Talent value evaluation method and system

Abstract

The invention relates to the technical field of talent values, in particular to a talent value evaluation method and system, and the method comprises the following steps: data acquisition: obtaining basic information and value-added information of a user through an information collection system; initial evaluation: generating an initial value evaluation result based on a preset reference person hypothesis parameter in combination with an area where the user is located; value-added evaluation: performing dynamic quantitative analysis on the value-added information through a value-added model to generate a value-added value; comprehensive evaluation: performing summation calculation on the initial value evaluation result and the added value to generate a final comprehensive value evaluation result; the system comprises a data acquisition module, an initial evaluation module, a value-added evaluation module, a comprehensive evaluation module and a dynamic correction module. The method has the effect of improving the accuracy of talent value evaluation.

Description

Technical Field

[0001] This application relates to the technical field of talent value, and particularly to a talent value evaluation method and system. Background Art

[0002] In the fields of human resource management and finance, accurately evaluating the value of talents is of great significance for aspects such as an enterprise's recruitment, selection, training, and salary design, or a bank's assessment of repayment ability. Traditional talent evaluation methods often focus on examining a talent's current capabilities while neglecting the assessment of their future potential.

[0003] In the prior art, talent value evaluation usually relies on static parameters and single-dimensional data. For example, it is estimated only through educational background or work experience, resulting in a relatively low accuracy of talent value evaluation. Summary of the Invention

[0004] To improve the accuracy of talent value evaluation, this application provides a talent value evaluation method and system.

[0005] In a first aspect, a talent value evaluation method provided by this application adopts the following technical solution: A talent value evaluation method includes the following steps: Data acquisition: Obtain the basic information and value-added information of a user through an information collection system; Initial evaluation: Generate an initial value evaluation result based on preset benchmark person hypothesis parameters and in combination with the region where the user is located; Value-added evaluation: Conduct dynamic quantitative analysis on the value-added information through a value-added model to generate a value-added value; Comprehensive evaluation: Non-linearly weight and integrate the initial value evaluation result and the value-added value to generate a final comprehensive value evaluation result.

[0006] By adopting the above technical solution, for data acquisition, initial evaluation (combining regional economic parameters), value-added evaluation (dynamic quantitative analysis), and comprehensive evaluation, the prior art only conducts evaluations based on static and limited user information (such as educational background and work experience). This solution obtains the basic information and value-added information of a user through an information collection system and conducts dynamic and comprehensive evaluations; it improves the accuracy and comprehensiveness of the evaluation, can more truly reflect the actual value of talents; the introduction of value-added information makes the evaluation result more timely, can reflect the achievements and potential of talents in specific fields, and enhances the flexibility and accuracy of the evaluation.

[0007] Optionally, the benchmark person hypothesis parameters include at least one of preset educational level, work experience, geographical distribution, and cognitive ability.

[0008] By adopting the above technical solution, the prior art does not clearly set the benchmark person hypothesis parameters, while this solution defines the benchmark person hypothesis parameters, including educational level, work experience, geographical distribution, cognitive ability, etc., integrates multi-dimensional parameters, enhances the comprehensiveness of the evaluation, and reduces the deviation caused by information loss; improves the standardization of the initial evaluation by presetting the benchmark parameters; provides a clear and comprehensive benchmark for the initial evaluation, making the evaluation results more comparable; the introduction of geographical distribution takes into account the impact of regional economic differences on the value of talents, improves the rationality of the evaluation, and makes the evaluation of talent value more regionally accurate.

[0009] Optionally, the value-added information includes at least one of skill certificates, social positions, honorary awards, and intellectual property rights, and the value-added model quantifies the influence weight of the value-added information through dynamically configured coefficients.

[0010] By adopting the above technical solution, the prior art does not consider value-added information or the quantification method of value-added information is relatively simple; this solution conducts dynamic quantitative analysis on value-added information through a value-added model, and introduces dynamically configured coefficients to support the differential impact of different types of value-added information, enhancing the adaptability of the model to different occupational scenarios; the quantitative analysis of value-added information makes the evaluation results more refined and accurate; the introduction of dynamically configured coefficients enables the weight of value-added information to be adjusted according to the actual situation, improving the flexibility of the evaluation.

[0011] Optionally, in the initial evaluation step, it further includes: dynamically generating a confidence coefficient based on the degree of information loss, which is used to adjust the uncertainty range of the initial value evaluation result.

[0012] By adopting the above technical solution, a confidence coefficient is dynamically generated based on the degree of information loss, which is used to adjust the uncertainty range of the initial value evaluation result; the introduction of the confidence coefficient makes the evaluation results more robust and reliable; the dynamic generation method of the confidence coefficient enables the evaluation results to become gradually precise as the user's information is improved.

