Enterprise project and personnel management method and system based on knowledge base and AI model, and medium

Abstract

The invention provides an enterprise project and personnel management method and system based on a knowledge base and an AI model and a medium, and belongs to the technical field of enterprise management.The method comprises the steps that implementation experience of historical projects of an enterprise is collected and analyzed based on a knowledge graph, and a project knowledge base is constructed; enterprise employees are evaluated, classification is carried out in combination with evaluation dimensions, and labels are set; and collecting real-time operation data of the project, and recommending and adjusting personnel allocation for the project in combination with employee labels and project attributes. According to the invention, full-life-cycle digital management of the project is realized, and a traditional management mode is broken; the project management efficiency and the resource utilization rate are improved through AI-driven dynamic decision and resource allocation; a knowledge base capable of being self-optimized is constructed, and technology and talent support is provided for enterprise development.

Description

Technical Field

[0001] This application belongs to the technical field of enterprise management, and particularly relates to a method, system and medium for enterprise personnel and project management based on a knowledge base and an AI model. Background Art

[0002] Enterprise project management, as a key link in enterprise operation and business growth, is becoming increasingly important. Engineering enterprises carry out various engineering projects to meet market demands. However, with the intensification of market competition, the development of technology and the diversification of customer demands, there are many problems in traditional enterprise management models, making it difficult to meet the growing demand for efficient management in enterprises.

[0003] First of all, traditional project management methods mainly rely on manual experience and fixed process templates. There are also deficiencies in personnel management in traditional engineering project management methods. It is difficult for enterprises to comprehensively and accurately evaluate and manage employees' capabilities, unable to precisely match suitable talents according to the needs of engineering projects, and it is also difficult to provide personalized career development plans and promotion paths for employees. This not only affects the efficiency of project collaboration but also restricts the long-term development of employees and enterprises.

[0004] In addition, project managers usually need to spend a lot of time and energy collecting engineering project information, coordinating various resources, formulating plans and monitoring. Such a management method is difficult to meet the current enterprises' requirements for efficient and precise engineering project management. For example, the collection and collation of engineering project information are often not timely and comprehensive enough, resulting in insufficient decision-making basis; resource allocation is mainly based on experience and intuition, lacking reasonable optimization methods, and it is easy to have situations of resource waste or shortage; the monitoring of the progress and risks of engineering projects is not real-time and accurate enough, unable to discover and solve problems in a timely manner, thus affecting the smooth progress of engineering projects. Summary of the Invention

[0005] In a first aspect, an embodiment of this application provides a method for enterprise personnel and project management based on a knowledge base and an AI model, including the following steps: S1. Collect the implementation experience of the enterprise's historical projects and analyze it based on a knowledge graph to construct a project knowledge base; S2. Evaluate enterprise employees, classify them by integrating evaluation dimensions, and set labels; S3. Collect real-time operation data of the project, and recommend and adjust personnel allocation for the project in combination with employee labels and project attributes.

[0006] Further, S4. Analyze the real-time operation data of the project to determine the project status and give early warnings about project risks; S5. Output project decision-making suggestions based on the project knowledge base, the collected real-time operation data of the project, and the determined project status.

[0007] Further, the specific steps of step S1 are as follows: S11. Collect the implementation experiences of the enterprise's historical projects, where the implementation experiences include accident reports, technical solutions, project progress data, and implementation results; S12. Use a knowledge graph to perform structured and correlation analysis on the collected project implementation experiences, and use natural language processing to parse the analysis results to extract key information and construct a project knowledge base; The specific steps of step S2 are as follows: S21. Determine the evaluation dimensions of enterprise employees; the evaluation dimensions include technical expertise, project experience, and collaboration ability; S22. Dynamically evaluate employees through an approval and scoring process, and set labels for employees according to the evaluation dimensions; S23. Use a coding method to vectorize the labels of employees to obtain vector labels for each employee; S24. Store the vector labels of employees in the project knowledge base.

[0008] Further, the specific steps of step S3 are as follows: S31. Collect real-time project operation data through an interface connection with the project management platform, where the real-time project operation data includes the progress, quality, and safety data of the project; S32. Respond to project requirements and vectorize the project requirements to obtain a requirement vector; S33. Calculate the similarity between the requirement vector and the vector labels of employees, and calculate the weighted matching degree according to the weights of different label categories preset; S34. Use an AI algorithm combined with the weighted matching degree of employees to recommend personnel for the project; S35. Dynamically adjust the project team configuration according to the real-time project operation data and the actual situation of personnel, and optimize the project implementation efficiency.

