two feature nodes are input into the decision tree to determine the correlation of the feature nodes. If the decision tree output is correlated, a connecting edge is generated between the feature nodes, the cosine similarity of the user embedding vectors in the connected feature nodes is calculated, and the angle between the connected feature nodes is obtained based on the cosine similarity; The application of decision trees enables the edges in the graph to more accurately reflect the correlation between feature nodes, ensuring that the connections between nodes in the graph are reasonable and consistent with the actual ability distribution of users. Through cosine similarity calculation and angle analysis, the system can more carefully evaluate the similarity between feature nodes and improve the correlation of edges. Calculate the weight of the jth feature node connected to the i-th feature node , based on the weights of two connected feature nodes and The mean of : And calculate the angle similarity based on the angle between the connected feature nodes : ; in and is the user embedding vector of the connected feature node i and feature node j, is the angle between feature node i and feature node j; The use of the angle similarity formula ensures that the weights of the edges in the graph are not only based on the initial calculation, but can also be adjusted continuously as the similarities between nodes increase, thereby more accurately showing the strength relationship between user capabilities; adjusting the initial weights of the connecting edges based on angle similarity Get the connection edge adjustment weight : ; Adjust the weight of the connecting edge Assign connection edges and combine feature nodes to build a user capability graph.

[0025] The system can adjust the weights of the connection edges in real time so that the user capability map can better reflect the actual user capability network structure. Through angle similarity, the present invention can further adjust the weights of the connection edges based on the angles of the feature nodes, thereby improving the accuracy and usability of the user capability map.

[0026] S2, a person-job matching module, which is used to match people with jobs based on the generated job micro-task map and user capability map, and generate job matching results; Specifically, matching people to positions is performed according to the generated position microtask graph and user capability graph, and generating a position matching result means obtaining the position microtask graph and the user capability graph, forming a position microtask graph matching list with all position microtask nodes, and calculating the cosine similarity between any feature node in the user capability graph and all position microtask nodes in the position microtask graph, and selecting the position microtask node with the highest cosine similarity as the matching node, and calculating the matching node matching degree: ; in Nodes in the job microtask graph and feature nodes in the user capability graph The matching degree between Nodes in the job microtask graph and feature nodes in the user capability graph The cosine similarity of Nodes in the job microtask graph The weight of Characteristic nodes in the user capability graph The weight of By combining the cosine similarity with the weight of each node, the matching degree not only reflects the similarity of the nodes, but also takes into account the importance of the nodes. In this way, even if a feature node has a high similarity with a job microtask node, if the weight is low, its overall matching degree will be adjusted accordingly to ensure a more accurate matching result. After obtaining the matching nodes, remove the job microtask nodes in the matching nodes from the job microtask graph matching list, select feature nodes from the user capability graph in turn, select matching nodes from the job microtask graph matching list, and record the matching degree of each pair of matching nodes. The matching degrees of all matching nodes are combined as the matching degree between the user and the job; The independence of each matching process allows the matching results to be gradually optimized, ensuring that the matching degree between users and positions is gradually improved. By comprehensively analyzing the matching degree of each pair of matching nodes, the overall fit between the user and the position can be accurately calculated to ensure the accuracy and comprehensiveness of the results. The matching value is not only used to evaluate a single position, but also as a comparison basis between multiple positions, thereby achieving the optimization and accurate recommendation of positions. Calculate the matching degree between users and different positions and sort them from high to low, and generate a person-position matching list as the position matching result.

[0027] By calculating the cosine similarity between user ability features and job microtasks, the system can ensure that the optimal matching node is selected in each matching process, maximize the fit between features, match user ability features with job microtasks one by one, and not miss any user ability feature nodes, so that the system can comprehensively evaluate all the user's skills and abilities.

[0028] S3, a development prediction module, used to predict the user's future capability development and update the user capability map, and predict future matching results based on the updated user capability map; Specifically, predicting the future capability development of users and updating the user capability map, predicting the future matching results based on the updated user capability map means building a long-term and short-term LSTM model, defining the model input as user information and the output as future user information, and training the long-term and short-term LSTM model parameters based on the training set and the loss function; The collected user information is input into the long-term and short-term LSTM model to obtain future user information, and based on the future user information, a future user capability map is constructed to update the current user capability map. Based on the user's future capability map, the matching degree between the user and different positions is calculated, and future matching results are generated.