[0013] Optionally, the generation logic of the confidence coefficient includes: Allocating an initial confidence interval according to the number of dimensions of user information loss; Dynamically narrowing the confidence interval and updating the confidence coefficient based on the progress of the user's subsequent information improvement; Wherein, the confidence coefficient is generated in the following manner: In the initial stage, a random perturbation coefficient is allocated according to the number of dimensions of user information loss, and the value of the random perturbation coefficient is 0.9 - 1.1; Gradually narrowing the confidence interval and correcting the perturbation coefficient as the user's information is improved; Adjusting the dynamic range of the confidence coefficient by combining regional economic parameters and industry average revenue data.

[0014] By adopting the above technical solution, by elaborating on the generation logic of the confidence coefficient, including the allocation of the initial confidence interval, the dynamic narrowing of the confidence interval, and the update of the confidence coefficient, etc., the dynamic confidence coefficient (in the range of 0.9 - 1.1) reflects the dynamic impact of information integrity, enabling the initial evaluation result to more truly reflect the potential risk of information loss and providing a quantitative basis for subsequent dynamic correction; the generation logic of the confidence coefficient quantifies and adjusts the uncertainty of the evaluation result; the dynamic update method of the confidence coefficient enables the evaluation result to gradually converge as the user information is improved.

[0015] Optionally, the initial evaluation step adopts the future earnings discount model, specifically including: Calculating the user's benchmark theoretical annual income through the Mincer equation; Estimating the future promotion probability and income growth rate; Combining the confidence coefficient to perform interval correction on the discount result to generate the initial value evaluation result.

[0016] By adopting the above technical solution, the prior art does not use the future earnings discount model or the Mincer equation for initial evaluation; this solution adopts the future earnings discount model and calculates the user's benchmark theoretical annual income through the Mincer equation; then converting the benchmark theoretical annual income into the value of the talent, making the evaluation result more practical and able to reflect the true value appreciation of the talent and the future earnings potential of the talent; the input parameters of the Mincer equation comprehensively consider various factors of the talent, improving the accuracy and comprehensiveness of the evaluation.

[0017] Optionally, the input parameters of the Mincer equation include: At least five of educational level, years of work, geographical distribution, gender, cognitive ability, and family environment; The geographical distribution is mapped to the major economic regions through the user's mobile phone number and associated with the regional average income parameter.

[0018] By adopting the above technical solution, the input parameters of the Mincer equation are clarified, including educational level, years of work, geographical distribution, gender, cognitive ability, family environment, etc.; the comprehensiveness of the input parameters makes the calculation result of the Mincer equation more accurate and reliable; the introduction of parameters such as geographical distribution and gender makes the evaluation result more in line with the actual situation and more representative of the region, and the growth of talents varies in different regions. Through differentiation, it is convenient to accurately evaluate the value of talents; by mapping to the major economic regions and associating with the regional income parameters; the regional economic differences directly affect the calculation of the theoretical annual income, enhancing the practical fit of the evaluation result; the automatic mapping of the mobile phone number simplifies the data collection process.

[0019] Optionally, the information collection system automatically completes the unfilled fields using the benchmark person hypothesis and marks them as items to be corrected.

[0020] By adopting the above technical solution, the information collection system automatically completes the unfilled fields by assuming a benchmark person and marks them as items to be corrected; the automatic completion function improves the efficiency and integrity of information collection, ensures the integrity of the initial evaluation, avoids interrupting the process due to data loss, and marking the items to be corrected guides the user to supplement key information subsequently; the marking of the items to be corrected enables the user to conveniently supplement and improve the information, improving the accuracy of the evaluation result; and the marking is convenient for reflecting the compliance and authenticity of the talent value evaluation when the talent value is feedback.

[0021] Optionally, the method further includes a dynamic correction step for monitoring the progress of the user's information improvement and updating the basic information and value-added information in real time; Re-execute the initial evaluation and value-added evaluation steps based on the updated data; Output the corrected comprehensive value evaluation result.

[0022] By adopting the above technical solution, this solution includes a dynamic correction step for monitoring the progress of the user's information improvement and updating the evaluation result in real time; the dynamic correction step enables the evaluation result to be continuously updated as the user's information is improved, improving the timeliness and accuracy of the evaluation; the evaluation result updated in real time can better reflect the actual value and development potential of the talent; ensure that the evaluation result is gradually optimized as the user's information is improved; enhance the user experience and the timeliness of the evaluation result.

