A method and system for intelligent recommendation of precise matching between people and jobs

Abstract

The present invention discloses a method and system for intelligent recommendation of precise matching of people and jobs, which relates to the field of intelligent recommendation technology, including real-time collection of multi-source data of job seekers and recruitment positions, and data cleaning, classification and standardization processing, and output of unstructured text data; extraction of emotional tendencies of job seekers through sentiment analysis methods, and construction of emotional portrait vectors of job seekers; utilization of deep transfer learning to transfer knowledge from a source domain to a target domain, optimize the matching accuracy between jobs and job seekers, and optimize job recommendations based on the transferred knowledge; generation of a personalized job recommendation list based on the emotional needs of job seekers and the cultural adaptability of jobs, and prioritizing the recommendation of jobs with the highest matching degree with job seekers' needs. The present invention utilizes a deep transfer learning framework to transfer knowledge from a source domain to a target domain, and optimize the matching accuracy between jobs and job seekers.

Description

Technical Field

[0001] The present invention relates to the field of intelligent recommendation technology, and in particular to a method and system for intelligent recommendation of precise person-job matching. Background Art

[0002] In recent years, with the development of artificial intelligence (AI) technologies, particularly advances in deep learning, natural language processing (NLP), and transfer learning, intelligent recommendation systems have gradually emerged in the recruitment field. Traditional job matching methods rely primarily on manual screening, which is inefficient and significantly influenced by subjective factors. Existing technologies can provide preliminary job recommendations by analyzing basic data on job seekers and job positions. However, these methods often overlook the matching of job seekers' emotional needs with job culture and are unable to dynamically adapt to the complex emotional and behavioral patterns between job seekers and positions. With the application of big data, job recommendation methods based on deep learning have gained widespread application. However, most systems rely solely on simple similarity calculations for matching, lacking high-precision recommendations and personalized adjustments, and struggle to cope with the challenges posed by data dimensionality and information asymmetry.

[0003] Existing job matching technologies generally fail to fully consider job seekers' individual needs, emotional tendencies, and job-culture compatibility, resulting in inaccurate and inefficient recommendations. Therefore, how to integrate job seekers' multi-dimensional characteristics, particularly their emotional needs, job-culture compatibility, and behavioral patterns, to make accurate job recommendations has become a pressing technical challenge. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method for intelligent recommendation of precise matching between people and jobs to solve the problem of how to accurately match job seekers with jobs, especially how to optimize job recommendations based on multi-source data and emotional needs.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for intelligently recommending precise job matching, which includes collecting multi-source data of job seekers and job openings in real time, performing data cleaning, classification, and standardization processing, and outputting unstructured text data;

[0008] Extract the emotional tendencies of job seekers through sentiment analysis methods and construct the emotional portrait vector of job seekers;

[0009] Using deep transfer learning, we transfer knowledge from the source domain to the target domain, optimize the matching accuracy between positions and job seekers, and optimize job recommendations based on the transferred knowledge.

[0010] Through a multi-dimensional feature fusion algorithm, the unstructured text data of job seekers is integrated with the emotional profile vector of job seekers to calculate the similarity between job seekers and positions and obtain a preliminary matching score.

[0011] Combining the emotional needs of job seekers and the cultural fit of positions, a personalized job recommendation list is generated, with priority given to positions that best match the job seekers' needs.

[0012] As a preferred solution of the method for intelligent recommendation of precise matching of people and jobs described in the present invention, the multi-source data of job seekers and recruitment positions include personal characteristic data, job information data, emotional demand data, job cultural adaptability data and job recommendation feedback data.

[0013] As a preferred solution of the method for intelligent recommendation of precise matching of people and jobs described in the present invention, the specific steps of performing data cleaning, classification and standardization and outputting unstructured text data are as follows:

[0014] Perform missing value checks, duplicate data processing, and outlier handling on multi-source data of job seekers and job openings;

[0015] Perform feature classification and text classification on the personal feature data and job information data in the multi-source data of job seekers and recruitment positions, and convert them into standardized labels;

[0016] Normalize the numerical data in the processed multi-source data of job seekers and job openings, and vectorize the text data using a pre-trained language model;

[0017] Output the cleaned, categorized, and standardized data into unstructured text format.

[0018] As a preferred solution of the method for intelligent recommendation of precise matching of people and jobs described in the present invention, wherein: the emotional tendency of job seekers is extracted by sentiment analysis method, and the emotional portrait vector of job seekers is constructed. The specific steps are as follows:

[0019] Segment and remove stop words from the job applicants' unstructured text data, and use NLP tools for part-of-speech tagging;

[0020] Fine-tune the unstructured text data of job seekers based on the BERT pre-trained model, classify the text into sentiment labels through sentiment classification, and predict the sentiment intensity value of each text segment;

[0021] The emotion intensity value is converted into a numerical vector and combined with the job applicant's personal characteristic data to form an emotion portrait vector.

