A large model-based exclusive team performance portrait generation and intelligent evaluation system

Abstract

The application discloses a kind of based on big model's exclusive team performance portrait generation and intelligent evaluation system, belong to artificial intelligence and performance management technical field.The system includes data acquisition module, index system management module, performance calculation engine module, portrait generation module, big model intelligent analysis module and visual display module.Index system adopts four-level structure, including six first-level indexes, twenty-four second-level indexes, fifty-eight third-level indexes and a number of fourth-level indexes.Performance calculation engine is based on difference ratio method to calculate index score, portrait generation module generates radar chart, star rating and ranking, and big model intelligent analysis module is based on big language model to carry out intelligent evaluation and ability analysis.The application realizes the scientificity, intelligentization and visualization of exclusive team performance management, and provides strong support for exclusive team construction decision.

Description

Technical Field

[0001] This invention relates to the fields of artificial intelligence and performance management technology, and in particular to a system for generating and intelligently evaluating the performance profiles of a sales team based on a large language model. Background Technology

[0002] The monopoly inspection team is a vital force in maintaining market order, and the performance evaluation of inspectors and the development of the team have always been key and challenging aspects of monopoly management. Traditional performance evaluation methods for monopoly teams suffer from the following problems: 1) Single evaluation indicators: Traditional evaluation mainly focuses on hard indicators such as the number of cases handled, and lacks a comprehensive evaluation of soft indicators such as work innovation ability, standardized management ability, and public recognition ability, making it difficult to fully reflect the true work ability and contribution of inspectors.

[0003] 2) Difficulty in data collection: The work data of inspectors are scattered in different systems. Data collection and summarization require a lot of manual operation, which is inefficient and prone to errors.

[0004] 3) Subjective evaluation methods: Traditional evaluations rely on manual scoring, the evaluation standards are not uniform, and subjective factors have a great influence, making it difficult to guarantee the fairness and objectivity of the evaluation.

[0005] 4) The profile display is not intuitive: The evaluation results are mostly presented in the form of tables, lacking intuitive visualization, which makes it difficult for managers to quickly understand the overall situation of the team and the individual ability characteristics.

[0006] 5) Lack of intelligent analysis: The existing system lacks intelligent analysis capabilities, cannot automatically identify personnel skill gaps, provide development suggestions, and is unable to provide strong support for team building decisions.

[0007] With the development of artificial intelligence technology, especially the maturity of Large Language Model (LLM) technology, new technical paths have been provided to solve the above problems. However, existing technologies have not yet provided a performance profile generation and intelligent evaluation system specifically tailored to the characteristics of sales teams and integrating large model technology. Summary of the Invention

[0008] To overcome the shortcomings of existing technologies, this invention provides a system for generating and intelligently evaluating the performance profiles of sales teams based on a large model, aiming to achieve scientific, intelligent, and visualized performance management of sales teams.

[0009] The technical solution adopted by this invention to solve its technical problem is: A system for generating and intelligently evaluating the performance profiles of a franchise team based on a large model includes a data acquisition module, an indicator system management module, a performance calculation engine module, a profile generation module, a large model intelligent analysis module, and a visualization display module.

[0010] The data acquisition module is used to collect basic information, case handling data, and performance evaluation data of the monopoly inspection personnel. It supports multiple data acquisition methods, including manual entry, batch import from Excel, and data integration with external systems, and also supports the uploading and association of supporting documents.

[0011] The indicator system management module is used to configure a multi-level evaluation indicator system, including six primary indicators, twenty-four secondary indicators, fifty-eight tertiary indicators, and several quaternary indicators. The six primary indicators include: case handling capability, case file preparation capability, work innovation capability, standardized management capability, theoretical literacy capability, and public recognition capability. It supports dynamic configuration of the weights of each level of indicator; the sum of the weights of the next lower-level indicators for each indicator is 100%, and the sum of the weights of the primary indicators is also 100%.

[0012] The performance calculation engine module is used to calculate the scores of each level of indicators based on the difference ratio method. The lowest level indicator is scored using the difference ratio method, and the calculation formula is: lowest level indicator score = difference ratio method score × indicator weight; the final score of the personnel = Σ first-level indicator weight × {Σ second-level indicator weight × [Σ third-level indicator weight × (Σ fourth-level indicator weight × difference ratio method score)]}.

