Flexible employment management system and skill evaluation method based on block chain and big data

Abstract

The invention relates to the technical field of employment management, in particular to a flexible employment management system based on a block chain and big data and a skill evaluation method. According to the invention, through autonomic skill label selection of the user and intelligent skill index generation, recommendation and matching are more accurately carried out on service supply and demand parties; according to the technical scheme, skill authentication information of a user is linked through the block chain technology, the skill authentication information comprises skill certificates and training experiences, the key problems of information asymmetry, non-transparent evaluation, low matching efficiency, insufficient right and interest guarantee and the like in a traditional system are effectively solved through combination of the block chain technology and the big data technology, and the user experience is improved. According to the flexible employment management system, a complete and coherent closed loop is formed from skill authentication to matching recommendation to right and interest guarantee and occupational development, the efficiency and fairness of a flexible employment market are greatly improved, and the sense of trust and the degree of participation of users are enhanced.

Description

Technical Field

[0001] The present invention relates to the field of employment management technology, and in particular to a flexible employment management system and a skill evaluation method based on blockchain and big data. Background Art

[0002] Driven by rapid economic development and technological progress, flexible employment models are becoming more and more common. Various employment forms including freelancers, part-time workers, migrant workers, etc. are receiving increasing attention. In the actual scenarios of flexible employment, the display and application of personal skills are becoming more and more important. In many industries, such as handicrafts, design, construction, and home services, personal professional skills have become the key to obtaining job opportunities and realizing self-worth. However, general employment platforms have problems such as information asymmetry and low efficiency in the display and matching of personal professional skills, which makes it difficult for many individuals with special skills to find suitable application scenarios. At the same time, the market demand for people with specific skills is difficult to be met in a timely manner. This phenomenon has become a key node restricting the development of the flexible employment industry.

[0003] The existing flexible employment management system relies on skill information manually input by users, and the matching algorithm is relatively simple, resulting in inaccurate display of skill information and a low match between job requirements and user skills, affecting the connection efficiency between supply and demand sides. At the same time, the skill evaluation in the system is often dominated by the platform or employer, lacks an open and transparent mechanism, and is easily affected by human factors, resulting in non-objective evaluation results, which in turn affects the user's career development and the employer's decision-making. In addition, due to the non-traditional nature of flexible employment, workers face many risks in terms of legal protection, and traditional systems are difficult to provide effective rights protection.

[0004] Although existing solutions have alleviated these problems to a certain extent through manual matching, centralized evaluation and offline rights protection, there are still key shortcomings such as inefficient information processing, lack of credibility in evaluation and weak rights protection. Therefore, there is an urgent need for a flexible employment management system and skill evaluation method based on blockchain and big data to solve such problems. Summary of the invention

[0005] To this end, the present invention provides a flexible employment management system and skill evaluation method based on blockchain and big data to overcome the problems of inefficient information processing, lack of credibility in evaluation, and weak rights and interests protection in the prior art.

[0006] To achieve the above objectives, on the one hand, the present invention provides a flexible employment management system based on blockchain and big data, comprising:

[0007] Skill label generation and display module: After the user completes real-name authentication in the flexible employment management system, he or she can select the corresponding skill specialty according to his or her professional skills. The skill label generation and display module performs skill authentication on the chain and analyzes the user's educational background, skill certificate, and work results information to generate a skill index and personalized skill cards, which are then displayed on the flexible employment management system.

[0008] Demand matching and recommendation module: When an enterprise or individual publishes odd job needs on the flexible employment management system, the demand matching and recommendation module intelligently matches the demand content with the user's skill tags;

[0009] Evaluation and feedback module, which allows both parties of skill provision and demand to evaluate and provide feedback on the cooperation process, and upload the evaluation and feedback data to the chain, and adjust the skill index based on the evaluation and feedback. The evaluation results are directly related to skill certification, which is used to optimize the matching algorithm and improve the user experience;

[0010] The offline application scenario docking module analyzes data based on online skill matching, contacts corresponding offline related institutions, and arranges skill training for jobs with high demand or high skill requirements;

[0011] The skill training module for special groups obtains the specific number of special groups based on user-selected tags and relevant certificates, and analyzes the actual needs of special groups in combination with the order data of special groups in the flexible employment management system;

[0012] Provide insurance services to protect the safety and interests of special groups in the process of skill training and practical application;

[0013] Insurance service module, where the flexible employment management system cooperates with insurance companies to launch flexible employment insurance services;

[0014] The rights and interests protection module and the flexible employment management system provide rights and interests protection services for special groups participating in training, including legal consultation, order-taking guidance, and skill improvement planning.