[0009] Further, the specific steps of step S31 are as follows: S311. Analyze project attributes according to project requirements to generate requirement labels; S312. Use the TF-IDF algorithm to calculate the weights of requirement labels;

[0010] where, f j represents the occurrence frequency of requirement label j, N represents the total number of projects, n j represents the number of projects containing label j, and m is the number of label categories; The specific steps of step S32 are as follows: S321. Calculate the cosine similarity between the employee label vector and the requirement vector label; S322. Hierarchically set the weights of the employee label vectors and adjust them based on the weights of the requirement labels; S323. Calculate the weighted matching degree between the requirement vector and the employee label vector; The specific steps of step S33 are as follows: S331. Classify employees using the K-means clustering algorithm; S332. Select the top N of the weighted matching degrees of each type of employee, aiming for the most types among project members, and combine them according to the project scale constraints to generate a recommended list; The specific steps of step S34 are as follows: S341. Obtain the project team effectiveness indicators in real time; S342. When the deviation of the project team's effectiveness indicators exceeds the set threshold, adjust the project team configuration.

[0011] Furthermore, the specific steps of step S4 are as follows: S41. Analyze the collected real-time project operation data through data flow analysis to dynamically perceive the project status; S42. Combine the project historical data and the real-time project operation data, and use deep learning algorithms to evaluate the project status and identify potential risks of the project; S43. Generate a warning message based on the identified potential risks and notify the management personnel.

[0012] Furthermore, the specific steps of step S5 are as follows: S51. Respond to the user request, and query similar historical cases from the project knowledge base according to the real-time project operation data; S52. Match the optimal solution from the knowledge base according to the similar historical cases and in combination with the case-based reasoning algorithm; S53. Generate decision-making suggestions for the project according to the matched optimal solution and in combination with the AI model; S54. Present the generated decision-making suggestions to the user, and optimize the project knowledge base according to the user's feedback on the decision-making suggestions.

[0013] Furthermore, the specific steps of step S51 are as follows: S511. Obtain the query request input by the user, and use the BERT pre-trained model to parse and vectorize the keywords in the query request; S512. Query historical cases through the vector similarity calculation method, and display the query results in the order of similarity to obtain historical cases; S513. Extract problem features from the query request input by the user, calculate the matching degree between the problem features of the query request and historical cases, and sort them in descending order of the matching degree. Screen out historical cases with a matching degree higher than the threshold as similar historical cases; The specific steps of step S52 are as follows: S521. Extract features from similar historical cases; S522. Use the case-based reasoning algorithm to calculate the comprehensive similarity between the current problem and similar historical cases:

[0014] where α is the feature weight, FSi is the technical parameter similarity, and CSi is the context similarity; S523. Sort by the comprehensive similarity and select the solutions of the top N cases as the optimal solutions; The specific steps of step S53 are as follows: S531. Input the optimal solution into the decision tree model and predict the success rate of the solution in combination with the real-time operation data of the project; S532. Filter out infeasible solutions through the rule engine to obtain the decision-making solution; S533. Determine the level, specific measures, and expected effects of the decision-making solution, and use natural language generation to construct a structured decision-making recommendation; The specific steps of step S54 are as follows: S541. Record the adoption situation of the user for the decision-making recommendation; S542. Update the case weight based on reinforcement learning:

[0015] where: w i represents the recommended weight of case i, r i represents the user feedback score, represents the average feedback score, v i represents the confidence level of the case based on the historical success rate; S543. Regularly clean up low-weight cases and supplement newly entered successful cases.

[0016] Second, the embodiments of the present application also provide an enterprise personnel and project management system based on a knowledge base and an AI model, including: A project knowledge base construction module, configured to collect implementation experiences based on enterprise historical projects and analyze them based on a knowledge graph to construct a project knowledge base; An employee label setting module, configured to evaluate enterprise employees, classify them in combination with evaluation dimensions, and set labels; A personnel allocation module, configured to collect real-time operation data of a project, and recommend and adjust personnel allocation for the project in combination with employee tags and project attributes.

[0017] Thirdly, an embodiment of the present application further provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the enterprise personnel and project management method based on a knowledge base and an AI model as described in the first aspect are implemented.

[0018] As can be seen from the above technical solutions, the present application has the following advantages: In the enterprise personnel and project management method, system, and medium based on a knowledge base and an AI model provided by the present application, through a knowledge graph and natural language processing, historical project experience is structurally stored to form reusable knowledge assets, avoiding repetitive errors; through multi-dimensional tags and a dynamic evaluation model, the visualization and precise matching of employee capabilities are realized, improving team collaboration efficiency; through the integration of deep learning and real-time data stream analysis, project risks are dynamically identified and warned, reducing the accident rate; through the combination of case-based reasoning and an AI model to generate decision-making suggestions, the interference of human subjective factors is reduced, improving the rationality and response speed of decision-making; through AI algorithms to optimize personnel allocation, balance project progress, quality, and risks, and achieve the optimal control of construction period, cost, and benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the present application, the drawings required for description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 It is a flowchart of the enterprise personnel and project management method based on a knowledge base and an AI model of the present invention.

