A big data-based employment platform and employment method

Abstract

The present invention is applicable to the field of job search and recruitment technology, and proposes a big data-based employment platform and employment method, including: uploading job search information; uploading recruitment information; matching all job search information with all recruitment information to generate a job seeker-recruiter recommendation list; receiving information about employers with bad credit uploaded by job search accounts, adding label information to the bad credit employer information, and establishing an employer comment area to display the reasons for the bad credit employer; determining the credit score of each employer identity based on the bad credit employer information, adjusting the job seeker-recruiter recommendation list based on the credit score, and determining the order in which recruitment information is pushed. By establishing an employer comment area and determining the credit score of each employer identity based on the bad credit employer information, job seekers are provided with comprehensive employer evaluations and credit information, helping them avoid bad credit employers and enhancing job search security.

Description

Technical Field

[0001] The present invention relates to the field of job search and recruitment technology, and in particular to an employment platform and employment method based on big data. Background Art

[0002] With rapid economic development and ongoing adjustments to industrial structures, flexible employment has become a crucial component of the labor market. Traditional employment methods often suffer from information asymmetry, inefficient matching, and high recruitment costs. Flexible employment, however, has gained widespread popularity among businesses and job seekers for its flexibility, efficiency, and low costs. However, existing flexible employment platforms still have numerous shortcomings in information processing, matching efficiency, and security.

[0003] First, the information posted by job seekers and employers on the platform often lacks depth and breadth, resulting in inaccurate matching results. Second, the platform lacks efficient data processing and analysis capabilities when handling large amounts of job and recruitment information, making the matching process time-consuming and inefficient. Furthermore, existing platforms have significant shortcomings in protecting job seekers' rights and preventing employers with poor credit standing. Job seekers often struggle to obtain comprehensive evaluations and credit information on employers, increasing the risk of job hunting. Therefore, there is a need for a big data-based employment platform and method to address these issues. Summary of the Invention

[0004] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide an employment platform and employment method based on big data to solve the problems existing in the above-mentioned background technology.

[0005] The present invention is implemented as follows: a big data-based employment method, the method comprising the following steps:

[0006] Upload job application information through a job application account, including the applicant's identity, job type, type of machine they can operate, dominant hand, age, and job location;

[0007] Upload recruitment information through a recruitment account, including the employer's identity, job type, required machine type, dominant hand, age, and work location;

[0008] Match all job application information with all recruitment information, conduct preliminary screening based on job type and hand preference, and obtain screening results;

[0009] Dynamic scoring is calculated based on the distance between the two parties, the rarity of the machine type, and the age requirement in the screening results. The current labor market supply and demand status is taken into account during the dynamic scoring calculation process to generate a matching score. Based on the matching score, a recommended list of job seekers and employers is generated.

[0010] Receiving information about employers with bad credit ratings uploaded by job-seeking accounts, the information including the employer's identity and the reason for the bad credit rating;

[0011] Add label information to the bad credit employer information, create an employer comment area, add the bad credit employer reasons to the employer comment area, and display the label information and the bad credit employer reasons to job seekers;

[0012] Determine the credit score of each employer based on the information of employers with bad credit, adjust the job seeker-employer recommendation list based on the credit score, and determine the order in which recruitment information is pushed;

[0013] Finally, conduct a comprehensive analysis of all job search and recruitment information to determine employment trend information.

[0014] Another object of the present invention is to provide a big data-based employment platform, comprising:

[0015] A job application information uploading module is used to upload job application information through a job application account. The job application information includes the applicant's identity, job type, type of machine that can be operated, dominant hand, age, and job application location.

[0016] A recruitment information upload module is used to upload recruitment information through a recruitment account. The recruitment information includes the employer's identity, job type, required machine type, dominant hand, age, and work location.

[0017] The job search and recruitment matching module is used to match all job search information with all recruitment information and generate a job seeker-recruiter recommendation list;

[0018] The bad credit employer information module is used to receive bad credit employer information uploaded by the job-seeking account, wherein the bad credit employer information includes the employer's identity and the reason for the bad credit employer;

[0019] The employer comment area module is used to add label information to the bad credit employer information, build an employer comment area, add the bad credit employer reasons to the employer comment area, and display the label information and the bad credit employer reasons to job seekers;

[0020] The credit score determination module is used to determine the credit score of each employer based on the information of employers with bad credit, adjust the job seeker-employer recommendation list based on the credit score, and determine the order of pushing recruitment information;

[0021] The employment trend information module is used to conduct a comprehensive analysis of all job search information and recruitment information to determine employment trend information.

[0022] Compared with the prior art, the present invention has the following beneficial effects:

[0023] In this invention, job seekers can upload information about employers with bad credit, add tags to this information, create an employer comment section, display the reasons for the employer's bad credit, and determine the credit score of each employer based on the bad credit employer information. This provides job seekers with comprehensive employer evaluation and credit information, helping them avoid employers with bad credit and enhancing job search security. The order in which job postings are pushed is also determined based on credit scores, allowing employers with good credit to receive priority attention from job seekers, improving the platform's overall credibility and user experience. It can comprehensively analyze all job and recruitment information and determine employment trend information, helping companies and job seekers better grasp market dynamics and make more informed decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a flowchart of a labor employment method based on big data.

