A method for creating a digital talent model based on artificial intelligence to measure the abilities of employees

Abstract

The present application relates to a method for creating a digital talent model based on artificial intelligence to measure the capabilities of employed persons. It includes: collecting information on the target talent at least once, obtaining the professional capability data of the target talent, and obtaining the evaluation score of the target talent based on the professional capability data; obtaining the natural growth value and event added value of the evaluation score of the target talent; when collecting information on the target talent for the first time: obtaining the initial professional capability data and initial evaluation score of the target talent, and establishing a target digital model of the target talent; when collecting information on the target talent for the non-initial time: obtaining the latest evaluation score and current predicted score of the target talent, and when the difference between the latest evaluation score and the current predicted score exceeds the first threshold, the natural growth value and event added value of the target talent are corrected. The present application solves the problems of high subjectivity in evaluation, inaccurate tracking of capability changes, and insufficient prediction of personalized development in the existing talent management system.

Description

Technical Field

[0001] The present application relates to the technical field of human resource management, and specifically to a method for creating a digital talent model based on artificial intelligence to measure the abilities of employees. Background Art

[0002] At present, the talent digital twin model based on artificial intelligence to measure the ability of employees is in a stage of rapid development and widespread application. These models combine digital twin technology with advanced artificial intelligence algorithms, and build highly personalized virtual images by integrating the professional behavior and ability data of employees in the physical world. They can not only monitor individuals' professional skill levels, work performance and development potential in real time, but also provide scientific decision-making support for talent management by simulating the effects of different career paths and training interventions. With the help of deep learning, big data analysis and other technologies, the talent digital twin model can accurately evaluate the ability of employees, predict their growth trends, and quickly adjust the talent development strategy in response to market changes, thus showing great potential in the fields of human resource planning, performance management, and career development path planning, and become an important tool for enterprises and organizations to optimize talent allocation and promote the value-added of talent capital.

[0003] The current talent management field faces challenges such as information fragmentation, strong subjectivity in evaluation, and lack of predictability in talent training. Traditional talent evaluation methods mostly rely on regular performance appraisals and subjective evaluations, lack continuous and comprehensive data analysis support, and are difficult to accurately capture the dynamic changes in individual capabilities and potential growth space. Especially in a rapidly changing work environment, the impact of career events (such as project participation, training experience, and job changes) on personal capabilities is complex and changeable, and these impacts are often not promptly and accurately incorporated into the consideration of talent development. In addition, the lack of effective prediction models to guide personalized career path planning and capability improvement strategies has led to inefficient allocation of talent resources, making it difficult for companies to fully tap and utilize talent potential. Therefore, there is an urgent need for a more accurate, dynamic, and forward-looking method to measure and predict the ability development of employees in order to optimize human resource management decisions. Against this background, an artificial intelligence-based talent digital twin model creation method has emerged, aiming to achieve all-round and refined management of talent capabilities and potential mining by integrating multi-source data, deep learning, and simulation prediction technology. Summary of the invention

[0004] This application mainly solves the problems of high subjectivity in assessment, inaccurate tracking of ability changes, and insufficient prediction of personalized development in existing talent management systems.

[0005] In an embodiment of the present application, a method for creating a talent digital model for measuring the ability of an employee based on artificial intelligence is provided, and the talent digital model creation method includes:

[0006] Collect information on the target talent at least once, obtain the target talent's professional ability data, and obtain the target talent's assessment score based on the professional ability data;

[0007] Obtain the natural growth value and event added value of the target talent's assessment score; the natural growth value is used to characterize the target talent's professional ability level that has increased over time since the last information collection; the event added value is used to characterize the target talent's professional ability level that has been affected by professional events since the last information collection;

[0008] in:

[0009] When collecting information on target talents for the first time:

[0010] Obtaining the initial professional competency data and initial assessment scores of the target talents, and establishing a target digital model of the target talents;

[0011] When collecting information on target talents other than for the first time:

[0012] The latest assessment score and current predicted score of the target talent are obtained, and when the difference between the latest assessment score and the current predicted score exceeds a first threshold, the natural growth value and event added value of the target talent are corrected.