[0022] As a preferred solution of the method for intelligent recommendation of precise matching of people and jobs described in the present invention, the method utilizes deep transfer learning to transfer knowledge from the source domain to the target domain, optimizes the matching accuracy between jobs and job seekers, and optimizes job recommendations based on the transferred knowledge. The specific steps are as follows:

[0023] Extract features from source domain data through a multi-layer neural network to generate a deep feature vector representation of the source domain;

[0024] Transfer the deep feature vector representation to the target domain, build an adaptive transfer learning framework, and transfer knowledge layer by layer by fine-tuning parameters;

[0025] In each layer, a nonlinear mapping function is used to fuse high-order features, thereby preserving the multi-scale information between the source and target domains;

[0026] Adaptive weighting method is used to align the multi-layer features of source and target domains. During the feature alignment process, the loss function is used for optimization.

[0027] The multi-dimensional features of job seekers and positions are integrated through Gaussian kernel function to build a nonlinear fusion mechanism;

[0028] A Q-learning network is constructed based on reinforcement learning to optimize job recommendations based on personal characteristic data, job information data, emotional demand data, job culture fit data, and job recommendation feedback data.

[0029] As a preferred solution of the method for intelligent recommendation of precise matching of people and jobs described in the present invention, wherein: the unstructured text data of job seekers is fused with the emotional profile of job seekers through a multi-dimensional feature fusion algorithm, the similarity between job seekers and jobs is calculated, and a preliminary matching score is obtained. The specific steps are as follows:

[0030] The BERT model is used to extract features from the unstructured text data of job seekers and generate a feature vector of the job seeker text.

[0031] Convert the predicted sentiment intensity value of each text in the sentiment portrait into a sentiment numerical vector;

[0032] Extracting job seekers' behavioral data from personal feature data and job recommendation feedback data, and processing it based on the LSTM time series model to capture the job seekers' behavioral trends and obtain their behavioral patterns;

[0033] Use multi-layer perceptron and deep neural network to fuse the text feature vector, sentiment value vector and behavior pattern of job applicants;

[0034] During the feature fusion and alignment process, the weights of different features are dynamically adjusted to align and standardize features from different data sources;

[0035] The fully connected layers integrate features of different modalities layer by layer. Each layer of the neural network further optimizes the relationship between different features through weighting, activation functions, and nonlinear mapping to generate a comprehensive feature vector for job seekers.

[0036] Generative adversarial network matching optimization is used. The generator accepts the comprehensive feature vector of the job seeker, the job information data and the job culture compatibility data, and generates a matching feature vector.

[0037] Based on historical job recommendation feedback data and manually labeled job matching data, it is trained through deep learning methods to output true matching feature vectors;

[0038] The discriminator compares the generated matching feature vector with the real matching feature vector to evaluate the match between the job seeker and the position, and outputs a matching score.

[0039] During generative adversarial training, the generator and the discriminator continuously optimize the generation process of matching feature vectors through mutual competition;

[0040] After generating adversarial training to obtain the matching feature vectors between job seekers and positions, the cosine similarity is used to calculate the matching degree between job seekers and positions;

[0041] The matching degree between the job seeker and the position is used as the preliminary matching score.

[0042] As a preferred solution of the method for intelligent recommendation of precise job matching according to the present invention, the method combines the emotional needs of job seekers and the cultural compatibility of jobs to generate a personalized job recommendation list, and prioritizes the jobs that have the highest matching degree with the job seekers' needs. The specific steps are as follows:

[0043] Standardize and align job seekers’ emotional needs data with job culture fit data;

[0044] Based on the matching scores, use the Top-K recommendation strategy to select the top K positions with the highest matching scores as candidate recommended positions;

[0045] Combining multi-source data of job seekers and recruitment positions, the preliminary recommendation list is sorted again, giving priority to displaying positions that have the highest match with the job seekers' emotional needs data and the cultural adaptability data of the positions, and outputting a personalized job recommendation list.

[0046] In a second aspect, the present invention provides a system for intelligent recommendation of precise matching of people and jobs, comprising a data collection module, an emotion profiling module, a knowledge transfer module, a feature fusion module, and a job recommendation module;

[0047] The data collection module is used to collect multi-source data of job seekers and recruitment positions in real time, and perform data cleaning, classification and standardization processing to output unstructured text data;

[0048] The emotional portrait module is used to extract the emotional tendencies of job seekers through emotional analysis methods and construct the emotional portrait vector of the job seekers;

[0049] The knowledge transfer module is used to transfer knowledge from the source domain to the target domain using deep transfer learning, optimize the matching accuracy between positions and job seekers, and optimize job recommendations based on the transferred knowledge;

[0050] The feature fusion module is used to fuse the job seeker's unstructured text data with the job seeker's emotional portrait vector through a multi-dimensional feature fusion algorithm, calculate the similarity between the job seeker and the position, and obtain a preliminary matching score;

[0051] The job recommendation module is used to generate a personalized job recommendation list based on the job seeker's emotional needs and the cultural compatibility of the job, and give priority to recommending jobs that have the highest degree of match with the job seeker's needs.

[0052] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the method for intelligent recommendation of precise matching of people and jobs as described in the first aspect of the present invention is implemented.