[0025] Figure 2 This is a structural diagram of a big data-based employment platform. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0027] The specific implementation of the present invention is described in detail below with reference to specific embodiments.

[0028] like Figure 1 As shown, an embodiment of the present invention provides a method for employing workers based on big data, the method comprising the following steps:

[0029] S100, uploading job application information through a job application account, wherein the job application information includes the job seeker's identity, job type, machine type that can be operated, dominant hand, age, and job application location;

[0030] S200, uploading recruitment information through a recruitment account, wherein the recruitment information includes the employer's identity, type of job, required machine type, dominant hand, age, and work location;

[0031] S300: Match all job application information with all recruitment information, perform preliminary screening based on job type and hand preference, and obtain screening results;

[0032] Dynamic scoring is calculated based on the distance between the two parties, the rarity of the machine type, and the age requirement in the screening results. The current labor market supply and demand status is taken into account during the dynamic scoring calculation process to generate a matching score. Based on the matching score, a recommended list of job seekers and employers is generated.

[0033] S400, receiving information about employers with bad credit uploaded by a job-seeking account, wherein the information about employers with bad credit includes the employer's identity and the reason for the bad credit;

[0034] S500, adding label information to the bad credit employer information, creating an employer comment area, adding the bad credit employer reason to the employer comment area, and displaying the label information and the bad credit employer reason to the job seeker;

[0035] S600, determining the credit score of each employer based on the information of employers with bad credit, adjusting the job seeker-employer recommendation list based on the credit score, and determining the order of pushing recruitment information;

[0036] S700 conducts comprehensive analysis of all job search and recruitment information to determine employment trend information.

[0037] It should be noted that existing flexible employment platforms still have many shortcomings in terms of information processing, matching efficiency and security. First, the information posted by job seekers and employers on the platform often lacks depth and breadth, resulting in inaccurate matching results. Secondly, when processing a large amount of job search and recruitment information, the platform lacks efficient data processing and analysis capabilities, making the matching process time-consuming and inefficient. In addition, existing platforms also have obvious shortcomings in protecting the rights and interests of job seekers and preventing employers with bad credit. Job seekers often find it difficult to obtain comprehensive evaluations and credit information of employers, which increases the risk of job hunting. The embodiments of the present invention are intended to solve the above problems.

[0038] In an embodiment of the present invention, job seekers first need to register a job search account, and recruiters need to register a recruitment account. Then, they upload their job application information through the job search account, and the recruitment information through the recruitment account. The job application information includes the job seeker's identity, job type, machine types they can operate, their dominant hand, age, and job location, while the recruitment information includes the employer's identity, job type, required machine types, their dominant hand, age, and job location. This more specific and comprehensive information makes the matching process more accurate, meeting the personalized needs of both employers and job seekers. All job application information and recruitment information are then matched to generate a recommended list of job seekers and recruiters, significantly reducing matching time and improving matching efficiency. Furthermore, job seekers can also upload information about employers with poor credit standing. This information includes the employer's identity and the reasons for the employer's poor credit standing. Tags are added to the employer information, and an employer comment section is created. The reasons for the employer's poor credit standing are added to the employer comment section for display. A credit score for each employer's identity is determined based on the employer information. This provides job seekers with comprehensive employer evaluations and credit information, helping them avoid employers with poor credit standing and enhancing job search security. Credit scores are also used to determine the order in which job postings are pushed, ensuring that employers with good credit scores receive priority attention from job seekers, enhancing the platform's overall credibility and user experience. Finally, a comprehensive analysis of all job postings and recruitment information is conducted to identify employment trends, helping both companies and job seekers better understand market dynamics and make more informed decisions.

[0039] As a preferred embodiment of the present invention, the steps of matching all job application information with all recruitment information, performing preliminary screening based on job type and dominant hand to obtain screening results, performing dynamic scoring calculation based on the distance between the two parties, the rarity of the machine type, and the age requirement in the screening results, taking into account the current labor market supply and demand status during the dynamic scoring calculation to generate a matching score, and generating a job seeker-recruiter recommendation list based on the matching score, specifically include:

[0040] S30201, obtaining a job classification code, matching the job classification code of the job seeker with the job classification code issued by the employer, and obtaining a first matching result in which the job classification codes are consistent;

[0041] S30202, comparing the job applicant's declared operating hand preference in the first matching result with the job applicant's operating hand preference requirements in the job position to obtain a screening result;

[0042] S30203, calculating the actual physical distance between the job seeker's job-seeking location and the employer's work location based on the latitude and longitude coordinates of the two locations in the screening results, and applying an exponential decay function to the actual physical distance to obtain an exponential decay coefficient;

[0043] S30204, obtain the administrative levels of the job search location and the work location, assign different weights according to the administrative level, and obtain the affiliation weight:

[0044] For example:

[0045] Completely the same street: membership is 1;

[0046] Different streets in the same district: the degree of affiliation is reduced to 0.8;

[0047] Different districts in the same city: the degree of affiliation is reduced to 0.6;

[0048] Similarly, the degree of affiliation is lowest when matching across provinces.