[0015] Furthermore, in the skill label generation and display module, the user's skill certification information, including skill certificates, training experience, and project experience, is uploaded to the chain through blockchain technology to generate a unique skill label;

[0016] In the demand matching and recommendation module, big data analysis technology is used to analyze market demand in real time, and combined with the skill data in the blockchain, suitable jobs or skill owners are automatically matched; at the same time, relevant odd jobs are actively pushed for matching based on the user's skill label and skill index;

[0017] In the offline application scenario docking module, skill training includes: handicraft weaving training, nursing knowledge training, and service standard training, providing a channel for skilled workers to improve their skills. Users can choose to participate in corresponding offline activities according to their skill tags and interests to practice and demonstrate their skills. At the same time, it also helps recruiters cultivate more talents to match their needs for skilled workers.

[0018] In the offline application scenario docking module, the user's skill development path and training experience are recorded through blockchain, and combined with big data analysis, personalized growth suggestions and skill improvement plans are provided to users;

[0019] The flexible employment management system cooperates with various official agencies to provide customized skills training courses for special groups; the courses are designed according to the specific needs and conditions of special groups.

[0020] On the other hand, the present invention also provides a skill evaluation method for a flexible employment management system based on blockchain and big data, comprising the following steps:

[0021] Step S1, skill label generation and display. After the user completes the real-name authentication, the user's education background, skill certificate, training experience, and work results information are automatically collected. The collected information is analyzed through big data analysis technology to generate the user's skill index and personalized skill card. The information is uploaded to the chain to generate a unique skill label. The skill label is displayed on the user's personal page for employers or demanders to view.

[0022] Step S2, collection and uploading of evaluations and feedback. After the skill provider and skill demander complete the cooperation, both parties evaluate each other's performance in the system, including work quality, time management, and communication skills. All evaluations and feedback are recorded on the blockchain. The user's skill index is adjusted based on the evaluation.

[0023] Step S3, dynamic adjustment of skill index and matching algorithm. Each evaluation and feedback data will have a direct impact on the user's skill index. For example, high-quality work feedback will improve the user's skill index, while bad evaluation may cause the skill index to decrease. The matching algorithm is dynamically adjusted according to the latest skill index and market demand.

[0024] Step S4, personalized growth suggestions and skill improvement plans, record the user's skill development path through blockchain, and combine big data analysis to provide users with personalized growth suggestions; suggestions are generated based on multi-dimensional data such as user skill tags, past evaluations, market demand, etc., to help users develop scientific skill improvement plans. After users participate in offline training or receive orders, the system continues to track their skill development through a feedback mechanism, and further optimizes growth suggestions to form a virtuous circle of skill improvement.

[0025] Furthermore, the skill label generation and display method in step S1 is:

[0026] Collect information about user education background, skill certificates, training experience, and work achievements, and express it in matrix form:

[0027] Du={du,1,du,2,...,du,n}, where Du represents the original data set of user u, du,i represents the i-th item of data of user u, and i refers to 1,2,...,n in the formula, such as academic qualifications and certificates. The specific form can be numerical, text or image data;

[0028] The data set is standardized, and the standardized data matrix is ​​expressed as:

[0029] Where n represents the total number of data items in the user data set, that is, the amount of information on the user's education background, skill certificates, training experience, and work achievements, Su represents the standardized data set, su,i represents the i-th data item after standardization, μi represents the global mean of the i-th data item, and σi represents the standard deviation of the i-th data item;

[0030] Map different types of data into a unified feature space and obtain the feature vector Fu through feature extraction:

[0031] Fu=We·Eu+Ws·Su+Wt·Tu+Wp·Pu, where Fu represents the feature vector of user u, Eu represents the feature vector of educational background, Su represents the feature vector of skill certificate, Tu represents the feature vector of training experience, Pu represents the feature vector of work results, and We, Ws, Wt, and Wp are the weight matrices of corresponding features. Weights are assigned to each feature according to market demand and industry standards:

[0032] Where wi,j represents the weight of the j-th feature i, αj represents the industry weight factor of the j-th feature, and fi represents the frequency of feature i, which refers to the frequency of occurrence in a certain type of work or industry;

[0033] Calculate the skill index based on the user's feature vector:

[0034] Where SΙu represents the skill index of user u, Fu,j represents the feature value of the user on the j-th feature, Wj represents the global weight matrix of the j-th feature, IMPj represents the importance parameter of the j-th feature, reflecting its influence in the skill index, and m represents the number of feature categories;

[0035] The skill label generation and display method in step S1 also includes:

[0036] Generate personalized skill cards using the user's feature vector and skill index. The card information includes skill name, skill level, and corresponding market value.

[0037] A hash function is used to upload the generated skill label, skill index and personalized skill card information to the chain to generate a unique blockchain identifier.

