Knowledge fusion algorithm-based digital implementation system for return-to-country talent entrepreneurship incentive mechanism

Abstract

The invention provides a digital implementation system for a return talent entrepreneurship incentive mechanism based on a knowledge fusion algorithm, and relates to the technical field of data processing. A data preprocessing module; a knowledge fusion algorithm module; an incentive mechanism module; according to the invention, the training scores of the return talent training course are collected, the actual ability and creativity level of the return talent are evaluated according to works, project results and published papers completed by the return talent during the training period, and a knowledge fusion algorithm is combined. Potential advantages of return talents in entrepreneurship are evaluated through training scores, actual capabilities and creativity levels, analysis of incentive strategies is facilitated according to tendencies of the return talents, the actual capabilities and the creativity levels, incentive strategy division is set according to tendencies of different return talents, design of differentiated incentive strategies is facilitated, and entrepreneurship efficiency is improved. Excitation measures are accurately implemented, and the country returning talents are helped to overcome actual difficulties in entrepreneurship.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and specifically to a digital implementation system for the entrepreneurship incentive mechanism for returned talents based on a knowledge fusion algorithm. Background Art

[0003] With the rapid development of the social economy, returned talents (i.e., talents who return to their local areas to start businesses or find employment after working or studying outside) are playing an increasingly important role in the local economic development.

[0004] By introducing the knowledge fusion algorithm, the integration of the knowledge resources of returned talents and the matching of their needs are realized, thereby optimizing the entrepreneurship incentive mechanism. It can dynamically analyze and match the knowledge resources with the entrepreneurship needs by combining the professional backgrounds, industry needs and regional resources of returned talents, and then provide personalized entrepreneurship support and incentive measures for returned talents.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide a digital implementation system for the entrepreneurship incentive mechanism for returned talents based on a knowledge fusion algorithm to solve the problems raised in the above background art.

[0007] To achieve the above purpose, the present invention provides the following technical solutions:

[0008] A digital implementation system for the entrepreneurship incentive mechanism for returned talents based on a knowledge fusion algorithm, comprising:

[0009] A data collection module: used to collect the training scores X of returned talents in various training courses j , collect the works, project achievements, and papers published by returned talents during the training period, and evaluate their practical abilities X p and creative levels X c ;

[0010] A data preprocessing module: preprocess the training scores X j , practical abilities X p and creative levels X c ;

[0011] A knowledge fusion algorithm module: combine the knowledge fusion algorithm to evaluate the potential advantages of returned talents in entrepreneurship through the training scores X j , practical abilities X p and creative levels X c ;

[0012] Incentive mechanism module: Design differentiated incentive strategies based on the potential advantages of returned talents in entrepreneurship analyzed by knowledge integration, and accurately implement the incentive strategies through digital means.

[0013] Further, the training score X j is the weighted sum score, that is, the scores of different classification items are processed by weighted summation, and the scores of different classification items are processed by weighted summation;

[0014] Among them, the set weight value is: if the classification item score is between 80 points and 100 points, the weight value is set to 0.5;

[0015] If the classification item score is between 60 points and 80 points, the weight value is set to 0.4;

[0016] If the classification item score is below 60 points, the weight value is set to 0.1;

[0017] Then the calculation of the score is as follows:

[0018]

[0019] Among them, X j represents the training score, n represents the number of classification items, i represents the sequence of classification items, w i represents the weight value with the serial number i, and x i represents the classification item score with the serial number i.

[0020] Further, the acquisition and analysis of the practical ability X p and the creative level X c are as follows:

[0021] Feature extraction: Extract features from the works, project results, and published papers completed by returned talents during the training period;

[0022] Ability evaluation dimension: Analyze and process according to the extracted features, analyze whether they can apply the knowledge learned to solve practical problems, whether they can discover market needs and propose innovative solutions, whether they can complete project tasks, and whether they have teamwork ability;

[0023] Innovation and creativity: Analyze and process according to the extracted features, analyze whether they have uniqueness and innovation, whether they can break through traditional thinking, discover new solutions, and whether they can integrate knowledge in different fields to form innovative thinking and solutions.