[0013] The profile generation module is used to generate multi-dimensional performance profiles based on the calculation results. This includes: radar chart display—using six primary indicators to construct a six-dimensional radar chart, visually displaying the capability distribution of each inspector; star rating—dividing each indicator into 10 intervals according to a ratio, with each interval representing one star, visually displaying the capability distribution of each inspector for each indicator across the city; and ranking calculation—ranking each indicator according to its score, visually displaying the inspector's ranking for each indicator across the city.

[0014] The large-scale intelligent analysis module is used to intelligently evaluate personnel capabilities, analyze weaknesses, and generate development suggestions based on a large language model. It includes a knowledge base unit for storing specialized business knowledge, evaluation rules, and historical cases; an NLP analysis unit for semantic understanding and feature extraction of personnel job descriptions; and an inference engine unit for capability assessment and development suggestion generation based on the large language model.

[0015] The visualization module is used to display individual and team profiles on a large data dashboard. It supports data display across multiple organizational levels, including city-wide, district / bureau, squadron, and individual, and supports multi-dimensional comparative analysis.

[0016] The beneficial effects of this invention are: (1) A scientific and comprehensive multi-level evaluation index system has been constructed, which realizes a comprehensive, objective and quantitative evaluation of the capabilities of inspectors; (2) The use of the difference ratio method for performance calculation ensures the fairness and comparability of the evaluation results; (3) Through various visualization methods such as radar charts, star ratings, and rankings, the capabilities and characteristics of personnel and teams can be displayed intuitively; (4) Introduce large language model technology to realize intelligent evaluation, weakness analysis and development suggestions, and improve the intelligence level of evaluation; (5) Supports hierarchical management and access control, adapting to the organizational structure characteristics of the monopoly team. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the overall system architecture of the present invention; Figure 2 This is a flowchart of the performance profile generation process of the present invention; Figure 3 This is a diagram of the index system structure of the present invention; Figure 4 This is a sequence diagram showing the data flow and processing of the present invention; Figure 5 This is a schematic diagram of the interface for displaying the image of the present invention. Detailed Implementation

[0018] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0019] Example 1: System Overall Architecture like Figure 1 As shown, the overall system architecture of this invention includes five layers: user interaction layer, application service layer, large model intelligent engine layer, data layer, and AI large model layer.

[0020] The user interaction layer includes three access methods: web, mobile, and large-screen display, to meet the needs of different scenarios. The web interface provides full system functionality for administrators; the mobile interface allows inspectors to view personal profiles and performance evaluation results at any time; and the large-screen display is used for data visualization in scenarios such as conference rooms.

[0021] The application service layer comprises five major functional modules: personnel management, indicator management, performance evaluation management, profile generation, and intelligent analysis. The personnel management module is responsible for the input and maintenance of basic information on inspectors; the indicator management module supports the configuration and weighting of multi-level indicator systems; the performance evaluation management module supports the creation of performance evaluation batches and the calculation of performance evaluation results; the profile generation module is responsible for generating profile elements such as radar charts, star ratings, and rankings; and the intelligent analysis module provides intelligent evaluation and suggestions based on a large-scale model.

[0022] The large-scale intelligent engine layer includes a performance calculation engine, a profile generation engine, an intelligent evaluation engine, and an NLP analysis engine. The performance calculation engine calculates indicator scores based on the difference ratio method; the profile generation engine is responsible for generating visualization elements such as radar charts; the intelligent evaluation engine uses the large-scale model to intelligently assess personnel capabilities; and the NLP analysis engine is used for semantic analysis of text data.

[0023] The data layer stores three core types of data: case data, indicator data, and personnel data. Case data includes the number of cases investigated, the number of seizures, and the methods of punishment; indicator data includes the definitions, weights, and scoring standards of indicators at all levels; and personnel data includes basic information, job information, and historical performance records.

[0024] The AI ​​large model layer includes a Large Language Model (LLM), a knowledge base, and an intelligent inference engine. The LLM is used to understand and generate natural language text; the knowledge base stores specialized business knowledge and evaluation rules; and the intelligent inference engine performs inference analysis based on the LLM and the knowledge base.

