Intelligent review method based on artificial intelligence and big data analysis

Abstract

The invention discloses an intelligent review method based on artificial intelligence and big data analysis, and relates to a power system. The method comprises the steps of 1, data collection and preprocessing; 2, performing model construction and training based on the preprocessed data to form a review model; 3, based on the review model, intelligent review execution is carried out; and step 4, based on a review result, performing feedback and optimization. In the working process, through informatization and digitization means, in combination with multi-dimensional heterogeneous service data of a power distribution network project, the intelligent review model is depended on, intelligent review execution is performed by a machine, and the defects that original manual processing is depended on, the working process is tedious, the subjective factor occupation is large, and the service requirement for personnel is high are overcome.

Description

Technical Field

[0001] The present invention relates to a power system, and in particular to an intelligent review method based on artificial intelligence and big data analysis. Background Art

[0002] In the power system, traditional review work mostly relies on manual operations, which has many problems such as low efficiency, strong subjectivity, difficulty in standardization, and chaotic data management during the review process. For example, in previous project reviews, manual review record filling and report generation are not only time-consuming and laborious, but also prone to errors. Different reviewers may have different evaluation criteria for the same project, which affects the fairness and accuracy of the review results. With the rapid development of information technology, how to use intelligent means to optimize the review process and improve the quality of the review has become a key issue that needs to be solved urgently. Summary of the invention

[0003] In view of the above problems, the present invention provides an intelligent review method based on artificial intelligence and big data analysis, which saves manpower and improves efficiency.

[0004] The technical solution of the present invention is: an intelligent review method based on artificial intelligence and big data analysis, comprising the following steps: Step 1: Data collection and preprocessing; Step 2: Based on the preprocessed data, build and train the model to form a review model; Step 3: Intelligent review execution based on the review model; Step 4: Provide feedback and optimization based on the review results.

[0005] Step one includes: Obtain various data required for project review; Clean the collected structured data to remove duplicate data, erroneous data, and incomplete data; identify unstructured data to form a structured data set; The cleaned data is standardized and converted to meet the data format requirements within the system.

[0006] Step 2 includes: Use natural language processing technology to conduct text mining on project application document data, extract key information and construct text feature vectors; The review model is constructed by combining historical review data and industry standard data using machine learning algorithms.

[0007] The review model develops corresponding review engines according to different project types, and each project type includes review type, review content category and review points.

[0008] Use cluster analysis algorithms to classify project data and identify characteristic patterns of different types of projects.

[0009] Step three includes: When there is a new review project, the project data is input into the review model, which automatically conducts a preliminary review and outputs preliminary review results and a list of issues; For the parts marked as requiring manual review in the preliminary review of the review model, the most suitable review expert is automatically matched based on the expert profile and project characteristics, and the task is assigned to the expert; During the review process, experts use auxiliary tools to perform review operations and directly fill in review opinions and problem details on the system interface; the auxiliary tools include the intelligent search function to quickly find relevant standards and historical cases; The system records the experts’ operations and opinions in real time and integrates them with the preliminary review results of the model; The review model and expert review opinions are integrated to generate the final review report and statements.

[0010] Step 4 includes: Feedback the review result data, including project characteristics, review opinions, final results, etc., into model construction and training to update the review model and expert portraits; Collect feedback from all parties during the review process, organize and analyze them, and optimize and improve the system's review standards based on the analysis results.

[0011] In operation, the present invention uses information and digital means, combines the multi-dimensional and heterogeneous business data of the distribution network project, relies on the intelligent review model, and is executed by machine intelligent review, avoiding the disadvantages of relying on manual processing, which has a cumbersome process, a large proportion of subjective factors, and high business requirements for personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the specific implementation of the present invention or the technical solution in the prior art, the following briefly introduces the drawings required for the specific implementation or the prior art description. In the drawings, each part is not necessarily drawn according to the actual scale.

[0013] Figure 1 It is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0014] The present invention Figure 1 As shown, an intelligent review method based on artificial intelligence and big data analysis is provided, which includes the following steps: Step 1: Data collection and preprocessing; Step 2: Based on the preprocessed data, build and train the model to form a review model; Step 3: Intelligent review execution based on the review model; Step 4: Provide feedback and optimization based on the review results.

[0015] In operation, the present invention uses information and digital means, combines the multi-dimensional and heterogeneous business data of the distribution network project, relies on the intelligent review model, and is executed by machine intelligent review, avoiding the disadvantages of relying on manual processing, which has a cumbersome process, a large proportion of subjective factors, and high business requirements for personnel.

[0016] Specifically, Step 1: Data collection and preprocessing ① Connect multi-source data and obtain various data required for project review according to the predetermined data collection rules. For example, basic project information and related attachments, including: project feasibility report, project budget, project design plan, design drawings, power grid reliability impact assessment report, supply list A, supply list B and other 11 types of files, involving material formats such as world, excel, PDF, CAD, pictures, etc.

[0017] ② Clean the collected structured data to remove duplicate data, erroneous data and incomplete data; intelligently identify unstructured data (various attachments) to form a structured data set.

[0018] ③ Standardize and convert the cleaned data to make it conform to the data format requirements within the system.