[0053] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the method for intelligent recommendation of precise matching of people and jobs as described in the first aspect of the present invention.

[0054] The beneficial effects of the present invention are as follows: the present invention pre-processes multi-source data by adopting data cleaning, classification and standardization processing to ensure the quality and consistency of the data; extracts the emotional tendencies of job seekers through sentiment analysis, and constructs emotional portraits based on their personal characteristics, which can accurately capture the emotional needs of job seekers; utilizes the deep transfer learning framework to transfer the knowledge of the source field to the target field, optimizes the matching accuracy between positions and job seekers, and at the same time improves the effect of feature fusion through adaptive weighted feature alignment. Furthermore, through a multi-dimensional feature fusion algorithm, multiple features such as text features, emotional portraits and behavioral patterns of job seekers are integrated to calculate the similarity between job seekers and positions; the generative adversarial network improves the matching accuracy and generates a personalized job recommendation list by continuously optimizing the matching feature vectors, ensuring that the recommendation results are more in line with the emotional needs of job seekers and the cultural compatibility of positions, effectively improving the matching accuracy and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0056] Figure 1 This is a flowchart of the method for intelligent recommendation of precise matching of people and jobs in Example 1.

[0057] Figure 2 This is a module diagram of the system for intelligent recommendation of precise matching of people and jobs in Example 1. DETAILED DESCRIPTION

[0058] 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 with reference to the accompanying drawings.

[0059] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. 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.

[0060] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0061] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a method for intelligent recommendation of precise person-job matching, including the following steps:

[0062] S1. Collect multi-source data of job seekers and recruitment positions in real time, clean, classify and standardize the data, and output unstructured text data.

[0063] Furthermore, the multi-source data of job seekers and recruitment positions include personal characteristics data, job information data, emotional needs data, job culture adaptability data, and job recommendation feedback data;

[0064] Perform missing value checks, duplicate data processing, and outlier handling on multi-source data of job seekers and job openings;

[0065] Among them, missing values ​​can be filled by reasonable inference (such as using the mean, mode or industry standard). If it cannot be filled, the data will be marked and ignored.

[0066] Specifically, for duplicate data processing, duplicate records are removed based on the applicant's unique identifier (such as mobile phone number) to retain the most complete data. For job information, job IDs and descriptions are used to remove duplicate positions. For outlier processing, outliers in personal characteristic data (such as age and work experience) and job data (such as salary range) are checked. If the data falls outside a reasonable range, the mean or median is used to fill the gap, or non-compliant data is deleted.

[0067] Perform feature classification and text classification on the personal feature data and job information data in the multi-source data of job seekers and recruitment positions, and convert them into standardized labels for job recommendation and matching;

[0068] Specifically, we categorize applicants' education and experience information (e.g., "bachelor's degree," "master's degree") from multi-source data on job seekers and job openings, and standardize job openings by industry (e.g., "software development," "data analysis") to facilitate subsequent matching. We also use NLP technology to extract keywords and classify text from job descriptions and applicant profiles, converting them into standardized tags (e.g., "Python," "Product Manager") for job recommendations and matching.

[0069] Standardize the numerical data in the processed multi-source data of job seekers and recruitment positions (such as the applicant's age, work experience, salary expectations, and other numerical data) to ensure the unified dimension of different features and improve the accuracy of subsequent model processing.

[0070] At the same time, use pre-trained language models (such as BERT or Word2Vec models) to vectorize the text data, improve the consistency and comparability of the data, and provide support for subsequent analysis and matching;

[0071] Output the data that has been cleaned, classified, and standardized into an unstructured text format, including core data such as the personal characteristics, emotional needs of the job seeker, and job information, providing high-quality input for sentiment analysis and personalized job recommendations.

[0072] S2. Extract the emotional tendency of the job seeker through sentiment analysis methods and construct the emotional portrait of the job seeker.

[0073] Furthermore, perform word segmentation and stop word removal on the unstructured text data of the job seeker, and use NLP tools such as jieba for word tagging (such as nouns, verbs, etc.);

[0074] Among them, the purpose of Chinese word segmentation is to split continuous text into words or phrases. Stop word removal refers to removing common but meaningless words (such as "de", "shi", "zai", etc.), and filtering using a predefined stop word list.

[0075] Fine-tune the unstructured text data of the job seeker based on the BERT pre-trained model, divide the emotional labels of the text through sentiment classification, and predict the emotional intensity value of each text segment;

[0076] It should be noted that BERT is a pre-trained language model based on Transformer, which can capture context information and is widely used in tasks such as text classification and sentiment analysis. BERT considers the left and right contexts of the sentence simultaneously through a bidirectional encoder, and can more accurately understand the emotional tendency in the text.