[0021] Figure 2 It is a flowchart of the enterprise personnel and project management system based on a knowledge base and an AI model of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] In the following, the specific steps of the enterprise personnel and project management method based on a knowledge base and an AI model will be described in detail, and various embodiments of the present disclosure will be described more comprehensively. The present disclosure can have various embodiments, and adjustments and changes can be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, but the present disclosure should be understood to cover all adjustments, equivalents, and / or alternative solutions falling within the spirit and scope of the various embodiments of the present disclosure.

[0023] Exemplarily, in order to respond to the ever-changing market demands, enterprises actively engage in various project activities such as product R & D, engineering construction, and marketing. However, in the face of increasingly fierce market competition, technological innovation, and diversified customer needs, the traditional enterprise management model gradually reveals many drawbacks and is difficult to meet the growing demand of enterprises for efficient management.

[0024] Traditional project management methods mainly rely on manual experience and established process frameworks. Project managers need to invest a large amount of time and energy in daily work for project information collection, resource coordination, plan formulation, and progress monitoring. However, this model is no longer able to meet the current requirements of enterprises for project management efficiency and accuracy. For example, the collection and integration of project information often lack timeliness and comprehensiveness, resulting in a lack of sufficient data support in the decision-making process; resource allocation more relies on personal experience and intuition, lacking scientific and reasonable optimization means, which is likely to cause resource idleness or shortage; the monitoring of project progress and potential risks is not real-time and accurate enough, making it difficult to detect and solve problems in a timely manner, thus hindering the project progress.

[0025] Moreover, traditional project management also has obvious shortcomings in personnel management. Enterprises are difficult to comprehensively and accurately evaluate and manage the comprehensive capabilities of employees, and cannot accurately match the appropriate human resources according to the actual project needs. At the same time, enterprises are unable to provide personalized career development blueprints and promotion channels for employees, which not only reduces the efficiency of project team collaboration but also limits the long-term development potential of employees and enterprises.

[0026] To address the above problems, this embodiment provides an enterprise personnel and project management method based on a knowledge base and an AI model, which realizes the intelligentization of project management and the precision of resource allocation through constructing a dynamic knowledge base, classifying employees by tags, and real-time data analysis.

[0027] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0028] Please refer to Figure 1 The flowchart of the enterprise personnel and project management method based on a knowledge base and an AI model in a specific embodiment is shown. The method includes the following steps: S1. Collect the implementation experience of the enterprise's historical projects and analyze it based on a knowledge graph to construct a project knowledge base; It should be noted that by building a project knowledge base, the experience of the enterprise's historical projects has been accumulated, providing reference for subsequent projects and promoting knowledge sharing; it provides data support for project decision-making, making the decision-making more accurate and reducing decision-making mistakes caused by insufficient information. S2. Evaluate the enterprise employees, classify them according to the evaluation dimensions, and set labels. It should be noted that classifying and labeling employees according to the evaluation dimensions realizes the accurate evaluation and management of employees' capabilities, improves the efficiency and rationality of personnel management; it can dynamically recommend suitable personnel according to project requirements, ensure that the personnel allocation of the project team matches the project requirements, and improve the project success rate. S3. Collect the real-time operation data of the project, and recommend and adjust the personnel allocation for the project in combination with the employee labels and project attributes. It should be noted that recommending and adjusting the personnel allocation in combination with the employee labels and project attributes optimizes the project team configuration, improves the cooperation efficiency of the project team and the project implementation efficiency; through accurate personnel matching and reasonable team configuration, it provides more projects suitable for employees' capabilities and development, promoting the career development of employees.

[0029] This embodiment realizes the digital management of the entire project life cycle, breaking the traditional management mode; through AI-driven dynamic decision-making and resource allocation, it improves the project management efficiency and resource utilization rate; it constructs a knowledge base that can self-optimize, providing technical and talent support for the long-term development of the enterprise.

[0030] Furthermore, as a refinement and extension of the specific implementation manner of the above embodiment, in order to fully illustrate the specific implementation process in this embodiment, another enterprise personnel and project management method based on a knowledge base and an AI model is provided. This method includes the following steps: S1. Collect the implementation experience of the enterprise's historical projects and analyze it based on a knowledge graph to build a project knowledge base. S2. Evaluate the enterprise employees, classify them according to the evaluation dimensions, and set labels. S3. Collect the real-time operation data of the project, and recommend and adjust the personnel allocation for the project in combination with the employee labels and project attributes. S4. Analyze the real-time operation data of the project to determine the project status and give early warnings of project risks. It should be noted that using the real-time operation data of the project to analyze the project status can timely discover potential risks in the project, give early warnings, enabling managers to take measures in time to reduce the risk impact; it provides real-time project status information for project management, facilitating managers to dynamically adjust management strategies according to the actual situation of the project to ensure the smooth progress of the project. S5. Output project decision-making suggestions based on the project knowledge base, the collected real-time operation data of the project, and the determined project status; It should be noted that outputting project decision-making suggestions based on the project knowledge base and the AI model provides reliable decision-making support for project managers, improving the accuracy and efficiency of decision-making; optimizing the project knowledge base according to the user's feedback on the decision-making suggestions realizes the dynamic update and continuous improvement of the knowledge base, and improves the quality of the knowledge base.

