An employee performance improvement method, device, equipment and medium

Abstract

The application discloses an employee performance improvement method, device, equipment and medium, the employee performance improvement method comprises the following steps: determining the work post of the employee to be promoted, and identifying the performance evaluation type of the employee to be promoted according to the work post; according to the performance evaluation type, the performance evaluation data of the employee to be promoted is obtained; based on the performance evaluation data, the performance improvement scheme of the employee to be promoted is generated through a large model; the execution feedback data of the employee to be promoted executing the performance improvement scheme is obtained, and based on the execution feedback data, the performance improvement result of the employee to be promoted is obtained. The method dynamically adapts the post characteristics and the performance evaluation type, utilizes the real-time analysis and intelligent decision-making capability of the large model on the multi-source data, generates a personalized performance improvement scheme, so that the employee to be promoted continuously obtains accurate guidance and positive motivation in the work process, and then actively improves the employee performance.

Description

Technical Field

[0001] This invention relates to the field of enterprise management and large-scale model application technology, and in particular to a method, device, equipment and medium for improving employee performance. Background Technology

[0002] In the field of corporate human resource management, employee performance evaluation is a core element in measuring the value of employees' work, driving employee growth, and improving corporate efficiency.

[0003] However, traditional employee performance appraisal models, whether based on indicator achievement rates or subjective evaluations by superiors, are concentrated at the end of each month or cycle. This leads to employees being unable to promptly identify shortcomings or risks in their work, resulting in a backlog of problems, delayed improvements, and slow organizational response. Although some companies have introduced data tools to assist in assessments, existing tools are still limited to static indicator collection and one-way result feedback, unable to provide real-time, personalized risk warnings and improvement guidance. This highlights the technical bottlenecks of traditional performance appraisal models in terms of timeliness, objectivity, and guidance value. Therefore, the current employee performance appraisal process suffers from significant delays, insufficient objectivity, and weak guidance for work improvement, failing to provide improvement guidance for enhancing employee performance. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and medium for improving employee performance, in order to solve the technical problems of strong lag, insufficient objectivity, and weak guidance for work improvement in existing employee performance evaluations.

[0005] Firstly, a method for improving employee performance is provided, comprising the steps of: determining the job position of the employee to be promoted, and identifying the performance evaluation type of the employee to be promoted based on the job position; obtaining performance evaluation data of the employee to be promoted based on the performance evaluation type; generating a performance improvement plan for the employee to be promoted based on the performance evaluation data through a large model; obtaining execution feedback data of the employee to be promoted executing the performance improvement plan, and obtaining the performance improvement result of the employee to be promoted based on the execution feedback data.

[0006] Secondly, an employee performance improvement device is provided, comprising: a type identification module for determining the job position of the employee to be improved and identifying the performance evaluation type of the employee to be improved based on the job position; a data acquisition module for acquiring performance evaluation data of the employee to be improved based on the performance evaluation type; a solution generation module for generating a performance improvement solution for the employee to be improved based on the performance evaluation data and through a large model; and a performance improvement module for acquiring execution feedback data of the employee to be improved executing the performance improvement solution and acquiring the performance improvement result of the employee to be improved based on the execution feedback data.

[0007] Thirdly, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the aforementioned employee performance improvement method.

[0008] Fourthly, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described employee performance improvement method.

[0009] The aforementioned technical solutions for employee performance improvement methods, devices, computer equipment, and storage media include the following steps: determining the job position of the employee to be improved and identifying the performance evaluation type based on the job position; acquiring performance evaluation data of the employee to be improved based on the performance evaluation type; generating a performance improvement plan for the employee to be improved using a large model based on the performance evaluation data; acquiring execution feedback data of the employee to be improved as they implement the performance improvement plan; and obtaining the performance improvement result of the employee to be improved based on the execution feedback data. This method dynamically adapts job characteristics and performance evaluation types, utilizes the real-time analysis and intelligent decision-making capabilities of a large model for multi-source data, and generates personalized performance improvement plans. This allows employees to receive continuous, precise guidance and positive incentives during their work, thereby proactively improving their performance. Attached Figure Description