[0024] Further, the evaluation criteria for the practical ability X p are as follows:

[0025] Score evaluation: The practical ability X pAssessment: Based on feature matching, identify the application of learned knowledge, innovative solutions, project completion, and teamwork; if all four items are fully matched, the actual ability is X p The score is set between 80 points and 100 points;

[0026] If the above three items are correspondingly matched, the actual ability is X p The score is set between 60 points and 80 points;

[0027] If the above two items are correspondingly matched, the actual ability is X p The score is set between 40 points and 60 points;

[0028] If the above one item is correspondingly matched, the actual ability is X p The score is set below 40 points;

[0029] The described creativity level is X c Assessment: Based on feature matching, having uniqueness and innovation, new solutions, and innovative thinking; if all three items are fully matched, the actual ability is X p The score is set between 80 points and 100 points;

[0030] If the above two items are correspondingly matched, the actual ability is X p The score is set between 60 points and 80 points;

[0031] If the above one item is correspondingly matched, the actual ability is X p The score is set below 60 points.

[0032] Furthermore, the processing steps of the data preprocessing module are as follows:

[0033] Data cleaning: Identify and process missing values in the data, identify and remove outliers, remove duplicate data records, ensure the uniqueness of the data, and perform interpolation filling of the missing values and removed outliers with the data average;

[0034] Data conversion: Convert the data from multiple original formats to a structured data format, and unify the units and scales of the data;

[0035] Data standardization: Normalize the data according to a certain standard, and standardize the format and structure of the data;

[0036] Data denoising: Remove the noise in the data to ensure the stability and accuracy of the data.

[0037] Furthermore, the calculation of the knowledge fusion algorithm is as follows:

[0038] Analyze the advantages and potential of the total score in different ability dimensions through the proportion analysis of the classification item scores:

[0039]

[0040] Among them, X j represents the training score, and w i x i represents the classification item score, represents the average value of the training score, and Y represents the ratio of the classification item score to the average value of the training score;

[0041] Moreover, if the ratio Y of the classification item score to the average value of the training score is > 1, it indicates that the returned rural migrant workers are classified item technicians;

[0042] If the ratio Y of the classification item score to the average value of the training score = 1, it indicates that the returned rural migrant workers are comprehensive technicians.

[0043] Furthermore, the classification items in the training score include technical classification, management classification, and language classification;

[0044] According to the advantages and potential in different ability dimensions, the incentive strategies are divided into the following categories:

[0045] Technical support - type incentive: Provide technical training, technical tools, and special - fund support; Focus on supporting returned rural migrant talents with strong technical capabilities;

[0046] Management support - type incentive: Provide project management training, team - collaboration support, and resource - integration guidance; Focus on supporting returned rural migrant talents with strong management capabilities;

[0047] Verbal support - type incentive: Provide communication - skill training, career - network building opportunities, and market - resource guidance; Focus on supporting returned rural migrant talents with strong verbal capabilities;

[0048] Comprehensive - type incentive: Provide multi - field ability - improvement plans covering technology, management, and language aspects; Focus on supporting returned rural migrant talents with strong comprehensive capabilities;

[0049] And for entrepreneurs, provide incentive strategies in terms of land and factory buildings, preferential policies, and tax policies.

[0050] Furthermore, the calculation and analysis of the incentive strategies are as follows:

[0051]

[0052] Among them, Z represents the incentive - strategy score of returned rural migrant workers with different potentials based on the actual ability X p and the creativity level X c The YX j represents calculating the training score through the proportion value ratio to obtain the scores of returned rural migrant workers with different potentials, and X p represents the actual ability, and X cis represented as the creativity level, m is represented as the type of calculated parameters, w j1 and w j2 and w j3 are respectively represented as the corresponding weight values, w j1 + w j2 + w j3 = 1.