[0049] S30205, the exponential decay coefficient is weighted and fused with the membership weight to generate a spatial matching score;

[0050] S30206, calculating the intersection and union of the machine types that the job seeker can operate and the machine types required by the employer in the screening results;

[0051] S30207, count the frequency of each machine type in the recruitment market, and assign a corresponding scarcity weight to each machine type based on its rarity;

[0052] S30208, calculating a weighted similarity based on the scarcity weights of the intersection machine types and the scarcity weights of the union machine types to obtain a device matching score;

[0053] S30209: Obtain the employer's age requirements, construct an S-shaped curve function, and use the employer's age requirements as the central transition zone of the S-shaped curve function. Substitute the applicant's actual age into the S-shaped curve function and obtain the corresponding age match score based on the slope of the S-shaped curve function.

[0054] S30210: Based on the current labor market supply and demand, dynamically assign weights to the spatial matching score, the equipment matching score, and the age matching score to obtain a comprehensive spatial matching score, a comprehensive equipment matching score, and a comprehensive age matching score, respectively. The spatial matching score, the equipment matching score, and the age matching score are weighted and fused according to the dynamic weights to obtain a final matching score.

[0055] S30211, sort all job seekers for the same recruitment position in descending order according to the final matching score, generate a recruitment position matching list, count the recruitment position matching lists of all positions, and generate a job seeker-recruiter recommendation list.

[0056] In this embodiment, rigid criteria such as job type and operator skill are used to quickly filter out invalid matches (e.g., a right-handed position will not recommend a left-handed applicant), thus avoiding resource waste. Flexible algorithms such as location decay and age fuzzy matching are also introduced. Once key constraints are met, quantitative scoring is used to achieve more refined prioritization. Furthermore, machine type matching uses industry scarcity weights (e.g., precision instruments are weighted higher than standard machine tools), reflecting the actual supply and demand relationship in the labor market and resolving the traditional matching issue of equipment with the same label but significant differences in actual skill requirements.

[0057] In addition, in order to adapt to market supply and demand, dynamic weights are designed to automatically adjust the weights of each dimension according to the supply and demand ratio of the job type (such as relaxing geographical restrictions and increasing equipment matching weights when there is a labor shortage), avoiding rigid rules that lead to an increase in matching failure rates.

[0058] As a preferred embodiment of the present invention, the steps of adding label information to the bad credit employer information, establishing an employer comment area, adding the bad credit employer reason to the employer comment area, and displaying the label information and the bad credit employer reason to the job seeker specifically include:

[0059] S501, classifying all bad credit employer information according to employer identity, where the employer identity in each category is the same;

[0060] S502, extracting high-frequency keywords related to the reasons for bad credit employers in each category, and adding label information to each employer's identity based on the high-frequency keywords;

[0061] S503, constructing an employer comment area, and adding the bad credit employer reason to the corresponding employer comment area;

[0062] S504: Display the bad credit employer label information and the bad credit employer reasons to serve as identification information for job seekers during the job search process.

[0063] In an embodiment of the present invention, in order to obtain an employer comment area, all information on bad credit employers will be classified according to the employer identity, and then high-frequency keywords of the reasons for bad credit employers in each category will be extracted based on natural language processing (NLP) technology. Label information will be added to each employer identity based on the high-frequency keywords, and an employer comment area will be constructed. The reasons for bad credit employers will be added to the corresponding employer comment area, so that job seekers can have a more comprehensive understanding of the employer.

[0064] As a preferred embodiment of the present invention, the step of classifying all bad credit employer information according to employer identity, wherein the employer identities in each category are the same, specifically includes:

[0065] S50101: Import the standard business registration dictionary into the enterprise credit information disclosure system. The standard business registration dictionary includes a standard vocabulary for industry classification and a vocabulary for standardized expressions of business scope;

[0066] S50102, employer identity includes employer name, business registration number, and unified social credit code. A bidirectional LSTM-CRF neural network model is used to perform fine-grained segmentation on the employer name to obtain the word segmentation result;

[0067] S50103, matching the word segmentation results with the standard business registration dictionary to extract core words and obtain the font size and industry characteristic words;

[0068] S50104: Establish a synonym mapping table, and use the synonym mapping table to perform standardized conversion on the industry characteristic words to obtain standardized industry characteristic words;

[0069] S50105: Build a global corpus using the font sizes of all employers, and use TF-IDF weight analysis to calculate the TF-IDF word frequency of font size in the global corpus to obtain the TF-IDF weight;

[0070] S50106: Use the pre-trained industry-specific word vector model to calculate the semantic similarity between standardized industry feature words and the standard business registration dictionary to obtain part-of-speech tags;

[0071] S50107: Perform Luhn algorithm verification on the business registration number to verify the legitimacy of the code and generate a binary check digit feature. The business registration number is parsed based on the binary check digit feature to obtain the registration area code.

