Power distribution network project whole process technical-economic intelligent management method and system based on artificial intelligence and big data, and medium

By constructing a dynamic technical and economic knowledge base and comparing multi-source data, combined with OCR and NLP technologies, the problems of low efficiency, difficulty in collaboration, and insufficient accuracy in the technical and economic management of power distribution network projects have been solved, realizing intelligent management throughout the entire process and improving review efficiency and accuracy.

CN121304061APending Publication Date: 2026-01-09STATE GRID HUBEI ELECTRIC POWER CO LTD WUHAN POWER SUPPLY CO
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202511348498.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-09-21
Publication Date
2026-01-09

AI Technical Summary

Technical Problem

The existing power distribution network engineering management suffers from low efficiency, difficulty in coordination, and insufficient accuracy. Traditional review models rely on manual labor, have long review cycles, limited coverage, scattered data, and lack intelligent analysis capabilities, making it impossible to achieve dynamic control throughout the entire process.

Method used

A dynamic technical and economic knowledge base based on artificial intelligence and big data is constructed. Combining OCR and natural language processing technologies, intelligent parsing and verification of engineering documents are achieved. Deviations and anomalies are identified through multi-source data comparison, forming a closed-loop feedback optimization mechanism to support collaborative management between the province and the city.

Benefits of technology

It has achieved standardization, dynamism, and intelligence in engineering technology and economic management, significantly reduced the rejection and reduction rates, optimized the investment surplus rate, improved the efficiency of material accounting, and helped the power industry's digital transformation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121304061A_ABST
    Figure CN121304061A_ABST
Patent Text Reader

Abstract

The invention relates to a power distribution network project whole-process technical-economic intelligent management method and system based on artificial intelligence and big data, and a medium. The system comprises a dynamic technical-economic knowledge base module which automatically repairs and compiles a typical cost base and automatically and dynamically updates knowledge base contents; the feasibility research initial intelligent review module is used for verifying the integrity of the design file and estimating or roughly calculating the compliance of the file, the quota application accuracy and the probability exceeding risk through a knowledge base, and generating a structured review report; the settlement intelligent review module is used for identifying material quantity deviation and price abnormity; and the closed loop feedback and optimization module forms a'typical problem library iteration-review auxiliary optimization 'closed loop. According to the method, the data barrier of a department is broken, the review process is promoted to be converted from manual spot check to intelligent full coverage, the review quit rate and the review subtraction rate are remarkably reduced, the investment balance rate is optimized, the material balance efficiency is improved, standardized and extensible intelligent support is provided for technical and economic management of a power distribution network project, and digital transformation of the power industry is assisted.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the field of power system automation, in particular to a power distribution network engineering whole-process technical and economic intelligent management method and system based on artificial intelligence and big data, and a medium. BACKGROUND

[0002] At present, the technical and economic management of power distribution network engineering generally faces problems such as low efficiency, difficulty in collaboration, and insufficient precision. The traditional review mode relies on manual sampling and offline multi-link submission, resulting in long review period, limited coverage, high review rate and high rejection rate, which is difficult to meet the demand of the increasing investment scale of power distribution network engineering year by year. At the same time, engineering technical and economic management involves multiple departments such as finance, materials, design institute, etc., and the data is scattered in heterogeneous platforms such as ERP system, as-built drawing, settlement book, etc., lacking unified knowledge base and dynamic correlation mechanism, and the cross-department collaboration efficiency is low, the material balance and financial transfer cycle is long, and the historical problems are difficult to trace. The professional level of technical and economic personnel is uneven, manual review is easily limited by experience, and problems such as deviation of fixed quota selection and non-uniformity of fee standards frequently occur. Combined with the lack of intelligent analysis capability of existing systems, it is impossible to realize automatic checking of “quantity, price, and fee”. The key links such as over-projection warning and surplus analysis rely on manual experience, resulting in weak dynamic control capability in the whole process. In addition, the typical design is updated slowly to typical cost, which is difficult to adapt to the latest pricing standards, and the coverage of the actual engineering application scheme is limited, further restricting the standardization and precision of cost audit.