[0010] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a flowchart of an employee performance improvement method according to an embodiment of the present invention; Figure 2 This is a detailed flowchart of step S3 in an embodiment of the employee performance improvement method of the present invention; Figure 3 This is a specific flowchart of step S31 in the employee performance improvement method according to an embodiment of the present invention; Figure 4 This is another specific flowchart of step S3 in the employee performance improvement method in one embodiment of the present invention; Figure 5 This is a partial flowchart of step S4 in an embodiment of the employee performance improvement method of the present invention; Figure 6 This is a schematic diagram of an employee performance improvement device according to an embodiment of the present invention; Figure 7 This is a schematic diagram of a computer device according to an embodiment of the present invention. Detailed Implementation

[0012] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0013] In one embodiment, such as Figure 1 As shown, a method for improving employee performance is provided, including the following steps: Step S1: Determine the job position of the employee to be promoted, and identify the performance appraisal type of the employee to be promoted based on the job position.

[0014] It should be noted that "employees requiring improvement" refers to current employees who have not met expected performance targets in their current performance evaluations and require systematic intervention to improve both their capabilities and output. A job position is a collection of job responsibilities and capability requirements, encompassing job level, functional sequence, core KPIs, and daily task scope, which dynamically maps to the performance evaluation type for employees requiring improvement. The performance evaluation type is determined by the job position and includes types such as performance indicator-based and behavioral performance-based evaluations.

[0015] In this embodiment, before executing step S1, employees within the company need to be divided into two categories based on whether or not performance indicators are available: employees with indicators and employees without indicators. Employees with indicators correspond to job positions with clearly defined quantitative standards in performance evaluation types, such as sales positions and core project positions, and possess quantifiable indicators such as KPIs (Key Performance Indicators) and OKRs (Objectives and Key Results). Employees without indicators correspond to job positions lacking clearly defined quantitative standards in performance evaluation types, such as some functional positions and administrative support positions, whose performance relies on qualitative evaluation and periodic review of their overall daily work performance.

[0016] In step S1, the system automatically identifies the performance appraisal type of the employee to be promoted based on their job position. This identification process is achieved through a pre-defined job position-performance appraisal type mapping rule base, which is jointly built by HR experts and business departments and supports dynamic iterative optimization based on historical verification data. This mapping mechanism is not a static label, but a dynamic system that is continuously calibrated as the organization's strategy evolves, job responsibilities are restructured, and performance concepts are updated. It transforms abstract human resource logic into an executable, traceable, and verifiable digital decision-making path, subtly driving performance management from experience-driven to cause-and-effect driven. For example, sales positions are automatically matched with performance indicator categories, while administrative positions are automatically matched with behavioral performance categories.

[0017] Step S2: Obtain the performance evaluation data of the employees to be promoted, based on the performance evaluation type.

[0018] It should be noted that performance evaluation data is the core basis for assessing the current performance of employees who need improvement. Different types of performance evaluations require the collection of performance evaluation data from different dimensions. Performance evaluation data includes performance indicator data and behavioral performance data. Among them, performance indicator data focuses on quantifiable results, such as real-time dynamic data of indicators such as daily sales, project progress, and task completion; behavioral performance data focuses on process observation, such as unstructured text data such as project progress documents, meeting minutes, to-do list details, and cross-departmental collaboration communication records.

[0019] If the performance evaluation type is determined to be performance indicator-based, then based on the performance indicator type, employees to be promoted are identified as performance indicator-based employees, and their performance indicator data is obtained. Specifically, for performance indicator-based employees, structured performance indicator data such as KPI achievement rate, OKR progress deviation, and task overdue frequency are automatically retrieved in real time from business systems such as CRM (Customer Relationship Management), project management systems, and attendance platforms via data interfaces, ensuring millisecond-level updates and cross-system consistency.

[0020] If the performance evaluation type is determined to be behavioral performance-based, employees to be promoted are identified as behavioral performance-based employees, and their work behavior data is obtained. Specifically, for behavioral performance-based employees, unstructured work behavior data, such as meeting speech summaries, task response timeliness, document revision records, and cross-departmental collaboration frequency, are extracted from OA office systems, email servers, instant messaging tools, and document collaboration platforms through multi-source data collection interfaces, ensuring the completeness and semantic parsing of the data collection.

