CN-122022731-A - Intelligent budget planning system for development of water conservancy informatization custom software

CN122022731ACN 122022731 ACN122022731 ACN 122022731ACN-122022731-A

Abstract

The invention discloses an intelligent budget planning system for development of water conservancy informatization custom software, and belongs to the technical field of information processing. The technical problem to be solved is how to improve timeliness and compliance. The technical scheme is characterized by comprising an intelligent recognition module, a multi-dimensional intelligent budget analysis module and an intelligent generation result report module, wherein the intelligent recognition module comprises a data acquisition module and an intelligent classification module, the data acquisition module is used for acquiring a document to be recognized, the intelligent classification module is used for recognizing the function point type of the acquired document to be recognized, the multi-dimensional intelligent budget analysis module is used for obtaining project expense according to the function point type recognized by the intelligent classification module, and the intelligent generation result report module is used for displaying the project expense obtained by the multi-dimensional intelligent budget analysis module.

Inventors

Jiao Ruxia
SONG XUMIN
XU WANTING
Jia Tianshuo
LI SHANFEI
WANG YUSHUANG
YANG XIJUN
ZHAO ZHENYU
LI WENKAI
Zhan Hongli
CHEN YUDU
HU XIAOQING

Assignees

中国电建集团北京勘测设计研究院有限公司

Dates

Publication Date: 20260512
Application Date: 20260130

Claims (10)

1. The intelligent budget planning system for the water conservancy informatization custom software development is characterized by comprising an intelligent identification module, a multi-dimensional intelligent budget analysis module and an intelligent generation result reporting module, wherein the intelligent identification module comprises a data acquisition module and an intelligent classification module, the data acquisition module is used for acquiring a document to be identified, the intelligent classification module is used for identifying the function point type of the acquired document to be identified, the multi-dimensional intelligent budget analysis module is used for obtaining project cost according to the function point type identified by the intelligent classification module, and the intelligent generation result reporting module is used for displaying the project cost obtained by the multi-dimensional intelligent budget analysis module.
2. The intelligent budget planning system for water conservancy informationized custom software development according to claim 1, wherein a water conservancy compliance cost mapping knowledge base is arranged in the intelligent classification module, and a LLM large language model and a BERT model are trained in the intelligent classification module for function point category analysis.
3. The intelligent budget planning system for water conservancy informationized custom software development according to claim 2, wherein in the intelligent classification module, the documents to be identified are divided into two types according to document types, namely a structured short text and an unstructured long text, the unstructured long text is subjected to functional point extraction by using a trained LLM large language model, the structured short text is subjected to functional point extraction by using a trained BERT model, when the functional points extracted by the two models are water conservancy professional functional points, the functional point type is output to a multi-dimensional intelligent budget analysis module, otherwise, the functional point type is identified as a conventional functional point, and the type identification is verified aiming at the conventional functional point.
4. The intelligent budget planning system for water conservancy informatization custom software development according to claim 3 is characterized in that the verification of category identification is carried out on conventional function points, and the specific method comprises the steps of obtaining confidence coefficient when a BERT model or a LLM large language model identifies the category of the conventional function points, outputting the category of the conventional function points to a multi-dimensional intelligent budget analysis module when the confidence coefficient of the BERT model or the LLM large language model after identifying the category of the conventional function points is more than or equal to 90%, and triggering a pre-set rule base to verify if the confidence coefficient is less than 90%.
5. The intelligent budget planning system for water conservancy informationized custom software development according to claim 4 is characterized in that the specific method for verifying the preposed rule base is that the category of the conventional function point is matched with the water conservancy compliance cost mapping knowledge base, if the function point exists in the water conservancy compliance cost mapping knowledge base, the category of the function point is output to a multi-dimensional intelligent budget analysis module, if the function point does not exist in the water conservancy compliance cost mapping knowledge base, the function point is input to a lightweight classifier, the confidence coefficient of the lightweight classifier after the category identification of the function point is obtained, when the confidence coefficient of the lightweight classifier after the category identification of the function point is greater than or equal to 85%, the lightweight classifier after the category identification of the function point is output, when the confidence coefficient is smaller than 85%, the function point category of the LLM large language model after the identification is output, the function point category of the lightweight classifier and the function point category of the LLM large language model identification are triggered, the confidence coefficient base after the function point category of the function point identification is triggered, the lightweight classifier and the multi-dimensional intelligent budget analysis module after the multi-dimensional intelligent budget analysis is carried out, and if the confidence coefficient of the lightweight classifier after the category identification of the function point is greater than or equal to 85%, the confidence coefficient of the function point is input to the LLM large language model.
6. The intelligent budget planning system for water conservancy informationized custom software development according to claim 1, wherein the multi-dimensional intelligent budget analysis module comprises a data access module, a classification calculation module and a compliance verification module, wherein the data access module is used for obtaining a function point type output by the intelligent classification module, the classification calculation module is used for calculating project expense according to the function point type, and the compliance verification module is used for verifying whether the calculated project expense is in compliance.
7. The intelligent budget design system for water conservancy informationized custom software development according to claim 6, wherein project cost is calculated by the formula project cost = project workload x people month rate x direct non-human cost.
8. The intelligent budgeting system for the development of water conservancy informatization custom software according to claim 7, wherein the project workload is calculated by the following formula: Project workload= (conventional AFP/conventional productivity) + (hydraulic AFP/hydraulic productivity); regular productivity = regular AFP/(regular productivity + hydraulic AFP); hydraulic productivity = hydraulic AFP/(regular productivity + hydraulic AFP).
9. The intelligent budgeting system for the development of water conservancy informationized custom software according to claim 8, wherein the conventional AFP and the water conservancy AFP are calculated specifically by the following formula: Conventional afp=ufp×scale change adjustment factor×software class adjustment factor×software quality characteristic adjustment factor×creation adjustment coefficient; Hydraulic afp=ufp×cf; The UFP represents the number of unadjusted function points, and the CF represents the setting scale changing factor.
10. The intelligent budgeting system for the development of water conservancy informationized custom software according to claim 9, wherein the UFP is calculated by the following formula: UFP= ; In the above-mentioned method, the step of, The weights of the various categories are represented, Representing the total number of categories identified in the intelligent classification module.