[0053] Furthermore, it also includes a feedback module. The feedback module is used for comprehensive optimization and continuous improvement. Through the combination of dynamic update, feedback mechanism and optimization, the specific process is as follows:

[0054] Initial strategy design: Set the initial incentive strategy division;

[0055] Dynamic update and feedback: Regularly conduct incentive strategy evaluation and feedback collection; According to the evaluation results and feedback data, dynamically adjust the incentive strategy;

[0056] Optimization model application: Use the optimization model to evaluate and improve the adjusted incentive strategy;

[0057] Innovation and adaptability: Introduce industry trends during the optimization process to dynamically adjust incentive measures; Ensure that the incentive strategy has strong adaptability and flexibility.

[0058] Compared with the prior art, the beneficial effects of the present invention are:

[0059] The present invention collects the training scores of the training courses for returned talents, and evaluates their actual abilities and creativity levels according to the works, project results, and published papers completed by the returned talents during the training period. Combining with the knowledge fusion algorithm, it evaluates the potential advantages of the returned talents in entrepreneurship through training scores, actual abilities and creativity levels, realizes the tendency evaluation and determination of the returned talents, determines the abilities of the returned talents, and then facilitates the analysis of incentive strategies according to the tendencies, actual abilities and creativity levels of the returned talents, and sets the incentive strategy division according to the tendencies of different returned talents, which is convenient for realizing the design of differentiated incentive strategies, accurately implementing incentive measures, and helping the returned talents overcome the actual difficulties in entrepreneurship;

[0060] The present invention also designs differentiated incentive strategies based on the specific needs and capabilities of returned talents to ensure the accuracy and effectiveness of incentive measures. Through a dynamic update and feedback mechanism, the incentive strategies can be adjusted in a timely manner to ensure the continuous optimization of policies and the maximization of implementation effects. By supporting the entrepreneurship of returned talents, the system can attract more high-quality talents to return to the local area, promote the construction of the local talent team and economic development. By implementing incentive policies, a good business environment can be created to attract more enterprises and investors to participate in local economic construction and promote the prosperity of the regional economy. Through knowledge fusion algorithms and differentiated incentive strategies, the system can adapt to the needs of different industries and regions, provide personalized support, and improve the overall performance and practicality of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 is a schematic structural diagram of the system of the present invention;

[0062] Figure 2 is a schematic diagram of the processing steps of the data preprocessing module of the present invention;

[0063] Figure 3 is a schematic flowchart of the feedback module of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0064] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with specific embodiments.

[0065] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those of ordinary skill in the field to which the present invention belongs. The "first", "second" and similar terms used in the present invention do not denote any order, quantity or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or objects appearing before the term cover the elements or objects listed after the term and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left" and "right" are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0066] Embodiment 1:

[0067] Please refer to Figures 1-3 , the present invention provides a technical solution: a digital implementation system for the entrepreneurship incentive mechanism of returned talents based on knowledge fusion algorithms, including:

[0068] Data collection module: used to collect the training scores X of returned talents in various training courses j , collect the works, project results, and papers published by returned talents during the training period, and evaluate their practical abilities X p and creative levels X c ;

[0069] Data preprocessing module: preprocess the training scores X j , practical abilities X p and creative levels X c ;

[0070] Knowledge fusion algorithm module: combine the knowledge fusion algorithm, and evaluate the potential advantages of returned talents in entrepreneurship through the training scores X j , practical abilities X p and creative levels X c ;

[0071] Incentive mechanism module: design a differentiated incentive strategy according to the potential advantages of returned talents in entrepreneurship analyzed by knowledge fusion, and accurately implement the incentive strategy through digital means.