[0023] In a second aspect, a system provided by the present application adopts the following technical solution: A talent value evaluation system includes the following modules: A data acquisition module: used to acquire the basic information and value-added information of the user through an information collection system; An initial evaluation module: the input end is connected to the output end of the data acquisition module, and is used to generate an initial value evaluation result based on preset benchmark person assumption parameters and in combination with the user's region; A value-added evaluation module: the input end is connected to the output end of the initial evaluation module, and is used to perform dynamic quantitative analysis on the value-added information through a value-added model to generate a value-added value; A comprehensive evaluation module: the input end is connected to the output end of the value-added evaluation module, and is used to non-linearly weighted integrate the initial value evaluation result and the value-added value to generate a final comprehensive value evaluation result.

[0024] By adopting the above technical solutions, users submit their basic information and value-added information through the information collection system; the data acquisition module receives and processes this information to ensure the integrity and accuracy of the data; for the fields that are not filled, the system automatically completes them using the benchmark person hypothesis and marks them as items to be corrected for subsequent improvement; the initial evaluation module receives the user information from the data acquisition module; based on the preset benchmark person hypothesis parameters (such as educational level, work experience, geographical distribution, cognitive ability, etc.), combined with the economic parameters of the region where the user is located, the future income discount model (especially the Mincer equation) is used to calculate the user's benchmark theoretical annual income; estimates the user's future promotion probability and income growth rate, and combines the confidence coefficient to correct the discount result within an interval to generate the initial value evaluation result; the value-added evaluation module receives the initial evaluation result and the user's value-added information (such as skill certificates, social positions, honorary awards, intellectual property rights, etc.); conducts dynamic quantitative analysis on the value-added information through the value-added model, considering the weights of different value-added information (determined by the dynamic configuration coefficient), and generates the value-added value; the comprehensive evaluation module receives the initial value evaluation result and the value-added value; integrates the two non-linearly with weights, considering the interaction and mutual influence among various factors, and generates the final comprehensive value evaluation result; the system continuously monitors the improvement progress of the user information; when the user information changes or is improved, the system updates the basic information and value-added information in real time; based on the updated data, the system re-executes the initial evaluation and value-added evaluation steps, and outputs the corrected comprehensive value evaluation result.

[0025] The modular design of the system makes the evaluation process clearer and more controllable; the connection and cooperation between modules enable the evaluation result to accurately and comprehensively reflect the value of talents; the scalability and maintainability of the system are improved, and it can adapt to the changes in different scenarios and requirements.

[0026] In summary, this application includes at least one of the following beneficial technical effects: 1. Data acquisition, initial evaluation (combined with regional economic parameters), value-added evaluation (dynamic quantitative analysis), comprehensive evaluation (non-linear weighted integration). The prior art only evaluates based on static and limited user information (such as educational background, work experience). This solution obtains the user's basic information and value-added information through the information collection system and conducts dynamic and comprehensive evaluations; improves the accuracy and comprehensiveness of the evaluation, and can more truly reflect the actual value of talents; the introduction of value-added information makes the evaluation result more timely, can reflect the achievements and potential of talents in specific fields, and enhances the flexibility and accuracy of the evaluation; 2. This solution adopts the future income discount model and calculates the user's benchmark theoretical annual income through the Mincer equation; then it converts the benchmark theoretical annual income into the value of talents, making the evaluation result more practical and capable of reflecting the true value appreciation of talents and their future income potential; the input parameters of the Mincer equation comprehensively consider various factors of talents, improving the accuracy and comprehensiveness of the evaluation; 3. The dynamic correction step enables the evaluation result to be continuously updated as the user information is improved, enhancing the timeliness and accuracy of the evaluation; the real-time updated evaluation result can better reflect the actual value and development potential of talents; it ensures that the evaluation result is gradually optimized as the user information is improved; it improves the user experience and the real-time nature of the evaluation result. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is the flowchart of the talent value evaluation method in the embodiment of the present application; Figure 2 is the detailed flowchart of the initial evaluation step in the embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The following Figures 1 to 2 is a further detailed description of the present application.

[0029] This embodiment discloses a talent value evaluation method.

[0030] Referring to Figure 1 and Figure 2 , the talent value evaluation method includes the following steps: Data acquisition: Obtain the user's basic information and value-added information through the information collection system; the value-added information includes at least one of skill certificates, social positions, honorary awards, and intellectual property rights; the information collection system automatically completes the unfilled fields using the benchmark person hypothesis and marks them as items to be corrected.

[0031] Specifically, the basic information includes: mobile phone number, ID number, gender, education level, graduation school, year of starting work, year of joining the current company, ethnicity, marital information, position (position category, industry), household type, work location, parents' education level, whether English is used at work, English proficiency, whether a computer is used at work, type of work unit, monthly income, and health status.