[0072] S50108, performs a SHA-256 hash operation on the unified social credit code to generate a fixed-length cryptographic signature digest;

[0073] S50109, combining the binary check bit feature with the cryptographic feature summary to obtain a coding check feature vector;

[0074] S50110 assigns corresponding industry classification weights based on the frequency of occurrence of industry characteristic words in the standard business registration dictionary. TF-IDF weights, part-of-speech tags, and industry classification weights are used as text feature vectors. The text feature vectors are orthogonally concatenated with the encoding verification feature vectors to form a multi-dimensional hybrid feature representation.

[0075] S50111, create independent clusters for each employer, each cluster contains a multi-dimensional mixed feature representation of a single employer;

[0076] S50112, setting a dynamic threshold in an incremental manner according to the clustering time period;

[0077] S50113, based on the set dynamic threshold, uses the Jaccard-Wasserstein composite metric to calculate the feature vector similarity between two clusters;

[0078] S50114: When the similarity between two clusters exceeds a dynamic threshold, the two clusters are merged to obtain a clustering result, where each cluster in the clustering result represents a category of employer identity.

[0079] In this embodiment of the present invention, multimodal feature fusion is employed to integrate structured coding information with unstructured text features, overcoming the limitations of traditional text matching. The Jaccard-Wasserstein composite metric considers both the collective similarity of text features and the distribution distance of coding features, ensuring clustering accuracy. Furthermore, to balance efficiency and accuracy, a dynamic threshold mechanism is established based on the clustering time period. Initially, a loose threshold is used to promote large-scale clustering, while later, a higher threshold is employed to ensure fine-grained differentiation.

[0080] Taking the employer name: XX Machinery Equipment Co., Ltd., business registration number: 12345678, unified social credit code: ******* as an example, the above scheme is explained as follows:

[0081] A bidirectional LSTM-CRF neural network model is used to perform fine-grained segmentation on the employer name, obtaining the word segmentation results ["XX", "machinery", "equipment", "Co., Ltd."];

[0082] Match the word segmentation results with the standard business registration dictionary, retaining "XX" (font size) and "machinery" (industry characteristic word) as core words; identify "machinery and equipment" as a standard business scope description;

[0083] The TF-IDF weight analysis is used to calculate the TF-IDF frequency of "XX" (font size) in the global corpus, and the TF-IDF value is 0.85;

[0084] The semantic similarity between the standardized industry characteristic word "machinery" and the standard industrial and commercial registration dictionary is 0.92;

[0085] Perform Luhn algorithm verification on the business registration number 12345678. The business registration number check digit is 1 (valid). The registration area code is parsed from the business registration number.

[0086] Perform hash operation on the social credit code *******, hash value: a1b2c3d4...;

[0087] Perform orthogonal concatenation of the TF-IDF value, semantic similarity, check digit, and hash value to obtain a mixed feature vector: [0.85, 0.92, 1, a1b2c3d4...];

[0088] The Jaccard-Wasserstein composite metric is used to calculate the similarity of the eigenvectors between two clusters:

[0089] Similarity with "XX Machinery Manufacturing Co., Ltd.": 0.89;

[0090] Text similarity: 0.85 (matching font sizes, similar industries);

[0091] Registration area code similarity: 0.93 (same registration location);

[0092] Similarity with "XX Mechanical and Electrical Equipment Company": 0.72;

[0093] Text similarity: 0.68 (difference in industry characteristics);

[0094] Registration area code similarity: 0.76 (different registration locations);

[0095] The current dynamic threshold is 0.85;

[0096] If the similarity with "XX Machinery Manufacturing Co., Ltd." is 0.89 and exceeds the dynamic threshold of 0.85, the merge operation is triggered;

[0097] Monte Carlo validation: 10 sampling similarities are all > 0.85, confirming the merger;

[0098] Generate classification label: "Mechanical equipment manufacturing enterprises"; record classification basis: core feature words: "XX", "mechanical"; registration place feature: *Hai; business scope: mechanical equipment manufacturing.

[0099] As a preferred embodiment of the present invention, the step of extracting high-frequency keywords related to the reasons for bad credit employers in each category and adding label information to each employer identity based on the high-frequency keywords specifically includes:

[0100] S50201, translate the text of bad credit employers into English and build a bilingual parallel corpus;

[0101] S50202 compares the semantic differences between Chinese and English texts and extracts cross-lingual vectors that are not affected by language;

[0102] S50203 uses the pre-trained Chinese BERT model to perform deep semantic capture on the text of the bad credit employer's case, obtaining a semantic vector containing contextual information;

[0103] S50204 uses a pre-trained BiLSTM model to analyze the word order relationship in the text of the employer's bad credit case to extract word order features. The word order features are then weighted using an attention mechanism to obtain a feature vector with temporal weights.