[0038] Furthermore, in step S2, the evaluation and feedback are collected and uploaded to the chain in the following manner:

[0039] Multiple evaluation dimensions are preset, including work quality, time management, and communication skills. The dimensions can be customized and expanded according to different job types or industry needs;

[0040] After the skill provider and the demander complete the cooperation, both parties will receive an evaluation request. Each evaluation dimension is set with a quantitative score (such as 1 to 5 points), and users are allowed to provide qualitative feedback (text comments);

[0041] All the collected evaluation and feedback data are packaged into a data package, including ratings, comments, timestamps, and related metadata (such as cooperation project ID, participant ID, etc.);

[0042] The evaluation data is also encrypted and a unique hash value is generated. The encrypted data packet and the corresponding hash value are recorded on the blockchain.

[0043] Furthermore, in step S2, the collection and uploading of evaluation and feedback also includes the adjustment of skill index:

[0044] The evaluation and feedback module automatically analyzes the evaluation data on the chain, summarizes the ratings and comments, and uses the weighted average and rating threshold method to calculate the overall evaluation results;

[0045] Dynamically adjust the user's skill index based on the analysis results; positive evaluations (high scores and positive text feedback) will increase the user's skill index, while negative evaluations (low scores and negative feedback) will cause the skill index to decrease;

[0046] The adjusted skill index is recorded in the user’s personal profile and a record is generated on the chain.

[0047] Furthermore, in step S3, the skill index and the matching algorithm are dynamically adjusted as follows:

[0048] According to the latest evaluation and feedback, the influence weight of each evaluation on the user's skill index is calculated. Assuming that the skill index of each user u is SΙu, the influence of a certain cooperation evaluation on the index is: Where ΔSΙu represents the adjustment value of the evaluation to the user skill index, wi is the weight of the evaluation dimension i (such as work quality, time management, communication ability, etc.), ei represents the score of the evaluation dimension i, and n is the number of evaluation dimensions;

[0049] Update the user's skill index based on different evaluation types:

[0050] in represents the adjusted skill index, represents the skill index before adjustment, is an exponential function, used to smoothly adjust the amplitude;

[0051] The matching method is adjusted based on the user's skill index and the current market demand. Let the market demand vector be Dt and the user's feature vector be Fu (based on his skill index), then the matching degree Mu is calculated as:

[0052] Where Mu is the matching score of user u, Fu represents the user’s feature vector, including the user’s skill index and other relevant features, Dt represents the current market demand vector, indicating the intensity of demand for skills at a certain moment in the market, and SIM(SΙu,Dt) is the similarity function, which evaluates the matching degree between the user’s skill index and the market demand.

[0053] Furthermore, in step S3, the skill index and the matching algorithm are dynamically adjusted in a dynamic adjustment manner by weighting:

[0054] Assume that the rate of change of market demand for a specific skill k at time t is ΔDk(t), then the corresponding matching weight wk(t) is updated as:

[0055] Where wk(t+1) represents the weight at time t+1, wk(t) represents the weight at time t, ΔDk(t) represents the change in demand at time t, and Dk(t) represents the demand intensity at time t;

[0056] After each match is completed, monitor the success rate of the matching results (such as whether the user accepts the recommended job, the employer's satisfaction, etc.), and use the success rate data to further optimize the matching algorithm:

[0057] ΔWk=η×(Succseek-Expectk), where ΔWk represents the weight adjustment amount, η represents the learning rate parameter, Succseek represents the actual matching success rate of skill k, and Expectk represents the expected success rate of skill k.

[0058] Furthermore, in step S4, the implementation method of the personalized growth advice and skill improvement plan includes:

[0059] Blockchain technology is used to record each user's skill certification, training experience, project experience, and work results. This information is stored in chronological order to form the user's skill development path;

[0060] The collected data includes not only the user's skill development path, but also the user's skill tags, past evaluation feedback, and market demand data;

[0061] Assess the user's current skill level, including weighting the user's existing skill tags to identify which skills are important in the current market demand and which skills may face a decline in demand;

[0062] Set growth goals for users based on market demand analysis and their personal development goals, including improving certain skills, learning new skills, or adjusting career direction.

[0063] Compared with the prior art, the present invention has the following beneficial effects:

[0064] The present invention, through the user's autonomous skill label selection and intelligent skill index generation, the platform can more accurately recommend and match services to both the supply and demand sides, improve the accuracy of skill display and the efficiency of matching, and help users find suitable flexible employment scenarios more quickly; through blockchain technology, the user's skill certification information is uploaded to the chain, the skill certification information includes skill certificates, training experience, etc., and a unique skill label is generated; the chain process ensures the immutability and openness and transparency of the data, effectively solving the problems of information asymmetry and inaccurate skill display. The blockchain ensures the authenticity of all skill information, and the platform can perform more accurate job matching based on this information, thereby improving matching efficiency.