[0013] In the above-mentioned method for creating a talent digital model for measuring the ability of employees based on artificial intelligence, as a preferred solution, the target digital model includes an interaction layer, a data layer, a simulation layer and an analysis layer;

[0014] The interaction layer is used to provide a user interface so that the user or target person can interact with the target digital model through the user interface;

[0015] The data layer is used to collect, store and manage information and data related to target talents;

[0016] The simulation layer is used to calculate the current prediction score based on the natural growth value and event added value of the target talent evaluation score;

[0017] The analysis layer is used to compare the latest evaluation score with the current prediction score, and when the difference between the latest evaluation score and the current prediction score exceeds a first threshold, correct the natural growth value and event added value of the target talent.

[0018] In the above-mentioned method for creating a talent digital model for measuring the ability of employees based on artificial intelligence, as a preferred solution, the latest evaluation score and current prediction score of the target talent are obtained, and when the difference between the latest evaluation score and the current prediction score exceeds a first threshold, the natural growth value and event added value of the target talent are corrected, including:

[0019] When collecting information on target talents other than for the first time:

[0020] Obtain the latest professional competency data and assessment scores of target talents;

[0021] Obtain the current predicted score of the target talent based on the evaluation score of the target talent at the last information collection, as well as the natural growth value and event added value;

[0022] Compare the current predicted score of the target talent with the latest evaluation score to obtain the current deviation value between the current predicted score and the latest evaluation score;

[0023] The calculation method of the natural growth value and event added value of the target talent will be revised based on the current deviation value.

[0024] In the above-mentioned method for creating a talent digital model based on artificial intelligence to measure the ability of employees, as a preferred solution, the natural growth value and event added value of the target talent evaluation score are obtained, including:

[0025] Get the time factor related to the natural growth value of the target talent assessment score, and calculate the natural growth value based on the time factor:

[0026] ;

[0027] Get the event factors related to the target talent assessment score event added value, and calculate the event added value based on the event factors:

[0028] ;

[0029] in, is the natural growth value, is the time between the current time and the last time of information collection, is the natural growth value per unit time; Add value to events. Event factors include positive events and negative events. is the weight coefficient of positive events, Positive events The corresponding added value size, is the weight coefficient of negative events, Negative events The corresponding added value.

[0030] In the above-mentioned method for creating a talent digital model based on artificial intelligence to measure the ability of employees, as a preferred solution, the step of obtaining the current predicted score of the target talent includes:

[0031] Calculate the current predicted score for the target talent:

[0032] ;

[0033] in, is the current prediction score, is the weight of the natural growth value, A weight that adds value to the event.

[0034] In the above-mentioned method for creating a talent digital model based on artificial intelligence to measure the ability of employees, as a preferred solution, the natural growth value and event added value of the target talent are corrected, including:

[0035] The weights of natural growth value and event added value are modified respectively;

[0036] Correcting the weight of the event added value also includes: correcting the weight coefficients of positive events and negative events.

[0037] In the above-mentioned method for creating a digital talent model for measuring the ability of employees based on artificial intelligence, as a preferred solution, the time factor related to the natural growth value of the target talent evaluation score is obtained, including:

[0038] Count the time from the current moment to the last time information was collected;

[0039] The event factors related to the event added value of the target talent assessment score are obtained, including:

[0040] Obtain career events in which target talents participate from public channels;

[0041] And / or, obtain daily assessment events of target talents’ participation in their occupations.

[0042] In the above-mentioned method for creating a digital talent model for measuring the ability of employees based on artificial intelligence, as a preferred solution, the information collection of the target talent is performed at least once to obtain the professional ability data of the target talent, and the evaluation score of the target talent is obtained according to the professional ability data, including:

[0043] Collect single capability data of target talents from at least one dimension;

[0044] Quantify each individual capability data to obtain a single score of at least one dimension of the target talent;

[0045] An assessment score of the target talent is obtained based on a single score of at least one dimension.

[0046] In the above-mentioned method for creating a talent digital model based on artificial intelligence to measure the ability of employees, as a preferred solution, the evaluation score of the target talent is calculated by the following formula:

[0047] ;

[0048] in, is the evaluation score of the target talent, at least one of the dimensions is 1, ..., k, k is a positive integer, is the weight coefficient of dimension k, is the single score of dimension k;

[0049] At least one of the dimensions includes professional knowledge, and / or skill level, and / or work experience, and / or innovative thinking ability, and / or teamwork ability, and / or leadership.