[0003] Although the existing technology attempts to optimize the process through informatization means, there are still significant defects. Most systems only support single-link online, and do not support intelligent review of the whole process of “(feasibility study) preliminary design-settlement”, and cannot realize one-key checking of batch engineering. The review mode is fixed and inefficient. The data mining capability is weak, lacking semantic understanding and intelligent matching technology driven by large models, making it difficult to automatically identify abnormal quota, price deviation and design change correlation, resulting in difficulty in improving the accuracy of review. The dynamic knowledge base construction lags behind, and the multi-dimensional data such as typical design, construction technology, and real-time price are not integrated, the review benchmark is static, and it is difficult to adapt to the rapid changes of complex engineering scenarios. These deficiencies make it difficult for existing systems to solve the core problems of low efficiency, poor precision, and difficult collaboration, and it is necessary to deeply integrate artificial intelligence and big data technology to build an intelligent technical and economic management system throughout the whole process, and promote the transformation from experience-driven to data-intelligent management. SUMMARY

[0004] The purpose of the embodiments of the present application is to provide a power distribution network engineering whole-process technical and economic intelligent management method and system based on artificial intelligence and big data, and a medium, which realizes the standardization, dynamic and intelligent of engineering technical and economic management throughout the whole process through the balanced design and collaborative optimization of the three core modules of technical and economic knowledge base, feasibility study preliminary design intelligent review, and settlement intelligent review.

[0005] To achieve the above object, the application provides the following technical solutions.

[0006] In a first aspect, the application provides a power distribution network engineering whole-process technical intelligent management system based on artificial intelligence and big data, comprising,

[0007] A dynamic technical knowledge base module is used for integrating a typical design library, a typical cost library, a construction technology library and a benchmark settlement library, realizing technical knowledge integration through a Guangming big model learning architecture, and accessing a regional information price platform, an ERP system and audit report data to automatically compile the typical cost library and automatically and dynamically update the knowledge base content;

[0008] A feasibility study and preliminary design intelligent review module is based on OCR and natural language processing technology to analyze unstructured engineering files, extract quantities, equipment parameters and cost standards, check the design file integrity, estimate or budget file compliance, quota application accuracy and super-probability risks through the knowledge base, and generate a structured review report;

[0009] A settlement intelligent review module is used to extract settlement quantity and price and as-built drawing material table data to generate target quantity and price, ERP material warehouse record quantity and budget book quantity and price for comparison, and identify material quantity deviation and price abnormalities;

[0010] A closed-loop feedback and optimization module is used to deposit review abnormal cases to a typical problem library, promote dynamic updating of the knowledge base, and form a "typical problem library iteration-review auxiliary optimization" closed loop.

[0011] The dynamic technical knowledge base module comprises a collaborative learning unit that supports local rules of city companies and realizes network-province-city knowledge base collaboration through data encryption and model aggregation; by comparing differences between new and old typical design material lists and matching logic of quotas and material and ERP correlation libraries, the typical cost is automatically and dynamically compiled, and for the part of the engineering without correlation libraries, knowledge base compilation suggestions are automatically generated, and after manual review, quota items and material price thresholds are updated.

[0012] The feasibility study and preliminary design intelligent review module comprises a multi-modal analysis unit that uses a handwriting detection model to identify unstructured data in drawings and associates typical cost and selection of corresponding cost components through a semantic matching algorithm; a preliminary design stage super-feasibility reply early warning unit that predicts deviation risks based on historical similar engineering investment data, generates priority correction suggestions and pushes them to design units.

[0013] The settlement intelligent review module comprises a model that extracts as-built material table data and automatically compares it with ERP warehouse records according to a set material quantity deviation; three comparison units that dynamically analyze settlement quantity and price, target quantity and price, and budget quantity and price, identify quota application abnormalities and price deviations, and generate a difference traceability report.

[0014] The closed-loop feedback and optimization module comprises a case collection unit that automatically classifies typical deviation items into a typical problem library and associates design change records, construction logs and rectification measures; and a knowledge iteration unit that improves quota association rules and construction loss coefficients based on feedback data to improve subsequent review accuracy.

[0015] In a second aspect, the embodiments of the present application provide a power distribution network engineering whole-process technical and economic intelligent management method based on artificial intelligence and big data, comprising the following steps: constructing a dynamic technical and economic knowledge base, integrating typical design and corresponding cost, quota rules and historical settlement data, and realizing multi-level collaboration and dynamic updating through node learning; obtaining as-built drawing material inventory data and comparing with ERP and settlement book in a multi-source manner, detecting deviations and tracing the root causes of problems.