[0019] Step 2: Model building and training ① Use natural language processing technology to conduct text mining on project application document data, extract key information and construct text feature vectors.

[0020] ② Combining historical review data and industry standard data, a machine learning algorithm is used to build a review model. The model develops corresponding review engines based on different project types, including grid projects, non-grid (capital) projects, non-grid (cost) projects, and rural grid projects. Each project type involves three major review types, 14 major review content categories, and 76 review points, as shown in Table 1.

[0021] Table 1 ③ Use cluster analysis algorithms to classify project data, identify characteristic patterns of different types of projects, and provide a basis for subsequent personalized reviews.

[0022] Step 3: Smart review execution ① When there is a new review project, the project data is input into the trained review model, and the model automatically conducts a preliminary review and outputs the preliminary review results and a list of issues. For example, the model determines whether the project support attachments meet the specifications, whether the content in the project basic information is consistent with the supporting materials, and whether the project plan is reasonable, etc., based on the project type (grid frame, non-grid frame).

[0023] ② For the parts marked as requiring manual review in the initial model review, the most suitable review expert is automatically matched based on the expert portrait and project characteristics, and the task is assigned to the expert.

[0024] Expert allocation principle: An automatic expert allocation algorithm is developed based on multi-dimensional factors such as the expert's professional knowledge, professional primary classification, professional secondary classification, review direction, business ability, work performance, unit, and project review points. The algorithm gives priority to the "mutual exclusion" principle of expert units and project units.

[0025] ③ During the review process, experts use the auxiliary tools provided by the system to perform review operations, such as quickly finding relevant standards and historical cases through the intelligent search function, and directly filling in review opinions and problem details on the system interface. The system records the expert's operations and opinions in real time and integrates them with the preliminary review results of the model.

[0026] ④ The final review report and report are generated based on the comprehensive model and expert review opinions. The review report includes the overall review conclusion of the project, detailed problem analysis and rectification suggestions, and the review report displays the key review information of the project in a preset format, such as review scores, classification statistics of major problems, etc.

[0027] Step 4: Feedback and Optimization ① Feedback the result data of this review, including project features, review opinions, final results, etc., into model construction and training to update the review model and expert portrait. For example, if a new project feature is found to have an important impact on the review results, but it has not been fully considered in the previous model, add the feature to the model's training data, retrain the model, and improve its accuracy.

[0028] ② Collect feedback from all parties during the review process, such as questions from project applicants about the review criteria, and suggestions from review experts on system functions. Categorize and analyze these feedbacks, and optimize and improve the system's review criteria, functional modules, etc. based on the analysis results. For example, if multiple experts report that the system's intelligent prompt function is not accurate enough, optimize the prompt algorithm to improve the relevance and accuracy of the prompt information.

[0029] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An intelligent review method based on artificial intelligence and big data analysis, characterized in that: The following steps are involved: Step 1: Data collection and preprocessing; Step 2: Based on the preprocessed data, build and train the model to form a review model; Step 3: Intelligent review execution based on the review model; Step 4: Provide feedback and optimization based on the review results.

2. According to claim 1, an intelligent review method based on artificial intelligence and big data analysis is characterized in that: Step one includes: Obtain various data required for project review; Clean the collected structured data to remove duplicate data, erroneous data, and incomplete data; identify unstructured data to form a structured data set; The cleaned data is standardized and converted to meet the data format requirements within the system.

3. The intelligent review method based on artificial intelligence and big data analysis according to claim 1 is characterized in that: Step 2 includes: Use natural language processing technology to conduct text mining on project application document data, extract key information and construct text feature vectors; The review model is constructed by combining historical review data and industry standard data using machine learning algorithms.

4. The intelligent review method based on artificial intelligence and big data analysis according to claim 3 is characterized in that: The review model develops corresponding review engines according to different project types, and each project type includes review type, review content category and review points.

5. The intelligent review method based on artificial intelligence and big data analysis according to claim 4 is characterized in that: Use cluster analysis algorithms to classify project data and identify characteristic patterns of different types of projects.

6. The intelligent review method based on artificial intelligence and big data analysis according to claim 1 is characterized in that: Step three includes: When there is a new review project, the project data is input into the review model, which automatically conducts a preliminary review and outputs preliminary review results and a list of issues; For the parts marked as requiring manual review in the preliminary review of the review model, the most suitable review expert is automatically matched based on the expert profile and project characteristics, and the task is assigned to the expert; During the review process, experts use auxiliary tools to perform review operations and directly fill in review opinions and problem details on the system interface; the auxiliary tools include the intelligent search function to quickly find relevant standards and historical cases; The system records the experts’ operations and opinions in real time and integrates them with the preliminary review results of the model; The review model and expert review opinions are integrated to generate the final review report and statements.

7. The intelligent review method based on artificial intelligence and big data analysis according to claim 1 is characterized in that: Step 4 includes: Feedback the review result data, including project characteristics, review opinions, final results, etc., into model construction and training to update the review model and expert portraits; Collect feedback from all parties during the review process, organize and analyze them, and optimize and improve the system's review standards based on the analysis results.

Images