[0050] In the above-mentioned method for creating a talent digital model based on artificial intelligence to measure the ability of employees, as a preferred solution, the talent digital model creation method also includes:

[0051] When the talent digital model of the target talent is accessed, a current prediction score of the target talent is provided.

[0052] According to the method for creating a digital talent model for measuring the capabilities of employees based on artificial intelligence in the above-mentioned embodiment, through at least one information collection, multi-dimensional professional capability data is integrated, and machine learning is used for comprehensive evaluation, thereby reducing subjective bias in traditional evaluations and improving the objectivity and comprehensiveness of evaluations; dynamically monitoring natural growth value and actuarial event added value, accurately tracking individual capabilities and reflecting external influences, ensuring accurate capture of personal capability development trajectories, and solving the problem of inaccurate tracking of capability changes; through the introduction of event added value, systematically evaluating the specific impact of each professional event on personal capabilities, and analyzing from a sophisticated analytical perspective, making up for the deficiency of traditional evaluations that ignores the role of external factors in improving capabilities; at the same time, through continuous feedback and correction of results, machine learning is performed, and the first threshold is used to determine when it is necessary to adjust the calculation method of natural growth value and event added value, so that the obtained prediction results can be made more and more accurate under a large number of samples. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 Flow chart (I) of a method for creating a digital talent model based on artificial intelligence to measure the abilities of employees provided in an embodiment of the present application;

[0054] Figure 2 Flow chart (II) of a method for creating a digital talent model based on artificial intelligence to measure the abilities of employees provided in an embodiment of the present application;

[0055] Figure 3 A schematic diagram of the structure of a talent digital model for measuring the abilities of employees based on artificial intelligence provided in an embodiment of the present application;

[0056] Figure 4Flowchart (III) of the method for creating a digital talent model based on artificial intelligence to measure the abilities of employees provided in the embodiment of the present application. DETAILED DESCRIPTION

[0057] The present application is further described in detail below by specific embodiments in conjunction with the accompanying drawings. Wherein similar elements in different embodiments adopt associated similar element numbers. In the following embodiments, many detailed descriptions are intended to enable the present application to be better understood. However, those skilled in the art can easily recognize that some of the features can be omitted in different situations, or can be replaced by other elements, materials, and methods. In some cases, some operations related to the present application are not shown or described in the specification, in order to avoid the core part of the present application being overwhelmed by too much description, and for those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations based on the description in the specification and the general technical knowledge in the art.

[0058] In addition, the features, operations or characteristics described in the specification can be combined in any appropriate manner to form various implementations. At the same time, the steps or actions in the method description can also be interchanged or adjusted in a manner that is obvious to those skilled in the art. Therefore, the various sequences in the specification and the drawings are only for the purpose of clearly describing a certain embodiment and are not meant to be a required sequence, unless otherwise specified that a certain sequence must be followed.

[0059] The serial numbers assigned to the components herein, such as "first", "second", etc., are only used to distinguish the objects described and do not have any order or technical meaning. The "connection" and "coupling" mentioned in this application, unless otherwise specified, include direct and indirect connections (couplings).

[0060] Please refer to Figure 1 In order to solve the problems of high subjectivity in evaluation, inaccurate tracking of ability changes and insufficient prediction of personalized development in existing talent management systems, a method for creating a digital talent model based on artificial intelligence to measure the ability of employees is provided in an embodiment of the present application. The method for creating a digital talent model includes the following steps.

[0061] Step S101: collect information on target talents at least once, obtain professional ability data of the target talents, and obtain an assessment score of the target talents based on the professional ability data.

[0062] Step S102: Obtain the natural growth value and event added value of the target talent's assessment score. The natural growth value is used to characterize the target talent's professional ability level that has increased over time since the last information collection; the event added value is used to characterize the target talent's professional ability level that has been affected by professional events since the last information collection.

[0063] in:

[0064] When collecting initial information on target talents: obtain the target talents' initial professional ability data and initial assessment scores, and establish a target digital model of the target talents.

[0065] When collecting information on target talents that is not the first time: obtain the latest assessment score and current forecast score of the target talents, and when the difference between the latest assessment score and the current forecast score exceeds a first threshold, revise the natural growth value and event added value of the target talents.

[0066] In some embodiments, personalized capability development path planning can also be implemented. That is, based on the target talent's assessment score, natural growth value and event added value, combined with artificial intelligence algorithms, their development potential and adaptability in different career paths are predicted; personalized training suggestions, project recommendations and career promotion paths are generated to maximize the matching degree between personal potential and organizational needs.