[0104] S50205: Dimensionally align the contextual semantic vector, the feature vector with temporal weights, and the cross-language vector through a fully connected layer.

[0105] S50206: Perform weighted fusion on the dimensionally aligned semantic vector of the contextual information, the feature vector with temporal weights, and the cross-language vector. During the weighted fusion process, the weights of the semantic vector of the contextual information and the feature vector with temporal weights are adjusted based on the length of the text of the employer's bad credit history to obtain a multimodal fusion vector.

[0106] S50207: Obtain a labor violation word library, search for the number and frequency of labor violation words in the text of the bad credit employer's reasons, and obtain the corresponding risk weight based on the number and frequency;

[0107] S50208, perform TF-IDF analysis on the text of the employer's reasons for bad credit, obtain the TF-IDF value, and weight the TF-IDF value with the risk weight to obtain the improvement value;

[0108] S50209, uses LDA to perform topic mining on multimodal fusion vectors and generate a topic-word distribution matrix;

[0109] S50210, based on the improvement value, select the top several high-frequency words as network nodes to construct a graph structure; and combine the topic-word distribution matrix to form a semantic network graph;

[0110] S50211, based on the co-occurrence strength of word pairs in the topic-vocabulary distribution matrix, uses a graph convolutional network to analyze the association strength between nodes in the graph structure and construct a weighted semantic network graph, where nodes are keywords and edge weights are association degrees;

[0111] S50212, using a density peak-based algorithm to identify core nodes in a weighted semantic network graph;

[0112] S50213, semantic clustering is performed based on the core nodes, and during the clustering process, the cluster radius is dynamically adjusted according to the edge weights in the weighted semantic network graph to obtain semantic clusters;

[0113] S50214: Calculate the eccentricity based on the improvement value and the centrality of the weighted semantic network graph. Select the first several words from the semantic cluster as label information of the employer's identity based on the eccentricity.

[0114] In the embodiment of the present invention, a cross-dimensional feature fusion method is adopted to overcome the inherent defect of contextual ambiguity in single text analysis through the complementary features of semantic depth and temporal association, and automatically optimize the weight distribution according to the text features. Compared with the fixed ratio fusion method, it can effectively improve the accuracy.

[0115] It also employs a dual "explicit + implicit" analysis, using TF-IDF to obtain surface word frequencies and LDA to identify latent topics. This collaborative application of surface word frequencies and latent topics allows it to capture high-frequency terms like "wage arrears" and identify implicit connections, such as between wage arrears and labor arbitration. Furthermore, by dynamically adjusting the cluster radius, it enables precise segmentation in high-density areas while avoiding over-segmentation in low-density areas. This effectively assigns keywords to employers with poor credit standing, providing job seekers with a more comprehensive understanding of employers.

[0116] Taking the example of a bad credit employer case, "Employees of a construction company reported that they had not been paid for six consecutive months and had not signed a written labor contract. After repeated unsuccessful negotiations, they complained to the relevant authorities," the above solution is explained as follows:

[0117] First, change the text range to English, and get the English text "Employees of a construction company reported unpaid wages for six consecutive months, with no written labor contract";

[0118] By extracting cross-language common features: "unpaid wages" and "labor contract" are identified as language-independent core elements;

[0119] When the employer's bad credit reason text is fed into BERT, BERT detects a strong correlation between "six consecutive months" and "not issued" (similarity 0.88).

[0120] The text of the employer's bad credit reasons is then fed into the BiLSTM and weighted by the attention mechanism to identify key temporal patterns: [Six consecutive months] Unpaid wages (Attention weight 0.94) → [Unsigned] labor contract (0.89) → [Complaint] (0.82);

[0121] The length of the employer's bad credit reason text is 49 words. We should assign 80% weight to the BERT semantic features and 20% weight to the BiLSTM temporal features, and then fuse them to generate a fusion vector. For example, we can highlight the composite features of "wage arrears" and "contract missing."

[0122] Improvement values are calculated for the text of the employer's reasons for bad credit, for example: "Unpaid wages" base value 23.5 × risk factor 3 → final score 70.5; "Employment contract" base value 18.2 × risk factor 3 → 54.6;

[0123] LDA is used to perform topic mining on the multimodal fusion vector and two potential topics are found, such as:

[0124] Topic 1: Salary payment | Hours | Negotiation (probability 0.63);

[0125] Topic 2: Contract signing | Legal procedures | Complaints (probability 0.57);

[0126] Based on the improvement value, words such as "unpaid wages", "labor contract", and "complaint" are selected as nodes;

[0127] The “failure to issue wages - labor contract” crosses topics and co-occurs twice → the basic edge weight is 0.4; the “wages - complaints” are on the same topic and co-occur three times → the edge weight is 0.4 + 0.3 = 0.7; a weighted semantic network graph is formed;

[0128] The density peak algorithm was used to identify core nodes in the weighted semantic network graph. Ultimately, "unpaid wages" became the core node (density value 8.7). Clustering was then performed to generate the semantic clusters: unpaid wages | duration of arrears | negotiation records.