[0065] The present invention establishes a complete evaluation and feedback mechanism. Employers can conduct comprehensive evaluation and problem feedback on skilled workers based on the quality of their work. The evaluation and feedback are reflected in the high and low changes in the skill index. At the same time, all evaluations and feedback are recorded on the chain, which not only helps to improve the service quality of the platform, but also provides a basis for mutual trust between users and demanders, and promotes a virtuous cycle of online skill matching; it provides guarantees for the fairness and credibility of the evaluation process, and enhances trust between users and employers; employers can understand the real skill level and work performance through historical records.

[0066] The present invention, through the application of big data analysis and artificial intelligence technology, the platform can continuously optimize the matching algorithm, improve the user experience, and realize the efficient combination of online matching and offline application of skill tags; use big data analysis technology to analyze market demand in real time, and combine the skill data in the blockchain to automatically match suitable jobs or skill owners; significantly improve the accuracy and efficiency of employment matching, continuously optimize the matching algorithm through big data analysis, and further improve the user experience.

[0067] The present invention combines online matching data and supply-demand relationships with offline targeted training, providing users with a reliable way to improve their skills and opportunities to practice their skills and showcase their achievements. It also provides demanders with skilled workers of higher standards, enhances the actual value and social recognition of skills, and the feasibility of flexible employment and flexible labor. It records users' skill development paths and training experiences through blockchain, and combines big data analysis to provide users with personalized growth suggestions and skill improvement plans.

[0068] The present invention, through the skill training module for special groups, provides more considerate and convenient skill improvement opportunities for special groups, helping them overcome employment barriers and improve their competitiveness.

[0069] The invention sets up the rights protection module, which ensures that the legitimate rights and interests of users in the process of skill training and application are protected, enhances their sense of security and trust, and promotes the virtuous cycle of the whole system.

[0070] The present invention, the introduction of the insurance service module, provides additional security for special groups of people, reduces the risk of their participation in skill training and application, and improves their enthusiasm for participation.

[0071] The present invention, through the optimization of the overall system and the collaborative work of modules, realizes the efficient combination of online matching and offline application of skill tags, especially provides more comprehensive and detailed services for special groups, and promotes social fairness and inclusiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 A flowchart of a skill evaluation method for a flexible employment management system based on blockchain and big data according to the present invention;

[0073] Figure 2 This is a schematic diagram of the structure of a flexible employment management system based on blockchain and big data of the present invention;

[0074] Figure 3 The flexible employment skills label display page of the present invention;

[0075] Figure 4 It is an online skill tag display diagram of the present invention;

[0076] Figure 5 This is a display diagram of the skill label card generated by the present invention. DETAILED DESCRIPTION

[0077] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0078] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0079] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0080] Example 1

[0081] See also Figure 1-Figure 5 The present invention provides a flexible employment management system based on blockchain and big data, comprising:

[0082] The skill label generation and display module is used to record the user's certification information and professional skills, generate personalized skill label cards, and display them on the platform. After the user registers and authenticates on the platform, he or she can choose a skill label that matches his or her skills and upload relevant certificates. The platform will conduct a comprehensive score based on the completeness of the user's information, convert it into a skill index, and display it in the personal profile.

[0083] The specific skill index has a full score of 100. When a user is only registered but not logged in, the default skill index is the lowest score of 0. After completing the real-name authentication, he / she will obtain a basic score of 55 points. There is also an additional score of 45 points. The overall score is calculated based on the choice of skill labels, the completeness of the personal data, the platform activity of the user, and the evaluation of the person who sends the job after completing the job. In addition, if the user is late for work, absent from work, or breaches the contract as the person who sends the job, and the person who sends the job complains about the termination of the contract, the platform will make corresponding deductions from the user's original score. The skill label card can also be used as a social method among platform users to share and collect with each other.

[0084] Specifically, the immutability of blockchain ensures the authenticity and integrity of skill data, effectively solving the problems of information asymmetry and inaccurate skill display. The platform facilitates the use of on-chain skill tags, analyzes market demand in real time through big data analysis technology, and dynamically adjusts matching algorithms. Blockchain ensures the authenticity of skill information, and combined with big data analysis technology, it can more accurately match jobs and skill owners, thereby improving the connection efficiency between supply and demand.

[0085] In the demand matching and recommendation module, the platform intelligently matches and recommends job seekers based on the user's skill label and skill index. When job seekers publish their odd job needs on the platform, they also select the skill requirements for employment. After the platform obtains and identifies them, it counts the job seekers with matching skills and performs intelligent matching and recommendation. In addition to the intelligent matching and recommendation of the flexible employment management system, job seekers can also actively search and view requirements that match their own skills. Job seekers can view the skill labels of job seekers and make choices, giving full play to the intelligence of the flexible employment management system and the initiative of users.