[0021] Step S3: Based on performance evaluation data, generate performance improvement plans for employees who need improvement through a large model.

[0022] It should be noted that "large-scale models" refer to generative AI models with massive parameter scales, possessing powerful natural language understanding, multimodal data analysis, and business logic learning capabilities. The performance improvement plan includes goal setting, capability enhancement paths, resource matching suggestions, and phased verification nodes; it is a structured action guide for specific employees seeking improvement.

[0023] Based on the multidimensional characteristics of performance evaluation data, the big model uses prompts to accurately analyze the root causes of indicator deviations and behavioral pattern shortcomings. Combined with industry best practice libraries, job competency maps, and organizational development stage goals, it generates personalized and implementable performance improvement plans.

[0024] like Figure 2 As shown, for performance indicator data, step S3 includes the following sub-steps: Step S31: Input the performance indicator data into the large model, and perform a comprehensive analysis of the performance indicator data through the large model to obtain the comprehensive analysis results of the performance indicator data.

[0025] It should be noted that the comprehensive analysis is a multi-dimensional dynamic analysis of performance indicator data based on the large model's learning of business logic and the patterns of indicator achievement. This analysis includes trend analysis of indicator completion, comparative analysis with historical periods / outstanding benchmarks, and breakdown of key factors influencing indicator achievement. The results of the comprehensive analysis are structured conclusions generated through in-depth reasoning by the large model and serve as the core basis for subsequently generating performance improvement plans.

[0026] In this embodiment, the performance indicator data is first cleaned and standardized before being input into a large model. Then, the large model performs a comprehensive analysis on the performance indicator data through a pre-trained business logic graph (including industry indicator system and historical best practice library) to obtain comprehensive analysis results. The comprehensive analysis results include the indicator completion trend of employees in performance indicator categories, indicator completion deviation, and key variables affecting indicator completion, so as to ensure the accuracy of the comprehensive analysis results and provide quantitative anchors for the subsequent generation of executable performance improvement plans.

[0027] like Figure 3 As shown, specifically, step S31 includes the following sub-steps: Step S311: Analyze the performance indicator data using a large model to obtain the indicator completion trend.

[0028] It should be noted that indicator trend analysis focuses on identifying the dynamic evolution patterns of performance indicators over time, including year-on-year growth, month-on-month fluctuations, periodic inflection points, and cyclical characteristics, identifying trends such as continuous improvement, intermittent decline, or structural imbalances. Indicator completion trends are a core dimension reflecting the stability and growth potential of employee performance, providing a baseline for setting subsequent goals.

[0029] The large model generates indicator completion trends based on time series algorithms, and integrates job characteristics and business cycle patterns to dynamically calibrate prediction confidence intervals. It also links to organizational strategic nodes and marks early warning thresholds for key trend turning points, ensuring that trend analysis is both data-accurate and aligned with actual management pace. Indicator completion trends are output as visual time series charts, which can be directly linked to subsequent deviation attribution and intervention strategy design by overlaying attribution labels, ensuring that each trend conclusion can be traced back to the original data slice and business drivers.

[0030] For example, for sales metrics, the large model can identify the "sawtooth" fluctuations caused by the end-of-quarter sprint; for R&D metrics, the large model can capture the regular peaks in patent applications before and after project milestones. This trend insight is not isolated, but embedded in the deep context of organizational evolution, reflecting the resonant rhythm of individual growth and organizational evolution.

[0031] Step S312: Compare and analyze the performance indicator data with the benchmark indicator data using a large model to obtain the deviation in indicator completion.

[0032] It should be noted that the benchmark data are industry averages, historical averages for the same period, or internal organizational benchmarks calibrated by a large model. This multi-dimensional benchmark alignment mechanism encompasses time dimensions (year-on-year / month-on-month), spatial dimensions (department / job sequence), and strategic dimensions (KPI weighting fit), ensuring that deviation analysis reflects both relative position and reveals strategic alignment gaps. Indicator achievement deviation is a key metric for measuring performance gaps, accurately quantifying the difference between the actual performance of employees in performance indicator categories and the multi-dimensional benchmarks, and identifying positive excesses or negative gaps.