[0067] In some embodiments, a dynamic feedback and adjustment mechanism can also be established. A regular or triggered review process is set up to encourage target talents, line managers and HR to submit real-time feedback on work achievements, new skills acquisition, career goal changes, etc. through the digital platform; these feedbacks will be used as supplementary data and updated to the talent digital model in real time to ensure the timeliness and accuracy of the model.

[0068] In some embodiments, external data sources can also be integrated to broaden the evaluation perspective. Integrating external data sources means cooperating with third parties such as industry certification agencies and online education platforms to access their authoritative certification records, online course completion status and other data, adding more objective basis to the comprehensive evaluation of talents, especially for the evaluation of cross-domain knowledge and skills and soft skills.

[0069] In some embodiments, the digital model of talents can also be used to develop scenario simulation and stress testing functions. Using simulation technology, according to the career path planning of talents and expected market changes, simulate the ability requirements and challenges in different scenarios, evaluate the ability of talents to cope with future uncertainties, and further refine and optimize personalized development strategies. During data collection or transmission, ensure that data protection laws and regulations are strictly observed throughout the process of information collection, processing, storage and transmission, and use encryption technology, access control and anonymization processing to protect the personal information security and privacy rights of target talents.

[0070] Please refer to Figure 2 In order to solve the problems of high subjectivity in evaluation, inaccurate tracking of ability changes and insufficient prediction of personalized development in existing talent management systems, a method for creating a digital talent model based on artificial intelligence to measure the ability of employees is provided in an embodiment of the present application. The method for creating a digital talent model includes the following steps.

[0071] Step S201: perform initial information collection on target talents, obtain initial professional ability data and initial assessment scores of target talents, and establish a target digital model of the target talents.

[0072] In some embodiments, the initial information collection should include but is not limited to basic skills, professional knowledge, work experience, project participation, leadership, teamwork ability, innovation ability, learning ability and other dimensions to ensure comprehensive coverage of the target talent's capabilities.

[0073] In some embodiments, a 360-degree feedback mechanism is used during initial information collection, i.e., information from superiors, colleagues, subordinates, and self-evaluation is collected to reduce subjective bias and improve data reliability.

[0074] In some embodiments, psychological assessment tools, such as personality tests, career interest scales, etc., can be added during the initial information collection to evaluate the psychological traits and potential abilities of talents and add depth to the digital model.

[0075] In some embodiments, the collected data is cleaned and normalized during the initial information collection to ensure the comparability of data from different sources and types and to provide clear data support for subsequent analysis.

[0076] Step S202: Obtain the natural growth value and event added value of the target talent's assessment score. The natural growth value is used to characterize the target talent's professional ability level that has increased over time since the last information collection; the event added value is used to characterize the target talent's professional ability level that has been affected by professional events since the last information collection.

[0077] In some embodiments, the calculation of natural growth value can be combined with historical data and use time series analysis methods to identify general trends and seasonal fluctuations in personal growth and improve prediction accuracy.

[0078] In some embodiments, when calculating the added value of events, career events are divided into two categories: positive (such as successfully completing a major project, obtaining professional certification) and negative (such as work mistakes, project delays), and their impact on capabilities is quantified separately to more carefully reflect the changes in capabilities caused by individual experiences.

[0079] In some embodiments, when calculating the natural growth value and event added value, a machine learning algorithm (such as random forest, neural network) is used to build a model to automatically learn the patterns of how different events affect the capabilities of different talents, thereby improving the intelligence of the added value calculation.

[0080] Step S203: perform non-initial information collection on the target talent, obtain the latest evaluation score and current prediction score of the target talent, and when the difference between the latest evaluation score and the current prediction score exceeds a first threshold, correct the natural growth value and event added value of the target talent.

[0081] In some embodiments, the first threshold can be dynamically adjusted based on factors such as the talent's historical performance, changes in industry standards, and corporate strategic goals to better adapt to environmental changes and differences in personal development speed.

[0082] In some embodiments, the first threshold is 10%, and the difference between the latest evaluation score and the current prediction score exceeding the first threshold means that the current prediction score is between 90% and 110% of the latest evaluation score.