[0032] Specifically, all the information collected is data information collected legally or obtained through legal channels.

[0033] Initial evaluation: Generate an initial value evaluation result based on the preset benchmark person hypothesis parameters and in combination with the user's region; among them, the benchmark person hypothesis parameters include at least one of the preset education level, work experience, geographical distribution, and cognitive ability; Dynamically generate a confidence coefficient based on the degree of information loss to adjust the uncertainty range of the initial value assessment result; the generation logic of the confidence coefficient includes: Allocate an initial confidence interval according to the number of missing dimensions of user information; Dynamically narrow the confidence interval and update the confidence coefficient based on the progress of the user's subsequent information improvement; Among them, the confidence coefficient is generated in the following manner: In the initial stage, allocate a random perturbation coefficient according to the number of missing dimensions of user information, and the value of the random perturbation coefficient is 0.9 - 1.1; As the user's information improvement progresses, gradually narrow the confidence interval and correct the perturbation coefficient; Adjust the dynamic range of the confidence coefficient by combining regional economic parameters and industry average revenue data.

[0034] Specifically, the initial evaluation step adopts the future income discount model, which specifically includes: Calculate the user's benchmark theoretical annual income through the Mincer equation; Estimate the future promotion probability and income growth rate; Perform interval correction on the discount result by combining the confidence coefficient to generate the initial value assessment result; the input parameters of the Mincer equation include: At least five of educational level, working years, regional distribution, gender, cognitive ability, and family environment; The regional distribution is mapped to a large economic region through the user's mobile phone number and associated with the regional average revenue parameter.

[0035] Specifically, the so-called benchmark person hypothesis means making assumptions at the average level or slightly lower than the average level for each variable parameter required for the calculation of the J-F lifetime income method model; the specific assumptions are: junior college degree, ordinary college; female; 38 years old, started working at 25 years old, joined the current company this year; tertiary industry, other personnel positions; urban household register, non-party member; neither parent has received a high school or above education; does not know English and does not need to use English at work; needs to use a computer at work; cognitive ability is at the average level, that is: 1.934808850288391; the work location is the area corresponding to the mobile phone number location; the salary level is the average salary level corresponding to the mobile phone number location; The original J-F lifetime income method was mainly used to estimate the macro stock of human capital in a region, but it was insufficient in accurately estimating specific individuals, especially heterogeneous human capital. Moreover, the original J-F lifetime income method only evaluated the impact of educational investment on human capital, which was not comprehensive enough. To solve this problem, in the research project in cooperation with Central University of Finance and Economics, Professor Li Haizheng further improved and extended this method, adding a comprehensive evaluation of dimensions such as "cognitive ability", "work experience", "gender", "ethnicity", "political status", "work area", and "family environment" of talents.

[0036] The J-F lifetime income method is a discount method based on future income, which calculates the total sum of the income that the evaluated person can obtain in the future during the time they stay in the labor market. The evaluation process is divided into five steps in total: The first step: Obtain information on the user's education level, work years, location, gender, ethnicity, cognitive level, and family environment, and then estimate the "theoretical annual income in the evaluation year" of the evaluated person through the Mincer equation.

[0037] The second step: Estimate the promotion probability of the evaluated person in the next 5 years through the work years and the coefficients given by Central University of Finance and Economics, and then take the average value and convert it into the promotion probability in the current year; The third step: Estimate how many times the income will increase after career promotion in different years, as well as the normal growth rate of wages in different years; The fourth step: Based on the "theoretical annual income in the evaluation year" obtained from the Mincer equation, multiply it by the different promotion probabilities and promotion income growth rates in future years to calculate the theoretical annual income of the evaluated person in future years until retirement; The fifth step: Accumulate the incomes in future years to obtain the "lifetime income" of the evaluated person, that is, the value of the person, and then combine it with the average value of the benchmark person to calculate the proportion of the evaluated person's value to the average value of the benchmark person, and convert it into the basic value, that is, the initial value.

[0038] Value-added evaluation: Dynamically quantify and analyze the value-added information through a value-added model to generate a value-added value; among them, the value-added model quantifies the influence weight of the value-added information through dynamically configured coefficients; Comprehensive evaluation: Sum up the initial value evaluation result and the value-added value to generate the final comprehensive value evaluation result; The method also includes a dynamic correction step for monitoring the progress of user information improvement and real-time updating of basic information and value-added information; Re-execute the initial evaluation and value-added evaluation steps based on the updated data; Output the corrected comprehensive value evaluation result.