[0129] Based on the eccentricity, the unpaid wages|delayed period (six months) is selected as the label information of the employer's identity.

[0130] As a preferred embodiment of the present invention, the step of determining the credit score of each employer based on the information of employers with bad credit specifically includes:

[0131] S601, analyzing all bad credit employer information for each employer identity to determine the credit type corresponding to the bad credit employer reason;

[0132] S602, determining the credit deduction points for each employer with bad credit according to the credit type, and summarizing all the credit deduction points to obtain the credit score of the corresponding employer identity.

[0133] In an embodiment of the present invention, a credit score is also calculated. Specifically, all bad credit employer information of each employer identity is analyzed to determine the credit type corresponding to the bad credit employer cause. The credit type includes wage arrears, wage deductions, non-compliance with contractual agreements, etc. Each credit type has corresponding credit deductions in advance. In this way, the credit deductions of each bad credit employer information are determined according to the credit type, and the credit score of the corresponding employer identity can be obtained by summarizing all the credit deductions.

[0134] As a preferred embodiment of the present invention, the step of comprehensively analyzing all job search information and recruitment information to determine employment trend information specifically includes:

[0135] S701, determining the recruitment quantity for each type of work, the recruitment quantity for each machine type, the job seeker quantity for each type of work, and the job seeker quantity for each machine type based on the job seeker information and the recruitment information;

[0136] S702, determining the employment trend of each job type based on the number of job openings and the number of job seekers for each job type;

[0137] S703 , determining the employment trend of each machine type based on the recruitment volume of each machine type and the job seeker volume of each machine type.

[0138] In an embodiment of the present invention, all job search information and recruitment information are integrated to determine the recruitment volume for each type of work, the recruitment volume for each machine type, the job search volume for each type of work, and the job search volume for each machine type. Then, based on the recruitment volume for each type of work and the job search volume for each type of work, the employment trend for each type of work is determined, and based on the recruitment volume for each machine type and the job search volume for each machine type, the employment trend for each machine type is determined. The employment trend indicates an increase in demand or a decrease in demand.

[0139] like Figure 2 As shown, an embodiment of the present invention further provides a big data-based employment platform, the platform comprising:

[0140] The job application information uploading module 100 is used to upload job application information through a job application account. The job application information includes the job applicant's identity, job type, type of machine that can be operated, dominant hand, age and job application location;

[0141] Recruitment information uploading module 200, used to upload recruitment information through a recruitment account, the recruitment information including employer identity, job type, required machine type, dominant hand, age and work location;

[0142] The job search and recruitment matching module 300 is used to match all job search information with all recruitment information and generate a job seeker-recruiter recommendation list;

[0143] The bad credit employer information module 400 is used to receive bad credit employer information uploaded by a job-seeking account, wherein the bad credit employer information includes the employer's identity and the reason for the bad credit employer;

[0144] The employer comment area module 500 is used to add label information to the bad credit employer information, build an employer comment area, add the bad credit employer reason to the employer comment area, and display the label information and the bad credit employer reason to the job seeker;

[0145] A credit score determination module 600 is used to determine the credit score of each employer based on the information of employers with bad credit, adjust the job seeker-employer recommendation list based on the credit score, and determine the order in which recruitment information is pushed;

[0146] The employment trend information module 700 is used to comprehensively analyze all job search information and recruitment information to determine employment trend information.