[0016] The dynamic updating comprises: automatically triggering a knowledge base revision process when regional information prices fluctuate beyond a threshold or new process requirements are detected; analyzing deviation causes through a scientific mechanism reasoning model, and updating quota association relationships and construction loss parameters.

[0017] The multi-source comparison comprises: comparing target quantity prices with settlement quantity prices to detect items with price deviations beyond a threshold; comparing as-built drawing material tables with ERP warehouse records to identify discrepancies in material accounts; and comparing settlement quantity prices with budget quantity prices to analyze investment surplus abnormalities and design deviations, and assist achievement evaluation units in assessment.

[0018] In a third aspect, the embodiments of the present application provide a computer readable storage medium storing program codes, which, when executed by a processor, implement the steps of the power distribution network engineering whole-process technical and economic intelligent management method based on artificial intelligence and big data as described above.

[0019] In a fourth aspect, the embodiments of the present application provide an electronic device comprising:

[0020] a memory for storing computer programs;

[0021] a processor for executing the computer programs stored on the memory to implement the steps of the power distribution network engineering whole-process technical and economic intelligent management method based on artificial intelligence and big data as described above.

[0022] Compared with the prior art, the beneficial effects of the present application are: in view of the problems of strong artificial dependence, low data collaboration efficiency, long review process and limited coverage in traditional technical management, a full-process intelligent solution scheme is proposed with a dynamic technical knowledge base as the core. The system integrates typical design and cost, quota rules, construction technology and benchmark historical settlement data to build a dynamically updated knowledge base system, supports network-province and city-level collaborative management, and real-time adapts to the latest policies, prices and process standards. The intelligent review module of the preliminary design combines OCR and natural language processing technology to analyze unstructured engineering files, automatically check the application coverage rate of engineering components, identify differences between the cost and fees in the preliminary design stage, identify quota application errors and super-batch risk in the preliminary design stage, generate a structured review report, and realize accurate control at the design source. The settlement intelligent review module detects the deviation of equipment and material quantity in the completion drawing and the equipment and material quantity in the settlement book and price anomalies through OCR identification and multi-source data comparison. The system breaks down departmental data barriers, promotes the review process from manual sampling to intelligent full coverage, significantly reduces the rejection rate and review reduction rate, optimizes the investment surplus rate, improves the material balance efficiency, provides standardized and scalable intelligent support for power distribution network engineering technical management, and helps the digital transformation of the power industry. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0024] Figure 1 is a system block diagram of the present application;

[0025] Figure 2 is a method flowchart of the present application. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present application will be described below in combination with the drawings in the embodiments of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0027] The terms "comprise", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element preceded by "comprises a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that comprises the recited element.

[0028] The terms "first", "second", and the like are used only to distinguish one entity or operation from another entity or operation, and do not imply or suggest relative importance, nor do they imply or suggest any such actual relationship or order between the entities or operations.

[0029] As shown in Figure 1 The embodiments of the present application provide a power distribution network engineering whole-process technical intelligent management system based on artificial intelligence and big data, which comprises,

[0030] A dynamic technical knowledge base module 1 is used for integrating a typical design library, a typical cost library, a construction technology library, and a benchmark settlement library, realizing technical knowledge integration through a Guangming big model learning architecture, and accessing a regional information price platform, an ERP system, and audit report data to automatically compile a typical cost library and automatically and dynamically update knowledge base content;

[0031] A feasibility study and initial design intelligent review module 2 extracts text and position information in scanned drawings or reports as machine text based on OCR technology (image preprocessing, text detection and recognition); then uses NLP technology (especially a pre-training model that fuses text semantics and layout information such as LayoutLM) for deep analysis: named entity recognition (NER) extracts key engineering elements (such as "concrete", "beam L-101", and "35MPa"), relationship extraction establishes connections between elements (such as "'C30 concrete' is used for 'piled pier'"), and finally outputs structured data to check the completeness of design files and the compliance of estimated or budgeted files, the accuracy of quota application, and the risk of over-budgeting in combination with a knowledge base, and generates a structured review report;

[0032] A settlement intelligent review module 3 is used for extracting settlement book quantity and price and completion drawing material table data to generate target quantity and price, ERP material out-of-stock record quantity, and budgeted book quantity and price for comparison to identify material quantity deviation and price abnormalities;