[0077] Specifically, the fine-tuning process is as follows: use the job seeker text data set with emotional labels to fine-tune the BERT model. A commonly used fine-tuning method is to optimize through the cross-entropy loss function;

[0078] The expression of the loss function L is:

[0079]

[0080] Among them, N represents the total number of samples, c represents the index variable of the sample, y

[0081] , ,

[0080] , , c , , , , , ,

[0077] ,

[0076] ,

[0075] , c , ,

[0074] , ,

[0079] ,

[0078] represents the emotional label of the c-th sample (such as positive, negative, and neutral), and k(y c ) represents the prediction probability of the BERT pre-trained model for the c-th sample belonging to a certain emotional label;

[0081] After fine-tuning, BERT will perform sentiment classification on each job applicant's text and output a sentiment label. At the same time, it will also predict a sentiment intensity value (between 0 and 1) for each text segment, indicating the intensity of the sentiment.

[0082] Convert the emotion intensity value into a numerical vector and combine it with the job applicant's personal characteristic data to form an emotion portrait vector;

[0083] The specific splicing process is as follows: vectorize the emotional labels (for example, "positive" is converted to 1) and emotional intensity values ​​(such as 0.85) obtained from sentiment analysis; standardize or encode the background feature data of job applicants (such as education, work experience, etc.); splice the emotional labels, emotional intensity values ​​and the background features of job applicants into a large vector, namely the emotional portrait vector; the spliced ​​large vector will represent the combination of the job applicant's emotional tendency and personal background characteristics.

[0084] It should be noted that the resulting emotional profile vector consists of two components: emotional tendency and intensity, and the applicant's personal background characteristics. Furthermore, the applicant's emotional profile vector not only reflects the applicant's emotional needs (such as positive or negative emotional tendencies) but also includes their personal background information, providing multi-dimensional support for subsequent job matching and recommendations.

[0085] S3. Use deep transfer learning to transfer knowledge from the source domain to the target domain, optimize the matching accuracy between positions and job seekers, and optimize job recommendations based on the transferred knowledge.

[0086] Furthermore, a multi-layer neural network is used to extract features from the source domain data and generate a deep feature vector representation of the source domain;

[0087] Transfer the deep feature vector representation to the target domain, build an adaptive transfer learning framework, and transfer knowledge layer by layer by fine-tuning parameters;

[0088] The source domain includes job seekers and job information from historical data sets, existing recruitment platforms, or other related fields. These data have been fully annotated and organized, covering the following aspects: personal characteristics of job seekers (such as education, work experience, skills, etc.), job information (such as job requirements, job responsibilities, salary range, etc.), emotional needs (such as emotional inclinations towards the work environment, emotional needs for job matching, etc.), job culture fit data (such as company culture, team atmosphere, etc.), and historical job recommendation feedback data. The data in the source domain is used to analyze factors such as the personal characteristics, job requirements, and emotional needs of job seekers, and on this basis, generate preliminary job matching rules, which can then be applied to the target domain.

[0089] The target domain refers to actual job seeker and job position data in a specific application scenario, typically consisting of a new dataset of job seekers and job postings. It should be noted that data in the target domain may be scarce or less reliant on annotated and historical data, necessitating optimization through knowledge transfer from the source domain. The target domain data includes job seekers' personal information, their emotional tendencies (based on the emotional demands of the target position), and various job position information. Through transfer learning, combined with knowledge from the source domain, precise job matching and recommendation optimization are achieved.

[0090] In each layer, a nonlinear mapping function is used to fuse high-order features, thereby preserving the multi-scale information between the source and target domains;

[0091] Specifically, at each layer of multi-level transfer learning, the features of the source domain and the target domain are processed through a nonlinear mapping function. The source domain feature vector and the target domain feature vector of each layer are processed through a nonlinear mapping function (such as the self-attention mechanism of a convolutional neural network or a transformer model) to generate a high-order feature vector of the source domain. These high-order feature vectors are compared with the features of the target domain and aligned through a nonlinear function to ensure that the features of the source and target domains are more consistent. The weighting function is used to adjust the mapping importance of the features of each layer to ensure that multi-scale information can be effectively transmitted and fused at each layer. Through this alternating calculation and feature fusion, the fused feature vector of each layer is finally used for subsequent deep network training, so that the multi-scale information of the source and target domains can be strengthened and the matching accuracy can be improved.

[0092] Adaptive weighting method is used to align the multi-layer features of source and target domains. During the feature alignment process, the loss function is used for optimization.

[0093] The loss function is expressed as:

[0094]

[0095] in, and are the b-th layer feature representations of the source domain and the target domain respectively, n represents the total number of feature layers, w b Represents the weighting coefficient of the b-th layer feature;

[0096] Preferably, this loss function enhances the migration capability of the deep transfer learning framework by minimizing the distance between the source domain and the target domain features, and ensures the effective transfer of knowledge.

[0097] Furthermore, after multi-level transfer learning, the features of the source and target domains are nonlinearly fused to further improve the accuracy of matching jobs and applicants. Traditional feature fusion methods often use simple weighted summation or linear transformations, but this method uses adaptive nonlinear mapping functions to achieve higher-order feature fusion, breaking through the limitations of linear mapping.