[0072] In this embodiment, preferably, the training score X j is the weighted sum score, that is, the scores of different classification items are subjected to weighted sum processing, and the scores of different classification items are subjected to weighted sum processing;

[0073] Among them, the set weight value is: if the classification item score is between 80 points and 100 points, the weight value is set to 0.5;

[0074] if the classification item score is between 60 points and 80 points, the weight value is set to 0.4;

[0075] if the classification item score is below 60 points, the weight value is set to 0.1;

[0076] Then the calculation of the score is as follows:

[0077]

[0078] Among them, X j represents the training score, n represents the number of classification items, i represents the sequence number of the classification item, w i represents the weight value with the serial number i, and x i represents the classification item score with the serial number i;

[0079] It should be noted that the training score X j is the weighted sum score, that is, the scores of different classification items are subjected to weighted sum processing to facilitate obtaining the training score X j, and the scores of different classification items are used to facilitate subsequent analysis and calculation of the abilities or potential tendencies of the returned rural workers.

[0080] In this embodiment, preferably, the actual ability X p and the creativity level X c are collected and analyzed as follows:

[0081] Feature extraction: Extract features from the works, project achievements, and published papers completed by the returned rural talents during the training period;

[0082] Ability evaluation dimension: Analyze and process according to the extracted features to determine whether they can apply the learned knowledge to solve practical problems, whether they can discover market demands and propose innovative solutions, whether they can complete project tasks, and whether they have teamwork abilities;

[0083] Innovation and creativity: Analyze and process according to the extracted features to determine whether they have uniqueness and innovation, whether they can break through traditional thinking and discover new solutions, and whether they can integrate knowledge from different fields to form innovative thinking and solutions;

[0084] It should be noted that by extracting features from the works, project achievements, and published papers completed during the training period, and performing matching feature analysis and processing according to the knowledge base, the abilities and innovation capabilities of the returned rural talents are analyzed, which is convenient for improving the determination of the tendency distribution of the returned rural talents.

[0085] In this embodiment, preferably, the evaluation criteria of the actual ability X p are as follows:

[0086] Score evaluation: Evaluation of the actual ability X p : According to feature matching, identify the application of learned knowledge, innovative solutions, project completion, and teamwork; if all four items are completely matched, the score of the actual ability X p is set between 80 points and 100 points;

[0087] If three of the above items are correspondingly matched, the score of the actual ability X p is set between 60 points and 80 points;

[0088] If two of the above items are correspondingly matched, the score of the actual ability X p is set between 40 points and 60 points;

[0089] If one of the above items is correspondingly matched, the score of the actual ability X p is set below 40 points;

[0090] The creativity level X cEvaluation: Based on feature matching, it has uniqueness and innovation, new solutions, and innovative thinking; if all three of the above are completely matched, the actual ability is X p The score is set between 80 and 100 points;

[0091] If two of the above are correspondingly matched, the actual ability is X p The score is set between 60 and 80 points;

[0092] If one of the above is correspondingly matched, the actual ability is X p The score is set below 60 points;

[0093] It should be noted that by performing feature matching on the feature knowledge base and calculating and determining the score according to the number of feature matches, the scores of the actual ability and creative level can be effectively calculated, which is convenient for subsequent potential analysis of returning talents.

[0094] In this embodiment, preferably, the processing steps of the data preprocessing module are as follows:

[0095] Data cleaning: Identify and process missing values in the data, identify and remove outliers, remove duplicate data records, ensure the uniqueness of the data, and use the data average to interpolate and fill the missing values and remove outliers;

[0096] Data conversion: Convert the data from multiple original formats to a structured data format, and unify the units and scales of the data;

[0097] Data standardization: Normalize the data according to certain standards, and standardize the format and structure of the data;

[0098] Data denoising: Remove the noise in the data to ensure the stability and accuracy of the data;

[0099] It should be noted that by removing missing values, the integrity of the data is ensured, outlier processing excludes data points that interfere with the analysis, and duplicate data removal ensures the uniqueness of the data; data conversion facilitates improving the unity between data and is convenient for subsequent processing of the data, data normalization scales data from different sources to the same range, data standardization ensures the consistency and comparability of the data, and data denoising ensures the stability and accuracy of the data;