[0031] Furthermore, as a refinement and extension of the specific implementation manner of the above embodiment, in order to completely illustrate the specific implementation process in this embodiment, another method for enterprise personnel and project management based on the knowledge base and the AI model is provided. The method includes the following steps: S1. Collect the implementation experience of the enterprise's historical projects and analyze it based on the knowledge graph to construct a project knowledge base; The specific steps of step S1 are as follows: S11. Collect the implementation experience of the enterprise's historical projects, and the implementation experience includes accident reports, technical solutions, project progress data, and implementation results; Exemplarily, the accident report includes fault description, handling measures, root cause analysis, the technical solution includes design parameters, implementation steps, acceptance criteria, the project progress data includes Gantt charts, milestone completion status, and the implementation result includes implementation success or implementation failure; S12. Use the knowledge graph to perform structured and associative analysis on the collected project implementation experience, and use natural language processing to parse the analysis results to extract key information to construct a project knowledge base; Exemplarily, construct an ontology model, define the entity relationship of "project - equipment - personnel - problem", use the Neo4j graph database to store associated data, and establish the following relationships: (Project) - [Used by] -> (Equipment) (Personnel) - [Responsible for] -> (Task) (Problem) - [Associated with] -> (Solution) Use the BERT model for named entity recognition to extract key technical parameters; Use the TextRank algorithm to extract text summaries; Construct a structured index, and the exemplary structured index is as follows: python{"case_id":"P2023-085","keywords":["Steam turbine","Abnormal vibration","Shaft alignment"],"feature_vector":[0.32,0.78,...,0.56] # 768-dimensional BERT vector; Set to regularly and automatically collect new project implementation data, and update the knowledge graph relationships in the project knowledge base using incremental learning; S2. Classify enterprise employees according to evaluation dimensions and set labels; The specific steps of step S2 are as follows: S21. Determine the evaluation dimensions of enterprise employees; The evaluation dimensions include technical expertise, project experience, and collaboration ability; Exemplarily, establish a three-dimensional evaluation system as follows: Technical expertise category, including professional field, skill level, and certification qualifications; Project experience category, including project type, participation role, and project scale; Collaboration ability category, including communication efficiency, team contribution, and problem-solving efficiency; S22. Dynamically evaluate employees through an approval and scoring process, and set labels for employees according to the evaluation dimensions; Exemplarily, collect the project review scores and training assessment results participated by employees through the office system; Set employee labels according to the evaluation dimensions and update them regularly and automatically; S23. Vectorize the labels of employees using an encoding method to obtain the vector labels of each employee; Exemplarily, use TF-IDF to calculate the weight labels;