[0098] Specifically, the multi-dimensional features of job seekers and positions are fused through the Gaussian kernel function to construct a nonlinear fusion mechanism, which is expressed as:

[0099]

[0100] Among them, F(p,j) is the fusion feature of job seeker p and job j, p i represents the i-th feature of the job seeker, j i represents the i-th feature of the position, i represents the index variable of the feature, m represents the total number of feature dimensions, γ i is the weight coefficient for each feature, is the standard deviation of the Gaussian kernel function, φ(p i ,j i ) is the adaptive mapping function between features;

[0101] Preferably, the nonlinear fusion mechanism can effectively capture the complex nonlinear relationship between job seekers and positions, avoid the linear assumption limitations of traditional methods, and significantly improve the matching accuracy.

[0102] Build a Q-learning network based on reinforcement learning to optimize job recommendations based on personal characteristic data, job information data, emotional demand data, job culture fit data, and job recommendation feedback data;

[0103] Dynamic matching Q value update formula, the expression is:

[0104] Q(s,a)=Q(s,a)+α(r+μmaxQ(s',a')-Q(s,a));

[0105] Where Q(s,a) is the Q value of taking action a in state s, α is the learning rate, μ is the discount factor, r is the immediate reward, s' represents the next state, and a' represents the next action;

[0106] Preferably, the nonlinear fusion mechanism continuously adjusts the recommendation strategy through reinforcement learning, optimizes the matching process based on the actual feedback of job seekers, and thus improves the accuracy of matching.

[0107] It should be noted that the combination of a multi-level transfer learning framework, nonlinear feature fusion, reinforcement learning, and high-order mapping functions significantly improves the accuracy of matching job seekers with jobs. This allows for processing more complex feature interactions and achieving precise, personalized job recommendations.

[0108] S4. Through the multi-dimensional feature fusion algorithm, the unstructured text data of the job seeker is integrated with the emotional portrait of the job seeker, the similarity between the job seeker and the position is calculated, and a preliminary matching score is obtained.

[0109] Furthermore, the BERT model is used to extract features from the unstructured text data of job seekers and generate a feature vector of the job seeker text;

[0110] Among them, the job applicant text feature vector includes the job applicant's language characteristics, skill description, work experience and other information.

[0111] Convert the predicted sentiment intensity value of each text in the sentiment portrait into a sentiment numerical vector;

[0112] The job seeker's behavioral data (such as browsing history, application records, interview feedback, etc.) is extracted from personal characteristic data and job recommendation feedback data, and processed based on the LSTM time series model to capture the job seeker's behavioral change trends and obtain the job seeker's behavioral patterns. This process can reveal information such as the job seeker's changes in interests and job search preferences.

[0113] Advantageously, the LSTM time series model captures the changing trends of job seekers' behaviors, not just relying on static personal information but also incorporating the dynamic factor of behavioral data. This enables the present invention to overcome the shortcomings of traditional methods in analyzing job seekers' dynamic behaviors and accurately reflect the changing trends of job seekers over time.

[0114] Use multi-layer perceptron and deep neural network to fuse the text feature vector, sentiment value vector and behavior pattern of job applicants;

[0115] During the feature fusion and alignment process, the weights of different features are dynamically adjusted, and features from different data sources are aligned and standardized to ensure that the contribution of each feature can be reasonably measured.

[0116] The fully connected layers integrate features of different modalities layer by layer. Each layer of the neural network further optimizes the relationship between different features through weighting, activation functions, and nonlinear mapping to generate a comprehensive feature vector for job seekers.

[0117] Specifically, the text feature vector, sentiment numerical vector and behavior pattern data are input into the neural network. During this process, all features will be standardized first to ensure that they are within the same dimensional range to avoid excessive influence of a certain feature on training. Then, these standardized features are sent to a multi-layer fully connected neural network (MLP), where linear transformation is performed through a weighted matrix in each layer, and nonlinear mapping is introduced through activation functions (such as ReLU) to improve the fitting ability and expression ability of the network. In addition, to avoid overfitting, the network will adopt regularization methods (such as Dropout). Through multi-layer weighting, activation and nonlinear mapping, a comprehensive feature vector is finally obtained. This comprehensive feature vector integrates data from different modalities and fully captures the complex relationship between the features.

[0118] Generative adversarial network matching optimization is used. The generator accepts the comprehensive feature vector of the job seeker, the job information data and the job culture compatibility data, and generates a matching feature vector.

[0119] Among them, the matching feature vector represents the potential matching degree between job seekers and positions.

[0120] Ideally, through generative adversarial training, the game between the generator and the discriminator can automatically optimize the matching feature vectors, improving the accuracy of the matching results. This not only solves the data scarcity and modeling difficulties in traditional recommendation systems, but also effectively improves the intelligence level of recommendations.

[0121] Based on historical job recommendation feedback data and manually labeled job matching data, it is trained through deep learning methods to output true matching feature vectors;

[0122] Among them, the true matching feature vector will be regarded as the reference standard to evaluate the accuracy of the matching feature vector output by the generator.

[0123] The discriminator compares the generated matching feature vector with the real matching feature vector to evaluate the match between the job seeker and the position, and outputs a matching score.