[0025] Example 2: Performance Profile Generation Process like Figure 2 As shown, the performance profile generation process includes the following steps: Step S1: Data Collection. The system collects basic information, case handling data, and performance evaluation data of inspectors through manual entry, batch import, or system integration. Indicators involving personal honors, awards, certificates, etc., are entered by individual inspectors who also upload supporting documents; indicators involving assessments, evaluations, examinations, etc., are entered by the team leader of the grassroots service station who also uploads supporting documents.

[0026] Step S2: Indicator Weight Calculation. The system calculates the weights of each level of indicators based on the preset indicator system and weight configuration. The sum of the weights of the next level indicators for each indicator is 100%, and the sum of the weights of the first level indicators is also 100%.

[0027] Step S3: Difference Ratio Scoring. For the lowest-level indicators, the system uses the difference ratio method to calculate the indicator score. The difference ratio method calculates the score based on the difference between the actual value and the target value of the indicator, according to a preset ratio rule.

[0028] Step S4: Radar Chart Generation. The system generates a six-dimensional radar chart based on the scores of six primary indicators. The six dimensions of the radar chart correspond to case handling ability, case file preparation ability, work innovation ability, standardized management ability, theoretical literacy ability, and public recognition ability.

[0029] Step S5: Star Rating. The system divides each indicator into 10 intervals according to a ratio, with each interval corresponding to 1 star. Based on the individual's score on that indicator, their star rating is determined.

[0030] Step S6: Ranking Calculation. The system sorts each indicator according to its score and calculates each person's ranking for that indicator.

[0031] Step S7: Large-Scale Intelligent Analysis. The system invokes the large-scale intelligent analysis module to analyze skill gaps and generate development suggestions based on personnel work data and profile results.

[0032] Step S8: Output of Profile Results. The system generates individual profile reports and team profile reports, and supports the export of evaluation results.

[0033] Example 3: Indicator System Architecture like Figure 3 As shown, the indicator system of this invention adopts a four-level structure, including six primary indicators, twenty-four secondary indicators, fifty-eight tertiary indicators, and several quaternary indicators.

[0034] The primary indicators of case handling capability include: the ability to handle ordinary cases (number of cases, number of cases seized), the ability to handle major cases (number of major cases), the ability to crack down on counterfeit and illegal networks (number of people criminally detained, number of people arrested, number of people sentenced), the methods of punishment (number of cigarettes confiscated, number of business licenses revoked, number of businesses suspended for rectification), and secondary indicators such as case leads (number of valid case leads).

[0035] The primary indicators for case file production capability include secondary indicators such as: case file awards (provincial and municipal), number of case files produced (number of administrative licensing case files and number of administrative penalty case files), and case file production quality (number of errors in case files).

[0036] The primary indicators of work innovation capability include: lean research projects (project approval, completion, and awards), QC group activities (project approval, completion, and awards), job innovation (submission and awards), competitions and contests (participation and awards), scientific and technological innovation (project approval, completion, and awards), patents, software copyrights, and papers (patents, software copyrights, and papers), and processes (project approval, completion, and awards).

[0037] The primary indicators for standardized management capabilities include: legal publicity (posting warning signs and ensuring effective customer outreach), standardized operations (the number of cigarettes flowing out of the business, the number of outflowing households, and the number of households with abnormal operations across three generations), and licensing management (displaying licenses in prominent locations at business premises, ensuring they are not obstructed, ensuring that the license and address do not match, and ensuring that licenses are issued near primary and secondary schools).

[0038] The primary indicators of theoretical literacy include secondary indicators such as skills assessment (levels 1 to 5), knowledge mastery (exams on essential knowledge and skills, a thorough understanding of market information, and identification of genuine and counterfeit cigarettes), and special skills and expertise (video production, information reporting).

[0039] The primary indicators of public recognition include: annual evaluation (excellent, good, qualified, unqualified), honors received (advanced worker, craftsman, pioneer, advanced individual in fighting counterfeits), and reports and complaints (number of reports and complaints, satisfaction rate of complaint handling), etc.