[0033] The large model calls upon historical data from the same period and internal benchmark data, calculates the deviation rate with the performance indicator data to locate the source of the gap, thereby obtaining the corresponding indicator completion deviation, and automatically labels the deviation significance level, such as "slight fluctuation", "moderate deviation" and "serious gap" three deviation significance levels, to ensure that the indicator completion deviation can directly drive the generation of subsequent attribution analysis and performance improvement plan.

[0034] Step S313: Perform attribution analysis on the deviation of the indicators using a large model to obtain key variables.

[0035] It should be noted that deviations in indicator performance can be further subdivided into structural deviations and execution deviations: the former points to systemic causes such as job design, resource allocation, or process mechanisms, while the latter focuses on dynamic variables such as individual capabilities, collaboration efficiency, or on-the-spot responsiveness. Key variables are the core output of attribution analysis; they are the underlying driving factors that can be intervened and identified through multi-layered causal reasoning in a large model, such as market environment, resource input, and operational procedures.

[0036] The large-scale model, based on a causal reasoning engine, employs a decision tree algorithm to analyze deviations in indicator performance layer by layer, tracing back to the root cause node to identify key variables affecting indicator performance. It automatically labels the attribution weight and intervention level of each key variable, generating corresponding attribution results. Simultaneously, these attribution results can be embedded into the organization's knowledge graph, linking similar historical deviation cases with validated intervention measures to form a dynamic attribution knowledge base. This allows key variables to be pushed to the corresponding responsible parties according to their intervention level, supporting management in quickly identifying leverage points and avoiding empirical attribution bias.

[0037] For example, when the sales collection deviation reaches a "serious gap", the big model can penetrate to three root causes: customer payment period policy adjustments, redundant credit approval processes, and delayed regional collection response, with weights of 42%, 31%, and 27%, respectively. Among them, the latter two have high intervention capabilities. If the deviation in R&D patent application stems from a misjudgment of the technical route, it is identified as a structural deviation, and the attribution weight is locked on the deviation transmission in the strategic decoding stage, triggering a cross-departmental collaborative review mechanism.

[0038] Step S32: Based on the comprehensive analysis results, generate performance improvement plans for employees with performance indicators.

[0039] The large model automatically generates performance improvement plans based on the performance indicator completion trends, deviations, and key variables affecting indicator completion for employees. These plans are presented as structured improvement suggestions and may include problem identification, data support, action plans, and simulated expected results.

[0040] For example, if sales growth slows down, the big model can combine market changes, customer profiles and other data to suggest adjusting customer outreach strategies, focusing on expanding the female user group aged 25-35; if project progress is lagging, it can suggest optimizing resource allocation or task priority to help employees with performance indicators improve their work methods in a timely manner to increase the achievement rate of indicators.

[0041] like Figure 4 As shown, for work behavior data, step S3 includes the following sub-steps: Step S301: Classify the work behavior data to obtain a sequence of tasks to be done containing multiple tasks.

[0042] It should be noted that the work behavior data covers multimodal behavior logs such as email sending and receiving, meeting participation, document collaboration, and system operation. Through time series modeling and semantic clustering, high-frequency behavior patterns and inefficient behavior clusters are identified. The to-do task sequence is dynamically sorted according to urgency, dependency relationship and cross-role collaboration needs, and the expected time, prerequisites and completion risk coefficient of each to-do task are marked, providing atomic-level behavior support for subsequent intelligent scheduling and process intervention.

[0043] Specifically, natural language processing technology is used to perform entity recognition (task subject, deadline, associated personnel) and intent classification (project / task / collaboration) on work behavior data. Knowledge graph technology is used to construct a network of relationships between pending tasks, and multiple pending tasks in the network are automatically sorted according to urgency / relevance to obtain a sequence of pending tasks.