[0124] Specifically, the generator generates a matching feature vector based on the candidate's comprehensive feature vector and job information data. Simultaneously, a discriminator model is trained based on historical job recommendation feedback and manually annotated job matching data. The discriminator receives two inputs: the matching feature vector output by the generator and a true matching feature vector based on historical data or manual annotations. The discriminator calculates the similarity between these two matching feature vectors, typically using metrics such as cosine similarity, Euclidean distance, or Manhattan distance. This allows the discriminator to determine whether the generated matching feature vector is close to the true matching feature vector, thereby assessing the match between the candidate and the job. The closer the generated matching feature vector is to the true matching feature vector, the higher the matching score output by the discriminator; otherwise, the score is lower. During adversarial training, the discriminator aims to distinguish the generated matching feature vector from the true matching feature vector as accurately as possible, while the generator strives to generate matching vectors closer to the true features to optimize matching accuracy. Through this game-playing process, the generator and discriminator evolve together, thereby improving the final job matching accuracy.

[0125] It should be noted that the relationship between the generated matching feature vector and the true matching feature vector is essentially the contrast relationship in generative adversarial training. During training, the generator generates a matching feature vector based on the input data, while the discriminator compares the generated matching feature vector with the true matching feature vector to evaluate the similarity between the two. The discriminator's goal is to distinguish the generated vector from the true vector, ensuring that the generator's output is closer to the true value.

[0126] During generative adversarial training, the generator and the discriminator continuously optimize the generation process of matching feature vectors through mutual competition;

[0127] After generating adversarial training to obtain the matching feature vectors between job seekers and positions, the cosine similarity is used to calculate the matching degree between job seekers and positions;

[0128] Furthermore, once the generator obtains the matching feature vectors of job seekers and positions through generative adversarial training, it is necessary to calculate the matching degree between job seekers and positions through cosine similarity.

[0129] Specifically, the matching feature vectors are generated by integrating the applicant's text features, emotional profile, behavioral patterns, and relevant information about the position, and cosine similarity is used to measure the similarity between these feature vectors. The calculation formula for cosine similarity is:

[0130]

[0131] Where C(A,B) represents the cosine similarity between vectors A and B, A and B represent the feature vectors of job seekers and positions respectively, ||A|| and ||B|| represent the Euclidean norm of vectors A and B respectively;

[0132] It should be noted that the value of cosine similarity ranges from -1 to 1. When the similarity is close to 1, it means that the match between the job seeker and the position is high; when it is close to -1, it means that the match is low; when it is close to 0, it means that the match between the two is weak.

[0133] The matching degree between the job seeker and the position is used as the preliminary matching score.

[0134] S5. Generate a personalized job recommendation list based on the emotional needs of job seekers and the cultural fit of the positions, giving priority to positions that best match the job seekers' needs.

[0135] Going a step further, the emotional needs data of job seekers is standardized and aligned with the job culture fit data;

[0136] Based on the matching scores, use the Top-K recommendation strategy to select the top K positions with the highest matching scores as candidate recommended positions;

[0137] Among them, the Top-K recommendation strategy is derived from a common practice in information retrieval and recommendation systems, which aims to select the top K items from a large number of candidate items. For the job recommendation in the present invention, the setting of the K value can be dynamically adjusted according to the specific application scenario, such as job seeker preferences, the number of positions, etc., so the rationality of the K value is closely related to the specific scenario requirements. By sorting the matching scores, the K value limits the length of the recommendation list, which not only improves the recommendation efficiency, but also avoids excessive redundancy in the recommendation results, helping job seekers quickly find the most suitable position.

[0138] Combining multi-source data on job seekers and job openings, the initial recommendation list is re-sorted, prioritizing the positions that have the highest match with emotional demand data and job culture compatibility data, and outputting a personalized job recommendation list;

[0139] Specifically, during the secondary ranking process, the positions in the initial recommendation list are first sorted based on their skill match scores with the job seeker, and the top K positions are selected as candidate positions. Next, these candidate positions are re-ranked, first assessing their cultural fit by calculating the match between the job seeker's emotional needs data and the job's cultural fit data. This process quantifies the job seeker's preferences for non-technical requirements, such as work environment and team atmosphere, and compares them with the job's cultural characteristics to obtain a cultural fit score for each position. The cultural fit score is then combined with the original skill match score to calculate a total fit score for each position. Finally, the candidate positions are re-ranked based on the total fit score, prioritizing those that best match the job seeker's emotional needs and cultural fit. This results in a final, personalized list of recommended positions, ensuring that the recommendations meet not only the job seeker's technical needs but also their cultural and emotional expectations, providing the most suitable position options.

[0140] The best approach is to combine multiple dimensions of information, such as the candidate's emotional needs and cultural compatibility, to generate personalized job recommendations that not only reflect technical ability but also take into account the candidate's emotional and cultural needs. This cross-dimensional, multi-faceted approach makes the recommendation system more intelligent and personalized.