[0086] Specifically, real-time analysis and optimization can significantly improve the accuracy and efficiency of job matching.

[0087] In the evaluation and feedback module, it is used to collect evaluations and feedback on the work quality and skill level of the job senders and the job matchmakers during the process of job creation. The platform uses this data to adjust the skill index of the job receivers, give priority to recommending job receivers with higher skill indexes, optimize the matching algorithm and improve the user experience, and also provide a reference for other users.

[0088] Specifically, in the evaluation and feedback module, all evaluations and feedback are recorded on the chain and cannot be tampered with, making the evaluation process more fair and credible, and enhancing trust between users and employers. The evaluation results are directly related to skill certification. Employers can view the user's historical skill level and work performance through on-chain records, making recruitment decisions more accurate.

[0089] In the offline application scenario docking module, the platform conducts specific analysis based on the online skill matching situation, cooperates with relevant offline institutions, and arranges skill training for several types of jobs with high demand or high skill requirements; offline training can help skilled workers improve their original skill level, thereby providing higher-level skill services to demanders and obtaining higher evaluations, thereby giving priority to platform recommendations, forming a virtuous circle, and creating a good flexible employment environment; offline training can also provide users with opportunities to learn other skills, expand their employment fields, and obtain more job opportunities;

[0090] Specifically, through personalized suggestions, users can improve their abilities in a targeted manner and thus adapt to the ever-changing market demands.

[0091] In the insurance service module, the platform cooperates with insurance companies to launch flexible employment accident insurance services to provide users with additional security throughout the entire work process, allowing users to use the platform with greater peace of mind. The platform in this article also refers to the flexible employment management system.

[0092] The present invention also provides a skill evaluation method for the above system, comprising the following steps:

[0093] Step S1, skill label generation and display. After the user completes the real-name authentication, the user's education background, skill certificate, training experience, and work results information are automatically collected. The collected information is analyzed through big data analysis technology to generate the user's skill index and personalized skill card. The information is uploaded to the chain to generate a unique skill label. The skill label is displayed on the user's personal page for employers or demanders to view.

[0094] The skill label generation and display method in step S1 is:

[0095] Collect information about user education background, skill certificates, training experience, and work achievements, and express it in matrix form:

[0096] Du={du,1,du,2,...,du,n}, where Du represents the original data set of user u, du,i represents the i-th item of data of user u, and i refers to 1,2,...,n in the formula, such as academic qualifications and certificates. The specific form can be numerical, text or image data;

[0097] The data set is standardized, and the standardized data matrix is ​​expressed as:

[0098] Where n represents the total number of data items in the user data set, that is, the amount of information on the user's education background, skill certificates, training experience, and work achievements, Su represents the standardized data set, su,i represents the i-th data item after standardization, μi represents the global mean of the i-th data item, and σi represents the standard deviation of the i-th data item;

[0099] Map different types of data into a unified feature space and obtain the feature vector Fu through feature extraction:

[0100] Fu=We·Eu+Ws·Su+Wt·Tu+Wp·Pu, where Fu represents the feature vector of user u, Eu represents the feature vector of educational background, Su represents the feature vector of skill certificate, Tu represents the feature vector of training experience, Pu represents the feature vector of work results, and We, Ws, Wt, and Wp are the weight matrices of corresponding features. Weights are assigned to each feature according to market demand and industry standards:

[0101] Where wi,j represents the weight of the j-th feature i, αj represents the industry weight factor of the j-th feature, and fi represents the frequency of feature i, which refers to the frequency of occurrence in a certain type of work or industry;

[0102] Calculate the skill index based on the user's feature vector:

[0103] Where SΙu represents the skill index of user u, Fu,j represents the feature value of the user on the j-th feature, Wj represents the global weight matrix of the j-th feature, IMPj represents the importance parameter of the j-th feature, reflecting its influence in the skill index, and m represents the number of feature categories;

[0104] The skill label generation and display method in step S1 also includes:

[0105] Generate personalized skill cards using the user's feature vector and skill index. The card information includes skill name, skill level, and corresponding market value.

[0106] Use hash functions to upload the generated skill labels, skill indexes, and personalized skill card information to the blockchain to generate a unique blockchain identifier;

[0107] Step S2, collection and uploading of evaluations and feedback. After the skill provider and skill demander complete the cooperation, both parties evaluate each other's performance in the system, including work quality, time management, and communication skills. All evaluations and feedback are recorded on the blockchain. The user's skill index is adjusted based on the evaluation.