[0147] The above is only a detailed description of the preferred embodiments of the present invention, which is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0148] It should be understood that, although the various steps in the flow chart of each embodiment of the present invention are shown in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0149] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When executed, the program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0150] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the disclosure in the specification and examples. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered merely as exemplary, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. A labor employment method based on big data, characterized in that: The method comprises the following steps: Upload job application information through a job application account, including the applicant's identity, job type, type of machine they can operate, dominant hand, age, and job location; Upload recruitment information through a recruitment account, including the employer's identity, job type, required machine type, dominant hand, age, and work location; Match all job application information with all recruitment information, conduct preliminary screening based on job type and hand preference, and obtain screening results; Dynamic scoring is calculated based on the distance between the two parties, the rarity of the machine type, and the age requirement in the screening results. The current labor market supply and demand status is taken into account during the dynamic scoring calculation process to generate a matching score. Based on the matching score, a recommended list of job seekers and employers is generated. Receiving information about employers with bad credit ratings uploaded by job-seeking accounts, the information including the employer's identity and the reason for the bad credit rating; Add label information to the bad credit employer information, create an employer comment area, add the bad credit employer reasons to the employer comment area, and display the label information and the bad credit employer reasons to job seekers; Determine the credit score of each employer based on the information of employers with bad credit, adjust the job seeker-employer recommendation list based on the credit score, and determine the order in which recruitment information is pushed; Conduct comprehensive analysis of all job search and recruitment information to determine employment trend information; The steps of matching all job search information with all recruitment information, performing preliminary screening based on job type and hand preference to obtain screening results, performing dynamic scoring calculation based on the distance between the two parties, the rarity of the machine type, and the age requirement in the screening results, and taking the current labor market supply and demand status into consideration during the dynamic scoring calculation to generate a matching score, and generating a job seeker-recruiter recommendation list based on the matching score include: Obtaining the job classification code, matching the job classification code of the job seeker with the job classification code issued by the employer, and obtaining a first matching result in which the job classification codes are consistent; The preferred operating hand declared by the job seeker in the first matching result is screened against the operating hand requirements of the position in the recruiting party to obtain a screening result; Calculate the actual physical distance between the job seeker's job location and the employer's job location based on the latitude and longitude coordinates of the two locations in the screening results, and apply an exponential decay function to the actual physical distance to calculate an exponential decay coefficient; Get the administrative levels of the job search location and the work location, assign different weights according to the administrative level, and get the affiliation weight: The exponential decay coefficient is weighted and fused with the membership weight to generate a spatial matching score; Calculate the intersection and union of the machine types that the job seeker can operate and the machine types required by the employer in the screening results; Count the frequency of each machine type in the recruitment market, and assign a corresponding scarcity weight to each machine type based on its rarity; The weighted similarity is calculated based on the scarcity weights of the intersection machine types and the scarcity weights of the union machine types to obtain the device matching score. Obtain the employer's age requirements, construct an S-shaped curve function, and use the employer's age requirements as the central transition zone of the S-shaped curve function. Substitute the job seeker's actual age into the S-shaped curve function, and determine the corresponding age match score based on the slope of the S-shaped curve function. According to the current supply and demand status of the labor market, dynamic weights are assigned to the spatial matching score, equipment matching score, and age matching score to obtain the spatial matching comprehensive score, equipment matching comprehensive score, and age matching comprehensive score respectively. The spatial matching comprehensive score, equipment matching comprehensive score, and age matching comprehensive score are weighted and fused according to the dynamic weights to obtain the final matching score. Arrange all job seekers for the same job position in descending order according to their final matching scores to generate a job position matching list. Count the job position matching lists for all positions and generate a job seeker-recruiter recommendation list. The steps of adding label information to the bad credit employer information, creating an employer comment area, adding the bad credit employer reason to the employer comment area, and displaying the label information and the bad credit employer reason to the job seeker specifically include: All bad credit employer information is classified according to the employer identity, and the employer identity in each category is the same; Extract high-frequency keywords related to bad credit employers in each category, and add label information to each employer based on the high-frequency keywords; Create an employer review area and add the reasons for bad credit employers to the corresponding employer review area; Displaying bad credit employer label information and reasons for bad credit employers as identification information for job seekers during the job search process; The steps of classifying all bad credit employer information according to employer identity, wherein the employer identities in each category are the same, specifically include: Import the standard business registration dictionary into the enterprise credit information disclosure system, which includes a standard vocabulary for industry classification and a vocabulary for standardized expressions of business scope; The employer identity includes the employer name, business registration number, and unified social credit code. A bidirectional LSTM-CRF neural network model is used to perform fine-grained segmentation on the employer name to obtain the word segmentation results. Match the word segmentation results with the standard business registration dictionary to extract core words and obtain font size and industry characteristic words; Establish a synonym mapping table, and use the synonym mapping table to perform standardized conversion on industry characteristic words to obtain standardized industry characteristic words; A global corpus was constructed using the font sizes of all employers. TF-IDF weight analysis was used to calculate the TF-IDF word frequency of the font size in the global corpus to obtain the TF-IDF weight. Use the pre-trained industry-specific word vector model to calculate the semantic similarity between standardized industry feature words and the standard business registration dictionary to obtain part-of-speech tags; Perform Luhn algorithm verification on the business registration number to verify the legitimacy of the code and generate a binary check digit feature. Analyze the business registration number based on the binary check digit feature to obtain the registration area code. Perform a SHA-256 hash operation on the unified social credit code to generate a fixed-length cryptographic feature summary; Combine the binary check bit feature with the cryptographic feature summary to obtain the encoding check feature vector; The industry classification weights are assigned based on the frequency of occurrence of industry characteristic words in the standard business registration dictionary. The TF-IDF weights, part-of-speech tags, and industry classification weights are used as text feature vectors. The text feature vectors are orthogonally concatenated with the coding verification feature vectors to form a multi-dimensional hybrid feature representation. Create independent clusters for each employer, each cluster containing a single employer's multidimensional mixed feature representation; According to the clustering time period, the dynamic threshold is set in an incremental manner; According to the set dynamic threshold, the Jaccard-Wasserstein composite metric is used to calculate the similarity of the feature vectors between two clusters; When the similarity of the feature vectors between two clusters exceeds a dynamic threshold, the two clusters are merged to obtain a clustering result, in which each cluster represents a category of employer identity; The step of extracting high-frequency keywords related to the reasons for bad credit employers in each category and adding label information to each employer identity based on the high-frequency keywords specifically includes: Translate the text of bad credit employers into English and build a bilingual parallel corpus; Compare the semantic differences between Chinese and English texts and extract cross-lingual vectors that are not affected by language; Use the pre-trained Chinese BERT model to perform deep semantic capture on the text of the employer's bad credit case, and obtain a semantic vector containing contextual information; A pre-trained BiLSTM model is used to analyze the word order relationship in the text of the employer's bad credit case to extract word order features. The word order features are then weighted using the attention mechanism to obtain a feature vector with time-series weights. The semantic vector of context information, the feature vector with temporal weights, and the cross-language vector are dimensionally aligned through a fully connected layer; The semantic vector of the dimensionally aligned contextual information, the feature vector with temporal weights, and the cross-language vector are weighted and fused. During the weighted fusion process, the weights of the semantic vector of the contextual information and the feature vector with temporal weights are adjusted according to the text length of the employer's bad credit reasons to obtain a multimodal fusion vector. Perform multi-dimensional analysis and clustering operations on the multimodal fusion vector and the text of the employer's bad credit reasons to obtain the label information of the employer's identity; The steps for performing multidimensional analysis and clustering operations on the multimodal fusion vector and the text of the employer's bad credit reasons to obtain the label information of the employer's identity include: Obtain a labor violation vocabulary, search for the number and frequency of labor violation words in the text of the bad credit employer's reasons, and obtain the corresponding risk weight based on the number and frequency; Perform TF-IDF analysis on the text of the bad credit employer's reasons to obtain the TF-IDF value, and weight the TF-IDF value with the risk weight to obtain the improvement value; LDA is used to perform topic mining on multimodal fusion vectors to generate a topic-word distribution matrix; According to the improvement value, the top several high-frequency words are selected as network nodes to construct a graph structure; and the semantic network graph is formed by combining the topic-vocabulary distribution matrix; Based on the co-occurrence strength of words in the topic-vocabulary distribution matrix, a graph convolutional network is used to analyze the correlation strength between nodes in the graph structure and construct a weighted semantic network graph; where nodes are keywords and edge weights are correlation degrees; The density peak algorithm is used to identify the core nodes in the weighted semantic network graph; Semantic clustering is performed based on core nodes. During the clustering process, the clustering radius is dynamically adjusted according to the edge weights in the weighted semantic network graph to obtain semantic clusters. The eccentricity is calculated based on the improvement value and the centrality of the weighted semantic network graph. Based on the eccentricity, the first several words in the semantic cluster are selected as the label information of the employer identity.