Description

Intelligent budget planning system for development of water conservancy informatization custom software Technical Field The invention relates to the technical field of information processing, in particular to an intelligent budget planning system for development of water conservancy informatization custom software. Background The conventional budget planning technology is still mainly a manual planning technology, has obvious limitations, and is difficult to meet the requirements of accurate, expected and efficient propulsion of the budget planning scheme developed by modern water conservancy informatization custom software. Therefore, by using the artificial intelligence technology, the intelligent transformation of the development budget of the water conservancy informatization custom software is realized, and the intelligent transformation becomes an important break for improving the budget efficiency of the water conservancy informatization project and becomes an important means for improving the compiling efficiency. Through analysis of industry current status, conventional budgeting technology limitations are mainly manifested in the following aspects: (1) The definition of the functional point division is low, the programming efficiency is low, and the time consumption is long, namely the conventional budget programming technology of the water conservancy informatization is low in efficiency and long in time consumption due to the fact that the definition of the functional point division is insufficient. The project decomposition fineness is low, the cost coverage is incomplete, and the real cost of software and hardware, operation and maintenance, integration and the like is difficult to accurately reflect. The fine adjustment of the project needs to be repeatedly checked and adjusted manually, so that the workload is increased, the approval decision-making period is prolonged, and the efficiency and timeliness of the whole programming are finally affected. (2) The real-time linkage capability is lacking, the conventional budget management mode is mostly one-time programming and staged adjustment, and when the project progress, design scheme or resource allocation is changed, the budget needs to be manually rechecked and adjusted, so that the problems of project delay, even budget superbranching and the like are often caused. Therefore, it is desirable to provide an intelligent budget planning system for development of water conservancy informatization custom software, which improves timeliness and compliance compared with the prior art. Disclosure of Invention The invention aims to provide that: An intelligent budget planning system for development of water conservancy informatization custom software and related technologies thereof are provided, so as to solve the technical problems of improving timeliness and compliance or the combination thereof. Description of the terminology: Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the inventive subject matter belongs. All patents, patent inventions, and publications cited herein are incorporated by reference in their entirety unless otherwise indicated. If there are multiple definitions of terms herein, the definitions of this chapter shall control. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the subject matter of the invention, as claimed. In the present invention, the singular is used to include the plural unless specifically stated otherwise. It should also be noted that the use of "or" means "and/or" unless stated otherwise. Furthermore, the terms "include," as well as other forms, such as "comprising," "including," and "containing," are not limiting. The definition of standard terms can be found in the reference "@ 2025 chinese software industry benchmark data". Conventional methods within the skill of the art, such as core budgeting methods, are employed unless otherwise indicated. Unless specifically defined, the use of various commercially available products as used herein employs standard techniques. The techniques and methods described above may generally be practiced according to conventional methods well known in the art, based on a number of general and more specific descriptions in the literature cited and discussed in this specification. The term "optionally/arbitrarily" or "optionally/arbitrarily" means that the subsequently described event or circumstance may or may not occur, and that the description includes instances where said event or circumstance occurs and instances where it does not. The term "LLM large language model" as used herein refers to a deep learning model that is trained on massive text, capable of understanding and generating human language. The term "BERT model" as used herein ref