[0033] The closed-loop feedback and optimization module 4 will review the abnormal case and deposit it to the typical problem library, input the machine-readable engineering text (such as the detection report string), and perform the following operations: (1) semantic analysis: use the domain pre-training language model (such as fine-tuned BERT) for hierarchical named entity recognition (NER), extract entities such as components, materials, and parameters (for example, identify [pier P5: component], [concrete: material], and [35.2 MPa: strength parameter] from "pier P5 concrete strength 35.2 MPa"), and generate triples through relation extraction (RE) (for example: (pier P5)-[material]->concrete, (pier P5)-[strength value]->35.2 MPa); (2) knowledge fusion: based on the standardized entities of the engineering ontology library (for example, map "concrete" to "concrete" and "HRB400" to "steel grade HRB400"), and link external databases to supplement attributes (for example, associate "concrete C30" with the elastic modulus in the material library); (3) knowledge storage: structured storage: convert to JSON format (for example: {"entity": "pier P5", "attributes": [{"type": "material", "value": "concrete"}, {"type": "strength", "value": 35.2, "unit": "MPa"}]} ) or database table; knowledge graph construction: store node relationships in a graph database (for example, Cypher: CREATE(:component{ name: "pier P5"})-[:strength]->(:parameter{ value: 35.2, unit: "MPa"}));

[0034] (5) Multi-level coordination mechanism: vertical coordination - sub-nodes report status to parent nodes (for example: quota coefficient adjustment -> standard module change), parent nodes issue strategies (for example: standard module cost deviation > 10%, initiate quota sub-item difference item early warning); horizontal coordination - nodes of the same level exchange data through graph neural network (GNN) message passing (for example: adjacent pier coordination to judge settlement risk);

[0035] Promote dynamic updating of the knowledge base and form a "typical problem library iteration - review assisted optimization" closed loop.

[0036] The dynamic technical knowledge base module includes a collaborative learning unit that supports city companies to expand localized rules and realizes the collaboration of the network-province-city knowledge base through data encryption and model aggregation; by comparing the differences between the new and old typical design material lists and the matching logic of the quota and material and ERP correlation library, the typical cost is automatically and dynamically revised, and for the part of the project that has no correlation library, the knowledge base revision suggestion is automatically generated, and after manual review, the quota items and material price threshold are updated.

[0037] The intelligent review module of the preliminary design includes a multi-modal analysis unit that uses a handwriting detection model to identify unstructured data in drawings and associates typical cost and selection of corresponding cost components through semantic matching algorithms; a preliminary design stage super-research reply early warning unit that predicts deviation risks based on historical similar engineering investment data, generates priority correction suggestions and pushes them to design units.

[0038] The intelligent review module of the settlement includes extracting data from the completion material table through the model, and automatically comparing it with the ERP out-of-warehouse records according to the set material quantity deviation. Three comparison units dynamically analyze the settlement quantity and price, the subject quantity and price, and the budget quantity and price, identify abnormal quota application and price deviation, and generate difference traceability reports.

[0039] The closed-loop feedback and optimization module includes a case collection unit that automatically classifies typical deviation projects into a typical problem library and associates design change records, construction logs, and rectification measures; a knowledge iteration unit that improves quota correlation rules and construction loss coefficients based on feedback data to improve the accuracy of subsequent review.

[0040] As shown in Figure 2 The present application provides a power distribution network engineering whole-process technical intelligent management method based on artificial intelligence and big data. Through the balanced collaboration of the three core modules of dynamic technical knowledge base, intelligent review of preliminary design and intelligent review of settlement, the standardization, digitization and intelligentization of engineering technical management whole process are realized. The implementation content focuses on data integration, intelligent technology application and cross-department collaboration, specifically covering the following aspects:

[0041] Technical knowledge base construction: Taking multi-source data fusion as the core, integrating typical design technical library (covering more than 90% of the scenes of distribution network engineering, various design standard engineering quantities), typical cost library (including quota rules, equipment and material prices and cost standard), construction technology library and benchmark settlement library, cleaning data through Guangmingda model and constructing semantic association network. Real-time access to regional information price platform, ERP material data and audit report, dynamically update knowledge base benchmark, ensure synchronization with market price and policy standard. Through the federal learning architecture to support the network-provincial-city two-level cooperation, the city company can extend the local rules (such as construction additional fee in alpine region), realize the fusion of "global standardization + regional individualization". The knowledge base is automatically revised and compiled every month, analyzes the common problems in the review (such as missing quota), generates revision suggestions and dynamically optimizes after manual review.