[0044] Step S302: Input the sequence of tasks to be done into the large model, and use the large model to perform behavior matching on each task in the sequence of tasks to be done, and identify the target behavior pattern that matches the work behavior data.

[0045] It should be noted that behavior matching refers to matching the behaviors of each task in the task sequence with similar task nodes in the historical behavior graph, thereby obtaining the optimal execution path that matches the target behavior pattern. The target behavior pattern refers to the combination of behaviors that has been verified as the optimal action based on the optimal execution path in a specific task scenario.

[0046] The large model uses multimodal behavior encoding and context-aware reasoning to map the semantic intent, temporal constraints, and resource status of pending tasks to a historical optimal behavior graph. By matching the behavior of similar task nodes in the historical behavior graph with the behavior of these nodes, the matching process integrates task semantic similarity, executor role profiles, and contextual temporal features, outputting a behavior matching score. Based on this score, the target behavior pattern with the highest matching degree is selected. This target behavior pattern represents the most suitable execution paradigm for the current pending task sequence, encompassing quantifiable action units such as task breakdown rhythm, collaborative response time, and document iteration frequency, and dynamically adapting to the executor's current workload and contextual environment.

[0047] For example, when it is detected that a user's meeting rate exceeds 65% for two consecutive days and the document modification delay rate increases, a lightweight intervention is automatically triggered: compressing unnecessary meeting agendas, pre-filling high-frequency collaboration templates, and pushing alternative asynchronous communication solutions, thereby improving behavioral conversion efficiency without increasing cognitive burden.

[0048] In some embodiments, the large model can also accurately capture the behavioral matching degree of multiple candidate historical behavioral patterns in the three dimensions of semantics, temporal sequence, and role collaboration through multimodal behavior encoding and cross-task attention mechanism, and output the behavior matching degree score. Based on the behavior matching degree score, the optimal target behavior pattern is selected from the candidate historical behavioral patterns, thereby automatically matching the historical optimal collaborative team configuration to ensure that the execution path conforms to both individual work habits and organizational collaboration norms.

[0049] Step S303: Based on the target behavioral pattern, generate performance improvement plans for employees with behavioral performance.

[0050] The large model, based on target behavior patterns and combined with job competency models, generates specific behavioral improvement suggestions and action lists for each task, including short-term corrective measures and medium- to long-term behavior development paths. It also generates performance improvement plans for employees with behavioral performance, covering dimensions such as task execution rhythm optimization, collaborative response threshold setting, and document iteration quality assessment, which can effectively improve task completion rate and team collaboration efficiency.

[0051] For example, for project tasks, more efficient execution paths, resource collaboration methods, and problem solutions are provided to ensure a significant increase in the on-time achievement rate of project goals. At the same time, a traceable behavior improvement dashboard is generated to provide real-time feedback on execution deviations and optimization progress.

[0052] Step S4: Obtain the execution feedback data of the performance improvement plan for the employees to be promoted, and obtain the performance improvement results of the employees to be promoted based on the execution feedback data.

[0053] It should be noted that the execution feedback data consists of multi-source heterogeneous data collected in real time during the execution of the performance improvement plan by employees to be improved, including behavioral logs, task completion time, collaboration response delays, document version iteration frequency, and quality scores. The performance improvement results are obtained by comprehensively analyzing the execution feedback data using a large model, showing the corresponding performance improvement goals achieved by the employees to be improved. The performance improvement goals include quantifiable indicators such as the increase in task completion rate, the reduction in collaboration response time, and the change in document first-pass rate.

[0054] In this embodiment, data is pushed to the workbench of the employee to be promoted in real time via an API interface, simultaneously triggering a periodic tracking mechanism to obtain execution feedback data during the employee's implementation of the performance improvement plan. The large model can then dynamically calibrate the performance improvement plan based on this feedback data. The calibration process incorporates reinforcement learning strategies, automatically adjusting the intervention intensity, frequency, and priority of the performance improvement plan based on behavioral deviation signals and goal achievement decay curves in the execution feedback data. This ensures that the performance improvement plan always aligns with the employee's actual performance capability evolution trajectory.