[0108] In step S2, the evaluation and feedback are collected and uploaded to the chain in the following way:

[0109] Multiple evaluation dimensions are preset, including work quality, time management, and communication skills. The dimensions can be customized and expanded according to different job types or industry needs;

[0110] After the skill provider and the demander complete the cooperation, both parties will receive an evaluation request. Each evaluation dimension is set with a quantitative score (such as 1 to 5 points), and users are allowed to provide qualitative feedback (text comments);

[0111] All the collected evaluation and feedback data are packaged into a data package, including ratings, comments, timestamps, and related metadata (such as cooperation project ID, participant ID, etc.);

[0112] The evaluation data is also encrypted and a unique hash value is generated. The encrypted data package and the corresponding hash value are recorded on the blockchain;

[0113] In step S2, the collection and uploading of evaluation and feedback also includes the adjustment of skill index:

[0114] The evaluation and feedback module automatically analyzes the evaluation data on the chain, summarizes the ratings and comments, and uses the weighted average and rating threshold method to calculate the overall evaluation results;

[0115] Dynamically adjust the user's skill index based on the analysis results; positive evaluations (high scores and positive text feedback) will increase the user's skill index, while negative evaluations (low scores and negative feedback) will cause the skill index to decrease;

[0116] Record the adjusted skill index in the user’s personal profile and generate a record on the chain;

[0117] Step S3, dynamic adjustment of skill index and matching algorithm. Each evaluation and feedback data will have a direct impact on the user's skill index. For example, high-quality work feedback will improve the user's skill index, while bad evaluation may cause the skill index to decrease. The matching algorithm is dynamically adjusted according to the latest skill index and market demand.

[0118] In step S3, the skill index and the matching algorithm are dynamically adjusted as follows:

[0119] According to the latest evaluation and feedback, the influence weight of each evaluation on the user's skill index is calculated. Assuming that the skill index of each user u is SΙu, the influence of a certain cooperation evaluation on the index is: Where ΔSΙu represents the adjustment value of the evaluation to the user skill index, wi is the weight of the evaluation dimension i (such as work quality, time management, communication ability, etc.), ei represents the score of the evaluation dimension i, and n is the number of evaluation dimensions;

[0120] Update the user's skill index based on different evaluation types:

[0121] in represents the adjusted skill index, represents the skill index before adjustment, is an exponential function, used to smoothly adjust the amplitude;

[0122] The matching method is adjusted based on the user's skill index and the current market demand. Let the market demand vector be Dt and the user's feature vector be Fu (based on his skill index), then the matching degree Mu is calculated as:

[0123] Where Mu is the matching score of user u, Fu represents the user's feature vector, including the user's skill index and other related features, Dt represents the current market demand vector, indicating the demand intensity for skills at a certain moment in the market, and SIM(SΙu,Dt) is a similarity function that evaluates the matching degree between the user's skill index and the market demand;

[0124] In step S3, the skill index and the matching algorithm are dynamically adjusted in a dynamic adjustment manner to adjust the weights:

[0125] Assume that the rate of change of market demand for a specific skill k at time t is ΔDk(t), then the corresponding matching weight wk(t) is updated as:

[0126] Where wk(t+1) represents the weight at time t+1, wk(t) represents the weight at time t, ΔDk(t) represents the change in demand at time t, and Dk(t) represents the demand intensity at time t;

[0127] After each match is completed, monitor the success rate of the matching results (such as whether the user accepts the recommended job, the employer's satisfaction, etc.), and use the success rate data to further optimize the matching algorithm:

[0128] ΔWk=η×(Succseek-Expectk), where ΔWk represents the weight adjustment amount, η represents the learning rate parameter, Succseek represents the actual matching success rate of skill k, and Expectk represents the expected success rate of skill k;

[0129] Step S4, personalized growth suggestions and skill improvement plans, record the user's skill development path through blockchain, and combine big data analysis to provide users with personalized growth suggestions; suggestions are generated based on multi-dimensional data such as user skill tags, past evaluations, market demand, etc., to help users formulate scientific skill improvement plans. After users participate in offline training or receive orders, the system continues to track their skill development through a feedback mechanism, and further optimizes growth suggestions to form a virtuous cycle of skill improvement;

[0130] In step S4, the implementation method of the personalized growth advice and skills improvement plan includes:

[0131] Blockchain technology is used to record each user's skill certification, training experience, project experience, and work results. This information is stored in chronological order to form the user's skill development path;

[0132] The collected data includes not only the user's skill development path, but also the user's skill tags, past evaluation feedback, and market demand data;

[0133] Assess the user's current skill level, including weighting the user's existing skill tags to identify which skills are important in the current market demand and which skills may face a decline in demand;

[0134] Set growth goals for users based on market demand analysis and their personal development goals, including improving a certain skill set, learning new skills, or adjusting career direction;

[0135] In summary, through the combination of blockchain and big data technology, the flexible employment management system and skill evaluation method of the present invention effectively solve key problems in traditional systems such as information asymmetry, opaque evaluation, low matching efficiency and insufficient rights protection. The flexible employment management system forms a complete and coherent closed loop from skill certification to matching recommendation, and then to rights protection and career development, which greatly improves the efficiency and fairness of the flexible employment market and enhances users' trust and participation.