[0100] Set the collected data X, perform median filtering using windows of different scales, and then perform weighted fusion on the filtering results of different scales;

[0101]

[0102] Among them, y irepresents the filtered output data; S represents the number of scales, that is, the number of different scales used in the median filtering operation, and each scale corresponds to a filtering window of a different size; w s represents the weight of scale S, which is used to perform weighted averaging on the filtering results of different scales; represents the result of median filtering the data at scale S. Specifically, is all the data within the window range at scale S, that is, the neighborhood data at this scale; window s represents the neighborhood window corresponding to scale S. At different scales, the size of the neighborhood window is different.

[0103] The calculation of cleaning for outlier detection is as follows:

[0104] By calculating the difference between the data and the mean divided by the standard deviation, the Z-score of the data is obtained;

[0105]

[0106] Among them, X is the value of the data point, μ is the mean of the data set, σ is the standard deviation of the data set, and points with a G value greater than 3 or less than -3 are considered outliers, and the outliers are removed;

[0107] Missing value compensation is used for the vacancies after outlier removal, and missing values are filled by the mean, and the calculation of the mean is as follows:

[0108]

[0109] Among them, x i is the value of non-missing data, and n is the number of non-missing data.

[0110] The calculation of normalization is as follows:

[0111]

[0112] Among them, X is the input data, x min is the minimum value in the data set, x max is the maximum value in the data set, and the data is scaled to the range of [0, 1].

[0113] In this embodiment, preferably, the calculation of the knowledge fusion algorithm is as follows:

[0114] Analyze the advantages and potential of the total score in different ability dimensions by the proportion of classification item scores:

[0115]

[0116] Among them, X j represents the training score, wi x i is expressed as the classification item score, is expressed as the average value of the training score, and Y is expressed as the ratio of the classification item score to the average value of the training score;

[0117] Moreover, if the ratio Y of the classification item score to the average value of the training score is greater than 1, it indicates that the returned migrant is a technical personnel in the classification item;

[0118] If the ratio Y of the classification item score to the average value of the training score is equal to 1, it indicates that the returned migrant is a comprehensive technical personnel;

[0119] It should be noted that by calculating the proportion of the classification item score in the total score, and then according to the proportion ratio, the potential tendency of the returned migrant talents is determined, which is convenient to give improvement and entrepreneurship suggestions or work suggestions to the returned migrant talents according to the potential tendency, so that the work or entrepreneurship can be more adapted to the returned migrant talents.

[0120] In this embodiment, preferably, the classification items in the training score include technical classification, management classification and language classification;

[0121] According to the advantages and potential in different ability dimensions, the incentive strategies are divided into the following categories:

[0122] Technical support type incentive: Provide technical training, technical tools and special funds support; Focus on supporting the returned migrant talents with stronger technical capabilities;

[0123] Management support type incentive: Provide project management training, team collaboration support and resource integration guidance; Focus on supporting the returned migrant talents with stronger management capabilities;

[0124] Verbal support type incentive: Provide communication skills training, career network building opportunities and market resource guidance; Focus on supporting the returned migrant talents with stronger verbal capabilities;

[0125] Comprehensive type incentive: Provide multi-field ability improvement plans, covering technology, management and language aspects; Focus on supporting the returned migrant talents with stronger comprehensive capabilities;

[0126] And for entrepreneurs, incentive strategies in terms of land and factory buildings, preferential policies and tax policies are provided;

[0127] It should be noted that according to the tendency of the returned migrant talents, the incentive strategies are tilted in different directions or special incentives are realized, improving the specific adaptability of the incentive strategies, enabling the tendency of different returned migrant talents to obtain adaptive incentive strategies, designing differentiated incentive strategies, and ensuring the accuracy and effectiveness of the incentive measures.