[0055] Furthermore, when the feedback data achieves the preset goals of the performance improvement plan, the system automatically determines that the performance improvement loop is complete, obtains the performance improvement results for the employees to be improved, and generates a structured performance improvement report covering core indicators such as the magnitude of behavioral change, the gain in collaborative effectiveness, and the leap in task delivery quality. Simultaneously, the performance improvement report is pushed to the HR system and the direct supervisor's end, supporting the generation of team capability maps on a quarterly basis, dynamically identifying high-potential positions and collaborative bottlenecks.

[0056] For employees with performance indicators, the system can directly connect to the OKR / KPI assessment system to capture real-time execution feedback data such as target achievement rate, key result completion rate, and weight deviation value. This real-time execution feedback data replaces the performance indicator data in step S31. A large model is used to comprehensively analyze the execution feedback data to obtain the comprehensive analysis results. Based on these results, the performance improvement plan for employees with performance indicators is precisely iterated and optimized to gradually improve the indicator achievement rate. This process continues until the performance improvement results for employees with performance indicators reach the preset performance improvement goals when the execution feedback data is comprehensively analyzed.

[0057] For example, a sales manager's target achievement rate was only 68% in Q1. The big data model identified that their customer follow-up response delay exceeded the threshold by 32%, and the performance improvement plan was adjusted accordingly: the frequency of morning review meetings was increased from once a week to three times a week, an AI-powered real-time script calibration module was embedded, and the lead generation cycle was dynamically compressed to a 48-hour closed loop. By the end of Q2, their target achievement rate had risen to 91%, customer follow-up response delay had been shortened to within the threshold, lead conversion cycle had been compressed by 42%, and script adoption rate had increased by 57%. This indicates that the sales manager's performance improvement loop was completed, and the system automatically generated a structured report and synchronized it to the HR system and the regional director's end; their competency map update showed that both "lead generation" and "customer response" dimensions jumped to the top 15% of the team, and they were dynamically marked as a high-potential management backbone.

[0058] Furthermore, for employees focused on behavioral performance, the progress of pending tasks is tracked in real time based on execution feedback data. When there are deviations in the progress of pending tasks, the big model immediately triggers task progress reminders and automatically re-prioritizes tasks in conjunction with the scheduling system to improve performance enhancement plans, ensuring that pending tasks are completed more efficiently and on time, thereby continuously optimizing performance during the work process and obtaining better work evaluations.

[0059] like Figure 5 As shown, in addition to obtaining feedback data on the implementation of performance improvement plans by employees in behavioral performance categories, the process also includes the following steps: Step S41: Based on the execution feedback data, identify the deviation in the progress of the task to be completed and obtain the task execution deviation.

[0060] Among them, the large model uses a time series prediction model to calculate the task completion probability curve in real time, and locates the progress lag node based on the degree of deviation between the task completion probability curve and the task progress corresponding to the pending task in the execution feedback data, thereby obtaining the task execution deviation and ensuring that the root cause of the execution deviation of the pending task can be accurately obtained, such as resource conflict, skill gap or collaboration obstruction.

[0061] Step S42: Based on the task execution deviation, use the large model to remind employees of task progress based on their behavioral performance.

[0062] When a deviation in task execution is detected, the rules engine triggers multi-dimensional progress reminders to help performance-oriented employees complete their tasks more efficiently and with higher quality. This provides full-process support for performance-oriented employees, enabling them to continuously optimize their performance and obtain better work evaluations, thereby improving their performance.

[0063] For example, based on information such as task deadlines and prerequisite dependencies, if a 15% delay in a prerequisite task is detected, the system will remind employees of the task progress in real time via desktop pop-ups, mobile push notifications, or email notifications to avoid a chain reaction of delays.

[0064] Meanwhile, if task execution deviations still exist after task progress reminders are issued, subsequent task dependencies need to be automatically adjusted, the priority of pending tasks and resource allocation strategies need to be dynamically rearranged, tasks need to be replanned and resources need to be rematched for employees with good performance, the corresponding performance improvement plan needs to be optimized, and the specific operations of step S4 need to be re-executed based on the optimized performance improvement plan. The execution effect of the replanned performance improvement plan needs to be continuously tracked until the task execution deviation converges to within the preset deviation threshold, and the corresponding performance improvement result that achieves the preset performance improvement goal can be obtained.