[0039] Specifically, data acquisition and benchmark person assumption: The user completes registration by entering a mobile phone number through the registration interface. The system automatically parses the location of the mobile phone number. According to Table 1: Mapping Table of Some Regions and Some Major Economic Regions, the user's work location is mapped to a preset major economic region (such as the eastern coastal area, central region, western region, or northeast region). For the unfilled basic information fields (such as education level, work experience), the system uses the benchmark person assumption to automatically complete the default parameters: Education level: College degree from a general institution; Work experience: Slightly lower than the industry average (default starting work at 25 years old and joining the current company at 38 years old); Geographic distribution: Mapped to the major economic region according to the location of the mobile phone number; Cognitive ability: Preset benchmark value of 1.934808850288391; The missing fields are marked as items to be corrected (such as "Educational background - to be supplemented"), and the progress bar on the user interface prompts information to improve the priority.

[0040] Table 1 Mapping Table of Some Regions and Some Major Economic Regions Eastern and coastal regions Northeastern region Western region Central region Beijing Municipality Heilongjiang Province Shaanxi Province Inner Mongolia Autonomous Region Tianjin Municipality Jilin Province Gansu Province Shanxi Province Shanghai Municipality Liaoning Province Ningxia Hui Autonomous Region Henan Province Hebei Province / Qinghai Province Anhui Province Shandong Province / Xinjiang Uygur Autonomous Region Jiangxi Province Jiangsu Province / Tibet Autonomous Region Hubei Province Zhejiang Province / Sichuan Province Hunan Province Fujian Province / Chongqing Municipality / Guangdong Province / Guizhou Province / Hainan Province / Yunnan Province / / / Guangxi Zhuang Autonomous Region / Initial assessment: Future income discount model: The initial assessment module calls the J-F lifetime income method. The specific process is as follows: The Mincer equation calculates the benchmark theoretical annual income. The input parameters include education level (X1_1~X1_7, see Table 2 below), work years (X2_1), geographic distribution (X10_1~X10_4), gender (X3), cognitive ability (X15), etc. Table 2 Model Variables and Their Code Tables of the Lifetime Income Method

[0041] The geographic parameters are mapped to the major economic region through the mobile phone number and associated with the regional income parameters in Table 3 below: Table of Average Wages in Some Regions.

[0042] Table 3 Table of Average Wages in Some Regions (2018 - 2019)

[0043] Example: A certain user is mapped to the eastern coastal area, and the average income parameter of this area is called as the benchmark input.

[0044] Estimate the future promotion probability and income growth rate: Generate a promotion probability curve based on the user's work years (such as 10 years) and the industry average promotion cycle (such as 5 years); Adjust the future income growth rate in combination with the industry fluctuation parameters of the major economic region (such as the income growth rate coefficient in the eastern region is 1.2 - 1.5 times).

[0045] Confidence coefficient correction: In the initial stage, a random perturbation coefficient (0.9 - 1.1) is assigned according to the number of missing information dimensions to generate an initial value evaluation interval (e.g., 3 million - 4 million). If the user only fills in 50% of the basic information, the confidence interval is ±15%; after it is completed to 80%, the interval is reduced to ±5%.

[0046] According to the complete parameters of the preset benchmark person, at the benchmark level of the average value in each information dimension required for the J-F lifetime income method evaluation, substitute it into the Mincer equation to calculate the benchmark personal value. Then, combined with the estimated initial personal value of the user, calculate the proportion of the user's initial personal value in the benchmark personal value at the average value benchmark level to obtain the user's initial value.

[0047] Incremental evaluation: Dynamic quantitative analysis: When the user supplements incremental information (such as "Certificate of TEM-8"), the incremental evaluation module performs the following operations: Dynamic configuration of weight coefficients: Match the preset weights according to the incremental item category (e.g., skill certificate im = 60, social position im = 100); Call the incremental item configuration table (see Table 4) to determine the parameters (r = 0.001, k = 1).