[0128] In this embodiment, preferably, the calculation and analysis of the incentive strategy are as follows:

[0129]

[0130] Among them, Z represents the incentive strategy scores of returned rural workers with different potentials based on the actual ability X p and the creativity level X c The YX j represents calculating the training scores by the proportion of the ratio value to obtain the scores of returned rural workers with different potentials, X p represents the actual ability, X c represents the creativity level, m represents the types of calculated parameters, w j1 、w j2 、w j3 respectively represent the corresponding weight values, w j1 +w j2 +w j3 = 1;

[0131] It should be noted that according to the proportion of the training scores, the actual ability and the creativity level are used to calculate and analyze the incentive strategy, and according to the specific ability or potential, the policy is inclined, so that the returned talents can obtain more resources and help during the entrepreneurship process, significantly improving the entrepreneurship success rate, and can provide targeted support according to the specific needs and abilities of the returned talents to help them overcome various difficulties in entrepreneurship

[0132] In this embodiment, preferably, it further includes a feedback module, and the feedback module is used for comprehensive optimization and continuous improvement. Through the combination of dynamic update, feedback mechanism and optimization, the specific process is as follows:

[0133] Initial strategy design: Set the initial incentive strategy division;

[0134] Dynamic update and feedback: Regularly conduct incentive strategy evaluation and feedback collection; Dynamically adjust the incentive strategy according to the evaluation results and feedback data;

[0135] Optimization model application: Use the optimization model to evaluate and improve the adjusted incentive strategy;

[0136] Innovation and adaptability: Introduce industry trends during the optimization process to dynamically adjust the incentive measures; Ensure that the incentive strategy has strong adaptability and flexibility;

[0137] It should be noted that the design has the characteristics of dynamic update and optimization, can be continuously adjusted and improved according to the actual situation, ensuring the flexibility and adaptability of the system. Through the knowledge fusion algorithm and the differential incentive strategy, the system can adapt to the needs of different industries and regions, provide personalized support, and improve the overall performance and practicality of the system.

[0138] The tendency analysis of this application also includes visual display analysis:

[0139] Quantitative Analysis and Data Processing

[0140] Statistical analysis: Calculate the average scores of returned rural talents in various training courses, and identify high-scoring and low-scoring returned rural talents. Analyze the correlations between different ability dimensions, and evaluate the synergy effects of returned rural talents in various aspects of abilities.

[0141] Data visualization: Use charts (such as bar charts, line charts, radar charts, etc.) to visually display the training scores, ability dimension evaluation results, and ability tendency analysis of returned rural talents. Data privacy protection: Ensure that the collected and processed data complies with relevant privacy protection laws and regulations, and protect the personal information of returned rural talents.

[0142] Qualitative Analysis and Case Studies

[0143] In-depth interviews: Adopt the in-depth interview method to focus on understanding the problems encountered by returned rural talents in training, their solutions, as well as their understanding and gains from the training content.

[0144] Case studies: Select representative cases of returned rural talents, and deeply analyze their training performances, ability characteristics, and ability development potentials.

[0145] Knowledge integration analysis: Combine knowledge integration algorithms to analyze the combination of the knowledge mastered by returned rural talents in training with their own backgrounds and industry needs, and evaluate their potential advantages in entrepreneurship.

[0146] Parameter Comparison Table with Existing Technologies

[0147]

[0148]

[0149]

[0150] Summary: By comparing the parameters of the digital implementation system of the entrepreneurship incentive mechanism for returned rural talents using knowledge integration algorithms with existing technologies, it can be seen that there are significant advantages in aspects such as knowledge integration algorithms, incentive mechanisms, and feedback optimization. Specifically, in terms of incentive strategy classification, content, and entrepreneurship support measures, the system provides more comprehensive incentive measures and can more accurately support the entrepreneurship development of returned rural talents.