[0042] Intelligent review of preliminary design: Based on OCR, NLP and handwriting detection technology, analyze unstructured files (such as preliminary design report, preliminary design drawings), extract engineering quantity, equipment parameter and other key fields and map them to standardized templates. Based on large model and typical design library, equipment selection compliance and quota application error, trigger super-probability warning (such as investment exceeding 10% of historical similar projects). For the uncoverted scene, the system automatically pushes the knowledge base gap warning, and the design unit is linked to supplement the case. Realize batch import of hundred-level engineering files and structured report generation, reduce the workload of manual review by 70%, and reduce the design rework rate by 50%.

[0043] Settlement intelligent review: Through the "three comparison" mechanism (comparison of subject quantity and price generated by completion drawing quantity, comparison of quantity generated by completion drawing quantity and ERP quantity, comparison of quantity and price of settlement book and quantity and price of budget book) to realize closed-loop control. Image recognition technology extracts the completion drawing material table, combines the quota correlation database to produce subject quantity and price, compares with the ERP out-of-stock record (threshold ≤8%), matches the benchmark settlement library to detect abnormal quota application (such as non-standard quota application) and price deviation (such as ±10% deviation from regional information price). Causal reasoning model traces the root cause of deviation (such as delayed change visa or construction problems), generates "one project one analysis" report and tracks rectification. The system automatically generates tamper-proof settlement book, synchronizes with the data of the audit department. The review rate is controlled within 5%, and the review reduction rate is stable at 8%-10%.

[0044] The embodiment of the application provides a kind of based on artificial intelligence and big data's distribution network engineering whole process technical intelligent management method, comprising the following steps: constructing dynamic technical knowledge base, integrating typical design and corresponding cost, quota rule and historical settlement data, realize multi-level cooperation and dynamic update by node learning;Obtain completion drawing material list data and compare with ERP, settlement book, detect deviation and trace problem root.

[0045] The dynamic updating includes: automatically triggering the knowledge base revision process when regional information price fluctuation exceeds a threshold or a new process requirement is detected; analyzing deviation reasons by a scientific mechanism reasoning model, and updating the quota correlation and construction loss parameters. The formula is as follows:

[0046]

[0047] Wherein X is a multi-source input feature vector, and Φ is a set of trainable parameters.

[0048] The parameter updating follows a dynamic feedback rule:

[0049]

[0050] The adaptive correction of the quota correlation and loss parameters is realized.

[0051] The multi-source comparison includes: comparing the target quantity price and the settlement quantity price to detect projects with price deviation exceeding a threshold; comparing the completion drawing material table and the ERP outbound record to identify material account discrepancies; realizing a multi-source comparison model taking the completion drawing and the inventory as comparison benchmarks, combining the settlement cost file and the ERP material cost outbound list as two correction parameters, correcting the inventory data with the settlement book, and then comparing the corrected inventory with the ERP outbound material list to quickly locate the material usage and realize the settlement engineering quantity multi-source comparison.

[0052] The embodiment of the application provides a computer readable storage medium, the computer readable storage medium stores program code, the program code is executed by a processor, and the steps of the power distribution network engineering whole process technical intelligent management method based on artificial intelligence and big data are realized.

[0053] The embodiment of the application provides an electronic device, which comprises:

[0054] A memory is used to store a computer program.

[0055] A processor is used to execute the computer program stored on the memory, and the steps of the power distribution network engineering whole process technical intelligent management method based on artificial intelligence and big data are executed.

[0056] Those skilled in the art should understand that the embodiments of the application can be provided as a method, a system or a computer program product. Therefore, the application can be in the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the application can be in the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0057] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or combination thereof. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or combination thereof.

[0058] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or combination thereof. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or combination thereof.

[0059] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or combination thereof. Figure 1 one or more flowcharts and / or blocks in the flowcharts and / or combination thereof.

[0060] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0061] The memory can include non-persistent memory and / or volatile memory, such as a random access memory (RAM) including a cache area for the temporary storage of data. The memory can also include non-volatile memory, such as read only memory (ROM) for storing structural information and / or instruction code to implement the functions of the computing device. The memory can additionally or alternatively include mass storage for persistent storage of information and instructions.