[0065] In other embodiments, quality data (such as document pass rate and meeting resolution execution rate) can be collected through data collection points to build a closed-loop feedback mechanism, continuously optimize the accuracy of performance improvement plans generated by large models, and finally realize the visualization and one-click execution of the plan through a low-code workbench. This helps employees with behavioral performance to complete their tasks more efficiently and with higher quality, thereby continuously optimizing their performance during the work process and obtaining better work evaluations, so as to improve employees' self-improvement capabilities and corresponding performance improvement results.

[0066] In summary, this application provides a method for improving employee performance. It identifies the performance evaluation type of the employee to be promoted based on their job position; obtains performance evaluation data based on the evaluation type; generates a performance improvement plan for the employee based on the performance evaluation data using a large-scale model; obtains execution feedback data of the employee implementing the performance improvement plan; and obtains the performance improvement result based on the execution feedback data. This method utilizes the real-time analysis and intelligent decision-making capabilities of a large-scale model to provide employees with personalized and precise improvement suggestions and progress reminders, transforming performance evaluation from "post-event statistics" to "dynamic guidance during the process." This allows employees to receive improvement suggestions and risk warnings during their work, overcoming the lag in traditional performance evaluation and improving the objectivity and effectiveness of performance guidance. At the same time, it covers employees with different job attributes within the enterprise who are to be promoted, enabling dynamic tracking of the indicators of employees with indicators and pushing improvement suggestions, and real-time analysis of the work content and full-process assistance of employees without indicators. Through the process assistance of the large model, the performance of employees to be promoted can be improved, laying a good foundation for the performance evaluation at the end of the cycle. It allows employees to be promoted to perceive risks in advance during the work process, optimize their work methods, and thus proactively improve their performance.

[0067] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0068] In one embodiment, an employee performance improvement device is provided, which corresponds one-to-one with the employee performance improvement methods described in the above embodiments. For example... Figure 6 As shown, the employee performance improvement device includes a type identification module 101, a data acquisition module 102, a solution generation module 103, and a performance improvement module 104. Detailed descriptions of each functional module are as follows: The type identification module 101 is used to determine the job position of the employee to be promoted and to identify the performance evaluation type of the employee to be promoted based on the job position.

[0069] The data acquisition module 102 is used to acquire the performance evaluation data of employees to be promoted according to the performance evaluation type.

[0070] The solution generation module 103 is used to generate performance improvement solutions for employees to be improved based on performance evaluation data and through a large model.

[0071] The performance improvement module 104 is used to obtain execution feedback data of the performance improvement plan implemented by the employees to be improved, and to obtain the performance improvement results of the employees to be improved based on the execution feedback data.

[0072] Specific limitations regarding the employee performance improvement device can be found in the limitations on employee performance improvement methods described above, and will not be repeated here. Each module in the aforementioned employee performance improvement device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0073] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for improving employee performance.

[0074] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the employee performance improvement method described in the above embodiments, for example... Figure 1 S1-S4, as shown, will not be described again here to avoid repetition. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in this embodiment of the employee performance improvement device, for example... Figure 6 The functions of the type identification module 101, data acquisition module 102, solution generation module 103, and performance improvement module 104 shown are not described again here to avoid duplication.

[0075] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When executed by a processor, the computer program implements the employee performance improvement method described in the above embodiment, for example... Figure 1 S1-S4, as shown, will not be described again here to avoid repetition. Alternatively, when the computer program is executed by the processor, it implements the functions of each module / unit in this embodiment of the employee performance improvement device, for example... Figure 6 The functions of the type identification module 101, data acquisition module 102, solution generation module 103, and performance improvement module 104 shown are not described again here to avoid duplication. The computer-readable storage medium can be non-volatile or volatile.