[0151] It should be noted that all the calculation formulas in this application document adopt regression analysis including but not limited to those in machine learning algorithms to deeply analyze the relevant parameters collected, identify their natural trends and interrelationships. Using professional software such as the Scikit-learn library of Python or the R language, a mathematical model matching the data is automatically generated. Then, the performance of the model is objectively evaluated through methods such as cross-validation, and combined with continuous feedback and optimization to ensure that the created formula truly reflects the internal laws of the data, thereby ensuring its effectiveness and accuracy. In all the calculation formulas of this application, the parameters in each formula are processed by dimensionlessization within a consistent range to ensure that different physical quantities are compared on the same scale; the technical means of dimensionlessization include but are not limited to Min-Max Normalization and Z-Score standardization;

[0152] Essentially, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disc of a computer, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of various embodiments of the present invention.

[0153] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus or device and execute the instructions), or used in combination with these instruction execution systems, apparatus or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by or in connection with an instruction execution system, apparatus or device.

[0154] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

[0155] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A digital implementation system for the entrepreneurial incentive mechanism for returned talents based on a knowledge fusion algorithm, characterized in that, include: Data collection module: used to collect the training scores X of returned talents in various training courses j , collect the works, project results, and published papers completed by returned talents during the training, and evaluate their practical abilities X p and creative levels X c ; Data preprocessing module: preprocess the training scores X j , actual capabilities X p and creativity levels X c ; Knowledge fusion algorithm module: Combining the knowledge fusion algorithm, evaluate the potential advantages of returning migrant talents in entrepreneurship through training performance X j , practical ability X p and creativity level X c ; Incentive mechanism module: Based on the potential advantages of returning talents in entrepreneurship analyzed through knowledge integration, differentiated incentive strategies are designed and accurately implemented through digital means.

2. The digital implementation system of the entrepreneurial incentive mechanism for returned talents based on the knowledge fusion algorithm according to claim 1, characterized in that: The training score X j is the weighted sum score, that is, the scores of different classification items are processed by weighted summation, and the scores of different classification items are processed by weighted summation; The weight value is set as follows: if the classification item score is between 80 points and 100 points, the weight value is set to 0.5; If the classification item score is between 60 and 80 points, the weight value is set to 0.4; If the classification item score is below 60 points, the weight value is set to 0.1; The scores are calculated as follows: Among them, X j represents the training score, n represents the number of classification items, i represents the sequence number of the classification item, and w i represents the weight value with the sequence number i, and x i represents the classification item score with the sequence number i.

3. The digital implementation system of the entrepreneurship incentive mechanism for returned talents based on the knowledge fusion algorithm according to claim 1, characterized in that: The actual ability X p and the creative level X c are collected and analyzed as follows: Feature extraction: Extract features from the works, project results, and published papers completed by returning talents during their training; Ability assessment dimensions: Analyze and process the extracted features to determine whether the candidate can apply the knowledge learned to solve practical problems, identify market needs and propose innovative solutions, complete project tasks, and possess teamwork skills. Innovation and Creativity: Analyze and process the extracted features to determine whether they are unique and innovative, whether they can break through traditional thinking and discover new solutions, and whether they can integrate knowledge from different fields to form innovative thinking and solutions.

4. The digital implementation system of the entrepreneurship incentive mechanism for returned talents based on the knowledge fusion algorithm according to claim 3, wherein: The actual ability X p Evaluation criteria: Score evaluation: actual ability X p Evaluation: Based on feature matching, identify the application of learned knowledge, innovative solutions, project completion, and teamwork; if all four items are completely matched, the actual ability is X p The score is set between 80 and 100 points; If it correspondingly matches the above three items, the actual ability X p The score is set between 60 points and 80 points; If it correspondingly matches the above two items, then the actual ability X p The score is set between 40 points and 60 points; If it correspondingly matches one of the above items, the actual ability X p The score is set to be below 40 points; The creative level X c Assessment: Based on feature matching, it has uniqueness and innovation, new solutions, and innovative thinking; if all three of the above are fully matched, the actual ability X p The score is set between 80 and 100 points; If it correspondingly matches the above two items, the actual ability X p The score is set between 60 points and 80 points; If it correspondingly matches one of the above items, the actual ability X p The score is set to be below 60 points.