[0062] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0063] The above only describes the embodiments of the present application and is not used to limit the protection scope of the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An intelligent management system for the whole process of power distribution network engineering based on artificial intelligence and big data, characterized in that, Comprising, A dynamic technical and economic knowledge base module for integrating typical design library, typical cost library, construction technology library and benchmark settlement library, realizing technical and economic knowledge integration through Guangmingda model learning architecture, and accessing regional information price platform, ERP system and audit report data to automatically compile and update typical cost library and knowledge base content; An intelligent review module for preliminary design based on OCR and natural language processing technology to analyze unstructured engineering files, extract quantities, equipment parameters and fee standards, check design file integrity, estimate or budget file compliance, quota application accuracy and super-probability risk through knowledge base, and generate a structured review report; A settlement intelligent review module for extracting settlement quantity and price and completion drawing material table data to generate target quantity and price, ERP material out-of-stock record quantity and budget book quantity and price for comparison to identify material quantity deviation and price anomaly; A closed-loop feedback and optimization module to sediment review abnormal cases to the typical problem library to promote dynamic updating of the knowledge base and form a "typical problem library iteration-review auxiliary optimization" closed loop. 2.The power distribution network engineering whole-process technical intelligent management system based on artificial intelligence and big data according to claim 1, characterized in that, The dynamic technical and economic knowledge base module comprises a collaborative learning unit supporting local rules expansion of city companies and realizing network-province-city knowledge base collaboration through data encryption and model aggregation; through comparison of differences between new and old typical design material lists and matching logic of quota and material and ERP correlation library, automatically and dynamically compiling typical cost, and for parts of engineering without correlation library, automatically generating knowledge base compilation suggestions, updating quota items and material price thresholds after manual review. 3.The power distribution network engineering whole-process technical intelligent management system based on artificial intelligence and big data according to claim 1, characterized in that, The intelligent review module for preliminary design comprises a multi-modal analysis unit using a handwriting detection model to identify unstructured data in drawings and associating typical cost and selection of corresponding cost components through semantic matching algorithm; a preliminary design stage super-research reply early warning unit based on historical similar engineering investment data to predict deviation risk, generate priority correction suggestions and push to design units. 4.The power distribution network engineering whole-process technical intelligent management system based on artificial intelligence and big data according to claim 1, characterized in that, The settlement intelligent review module comprises a model for extracting completion material table data and automatically comparing with ERP out-of-stock records according to set material quantity deviation; three comparison units for dynamic analysis of settlement quantity and price, target quantity and price and budget quantity and price to identify quota application anomaly and price deviation and generate difference traceability report. 5.The power distribution network engineering whole-process technical intelligent management system based on artificial intelligence and big data according to claim 1, characterized in that, The closed-loop feedback and optimization module comprises a case collection unit to automatically classify typical deviation projects into the typical problem library and associate design change records, construction log and rectification measures; a knowledge iteration unit to improve quota correlation rules and construction loss coefficient based on feedback data to improve subsequent review accuracy.

6. An intelligent management method for the whole process of power distribution network engineering based on artificial intelligence and big data, characterized in that, The method comprises the following steps: Building a dynamic technical and economic knowledge base, integrating typical design and corresponding cost, quota rules and historical settlement data, realizing multi-level collaboration and dynamic updating through node learning; obtaining completion drawing material list data and comparing with ERP and settlement book for multi-source comparison, detecting deviation and tracing problem root cause. 7.The power distribution network engineering whole-process technical intelligent management method based on artificial intelligence and big data according to claim 6, characterized in that, The dynamic updating comprises automatically triggering knowledge base compilation process when regional information price fluctuation exceeds threshold or new technology demand is detected; analyzing deviation reasons through scientific mechanism reasoning model to update quota correlation and construction loss parameters. 8.The power distribution network engineering whole-process technical intelligent management method based on artificial intelligence and big data according to claim 6, characterized in that, The multi-source comparison includes: target quantity price and settlement quantity price comparison, detecting items deviating from the price threshold; comparison between the completion map material table and the ERP outbound record, identifying material account discrepancies; comparison between the settlement quantity price and the estimated quantity price, analyzing investment surplus abnormalities and design deviations, and assisting the achievement evaluation unit in assessment.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores program code, and the program code is executed by the processor to implement the steps of the power distribution network engineering whole-process technical intelligent management method based on artificial intelligence and big data according to any one of claims 6 to 8.

10. An electronic device, comprising: Comprise: Memory for storing computer programs; The processor is used for executing the computer program stored on the memory, and executes the steps of the power distribution network engineering whole-process technical intelligent management method based on artificial intelligence and big data according to any one of claims 6 to 8.