[0136] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A flexible employment management system based on blockchain and big data, characterized in that: include: Skill label generation and display module, users can select corresponding skills based on their professional skills after real-name authentication in the flexible employment management system; The skill label generation and display module performs skill certification on the chain and analyzes the user's educational background, skill certificate, and work performance information to generate a skill index and personalized skill cards, which are then displayed on the flexible employment management system; Demand matching and recommendation module: When an enterprise or individual publishes odd job needs on the flexible employment management system, the demand matching and recommendation module intelligently matches the demand content with the user's skill tags; Evaluation and feedback module, which allows both parties of skill provision and demand to evaluate and provide feedback on the cooperation process, and upload the evaluation and feedback data to the chain, and adjust the skill index based on the evaluation and feedback. The evaluation results are directly related to skill certification; The offline application scenario docking module conducts data analysis based on the online skill matching situation, contacts the corresponding offline related institutions, and arranges skill training for jobs with high demand or high skill requirements.

2. According to claim 1, a flexible employment management system based on blockchain and big data is characterized in that: Also includes: The skill training module for special groups obtains the specific number of special groups based on user-selected tags and relevant certificates, and analyzes the actual needs of special groups in combination with the order data of special groups in the flexible employment management system; Insurance service module, where the flexible employment management system cooperates with insurance companies to launch flexible employment insurance services; The rights and interests protection module and the flexible employment management system provide rights and interests protection services for special groups participating in training, including legal consultation, order-taking guidance, and skill improvement planning.

3. According to claim 2, a flexible employment management system based on blockchain and big data is characterized in that: In the skill label generation and display module, the user's skill certification information is uploaded to the chain through blockchain technology, including skill certificates, training experience, and project experience, to generate a unique skill label; In the demand matching and recommendation module, big data analysis technology is used to analyze market demand in real time, and combined with the skill data in the blockchain, suitable jobs or skill owners are automatically matched; at the same time, relevant odd jobs are actively pushed for matching based on the user's skill label and skill index; In the offline application scenario docking module, skill training includes: handicraft weaving training, nursing knowledge training, and service standard training; In the offline application scenario docking module, the user's skill development path and training experience are recorded through blockchain, and combined with big data analysis, personalized growth suggestions and skill improvement plans are provided to users; The flexible employment management system cooperates with various official agencies to provide customized skills training courses for special groups; the courses are designed according to the specific needs and conditions of special groups.

4. A skill evaluation method for a flexible employment management system based on blockchain and big data, characterized in that: A flexible employment management system based on blockchain and big data as described in any one of claims 1 to 3 is used, comprising the following steps: Step S1, skill label generation and display. After the user completes the real-name authentication, the user's education background, skill certificate, training experience, and work results information are automatically collected. The collected information is analyzed through big data analysis technology to generate the user's skill index and personalized skill card. The information is uploaded to the chain to generate a unique skill label. The skill label is displayed on the user's personal page for employers or demanders to view. Step S2, collection and uploading of evaluations and feedback. After the skill provider and skill demander complete the cooperation, both parties evaluate each other's performance in the system, including work quality, time management, and communication skills. All evaluations and feedback are recorded on the blockchain. The user's skill index is adjusted based on the evaluation. Step S3, dynamic adjustment of skill index and matching algorithm. Each evaluation and feedback data will have a direct impact on the user's skill index. The matching algorithm is dynamically adjusted according to the latest skill index and market demand. Step S4, personalized growth advice and skill improvement plan, records the user's skill development path through blockchain, and combines big data analysis to provide users with personalized growth advice.

5. According to claim 4, a skill evaluation method for a flexible employment management system based on blockchain and big data is characterized in that: The skill label generation and display method in step S1 is: Collect information about user education background, skill certificates, training experience, and work achievements, and express it in matrix form: Du={du,1,du,2,...,du,n}, where Du represents the original data set of user u, du,i represents the i-th data of user u, and i refers to 1,2,...,n in the formula; The data set is standardized, and the standardized data matrix is ​​expressed as: Where n represents the total number of data items in the user data set, that is, the amount of information on the user's education background, skill certificates, training experience, and work achievements, Su represents the standardized data set, su,i represents the i-th data item after standardization, μi represents the global mean of the i-th data item, and σi represents the standard deviation of the i-th data item; Map different types of data into a unified feature space and obtain the feature vector Fu through feature extraction: Fu=We·Eu+Ws·Su+Wt·Tu+Wp·Pu, where Fu represents the feature vector of user u, Eu represents the feature vector of educational background, Su represents the feature vector of skill certificate, Tu represents the feature vector of training experience, Pu represents the feature vector of work results, and We, Ws, Wt, and Wp are the weight matrices of corresponding features. Weights are assigned to each feature according to market demand and industry standards: Where wi,j represents the weight of the j-th feature i, αj represents the industry weight factor of the j-th feature, and fi represents the frequency of feature i; Calculate the skill index based on the user's feature vector: Where SΙu represents the skill index of user u, Fu,j represents the feature value of the user on the j-th feature, Wj represents the global weight matrix of the j-th feature, IMPj represents the importance parameter of the j-th feature, reflecting its influence in the skill index, and m represents the number of feature categories; The skill label generation and display method in step S1 also includes: Generate personalized skill cards using the user's feature vector and skill index. The card information includes skill name, skill level, and corresponding market value. A hash function is used to upload the generated skill label, skill index and personalized skill card information to the chain to generate a unique blockchain identifier.