[0029] By using the LSTM model to predict future user information and update the current capability map, the system can ensure that the user capability map is dynamic and forward-looking, reflecting the user's future development potential. The construction of the future user capability map provides more comprehensive data support for subsequent job matching, enabling the system to recommend jobs suitable for the user's future development, thereby improving the accuracy of matching.

[0030] Matching based on future capability maps can provide users with forward-looking career development suggestions. For example, if the user's future skill development meets the requirements of a high-paying position, the system can give priority to recommending that position and give the user corresponding career planning guidance. The display of future matching results allows users to intuitively see the various possibilities for their future career development. By providing clear matching rankings and detailed job information, users can quickly understand which positions are more in line with their career goals. The system not only displays future matching results, but also provides users with specific improvement suggestions. For example, when users see the gap between the requirements of a future position and their own future skill development, they can conduct targeted training and learning based on the system's suggestions, thereby better improving their professional competitiveness.

[0031] S4, a display storage module, used to display the job matching results and future matching results, and store them in the database; Specifically, displaying the job matching results and the future matching results means obtaining the user capability map and the future user capability map respectively after obtaining the job matching results and the future matching results, displaying the job matching results and the user capability map in correspondence, and marking and displaying the differences between the user capability map and the future user capability map.

[0032] By displaying the correspondence between the future capability map and the job matching results, users can see possible future development paths and understand which skills or experiences need to be focused on in their future careers. This helps users develop long-term career plans. By marking the differences between the user's capability map and the future capability map, users can intuitively understand the changing trends in their capability development and thus better understand their own growth process.

[0033] Furthermore, storing in a database means storing user capability maps, job matching results, future user capability maps, future matching results and user information in the database, and storing them in categories according to user information. The database synchronizes the stored data to the cloud for backup.

[0034] Example 2 Reference Figure 2 , which is a second embodiment of the present invention, and which is different from the previous embodiment, provides a method for automatic matching of people and positions, which includes: Obtain job information, analyze and cluster to generate job micro-task maps, and collect user information, analyze and generate user capability maps; Perform job matching based on the generated job micro-task map and user capability map, and generate job matching results; Predict the user's future capability development and update the user's capability map, and predict future matching results based on the updated user capability map; The job matching results and future matching results are displayed and stored in the database.

[0035] If the functions are implemented in the form of software functional units and sold or used as independent products, they 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 to enable 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 described in various embodiments 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., which can store program codes.

[0036] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0037] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0038] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit with a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit with a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0039] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A system for automatic matching of people and positions, characterized by: include, The information analysis module is used to obtain job information, analyze and cluster to generate job micro-task maps, and collect user information to analyze and generate user capability maps; The person-job matching module is used to match people with jobs based on the generated job micro-task map and user capability map, and generate job matching results; The development prediction module is used to predict the user's future capability development and update the user's capability map, and predict future matching results based on the updated user capability map; The display and storage module is used to display the job matching results and future matching results and store them in the database; The obtaining of job information and performing analysis and clustering to generate a job microtask graph refers to obtaining job information through the Internet, processing the job information using NLP technology, extracting keywords from the job information using the TD-IDF algorithm, and generating a job keyword vector based on the keywords and TD-IDF values; Randomly select K initial cluster centers and use the K-means clustering algorithm to cluster the job keyword vectors; Treat each cluster as a job micro-task, calculate the average distance between all job keyword vectors in each cluster and the cluster center as the weight of each job micro-task, and simultaneously calculate the distance between cluster centers of different clusters; Each job microtask is regarded as a node, and the two job microtasks with the shortest distance between cluster centers are regarded as connections to add connecting edges. The mean of the connected job microtask weights is calculated as the connecting edge weight to construct a job microtask graph.