[0083] In some embodiments, while correcting the natural growth value and event added value, a feedback mechanism is established to analyze the causes of forecast deviations and continuously optimize the forecast model and evaluation indicator system. After each information collection, the difference between the actual evaluation score and the model prediction score is recorded in detail, and cases with significant deviations are marked. Deviation analysis not only focuses on absolute numerical differences, but also considers directionality and trend consistency. Conduct an in-depth analysis of the identified forecast deviations to explore whether the deviations are caused by factors such as the limitations of the model itself (such as method selection, improper parameter settings), data quality (such as the completeness and accuracy of information collection), or changes in the external environment (such as adjustments to industry standards and the impact of the economic situation).

[0084] In some embodiments, when a significant difference is found between the prediction and the actual evaluation, a personalized improvement plan is automatically triggered, including customized training, mentor coaching, project recommendations, etc., to promote personal growth in a targeted manner. When the system detects a significant difference between the predicted evaluation and the actual performance, an integrated personalized improvement process is initiated. First, analyze the root cause of the difference and identify specific shortcomings or underutilized potential areas in capability development. Subsequently, a customized growth plan is generated, which includes but is not limited to: arranging professional training courses focused on improving weaknesses, which are customized according to personal learning style and progress; matching experienced mentors for one-on-one coaching, and the selection of mentors is based on their professional fields, successful cases and personality matching of the coachee; recommending challenging project or task participation opportunities, aiming to accelerate capability improvement and stimulate innovative thinking in actual combat.

[0085] In some embodiments, the implemented intervention measures are tracked and recorded, and their actual effects on personal capacity improvement are regularly evaluated to form a closed-loop management to ensure that each step of adjustment is based on empirical data. In order to ensure the effectiveness of intervention measures and continuous personal development, a tracking and evaluation mechanism needs to be implemented. Each customized improvement plan or intervention measure, which can include training courses, mentor guidance, and project practice, is recorded in the personal growth log of the target talent, covering participation time, completion status, learning outcomes, and feedback. Using data analysis tools, these data are regularly summarized and quantitative and qualitative evaluations are conducted against the pre-set capacity improvement goals. By comparing key indicators such as performance indicators, skill mastery, and job satisfaction before and after the intervention, the impact of each measure is objectively measured. Based on the evaluation results, timely adjust and optimize the improvement strategy, strengthen the methods with significant results, and replace or improve the parts with poor results.

[0086] Please refer to Figure 3 In the above-mentioned method for creating a digital talent model for measuring the abilities of employed persons based on artificial intelligence, as a preferred solution, the target digital model includes an interaction layer, a data layer, a simulation layer and an analysis layer; the interaction layer is used to provide a user interface so that users or target personnel can interact with the target digital model through the user interface; the data layer is used to collect, store and manage information and data related to the target talent; the simulation layer is used to calculate the current prediction score based on the natural growth value and event added value of the target talent's evaluation score; the analysis layer is used to compare the latest evaluation score with the current prediction score, and when the difference between the latest evaluation score and the current prediction score exceeds a first threshold, the natural growth value and event added value of the target talent are corrected.

[0087] Please refer to Figure 4 In the above-mentioned method for creating a digital talent model for measuring the ability of employees based on artificial intelligence, as a preferred solution, in the above-mentioned steps S101-S102 or step S203, when the latest evaluation score and the current predicted score of the target talent are obtained, and when the difference between the latest evaluation score and the current predicted score exceeds the first threshold, the natural growth value and the event added value of the target talent are corrected, especially when non-initial information collection is performed on the target talent, the following steps are performed:

[0088] Step S401: Obtain the latest professional ability data and latest assessment scores of target talents.

[0089] Step S402: Obtain the current predicted score of the target talent based on the evaluation score of the target talent during the last information collection, as well as the natural growth value and the event added value.

[0090] Step S403: Compare the current predicted score of the target talent with the latest evaluation score to obtain the current deviation value between the current predicted score and the latest evaluation score.

[0091] Step S404: modify the calculation method of the natural growth value and event added value of the target talent according to the current deviation value.

[0092] In the above-mentioned method for creating a talent digital model based on artificial intelligence to measure the ability of employees, as a preferred solution, the natural growth value and event added value of the target talent evaluation score are obtained, including:

[0093] Get the time factor related to the natural growth value of the target talent assessment score, and calculate the natural growth value based on the time factor:

[0094] ;

[0095] Get the event factors related to the target talent assessment score event added value, and calculate the event added value based on the event factors:

[0096] ;

[0097] in, is the natural growth value, is the time between the current time and the last time of information collection, is the natural growth value per unit time; Add value to events. Event factors include positive events and negative events. is the weight coefficient of positive events, Positive events The corresponding added value size, is the weight coefficient of negative events, Negative events The corresponding added value.