[0032] Generate the following employee feature vectors and store them in the Redis cluster: E = {"T": [0.8, 0.2,..., 0.5], # Technical expertise dimension "P": [0.6, 0.9,..., 0.3], # Project experience dimension "C": [0.7, 0.4,..., 0.8] # Collaboration ability dimension} S24. Store the vector labels of employees in the project knowledge base; Specifically, use Elasticsearch to establish an index for the vector labels of employees and set a vector similarity cache, thereby achieving millisecond-level retrieval response; S3. Collect real-time project operation data, and combine employee labels and project attributes to recommend and adjust personnel allocation for the project; The specific steps of step S3 are as follows: S31. Through the interface docking with the project management platform, collect real-time project operation data, and the real-time project operation data includes the progress, quality, and safety data of the project; Specifically, dock with the project management platform through the REST API to pull data in real time. Exemplarily, device sensor data is defined through the MQTT protocol; Clean the collected real-time operation data of the project, filter out invalid data (such as the abnormal value of -274°C returned by the temperature sensor) and align the time; Specifically, the progress data of the project includes the following: Task completion status. For example, 80% of the basic project has been completed, and the construction progress of the main structure has reached 60%; Milestone achievement status. For example, in the xxx project plan, the expected completion time of the milestone is May 30, 2025, and the actual completion time is June 5, 2025, with a delay of 5 days; Schedule deviation rate. By comparing the actual progress with the planned progress, calculate the schedule deviation rate; for example, the current overall schedule deviation rate is -10% (indicating that the overall progress lags behind the planned progress by 10%); The quality data of the project includes the following: Quality inspection results. For example, the concrete strength inspection result is C40, meeting the design requirements; in the welding quality inspection, the unqualified rate of a certain batch of welds is 5%; Quality qualification rate, that is, statistically calculate the qualification rate of various quality inspections in the project; for example, the qualification rate of building materials entering the site for inspection is 95%, and the qualification rate of process quality acceptance during construction is 90%; Quality problem records, that is, record the quality problems that occur during the construction process, such as the verticality deviation of the wall on a certain floor exceeding the standard and needing rectification; The safety data of the project includes the following: Safety incident records, that is, record various safety incidents that occur at the construction site, such as a small machinery injury accident occurred one day, resulting in a minor injury to a worker; Safety hazard inspection results, that is, regularly conduct safety hazard inspections and record the number and types of hazards found; for example, during a safety inspection, it is found that there are 5 insecure connections in the scaffolding and the safety passage is partially blocked; Safety risk level, that is, evaluate the overall safety risk level of the project based on safety incidents and hazard situations; for example, the current safety risk level of the project is "medium", and safety management measures need to be strengthened; S32. Respond to the project requirements and quantify the project requirements to obtain a requirement vector; specifically, S321. Analyze the project attributes according to the project requirements and generate requirement tags; It should be noted that the project attributes include different stages of the project and project requirements; specifically, the project stages include the design stage, construction stage, commissioning stage, and delivery stage, and the project requirements include technical requirements, safety requirements, and collaboration requirements. Exemplarily, the project attributes can be "offshore wind power installation", "operation in high-temperature environment", and the requirement tags can be "technical - offshore operation, experience - extreme weather, collaboration - emergency response"; The process of analyzing project requirements is as follows: Input project requirements, which can be obtained in the following ways: through project approval documents, such as requirement specifications and technical agreements; through keywords manually input by project personnel, such as "construction in high-temperature environment"; through requirement templates of historical similar projects, such as matching through the project knowledge base; Preprocess the project requirements, remove stop words, such as meaningless words like "of" and "and", standardize terms, such as unifying "AI algorithm" to "artificial intelligence", and perform word segmentation, such as using NLP tools like Jieba or BERT for word segmentation; Extract phase attributes based on keywords, and judge the current phase of the project through a rule engine. For example, judge the "design phase" based on the keyword "construction drawing", and judge the "construction phase" based on "concrete pouring". Perform requirement attribute extraction, and use a named entity recognition (NER) model to extract key requirements: Technical requirements, such as "thermal control system debugging" Resource requirements, such as "crane rental" Risk requirements, such as "offshore corrosion protection" Output is as follows: {"Requirement type": ["Technical", "Safety"], "Keywords": ["Anti-corrosion coating", "Salt spray test"]} For example, for the project phase of "construction phase", set the label "P - Construction management", and for the requirement attribute of "high temperature", set the labels ["S - Heat prevention", "C - Emergency response"]; S322. Use the TF-IDF algorithm to calculate the weights of requirement labels;

[0033] Among them, f j represents the occurrence frequency of requirement label j, N represents the total number of projects, n j represents the number of projects containing label j, and m is the number of label categories; S33. Calculate the similarity between the requirement vector and the employee vector label, and calculate the weighted matching degree according to the weights of different preset label categories; specifically, S331. Calculate the cosine similarity between the requirement vector label and the employee label vector ;

[0034] Among them, E i B represents the employee label vector, represents the requirement vector label; Ei =( T 1, T 2,…, Tk , P 1, P 2,…, Pk , C 1, C 2,…, Ck ), where T 1, T 2,…, Tk represents multiple sub - features of the technical expertise - type label, P 1, P 2,…, Pk represents multiple sub - features of the project experience - type label, C 1, C 2,…, Ck represents multiple sub - features of the project collaboration - type label; S332. Set the weights of the employee label vectors hierarchically and adjust them based on the weights of the requirement labels; Exemplarily, the weight of the technical expertise - type label \(W\) T = 0.5, the weight of the project experience - type label \(W\) P = 0.3, and the weight of the teamwork - type label \(W\) C = 0.2; S333. Calculate the weighted matching degree between the requirement vector and the employee label vector; S i = W T × Sim Ti + W P × Sim Pi + W C × Sim Ci ; S34. Use the AI algorithm combined with the weighted matching degree of the employees to make personnel recommendations for the project; specifically, S341. Use the K - means clustering algorithm to classify the employees; exemplarily divided into three categories: "core backbone", "potential newcomer", and "auxiliary support"; S342. Select the top \(N\) (e.g., top 10) of the weighted matching degrees of each category of employees, aiming for the most diverse categories among project members, and combine them according to the project scale constraints to generate a recommended list; Exemplarily, the diversity objective function:

[0035] Constraint: Team size ≤ 15 people; S35. Dynamically adjust the project team configuration according to the real-time operation data of the project and the actual situation of the personnel, and optimize the project implementation efficiency; specifically, S351. Obtain the project team effectiveness indicators in real time; S352. When the deviation of the project team's effectiveness indicators exceeds the set threshold, adjust the project team configuration; Exemplarily, if the progress lags behind > 10%, preferentially allocate highly efficient execution-oriented employees; if the quality risk > 0.7, add quality control experts; S4. Analyze the real-time operation data of the project to determine the project status and give early warnings about project risks; S41. Analyze the collected real-time operation data of the project through data flow analysis to dynamically perceive the project status; Exemplarily, use the Flink streaming framework real-time computing framework to process the data flow, for example, set the window to 5 minutes; Calculate the progress deviation rate and quality qualification rate in real time, and detect outliers (for example, a welder's welding strength fails to meet the standard continuously 3 times); S42. Combine the project historical data and the real-time operation data of the project, and use deep learning algorithms to evaluate the project status and identify potential risks of the project; Exemplarily, establish the following feature matrix according to the project historical data and the real-time operation data of the project X = T Progress deviation, T Quality qualification rate, C Frequency of safety incidents]; Use a random forest model to output the risk probability:

[0036] Identify potential risks of the project based on the following pre-set early warning classification: Red early warning: P≥0.8 (such as the progress delay exceeds 20%); Yellow early warning: 0.3≤P<0.8 (such as the quality qualification rate is lower than 90%); Blue early warning: P<0.3 (such as normal progress fluctuations); S43. Generate early warning information according to the identified potential risks and notify the management personnel; Exemplarily, the early warning information may include the risk type, the affected scope, the recommended measures, and the link to the associated historical cases; The early warning information can be notified to the management personnel through WeChat; S5. Output project decision-making suggestions based on the project knowledge base, the collected real-time operation data of the project, and the determined project status; S51. In response to a user request, query similar historical cases from the project knowledge base according to the real-time operation data of the project; specifically, Specifically, S511. Obtain the query request input by the user, and use the BERT pre-trained model to parse and vectorize the keywords in the query request; S512. Query historical cases through the vector similarity calculation method, and display the query results in the similarity ranking manner to obtain historical cases; S513. Extract problem features from the query request input by the user, such as fault types and environmental parameters, calculate the matching degree between the problem features of the query request and the historical cases, and sort them in descending order of the matching degree. Screen out historical cases with a matching degree higher than the threshold (such as 85%) as similar historical cases; S52. Match the optimal solution from the knowledge base according to the similar historical cases and in combination with the case-based reasoning algorithm; specifically, S521. Extract features from the similar historical cases, such as equipment models, treatment measures, and implementation effects; S522. Use the case-based reasoning algorithm to calculate the comprehensive similarity between the current problem and the similar historical cases:

[0037] where α is the feature weight, by default taking 0.7, FSi is the technical parameter similarity, and CSi is the context environment similarity; S523. Sort by the comprehensive similarity, and select the solutions of the top N cases as the optimal solutions; S53. Generate decision suggestions for the project according to the matched optimal solution and in combination with the AI model; specifically, S531. Input the optimal solution into the decision tree model, and predict the success rate of the solution in combination with the real-time operation data of the project (such as the project schedule deviation rate and the safety risk value); S532. Filter out infeasible solutions (such as budget overrun or resource conflict) through the rule engine to obtain decision-making solutions; S533. Determine the level (high / medium / low) of the decision-making solution, specific measures (such as "add 2 thermal control engineers"), expected effects (such as "reduce the risk of schedule delay by 20%"), and use the natural language generation method to construct structured decision suggestions; S54. Submit the generated decision suggestions to the user, and optimize the project knowledge base according to the user's feedback on the decision suggestions; specifically, S541. Record the adoption situation (success / failure / partial adoption) of the user for the decision suggestions; S542. Update the case weights based on reinforcement learning:

[0038] Wherein: w i represents the recommendation weight of case i, r i represents the user feedback score (success = 1, failure = -1), represents the average feedback score, v i represents the confidence of the case based on the historical success rate; S543. Regularly clean up low-weight cases (such as not being adopted three times in a row), and supplement newly entered successful cases.

[0039] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0040] As Figure 2 shown, the following are embodiments of an enterprise personnel and project management system based on a knowledge base and an AI model provided by the embodiments of the present disclosure. This system and the enterprise personnel and project management method based on a knowledge base and an AI model in the above embodiments belong to the same inventive concept. For the details not described in detail in the embodiments of the enterprise personnel and project management system based on a knowledge base and an AI model, reference can be made to the embodiments of the enterprise personnel and project management method based on a knowledge base and an AI model.

[0041] The system includes: A project knowledge base construction module, configured to collect the implementation experience of the enterprise's historical projects and analyze it based on a knowledge graph to construct a project knowledge base; An employee label setting module, configured to evaluate enterprise employees, classify them in combination with evaluation dimensions, and set labels; A personnel allocation module, configured to collect real-time operation data of a project, and recommend and adjust personnel allocation for the project in combination with employee labels and project attributes.

[0042] Through the interactive cooperation of the project knowledge base construction module, the employee label setting module, and the personnel allocation module in this embodiment, dynamic knowledge base construction, employee label classification, and real-time data analysis are realized, achieving the intelligence of project management and the precision of resource allocation.