2. The system for automatic matching of people and positions as claimed in claim 1, characterized in that: The collecting of user information and analyzing and generating a user capability map refers to collecting user information through the network, using the Word2Vec model for word segmentation and word vector representation, converting the user information into a user embedding vector and mapping it to a feature node in the map, querying the time node of each feature node according to the user information, integrating the time nodes of all feature nodes to form a time series, and calculating the feature node weight based on the time node of each feature node using time decay weighting: ； in is the weight of the i-th feature node, is the time node of the feature node, is the current time, is the time decay rate, is the time node of the characteristic node in the time series and ≠ , G is the time series; Select the CART algorithm to build a decision tree, and set the classification target of the decision tree to relevance; The user embedding vectors of two feature nodes are input into the decision tree to determine the correlation of the feature nodes. If the decision tree output is correlated, a connecting edge is generated between the feature nodes, the cosine similarity of the user embedding vectors in the connected feature nodes is calculated, and the angle between the connected feature nodes is obtained based on the cosine similarity; Calculate the weight of the jth feature node connected to the i-th feature node , based on the weights of two connected feature nodes and The mean of , and calculate the angle similarity based on the angle between the connected feature nodes : ; in and is the user embedding vector of the connected feature node i and feature node j, is the angle between feature node i and feature node j; Adjust the initial weight of the connecting edge according to the angle similarity Get the connection edge adjustment weight : ; Adjust the weight of the connecting edge Assign connection edges and combine feature nodes to build a user capability graph.

3. The system for automatic matching of people and positions as claimed in claim 2, characterized in that: The method of matching people to positions based on the generated position microtask map and user capability map and generating a position matching result refers to obtaining the position microtask map and the user capability map, forming a position microtask map matching list with all position microtask nodes, and calculating the cosine similarity between any feature node in the user capability map and all position microtask nodes in the position microtask map, and selecting the position microtask node with the highest cosine similarity as the matching node, and calculating the matching node matching degree: ； in Nodes in the job microtask graph and feature nodes in the user capability graph The matching degree between Nodes in the job microtask graph and feature nodes in the user capability graph The cosine similarity of Nodes in the job microtask graph The weight of Characteristic nodes in the user capability graph The weight of After obtaining the matching nodes, remove the job microtask nodes in the matching nodes from the job microtask graph matching list, select feature nodes from the user capability graph in turn, select matching nodes from the job microtask graph matching list, and record the matching degree of each pair of matching nodes. The matching degrees of all matching nodes are combined as the matching degree between the user and the job; Calculate the matching degree between users and different positions and sort them from high to low, and generate a person-position matching list as the position matching result.

4. The system for automatic matching of people and positions as claimed in claim 3, characterized in that: The predicting of the user's future capability development and updating the user capability map, and predicting future matching results based on the updated user capability map refers to constructing a long-term and short-term LSTM model to input the collected user information into the long-term and short-term LSTM model to obtain future user information, and constructing a future user capability map based on the future user information to update the current user capability map, and calculating the matching degree between the user and different positions based on the user's future capability map, and generating future matching results.

5. The system for automatic matching of people and positions as claimed in claim 4, characterized in that: Displaying the job matching results and the future matching results means obtaining the user capability map and the future user capability map respectively after obtaining the job matching results and the future matching results, displaying the job matching results and the user capability map in correspondence, and marking and displaying the differences between the user capability map and the future user capability map.

6. The system for automatic matching of people and positions as claimed in claim 5, characterized in that: The storage in the database refers to storing the user capability map, job matching results, future user capability map, future matching results and user information in the database, and storing them in categories according to the user information. The database will synchronize the stored data to the cloud for backup.

7. A method for automatic job matching based on the system for automatic job matching according to any one of claims 1 to 6, characterized in that: include, Obtain job information, analyze and cluster to generate job micro-task maps, and collect user information, analyze and generate user capability maps; Perform job matching based on the generated job micro-task map and user capability map, and generate job matching results; Predict the user's future capability development and update the user's capability map, and predict future matching results based on the updated user capability map; The job matching results and future matching results are displayed and stored in the database.

Images