[0141] This embodiment also provides a system for intelligent recommendation of precise matching between people and jobs, including: a data collection module, a sentiment portrait module, a knowledge transfer module, a feature fusion module and a job recommendation module; the data collection module is used to collect multi-source data of job seekers and recruitment jobs in real time, and perform data cleaning, classification and standardization processing to output unstructured text data; the sentiment portrait module is used to extract the emotional tendencies of job seekers through sentiment analysis methods and construct the emotional portrait vector of job seekers; the knowledge transfer module is used to use deep transfer learning to transfer knowledge from the source field to the target field, optimize the matching accuracy between jobs and job seekers, and optimize job recommendations based on the transferred knowledge; the feature fusion module is used to fuse the unstructured text data of job seekers with the emotional portrait vector of job seekers through a multi-dimensional feature fusion algorithm, calculate the similarity between job seekers and jobs, and obtain a preliminary matching score; the job recommendation module is used to combine the emotional needs of job seekers and the cultural adaptability of jobs to generate a personalized job recommendation list, and give priority to recommending jobs with the highest matching degree with job seekers' needs.

[0142] This embodiment also provides a computer device suitable for the method of intelligent recommendation of precise matching of people and jobs, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the method of intelligent recommendation of precise matching of people and jobs proposed in the above embodiment.

[0143] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0144] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for realizing intelligent recommendation of accurate matching of people and jobs as proposed in the above embodiment; the 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, disk or optical disk.

[0145] In summary, the present invention pre-processes multi-source data by using data cleaning, classification and standardization to ensure data quality and consistency; extracts the emotional tendencies of job seekers through sentiment analysis, and constructs emotional portraits based on their personal characteristics, which can accurately capture the emotional needs of job seekers; utilizes a deep transfer learning framework to transfer knowledge from the source field to the target field, optimizes the matching accuracy between positions and job seekers, and at the same time improves the effect of feature fusion through adaptive weighted feature alignment. Furthermore, through a multi-dimensional feature fusion algorithm, multiple features such as text features, emotional portraits and behavioral patterns of job seekers are integrated to calculate the similarity between job seekers and positions; the generative adversarial network continuously optimizes the matching feature vectors to improve matching accuracy and generate a personalized job recommendation list, ensuring that the recommendation results are more in line with the emotional needs of job seekers and the cultural compatibility of positions, effectively improving the matching accuracy and user experience.

[0146] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. 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 method for intelligent recommendation of precise matching of people and jobs, characterized by: include, Collect multi-source data of job seekers and job openings in real time, clean, classify and standardize the data, and output unstructured text data; Extract the emotional tendencies of job seekers through sentiment analysis methods and construct the emotional portrait vector of job seekers; Using deep transfer learning, we transfer knowledge from the source domain to the target domain, optimize the matching accuracy between positions and job seekers, and optimize job recommendations based on the transferred knowledge. The specific steps are as follows: Extract features from source domain data through a multi-layer neural network to generate a deep feature vector representation of the source domain; Transfer the deep feature vector representation to the target domain, build an adaptive transfer learning framework, and transfer knowledge layer by layer by fine-tuning parameters; In each layer, a nonlinear mapping function is used to fuse high-order features, thereby preserving the multi-scale information between the source and target domains; Adaptive weighting method is used to align the multi-layer features of source and target domains. During the feature alignment process, the loss function is used for optimization. The multi-dimensional features of job seekers and positions are integrated through Gaussian kernel function to build a nonlinear fusion mechanism; Build a Q-learning network based on reinforcement learning to optimize job recommendations based on personal characteristic data, job information data, emotional demand data, job culture fit data, and job recommendation feedback data; Through a multi-dimensional feature fusion algorithm, the unstructured text data of job seekers is integrated with the emotional profile vector of job seekers to calculate the similarity between job seekers and positions and obtain a preliminary matching score. Combine the emotional needs of job seekers and the cultural fit of the positions to generate a personalized job recommendation list, giving priority to the positions that best match the job seekers' needs. The specific steps are as follows: Standardize and align job seekers’ emotional needs data with job culture fit data; Based on the preliminary matching scores, use the Top-K recommendation strategy to select the top K positions with the highest matching scores as candidate recommended positions; Combining multi-source data of job seekers and recruitment positions, the preliminary recommendation list is sorted again, giving priority to displaying positions that have the highest match with the job seekers' emotional needs data and the cultural adaptability data of the positions, and outputting a personalized job recommendation list.

2. The method for intelligent recommendation of precise person-job matching according to claim 1, characterized in that: The multi-source data of job seekers and recruitment positions include personal characteristic data, position information data, emotional demand data, position culture adaptability data and position recommendation feedback data.

3. The method for intelligent recommendation of precise person-job matching according to claim 2, characterized in that: The data cleaning, classification and standardization are performed to output unstructured text data. The specific steps are as follows: Perform missing value checks, duplicate data processing, and outlier handling on multi-source data of job seekers and job openings; Perform feature classification and text classification on the personal feature data and job information data in the multi-source data of job seekers and recruitment positions, and convert them into standardized labels; Normalize the numerical data in the processed multi-source data of job seekers and job openings, and vectorize the text data using a pre-trained language model; Output the cleaned, categorized, and standardized data into unstructured text format.