[0040] Example 4: Data Flow and Processing like Figure 4 As shown, the system's data flow and processing sequence are as follows: (1) Users initiate evaluation requests through web applications; (2) The web application calls the performance calculation engine; (3) The performance calculation engine queries the database for indicator data; (4) The database returns the original data; (5) The performance calculation engine requests intelligent analysis from the large model; (6) The large model returns the analysis results; (7) The performance calculation engine calculates the overall score; (8) The performance calculation engine generates radar chart data; (9) The performance calculation engine calculates star ratings; (10) The performance calculation engine returns profile results to the web application; (11) Web applications display profile reports to users.

[0041] Example 5: Image Display Interface like Figure 5 As shown, the portrait display interface includes the following elements: (1) Basic personal information: Displays the inspector's name, photo, unit, position, length of service and other basic information; (2) Capability Radar Chart: A six-dimensional radar chart generated based on six primary indicators, which intuitively displays the distribution of personnel capabilities; (3) Star rating and ranking: Displays the star rating and city-wide ranking of each indicator; (4) Overall score: The final evaluation score of the presenter; (5) Scoring trend: Shows the recent performance evaluation score trend of the personnel.

[0042] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A system for generating and intelligently evaluating the performance profiles of a franchise sales team based on a large model, characterized in that: include: The data collection module is used to collect basic information, case investigation data, and performance evaluation data of the monopoly inspectors. The indicator system management module is used to configure a multi-level evaluation indicator system, including six primary indicators, twenty-four secondary indicators, fifty-eight tertiary indicators and several quaternary indicators, and supports dynamic configuration of the weights of each level of indicators. The performance calculation engine module is used to calculate the scores of each level of indicators based on the difference ratio method and to summarize and generate the final scores of the personnel. The profile generation module is used to generate multi-dimensional performance profiles based on the calculation results, including radar chart display, star rating, and ranking calculation. The large-scale intelligent analysis module is used to intelligently evaluate personnel capabilities, analyze shortcomings, and generate development suggestions based on a large language model. The visualization module is used to display individual and team profiles on a large data dashboard.

2. The system according to claim 1, characterized in that: The six primary indicators include case handling ability, case file preparation ability, work innovation ability, standardized management ability, theoretical literacy ability, and public recognition ability.

3. The system according to claim 1, characterized in that: The performance calculation engine uses the difference ratio method to calculate indicator scores. The calculation formula is: lowest level indicator score = difference ratio method score × indicator weight; final score of personnel = Σ first-level indicator weight × {Σ second-level indicator weight × [Σ third-level indicator weight × (Σ fourth-level indicator weight × difference ratio method score)]}.

4. The system according to claim 1, characterized in that: The radar chart generated by the profile generation module is based on six primary indicators and constructs six dimensions to intuitively display the capability distribution of each inspector.

5. The system according to claim 1, characterized in that: The star rating system divides each indicator into 10 intervals according to a ratio, with each interval being 1 star, which intuitively shows the distribution of inspectors' capabilities for each indicator across the city.

6. The system according to claim 1, characterized in that: The large-scale model intelligent analysis module includes: The knowledge base unit is used to store franchise business knowledge, evaluation rules, and historical cases; The NLP analysis unit is used for semantic understanding and feature extraction of personnel job descriptions; The inference engine unit is used for capability assessment and development suggestion generation based on a large language model.

7. The system according to claim 1, characterized in that: The indicator system management module supports personnel profile calculations on a monthly, quarterly, semi-annual, and annual basis, and also supports custom evaluation batches.

8. The system according to claim 1, characterized in that: The data acquisition module supports multiple data acquisition methods, including manual entry, batch import from Excel, and data integration with external systems, and also supports the uploading and association of supporting documents.

9. The system according to claim 1, characterized in that: The visualization module supports data display across multiple organizational levels, including four levels: city-wide, district bureau, squadron, and individual, and supports multi-dimensional comparative analysis.

10. The system according to claim 1, characterized in that: It also includes a permission management module for hierarchical management, supporting super administrator accounts and hierarchical administrator accounts, and allowing configuration of viewing, adding, editing, and deleting permissions for different levels of organizations.

Images