[0048] Since the total number of incremental items available for evaluation in reality cannot be determined and is constantly changing, a dynamic configuration method will be used to control the incremental items. The specific configuration method is as follows: Table 4 Configuration of Incremental Items Value-added project ID Value-added project name Value-added category Curve coefficient r Important coefficient im Refinement coefficient k Switch c 100001 Professional English Test Band 8 Skill certificate 0.001 60 1 1 100002 Broker certificate Skill certificate 0.001 35 1 1 200001 Municipal Political Consultative Conference member Social position 0.001 100 1 1 300001 Municipal model worker Meritorious honor 0.001 50 1 1 400001 Nobel Prize in Physics Award 0.001 320 1 1 400002 Fields Medal Award 0.001 280 1 1 500001 Real estate Immovable property 0.001 120 1 1 The values in the table are all examples. The specific values need to be verified and studied according to the actual situation before being finally determined; in the future, with the expansion of the incremental formula, the configuration items in the configuration table will also increase; Substitute into the incremental model formula: ; In the formula, is the time that the user to be evaluated stays in the labor market from the evaluation year until retirement, is the year, ; is the total working time in the year, that is, Exp = current year - year of starting work; is the time when the user obtains this incremental item in the year; is the age of the user in the year; is the curve parameter, used to control the curvature of the dynamic curve, and the default value is 0.001; is an importance coefficient, used to express the impact degree of this value-added item on the personal value, with a value range of 1 - 1000. The larger the value, the higher the weight; is a switch control coefficient, with a value of 0 or 1. When it is 0, this value-added item is turned off and no longer takes effect; when it is 1, this value-added item is turned on; is a magnification refinement coefficient, used to refine the magnification of the impact of the value-added item on the income; is the theoretical annual income of the current year, calculated by the Mincer equation; Through the above formula, the original value-added value is calculated, and then the original value-added value is converted. By calculating the proportion of the original value-added value to the average personal value of the benchmark person, the final value-added value is obtained.

[0049] Comprehensive evaluation: Calculate the final talent value, and the calculation method is to calculate the sum of the basic value and the value-added value; In other implementation manners, since the basic value is the user value calculated by using the JF lifetime income method through the user's core long-term information, the result is relatively stable and has a high weight; the value-added value is the value-added part based on the core value converted through the accounting of some value-added items of the user, and the result has a higher degree of dynamics and a lower weight. Non-linear weighted integration can be adopted: The comprehensive evaluation module performs non-linear integration on the initial value evaluation result and the value-added value: Weight distribution: The weight of the basic value is 70%, and the weight of the value-added value is 30%; Non-linear correction: If the value-added item is highly matched with the target position (such as an IT certificate matching a technical position), trigger the magnification coefficient to increase the value-added weight, and finally output the comprehensive value evaluation result.

[0050] Dynamic correction and scenario adaptation: Dynamic correction: When the user updates the education level to a postgraduate degree, the system re-executes the Mincer equation calculation to correct the theoretical annual income; The confidence interval shrinks from ±10% to ±5% as the information completeness improves; The update log records the changes in the evaluation results before and after the correction.

[0051] Scenario adaptation output: Financial adaptation value: Based on the disposable income model, combined with the age coefficient (1.2 for 31 - 40 years old), marital status (1.2 for married), and external credit data (Lingxi score / 700), generate a credit adaptation interval; Among them, according to the user's comprehensive income assessment, combined with the user's reasonable income adjustment coefficient, subtracting the basic expenditure, the user's disposable income can be calculated; The income adjustment coefficients are as follows (see Tables 5-1, 5-2, 5-3, and 5-4): Table 5-1 Income Adjustment Coefficient for Age Age Coefficient Under 18 years old 0 18 - 30 years old 1 31 - 40 years old 1.2 41 - 50 years old 1.2 51 - 65 years old 1.1 Over 65 years old 0 Table 5-2 Income Adjustment Coefficient for Education Level Educational background Coefficient Technical secondary school or below 0.7 Junior college 0.8 Undergraduate 1 Postgraduate 1.2 Doctor or above 1.5 Table 5-3 Income Adjustment Coefficient for Marital Status Marital status Coefficient Unmarried 0.8 Married 1.2 Table 5-4 Income Adjustment Coefficient for Real Estate Situation

[0052] According to the financial industry convention, 70% of the disposable income can be recognized as the user's debt repayment ability; According to the average annualized interest rate of 10% that an ordinary individual can apply for in the financial market, for a ten-year equal principal and interest credit loan product, the monthly repayment amount for a principal of 100,000 yuan is 2,124 yuan; (User's debt repayment ability / 2,124 yuan) × 100,000 yuan is the financial value of the customer; Considering the particularity of high-level talents, the following corresponding values are additionally added to their financial value (see Table 6): Table 6 Additional Value for Talent Rating Talent rating Value-added amount Class A 10 million Class B 5 million Class C 1 million Class D 500,000 Class E 200,000 Considering that there is a chance that the financial value is higher than the personal value, take the minimum value between the financial value and personal value * 0.7; Finally, the financial value is further processed by introducing the external Lingxi score and blacklist. If the blacklist is hit, take 0.2 of the financial value, and if not hit, it is 1; referring to the previous application of the Lingxi score, use the Lingxi score divided by 700 as the adjustment coefficient; Financial Value Evaluation Model: Financial Value: The reasonable credit debt-bearing ability of the user User income = (Job value / 12) × 0.5 + Local average monthly salary × 0.2 + Customer-reported monthly income × 0.3; User income adjustment coefficient = Age coefficient + Education coefficient + Marital coefficient + Real estate coefficient; User's average monthly basic expenditure = 2,000; User's monthly disposable income = Income × coefficient - Average basic expenditure; If the monthly disposable income is less than 0, count it as 0; User's monthly repayment ability = Monthly disposable income × 0.7; Combining the financial loan market, an ordinary individual can apply for a five-year personal consumption loan with an average annualized interest rate of 10% and an equal principal and interest repayment method. The monthly repayment amount for every 100,000 yuan is 2,124 yuan; Financial value 1 = (((Income × coefficient - Average basic expenditure) × 0.7) / 2,124) × 100,000; Considering the particularity of high-level talents, their financial value is additionally increased by the corresponding financial value; Considering the possibility that the financial value is higher than the personal value, take the minimum value between the financial value and 0.7 times the personal value; Finally, the external Lingxi score and blacklist are introduced into the financial value for further processing. If the blacklist is hit, take 0.2 of the financial value; if not, it is 1.