[0076] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0077] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0078] It should be noted that any AI models, software tools, or components not belonging to this company appearing in the embodiments of this application are merely illustrative examples and do not represent actual use. All user personal information involved in the embodiments of this application has been authorized (with the knowledge and consent) by the relevant parties or has been fully authorized by all parties, and the executing entity may obtain it through various legal and compliant means. The collection, storage, use, processing, transmission, provision, and disclosure of the information, data, and signals involved all comply with relevant laws and regulations and do not violate public order and good morals.

[0079] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for improving employee performance, characterized in that, Including the following steps: Identify the job positions of employees to be promoted, and determine the performance evaluation type of the employees to be promoted based on the job positions; Based on the performance evaluation type, obtain the performance evaluation data of the employee to be promoted; Based on the performance evaluation data, a performance improvement plan for the employee to be improved is generated through a large model; Obtain the execution feedback data of the employee to be promoted in implementing the performance improvement plan, and obtain the performance improvement result of the employee to be promoted based on the execution feedback data.

2. The employee performance improvement method according to claim 1, characterized in that, The performance evaluation type includes performance indicator type, and the performance evaluation data includes performance indicator data; obtaining the performance evaluation data of the employee to be promoted according to the performance evaluation type includes: Based on the aforementioned performance indicator class, the employee to be promoted is identified as a performance indicator class employee, and the performance indicator data of the performance indicator class employee is obtained.

3. The employee performance improvement method according to claim 2, characterized in that, The step of generating a performance improvement plan for the employee to be promoted based on the performance evaluation data using a large model includes: The performance indicator data is input into the large model, and the large model is used to perform a comprehensive analysis of the performance indicator data to obtain the comprehensive analysis results of the performance indicator data. Based on the comprehensive analysis results, a performance improvement plan for the employees in the aforementioned performance indicator category is generated.

4. The employee performance improvement method according to claim 3, characterized in that, The comprehensive analysis results include the indicator completion trends, indicator completion deviations, and key variables affecting indicator completion for employees in the aforementioned performance indicator categories; the comprehensive analysis of the performance indicator data using the large model to obtain the comprehensive analysis results of the performance indicator data includes: The performance indicator data is analyzed using the large model to obtain the indicator completion trend. The performance indicator data and benchmark indicator data are compared and analyzed using the large model to obtain the deviation of the indicator completion. The key variables are obtained by performing attribution analysis on the deviation of the indicators using the large model.

5. The employee performance improvement method according to claim 1, characterized in that, The performance evaluation type includes behavioral performance type, and the performance evaluation data includes work behavior data; obtaining the performance evaluation data of the employee to be promoted according to the performance evaluation type includes: Based on the aforementioned behavior performance category, the employee to be promoted is identified as a behavior performance category employee, and the work behavior data of the behavior performance category employee is obtained.

6. The employee performance improvement method according to claim 5, characterized in that, The step of generating a performance improvement plan for the employee to be promoted based on the performance evaluation data using a large model includes: The work behavior data is classified to obtain a sequence of tasks to be done containing multiple tasks. The sequence of tasks to be done is input into the large model, and the large model performs behavior matching on each task in the sequence of tasks to be done to identify the target behavior pattern that matches the work behavior data. Based on the target behavioral pattern, a performance improvement plan is generated for the employees whose behavioral performance is described.

7. The employee performance improvement method according to claim 6, characterized in that, The process of obtaining execution feedback data of the employee to be promoted in implementing the performance improvement plan also includes: Based on the execution feedback data, the task progress of the pending tasks is deviated to identify the task execution deviation. Based on the task execution deviation, the large model provides task progress reminders to employees of the behavioral performance category.

8. An employee performance evaluation device, characterized in that, include: The type identification module is used to determine the job position of the employee to be promoted, and to identify the performance evaluation type of the employee to be promoted based on the job position. The data acquisition module is used to acquire the performance evaluation data of the employee to be promoted according to the performance evaluation type. The solution generation module is used to generate a performance improvement plan for the employee to be improved based on the performance evaluation data and through a large model. The performance improvement module is used to obtain the execution feedback data of the employee to be improved in implementing the performance improvement plan, and to obtain the performance improvement result of the employee to be improved based on the execution feedback data.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the employee performance improvement method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the employee performance improvement method as described in any one of claims 1 to 7.

Images