5. The digital implementation system of the entrepreneurship incentive mechanism for returned talents based on the knowledge fusion algorithm according to claim 1, characterized in that: The processing steps of the data preprocessing module are: Data cleaning: Identify and process missing values in the data, identify and remove outliers, remove duplicate data records, ensure data uniqueness, and interpolate missing values and remove outliers using the average value of the data; Data conversion: converting data from various raw formats into structured data formats, unifying the units and scales of the data; Data standardization: normalize the data according to certain standards and standardize the format and structure of the data; Data denoising: Remove noise from data to ensure data stability and accuracy.

6. The digital implementation system of the entrepreneurship incentive mechanism for returned talents based on the knowledge fusion algorithm according to claim 1, characterized in that: The calculation of the knowledge fusion algorithm is as follows: Analyze the advantages and potential in different ability dimensions by using the proportion of the total score of the classification items: Among them, X j represents the training score, w i x i represents the classification item score, represents the average value of the training scores, and Y represents the ratio of the classification item score to the average value of the training scores; Moreover, if the ratio of the classification item scores to the average value of the training scores is greater than 1, it means that the returnees are classified item technicians; If the ratio of the classification item scores to the average training score is Y=1, it means that the returnees are comprehensive technical personnel.

7. The digital implementation system of the entrepreneurship incentive mechanism for returned talents based on the knowledge fusion algorithm according to claim 1, characterized in that: The classification items in the training results include technical classification, management classification and language classification; Incentive strategies are divided into the following categories based on the strengths and potentials in different capability dimensions: Technical support incentives: providing technical training, technical tools and special funding support; focusing on supporting returning talents with strong technical capabilities; Management support incentives: Provide project management training, team collaboration support, and resource integration guidance; focus on supporting returning talents with strong management capabilities; Verbal support incentives: providing communication skills training, career networking opportunities, and market resource guidance; focusing on supporting returning talents with strong verbal skills; Comprehensive incentives: Provide multi-disciplinary capacity-building programs covering technical, management, and language skills, with a focus on supporting returning talents with strong comprehensive abilities. We also provide entrepreneurs with incentive strategies in terms of land, factories, preferential policies and tax policies.

8. The digital implementation system of the entrepreneurship incentive mechanism for returned talents based on the knowledge fusion algorithm according to claim 1, characterized in that: The calculation analysis of the incentive strategy is as follows: Among them, Z represents the incentive strategy scores for returning rural workers with different potentials based on their actual ability X p and creative level X c The score of YX j is represented as the training score calculated by the proportion value, and the scores of returning rural workers with different potentials are obtained. X p represents the actual ability, X c represents the creative level, m represents the type of calculation parameters, w j1 、w j2 、w j3 respectively represent the corresponding weight values, w j1 +w j2 +w j3 = 1.

9. The digital implementation system of the entrepreneurship incentive mechanism for returned talents based on the knowledge fusion algorithm according to claim 1, characterized in that: It also includes a feedback module, which is used for comprehensive optimization and continuous improvement. Through the combination of dynamic update, feedback mechanism and optimization, the specific process is as follows: Initial strategy design: Set the initial incentive strategy division; Dynamic update and feedback: Regularly conduct incentive strategy evaluation and feedback collection; Dynamically adjust the incentive strategy according to the evaluation results and feedback data; Optimization model application: Use the optimization model to evaluate and improve the adjusted incentive strategy; Innovation and adaptability: Introduce industry trends during the optimization process to dynamically adjust incentive measures; Ensure that the incentive strategy has strong adaptability and flexibility.

Images