[0053] Referring to the previous application of the Lingxi score, use the Lingxi score divided by 700 as the adjustment coefficient.

[0054] Job matching value: The job personal value is the evaluated personal value for the application scenario of users "doing things". Our definition of the job personal value is: The different annual salary levels corresponding to different users in different positions.

[0055] The job personal value will establish different job salary databases for positions in different regions, with different work experiences and different industries through the method of Internet big data capture. Finally, according to the user information, it is mapped into different job personal values.

[0056] Capture the industry benchmark parameters of the target position (such as "senior engineer"), match the user's skill certificates and work years, and output the percentile level (such as Top 20%).

[0057] Visual feedback and optimization suggestions: Information completeness interface: The progress bar shows the current completeness (such as 80%), and highlights the items to be corrected (such as "Mother's education level - to be supplemented"); Prompt the user to complete high-priority information (such as educational background, work experience).

[0058] Evaluation result display: The radar chart shows the correlation of the comprehensive value, financial adaptation value, and job adaptation value; the heat map shows the contribution degree of the value-added items to the evaluation result (such as the certificate accounts for 40%, and the honor accounts for 30%).

[0059] Configuration suggestion tool: Simulate the change of the evaluation result after the user adds "real estate" (im = 120) (such as the comprehensive value increases by 15%); recommend high-weight value-added items (such as "provincial award im = 200").

[0060] Specifically, the refined evaluation of the comprehensive value refers to the process in which after the user becomes a platform user, as the use of the platform products deepens, gradually improves the information in each dimension, thus continuously correcting the personal value and obtaining a more accurate comprehensive personal value evaluation result.

[0061] For the improvement of information, it mainly includes two parts: Improvement of basic information: The basic information will be used in the J-F lifetime income method model to evaluate the basic value of the user. When the user first registers, the basic information in each dimension uses the benchmark person hypothesis. As the user's information is improved, the default values in each dimension of the benchmark person hypothesis will be corrected. While obtaining a more accurate user profile, a more accurate comprehensive value evaluation result will also be obtained.

[0062] Improvement of value-added information: The value-added information will be used in the value-added model to calculate the value-added of the user. The user can add new value-added items at any time. After being calculated by the value-added model, this item will be converted into value and added to the user's comprehensive value.

[0063] In the solution of this application, the acquisition of economic data changes according to the annual summary of economic data, such as average monthly salary and average annual salary.

[0064] In this embodiment, the confidence coefficient and the dynamic correction mechanism are used to ensure that the evaluation result gradually converges to the true value as the information is improved; the regional economic parameters and the value-added model (non-linear formula) enhance the adaptability of the region and the scenario. The benchmark person hypothesis covers multiple dimensions such as education, experience, and region, reducing the deviation caused by information loss; the financial and job matching value meets the needs of multiple scenarios (job hunting, credit); the visual interface guides the user to improve information and enhances the sense of participation; the real-time feedback and simulation tools help the user formulate a value improvement strategy.

[0065] In other embodiments, there are differences in the value representation and income between men and women. In order to better calculate the value of talents accurately, the calculation model of the value-added value is updated as follows: ; Among them, s is the gender, the index of men is greater than that of women, the value range of s is 0-1, and the value of the index is determined according to actual needs.