[0098] In the above-mentioned method for creating a talent digital model based on artificial intelligence to measure the ability of employees, as a preferred solution, the step of obtaining the current predicted score of the target talent includes:

[0099] Calculate the current predicted score for the target talent:

[0100] ;

[0101] in, is the current prediction score, is the weight of the natural growth value, A weight that adds value to the event.

[0102] In the above-mentioned method for creating a talent digital model based on artificial intelligence to measure the ability of employees, as a preferred solution, the natural growth value and event added value of the target talent are corrected, including:

[0103] The weights of natural growth value and event added value are modified respectively;

[0104] Correcting the weight of the event added value also includes: correcting the weight coefficients of positive events and negative events.

[0105] In the above-mentioned method for creating a digital talent model based on artificial intelligence to measure the abilities of employees, as a preferred solution, the acquisition of the time factor related to the natural growth value of the target talent assessment score includes: counting the time from the current moment to the last information collection moment.

[0106] The obtaining of event factors related to the added value of the target talent's assessment score event includes: obtaining from public channels professional events in which the target talent participates; and / or obtaining daily assessment events in which the target talent participates in the profession.

[0107] In the above-mentioned method for creating a digital talent model for measuring the ability of employees based on artificial intelligence, as a preferred solution, the information collection of the target talent is performed at least once to obtain the professional ability data of the target talent, and the evaluation score of the target talent is obtained according to the professional ability data, including:

[0108] Collect single capability data of target talents from at least one dimension;

[0109] Quantify each individual capability data to obtain a single score of at least one dimension of the target talent;

[0110] An assessment score of the target talent is obtained based on a single score of at least one dimension.

[0111] In the above-mentioned method for creating a talent digital model based on artificial intelligence to measure the ability of employees, as a preferred solution, the evaluation score of the target talent is calculated by the following formula:

[0112] ;

[0113] in, is the evaluation score of the target talent, at least one of the dimensions is 1, ..., k, k is a positive integer, is the weight coefficient of dimension k, is the single score of dimension k;

[0114] At least one of the dimensions includes professional knowledge, and / or skill level, and / or work experience, and / or innovative thinking ability, and / or teamwork ability, and / or leadership.

[0115] In the above-mentioned method for creating a talent digital model based on artificial intelligence to measure the ability of employees, as a preferred solution, the talent digital model creation method also includes:

[0116] When the digital talent model of the target talent is accessed, the current predicted score of the target talent is provided. When a recruiting company needs to obtain job seeker information, the talent with the latest predicted score of the digital talent model is pushed to the recruiting company.

[0117] Those skilled in the art will appreciate that all or part of the functions of the various methods in the above-mentioned embodiments can be implemented by hardware or by computer programs. When all or part of the functions in the above-mentioned embodiments are implemented by computer programs, the program can be stored in a computer-readable storage medium, and the storage medium can include: read-only memory, random access memory, disk, optical disk, hard disk, etc., and the program is executed by a computer to implement the above-mentioned functions. For example, the program is stored in the memory of the device, and when the program in the memory is executed by the processor, all or part of the above-mentioned functions can be implemented. In addition, when all or part of the functions in the above-mentioned embodiments are implemented by computer programs, the program can also be stored in a storage medium such as a server, another computer, disk, optical disk, flash disk or mobile hard disk, and can be downloaded or copied and saved in the memory of the local device, or the system of the local device is updated, and when the program in the memory is executed by the processor, all or part of the functions in the above-mentioned embodiments can be implemented.

[0118] The above specific examples are used to illustrate the present application, which is only used to help understand the present application and is not intended to limit the present application. For technicians in the technical field to which the present application belongs, they can also make some simple deductions, deformations or substitutions based on the ideas of the present application.