6. According to claim 5, a skill evaluation method for a flexible employment management system based on blockchain and big data is characterized in that: In step S2, the evaluation and feedback are collected and uploaded to the chain in the following way: Preset multiple evaluation dimensions, including work quality, time management, and communication skills; After the skill provider and the demander complete the cooperation, both parties will receive an evaluation request. Each evaluation dimension is set with a quantitative score, and users are allowed to provide qualitative feedback. All the collected evaluation and feedback data are packaged into a data package, including ratings, comments, timestamps, and related metadata; The evaluation data is also encrypted and a unique hash value is generated. The encrypted data packet and the corresponding hash value are recorded on the blockchain.

7. According to claim 6, a skill evaluation method for a flexible employment management system based on blockchain and big data is characterized in that: In step S2, the collection and uploading of evaluation and feedback also includes the adjustment of skill index: The evaluation and feedback module automatically analyzes the evaluation data on the chain, summarizes the ratings and comments, and uses the weighted average and rating threshold method to calculate the overall evaluation results; Dynamically adjust the user's skill index based on the analysis results; The adjusted skill index is recorded in the user’s personal profile and a record is generated on the chain.

8. According to claim 7, a skill evaluation method for a flexible employment management system based on blockchain and big data is characterized in that: In step S3, the skill index and the matching algorithm are dynamically adjusted as follows: According to the latest evaluation and feedback, the influence weight of each evaluation on the user's skill index is calculated. Assuming that the skill index of each user u is SΙu, the influence of a certain cooperation evaluation on the index is: Where ΔSΙu represents the adjustment value of the evaluation to the user skill index, wi is the weight of the evaluation dimension i, ei represents the score of the evaluation dimension i, and n is the number of evaluation dimensions; Update the user's skill index based on different evaluation types: in represents the adjusted skill index, Indicates adjustment -ΔSΙ The previous skill index, eu is an exponential function used to smooth the adjustment amplitude; The matching method is adjusted based on the user's skill index and the current market demand. Assuming the market demand vector is Dt and the user's feature vector is Fu, the matching degree Mu is calculated as: Where Mu is the matching score of user u, Fu represents the user’s feature vector, including the user’s skill index and other relevant features, Dt represents the current market demand vector, indicating the intensity of demand for skills at a certain moment in the market, and SIM(SΙu,Dt) is the similarity function, which evaluates the matching degree between the user’s skill index and the market demand.

9. According to claim 8, a skill evaluation method for a flexible employment management system based on blockchain and big data is characterized in that: In step S3, the skill index and the matching algorithm are dynamically adjusted in a dynamic adjustment manner to adjust the weights: Assume that the rate of change of market demand for a specific skill k at time t is ΔDk(t), then the corresponding matching weight wk(t) is updated as: Where wk(t+1) represents the weight at time t+1, wk(t) represents the weight at time t, ΔDk(t) represents the change in demand at time t, and Dk(t) represents the demand intensity at time t; After each match is completed, monitor the success rate of the matching results and use the success rate data to further optimize the matching algorithm: ΔWk=η×(Succseek-Expectk), where ΔWk represents the weight adjustment amount, η represents the learning rate parameter, Succseek represents the actual matching success rate of skill k, and Expectk represents the expected success rate of skill k.

10. A skill evaluation method for a flexible employment management system based on blockchain and big data according to claim 9, characterized in that: In step S4, the implementation method of the personalized growth advice and skills improvement plan includes: Blockchain technology is used to record each user's skill certification, training experience, project experience, and work results. This information is stored in chronological order to form the user's skill development path; The collected data includes not only the user's skill development path, but also the user's skill tags, past evaluation feedback, and market demand data; Assess the user's current skill level, including weighting the user's existing skill tags to identify which skills are important in the current market demand and which skills may face a decline in demand; Set growth goals for users based on market demand analysis and their personal development goals.

Images