2. The big data-based employment method according to claim 1, characterized in that: The step of determining the credit score of each employer based on the bad credit employer information specifically includes: Analyze all bad credit employer information for each employer identity and determine the credit type corresponding to the bad credit employer reason; The credit deduction points for each employer with bad credit are determined based on the credit type, and all the credit deduction points are aggregated to obtain the credit score of the corresponding employer identity.

3. The big data-based employment method according to claim 2, characterized in that: The steps of comprehensively analyzing all job search information and recruitment information to determine employment trend information specifically include: Determine the recruitment volume for each type of work, the recruitment volume for each machine type, the job seeker volume for each type of work, and the job seeker volume for each machine type based on job search information and recruitment information; Determine the employment trend of each job type based on the number of job openings and job seekers for each job type; Determine the employment trend of each machine type based on the number of job openings for each machine type and the number of job seekers for each machine type.

4. A big data-based employment platform, which is applied to the big data-based employment method according to any one of claims 1 to 3, characterized in that: The platform includes: A job application information uploading module is used to upload job application information through a job application account. The job application information includes the applicant's identity, job type, type of machine that can be operated, dominant hand, age, and job application location. A recruitment information upload module is used to upload recruitment information through a recruitment account. The recruitment information includes the employer's identity, job type, required machine type, dominant hand, age, and work location. The job search and recruitment matching module is used to match all job search information with all recruitment information and generate a job seeker-recruiter recommendation list; The bad credit employer information module is used to receive bad credit employer information uploaded by the job-seeking account, wherein the bad credit employer information includes the employer's identity and the reason for the bad credit employer; The employer comment area module is used to add label information to the bad credit employer information, build an employer comment area, add the bad credit employer reasons to the employer comment area, and display the label information and the bad credit employer reasons to job seekers; The credit score determination module is used to determine the credit score of each employer based on the information of employers with bad credit, adjust the job seeker-employer recommendation list based on the credit score, and determine the order of pushing recruitment information; The employment trend information module is used to conduct a comprehensive analysis of all job search information and recruitment information to determine employment trend information.

Images