Claims

1. A method for creating a talent digital model based on artificial intelligence to measure the ability of employees, characterized in that: The talent digital model creation method comprises: Collect information on the target talent at least once, obtain the target talent's professional ability data, and obtain the target talent's assessment score based on the professional ability data; Obtain the natural growth value and event added value of the target talent's assessment score; the natural growth value is used to characterize the target talent's professional ability level that has increased over time since the last information collection; the event added value is used to characterize the target talent's professional ability level that has been affected by professional events since the last information collection; in: When collecting information on target talents for the first time: Obtaining the initial professional competency data and initial assessment scores of the target talents, and establishing a target digital model of the target talents; When collecting information on target talents other than for the first time: Obtain the latest assessment score and current forecast score of the target talent, and when the difference between the latest assessment score and the current forecast score exceeds a first threshold, revise the natural growth value and event added value of the target talent; The natural growth value and event added value of the target talent assessment score obtained include: Get the time factor related to the natural growth value of the target talent assessment score, and calculate the natural growth value based on the time factor: ； Get the event factors related to the target talent assessment score event added value, and calculate the event added value based on the event factors: ； The obtaining of the current predicted score of the target talent includes: Calculate the current predicted score for the target talent: ； The step of collecting information on the target talent at least once, obtaining the professional ability data of the target talent, and obtaining the evaluation score of the target talent according to the professional ability data includes: Collect single capability data of target talents from at least one dimension; Quantify each individual capability data to obtain a single score of at least one dimension of the target talent; The evaluation score of the target talent is obtained according to the single score of at least one dimension; the evaluation score of the target talent is calculated by the following formula: ； At least one of the dimensions includes professional knowledge, and / or skill level, and / or work experience, and / or innovative thinking ability, and / or teamwork ability, and / or leadership in, is the natural growth value, is the time between the current time and the last time of information collection, is the natural growth value per unit time; Add value to events. Event factors include positive events and negative events. For positive events Weight coefficient, Positive events The corresponding added value size, is the weight coefficient of negative events, Negative events The corresponding added value; is the current prediction score, is the weight of the natural growth value, The weights that add value to events; is the evaluation score of the target talent, at least one of the dimensions is 1, ..., k, k is a positive integer, is the weight coefficient of dimension k, is the single score of dimension k.

2. The method for creating a digital talent model for measuring the ability of employees based on artificial intelligence as claimed in claim 1, characterized in that: The target digital model includes an interaction layer, a data layer, a simulation layer and an analysis layer; The interaction layer is used to provide a user interface so that the user or target person can interact with the target digital model through the user interface; The data layer is used to collect, store and manage information and data related to target talents; The simulation layer is used to calculate the current prediction score based on the natural growth value and event added value of the target talent evaluation score; The analysis layer is used to compare the latest evaluation score with the current prediction score, and when the difference between the latest evaluation score and the current prediction score exceeds a first threshold, correct the natural growth value and event added value of the target talent.

3. The method for creating a digital talent model for measuring the ability of employees based on artificial intelligence as claimed in claim 1, characterized in that: The obtaining of the latest evaluation score and the current predicted score of the target talent, and when the difference between the latest evaluation score and the current predicted score exceeds a first threshold, revising the natural growth value and the event added value of the target talent, includes: When collecting information on target talents other than for the first time: Obtain the latest professional competency data and assessment scores of target talents; Obtain the current predicted score of the target talent based on the evaluation score of the target talent at the last information collection, as well as the natural growth value and event added value; Compare the current predicted score of the target talent with the latest evaluation score to obtain the current deviation value between the current predicted score and the latest evaluation score; The calculation method of the natural growth value and event added value of the target talent will be revised based on the current deviation value.

4. The method for creating a digital talent model for measuring the ability of employees based on artificial intelligence as claimed in claim 1, characterized in that: The above mentioned corrections to the natural growth value and event added value of the target talent include: The weights of natural growth value and event added value are modified respectively; Correcting the weight of the event added value also includes: correcting the weight coefficients of positive events and negative events.

5. The method for creating a digital talent model for measuring the ability of employees based on artificial intelligence as claimed in claim 1, characterized in that: The time factors related to the natural growth value of the target talent assessment score include: Count the time from the current moment to the last time information was collected; The event factors related to the event added value of the target talent assessment score are obtained, including: Obtain career events in which target talents participate from public channels; And / or, obtain daily assessment events of target talents’ participation in their occupations.

6. The method for creating a digital talent model for measuring the ability of employees based on artificial intelligence as claimed in claim 1, characterized in that: The talent digital model creation method further includes: When the talent digital model of the target talent is accessed, a current prediction score of the target talent is provided.

Images