4. The method for intelligent recommendation of precise person-job matching according to claim 3, characterized in that: The emotional tendency of job seekers is extracted by sentiment analysis method, and the emotional portrait vector of job seekers is constructed. The specific steps are as follows: Segment and remove stop words from the job applicants' unstructured text data, and use NLP tools for part-of-speech tagging; Fine-tune the unstructured text data of job seekers based on the BERT pre-trained model, classify the text into sentiment labels through sentiment classification, and predict the sentiment intensity value of each text segment; The emotion intensity value is converted into a numerical vector and combined with the job applicant's personal characteristic data to form an emotion portrait vector.

5. The method for intelligent recommendation of precise person-job matching according to claim 4, characterized in that: The multi-dimensional feature fusion algorithm is used to fuse the unstructured text data of the job seeker with the job seeker's emotional portrait, calculate the similarity between the job seeker and the position, and obtain a preliminary matching score. The specific steps are as follows: The BERT model is used to extract features from the unstructured text data of job seekers and generate a feature vector of the job seeker text. Convert the predicted sentiment intensity value of each text in the sentiment portrait into a sentiment numerical vector; Extracting job seekers' behavioral data from personal feature data and job recommendation feedback data, and processing it based on the LSTM time series model to capture the job seekers' behavioral trends and obtain their behavioral patterns; Use multi-layer perceptron and deep neural network to fuse the text feature vector, sentiment value vector and behavior pattern of job applicants; During the feature fusion and alignment process, the weights of different features are dynamically adjusted to align and standardize features from different data sources; The fully connected layers integrate features of different modalities layer by layer. Each layer of the neural network further optimizes the relationship between different features through weighting, activation functions, and nonlinear mapping to generate a comprehensive feature vector for job seekers. Generative adversarial network matching optimization is used. The generator accepts the comprehensive feature vector of the job seeker, the job information data and the job culture compatibility data, and generates a matching feature vector. Based on historical job recommendation feedback data and manually labeled job matching data, it is trained through deep learning methods to output true matching feature vectors; The discriminator evaluates the match between the job applicant and the position by comparing the generated matching feature vector with the real matching feature vector; During generative adversarial training, the generator and the discriminator continuously optimize the generation process of matching feature vectors through mutual competition; After generating adversarial training to obtain the matching feature vectors between job seekers and positions, the cosine similarity is used to calculate the matching degree between job seekers and positions; The degree of match between the job seeker and the position is used as the preliminary match score.

6. A system for intelligently recommending precise job matching, based on the method for intelligently recommending precise job matching according to any one of claims 1 to 5, characterized in that: Including data collection module, emotion profiling module, knowledge transfer module, feature fusion module and job recommendation module; The data collection module is used to collect multi-source data of job seekers and recruitment positions in real time, and perform data cleaning, classification and standardization processing to output unstructured text data; The emotional portrait module is used to extract the emotional tendencies of job seekers through emotional analysis methods and construct the emotional portrait vector of the job seekers; The knowledge transfer module is used to transfer knowledge from the source domain to the target domain using deep transfer learning, optimize the matching accuracy between positions and job seekers, and optimize job recommendations based on the transferred knowledge. The specific steps are as follows: Extract features from source domain data through a multi-layer neural network to generate a deep feature vector representation of the source domain; Transfer the deep feature vector representation to the target domain, build an adaptive transfer learning framework, and transfer knowledge layer by layer by fine-tuning parameters; In each layer, a nonlinear mapping function is used to fuse high-order features, thereby preserving the multi-scale information between the source and target domains; Adaptive weighting method is used to align the multi-layer features of source and target domains. During the feature alignment process, the loss function is used for optimization. The multi-dimensional features of job seekers and positions are integrated through Gaussian kernel function to build a nonlinear fusion mechanism; Build a Q-learning network based on reinforcement learning to optimize job recommendations based on personal characteristic data, job information data, emotional demand data, job culture fit data, and job recommendation feedback data; The feature fusion module is used to fuse the job seeker's unstructured text data with the job seeker's emotional portrait vector through a multi-dimensional feature fusion algorithm, calculate the similarity between the job seeker and the position, and obtain a preliminary matching score; The job recommendation module is used to combine the emotional needs of job seekers and the cultural adaptability of positions to generate a personalized job recommendation list, giving priority to recommending positions that have the highest degree of match with job seekers' needs. The specific steps are as follows: Standardize and align job seekers’ emotional needs data with job culture fit data; Based on the preliminary matching scores, use the Top-K recommendation strategy to select the top K positions with the highest matching scores as candidate recommended positions; Combining multi-source data of job seekers and recruitment positions, the preliminary recommendation list is sorted again, giving priority to displaying positions that have the highest match with the job seekers' emotional needs data and the cultural adaptability data of the positions, and outputting a personalized job recommendation list.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for intelligent recommendation of precise matching of people and jobs described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for intelligent recommendation of precise matching of people and jobs described in any one of claims 1 to 5 are implemented.

Images