[0066] This embodiment of the application also provides a talent value evaluation system, including the following modules for implementing the talent value evaluation method in the previous embodiment: Data acquisition module: used to obtain the basic information and value-added information of the user through the information collection system; Initial evaluation module: The input end is connected to the output end of the data acquisition module, and is used to generate an initial value evaluation result based on the preset benchmark person hypothesis parameters and in combination with the region where the user is located; Value-added evaluation module: The input end is connected to the output end of the initial evaluation module, and is used to perform dynamic quantitative analysis on the value-added information through the value-added model to generate a value-added value; Comprehensive evaluation module: The input end is connected to the output end of the value-added evaluation module, and is used to perform non-linear weighted integration on the initial value evaluation result and the value-added value to generate a final comprehensive value evaluation result.

[0067] Dynamic correction module: Its input end is connected to the output end of the comprehensive evaluation module, and its output end is connected to the input end of the initial evaluation module. It is used to monitor the progress of user information improvement, update basic information and value-added information in real time, re-execute the initial evaluation and value-added evaluation steps based on the updated data, and output the corrected comprehensive value evaluation result.

[0068] The above are all preferred embodiments of this application. The protection scope of this application is not limited accordingly. Therefore, all equivalent changes made according to the structure, shape, and principle of this application shall be covered within the protection scope of this application.

Claims

1. A method for evaluating talent value, characterized in that: It includes the following steps: Data acquisition: Obtain the basic information and value-added information of the user through the information collection system; Initial evaluation: Based on the preset benchmark person hypothesis parameters and combined with the user's location area, generate the initial value evaluation result; Value-added evaluation: Dynamically quantify and analyze the value-added information through the value-added model to generate the value-added value; Comprehensive evaluation: Sum up the initial value evaluation result and the value-added value to generate the final comprehensive value evaluation result.

2. The talent value evaluation method according to claim 1, wherein: The benchmark person hypothesis parameters include at least one of the preset education level, work experience, geographical distribution, and cognitive ability.

3. The talent value evaluation method according to claim 2, wherein: The value-added information includes at least one of skill certificates, social positions, honor awards, and intellectual property rights, and the value-added model quantifies the influence weight of the value-added information through dynamically configured coefficients.

4. The talent value evaluation method according to any one of claims 1-3, characterized in that: In the initial evaluation step, it also includes: Dynamically generate a confidence coefficient based on the degree of information missing to adjust the uncertainty range of the initial value evaluation result.

5. The talent value evaluation method according to claim 4, characterized in that: The generation logic of the confidence coefficient includes: Allocate the initial confidence interval according to the number of dimensions of the user information missing; Dynamically narrow the confidence interval and update the confidence coefficient based on the progress of the user's subsequent information improvement; Among them, the confidence coefficient is generated in the following way: In the initial stage, allocate a random perturbation coefficient according to the number of dimensions of the user information missing, and the value of the random perturbation coefficient is 0.9 - 1.1; As the user information improvement progresses, gradually narrow the confidence interval and correct the perturbation coefficient; Adjust the dynamic range of the confidence coefficient by combining the regional economic parameters and the industry average income data.

6. The talent value evaluation method according to claim 5, wherein: The initial evaluation step adopts the future income discount model, specifically including: Calculate the user's benchmark theoretical annual income through the Mincer equation; Estimate the future promotion probability and income growth rate; Combine the confidence coefficient to correct the discount result within an interval to generate the initial value evaluation result.

7. The talent value evaluation method according to claim 6, wherein: The input parameters of the Mincer equation include: At least five of education level, work years, geographical distribution, gender, cognitive ability, and family environment; The geographical distribution is mapped to the major economic regions through the user's mobile phone number and associated with the regional average income parameters.

8. The talent value evaluation method according to any one of claims 1-3, characterized in that: The information collection system automatically completes the unfilled fields using the benchmark person hypothesis and marks them as items to be corrected.

9. The talent value evaluation method according to claim 7, wherein: The method also includes a dynamic correction step for monitoring the progress of the user information improvement and real-time updating the basic information and value-added information; Re-execute the initial evaluation and value-added evaluation steps based on the updated data; Output the corrected comprehensive value evaluation result.

10. A system for implementing the talent value evaluation method according to any one of claims 1-9, characterized in that, It includes the following modules: Data acquisition module: Used to obtain the basic information and value-added information of the user through the information collection system; Initial evaluation module: The input end is connected to the output end of the data acquisition module, and is used to generate the initial value evaluation result based on the preset benchmark person hypothesis parameters and combined with the user's location area; Value-added evaluation module: The input end is connected to the output end of the initial evaluation module, and is used to dynamically quantify and analyze the value-added information through the value-added model to generate the value-added value; Comprehensive evaluation module: The input end is connected to the output end of the value-added evaluation module, and is used to non-linearly weighted integrate the initial value evaluation result and the value-added value to generate the final comprehensive value evaluation result.

Images