[0043] The enterprise personnel and project management method based on the knowledge base and AI model provided by the embodiments of the present application can be applied to an electronic device. Those skilled in the art can understand that the structure of the electronic device involved in the embodiments of the present invention does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements. In the embodiments of the present invention, the electronic device includes, but is not limited to, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of the present application described herein and / or claimed.

[0044] The electronic device may include a processor, an external memory interface, an internal memory, a universal serial bus (USB) interface, a charging management module, a power management module, a battery, a wireless communication module, an audio module, a speaker, a microphone, a sensor module, a key, a camera, a display screen, and a SIM card interface, etc.

[0045] It can be understood that the structure schematically shown in the embodiments of the present application does not constitute a specific limitation on the electronic device. In other embodiments of the present application, the electronic device may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or have different component arrangements. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0046] The processor may include one or more processing units. For example, the processor may include a central processing unit (CPU), etc., an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Among them, different processing units may be independent devices or integrated in one or more processors.

[0047] Among them, the processor can be the nerve center and command center of the electronic device. The controller can generate operation control signals according to the instruction operation code and timing signals to complete the control of fetching and executing instructions.

[0048] A memory can also be set in the processor for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can save the instructions or data that the processor has just used or reused in a loop. If the processor needs to use the instruction or data again, it can directly call it from this memory. This avoids repeated accesses, reduces the waiting time of the processor, and thus improves the system efficiency.

[0049] The above-mentioned electronic device implements the technical solution of the enterprise personnel and project management method based on the knowledge base and AI model of the present application, which collects the implementation experience of the enterprise's historical projects and analyzes it based on the knowledge graph to build a project knowledge base; evaluates the enterprise employees, classifies them in combination with evaluation dimensions, and sets labels; collects the real-time operation data of the project, and recommends and adjusts the personnel allocation for the project in combination with the employee labels and project attributes, achieving the beneficial effect of realizing the intelligentization of project management and the precision of resource allocation through building a dynamic knowledge base, employee labeling classification, and real-time data analysis.

[0050] In the storage medium provided by the present application, there is a program product capable of implementing the enterprise personnel and project management method based on the knowledge base and AI model.

[0051] The enterprise personnel and project management method based on the knowledge base and AI model includes: collecting the implementation experience of the enterprise's historical projects and analyzing it based on the knowledge graph to build a project knowledge base; evaluating the enterprise employees, classifying them in combination with evaluation dimensions, and setting labels; collecting the real-time operation data of the project, and recommending and adjusting the personnel allocation for the project in combination with the employee labels and project attributes.

[0052] In some possible implementation manners, the enterprise personnel and project management method based on the knowledge base and AI model of the present disclosure can be implemented in the form of a program product, which includes program code, and when the program product runs on the terminal device, the program code is used to make the terminal device execute the steps according to various exemplary embodiments of the present disclosure described in the "Exemplary Method" section above of this specification.

[0053] The storage medium of the present disclosure may employ any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0054] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An enterprise personnel and project management method based on a knowledge base and an AI model, characterized in that It includes the following steps: S1. Collect the implementation experience of the enterprise's historical projects, analyze it based on the knowledge graph, and construct a project knowledge base; S2. Evaluate the enterprise employees, classify them in combination with the evaluation dimensions, and set labels; S3. Collect the real-time operation data of the project, and recommend and adjust the personnel allocation for the project in combination with the employee labels and project attributes.

2. The enterprise personnel and project management method based on the knowledge base and the AI model according to claim 1, characterized in that, It also includes the following steps: S4. Analyze the real-time operation data of the project, determine the project status and give early warnings for project risks; S5. Output project decision-making suggestions based on the project knowledge base, the collected real-time operation data of the project, and the determined project status.

3. The enterprise personnel and project management method based on a knowledge base and an AI model according to claim 2, wherein The specific steps of step S1 are as follows: S11. Collect the implementation experience of the enterprise's historical projects, and the implementation experience includes accident reports, technical solutions, project progress data, and implementation results; S12. Use the knowledge graph to perform structured and correlation analysis on the collected project implementation experience, and use natural language processing to parse the analysis results to extract key information and construct a project knowledge base; The specific steps of step S2 are as follows: S21. Determine the evaluation dimensions of enterprise employees; the evaluation dimensions include technical expertise, project experience, and collaboration ability; S22. Dynamically evaluate employees through an approval and scoring process, and set labels for employees according to the evaluation dimensions; S23. Vectorize the labels of employees by coding to obtain the vector labels of each employee; S24. Store the vector labels of employees in the project knowledge base.

4. The enterprise personnel and project management method based on a knowledge base and an AI model according to claim 3, characterized in that, The specific steps of step S3 are as follows: S31. Through the interface docking with the project management platform, collect the real-time operation data of the project, and the real-time operation data of the project includes the progress, quality, and safety data of the project; S32. Respond to the project requirements, vectorize the project requirements to obtain a requirement vector; S33. Calculate the similarity between the requirement vector and the employee vector labels, and calculate the weighted matching degree according to the weights of different label categories preset; S34. Use the AI algorithm to combine the weighted matching degree of employees to recommend personnel for the project; S35. Dynamically adjust the project team configuration according to the real-time operation data of the project and the actual situation of personnel to optimize the project implementation efficiency.

5. The enterprise personnel and project management method based on a knowledge base and an AI model according to claim 4, characterized in that The specific steps of step S31 are as follows: S311. Analyze the project attributes according to the project requirements to generate requirement labels; S312. Use the TF-IDF algorithm to calculate the weights of the requirement labels; Among them, f j represents the occurrence frequency of requirement label j, N represents the total number of items, n j represents the number of items containing label j, and m is the number of label categories; The specific steps of step S32 are as follows: S321. Calculate the cosine similarity between the employee label vector and the requirement vector label; S322. Set the weights of the employee label vectors hierarchically and adjust them based on the weights of the requirement labels; S323. Calculate the weighted matching degree between the requirement vector and the employee label vector; The specific steps of step S33 are as follows: S331. Use the K-means clustering algorithm to classify employees; S332. Select the top N of the weighted matching degrees of each type of employee, aim at the largest number of categories among project members, and combine them according to the project scale constraints to generate a recommended list; The specific steps of step S34 are as follows: S341. Obtain the project team effectiveness indicators in real time; S342. When the deviation of the project team's effectiveness indicators exceeds the set threshold, adjust the project team configuration.

6. The enterprise personnel and project management method based on a knowledge base and an AI model according to claim 4, wherein, Step S4 is specifically as follows: S41. Analyze the collected real-time operation data of the project through data flow analysis to dynamically perceive the project status; S42. Combine the project historical data and the real-time operation data of the project, and use deep learning algorithms to evaluate the project status and identify potential risks of the project; S43. Generate early warning information according to the identified potential risks and notify the management personnel.

7. The enterprise personnel and project management method based on a knowledge base and an AI model according to claim 6, wherein, Step S5 is specifically as follows: S51. Respond to the user request, and query similar historical cases from the project knowledge base according to the real-time operation data of the project; S52. Match the optimal solution from the knowledge base according to the similar historical cases and combined with case-based reasoning algorithms; S53. Generate decision-making suggestions for the project according to the matched optimal solution and combined with the AI model; S54. Provide the generated decision-making suggestions to the user, and optimize the project knowledge base according to the user's feedback on the decision-making suggestions.

8. The enterprise personnel and project management method based on the knowledge base and AI model according to claim 7, characterized in that, The specific steps of step S51 are as follows: S511. Obtain the query request input by the user, and use the BERT pre-trained model to parse and vectorize the keywords in the query request; S512. Query historical cases through vector similarity calculation, and display the query results in the order of similarity to obtain historical cases; S513. Extract the problem features from the query request input by the user, calculate the matching degree between the problem features of the query request and the historical cases, and sort them in descending order of the matching degree. Screen out the historical cases with a matching degree higher than the threshold as similar historical cases; The specific steps of step S52 are as follows: S521. Extract features from similar historical cases; S522. Use case-based reasoning algorithms to calculate the comprehensive similarity between the current problem and similar historical cases: where α is the feature weight, FSi is the technical parameter similarity, and CSi is the context environment similarity; S523. Sort by the comprehensive similarity, and select the solutions of the top N cases as the optimal solution; The specific steps of step S53 are as follows: S531. Input the optimal solution into the decision tree model, and predict the success rate of the solution combined with the real-time operation data of the project; S532. Filter out infeasible solutions through the rule engine to obtain decision-making solutions; S533. Determine the level, specific measures, and expected effects of the decision-making solution, and use natural language generation to construct structured decision-making suggestions; The specific steps of step S54 are as follows: S541. Record the adoption of the decision-making suggestions by the user; S542. Update the case weights based on reinforcement learning: Wherein: w i represents the recommendation weight of case i, r i represents the user feedback score, represents the average feedback score, v i represents the confidence of the case based on the historical success rate; S543. Regularly clean up low-weight cases and supplement newly entered successful cases.

9. An enterprise personnel and project management system based on a knowledge base and an AI model, characterized in that, Including: A project knowledge base construction module, which is used to collect the implementation experience of the enterprise's historical projects and analyze them based on the knowledge graph to construct a project knowledge base; An employee label setting module, which is used to evaluate the enterprise employees, classify them according to the evaluation dimensions, and set labels; A personnel allocation module, which is used to collect the real-time operation data of the project, and recommend and adjust the personnel allocation for the project in combination with the employee labels and project attributes.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the enterprise personnel and project management method based on the knowledge base and AI model according to any one of claims 1 to 8.

Images