A project management method and device, and a storage medium

Abstract

The application provides a project management method, device and storage medium, and belongs to the technical field of project management.The method comprises the following steps: importing multiple scene classification data, multiple business urgency data, multiple requirement description texts, multiple subject submission times and multiple department information, and collecting all the scene classification data, all the business urgency data, all the requirement description texts, all the subject submission times and all the department information to obtain an original requirement data set; and the original requirement data set is preprocessed to obtain a preprocessed requirement data set.The application reduces the dependence on subjective experience in the project establishment process, improves the objectivity, efficiency and decision-making scientificity of the subject condensation process, greatly improves the document preparation efficiency, ensures the structural integrity and format professionalism of the output content, and reduces the repetitive work.

Description

Technical Field

[0001] This invention relates to the field of project management technology, specifically to a project management method, apparatus, and storage medium. Background Technology

[0002] The following pain points exist in the current management of technological innovation projects by telecommunications operators: (1) Lack of demand and scientific research transformation mechanism: Existing technologies rely on manual collection and summarization of business needs, lacking a systematic method for automated clustering, analysis and condensation of scattered and short-term business needs. It is difficult to efficiently identify high-quality scientific research topics with universality and foresight from massive business feedback, resulting in a disconnect between scientific research investment and real business pain points.

[0003] (2) The process of formulating research topics relies on subjective judgment: Existing technologies typically employ manual methods such as expert review and conference discussions to formulate, screen, and decide on project establishment, lacking data-driven automated analysis, prioritization, and intelligent recommendation capabilities. This process is not only inefficient and highly subjective, but also makes it difficult to guarantee the forward-looking nature of the research topics, the completeness of their coverage, and the scientific nature of resource allocation.

[0004] (3) Low level of automation in project document preparation: Under the current technological environment, various standardized documents (such as PPT and Word reports) required for project initiation, review, and reporting mainly rely on manual preparation. This process is time-consuming, labor-intensive, and highly repetitive, and the quality of documents varies depending on individual abilities, making it difficult to unify standardization. At the same time, there is a lack of effective knowledge reuse mechanisms, and historical project data, charts, and information cannot be intelligently retrieved and reorganized, resulting in a large amount of repetitive work and seriously squeezing out core R&D and innovation time. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a project management method, apparatus and storage medium to address the shortcomings of the prior art.

[0006] The technical solution of this invention to solve the above-mentioned technical problems is as follows: A project management method, comprising the following steps: Import multiple scenario classification data, multiple business urgency data, multiple requirement description texts, multiple project submission times, and multiple department information, and combine all the aforementioned scenario classification data, all the aforementioned business urgency data, all the aforementioned requirement description texts, all the aforementioned project submission times, and all the aforementioned department information to obtain the original requirement dataset; The original demand dataset is preprocessed to obtain the preprocessed demand dataset; The preprocessed demand dataset is analyzed to obtain a draft research topic for conducting research on the technological innovation projects of telecommunications operators. Import multiple user application information used to provide user information for scientific research projects, analyze all the user application information and the project drafts to obtain the target project approval document for approving the scientific and technological innovation projects of the telecommunications operators.

[0007] Another technical solution of the present invention to solve the above-mentioned technical problems is as follows: A project management device, comprising: The import module is used to import data from multiple scenario categories, multiple business urgency levels, multiple requirement description texts, multiple project submission times, and multiple departmental information. The data set module is used to collect all the scenario classification data, all the business urgency data, all the requirement description texts, all the project submission times, and all the department information to obtain the original requirement dataset. The preprocessing module is used to preprocess the original requirement dataset to obtain a preprocessed requirement dataset. The project draft analysis module is used to analyze the preprocessed demand dataset to obtain project drafts for research on the technological innovation projects of telecommunications operators. The import module is also used to import multiple user application information for providing user information for scientific research projects; The project approval document acquisition module is used to analyze all the user application information and the project draft to obtain the target project approval document for the telecommunications operator's science and technology innovation project.

[0008] Based on the above-mentioned project management method, the present invention also provides a project management system.

[0009] Another technical solution of the present invention to solve the above-mentioned technical problems is as follows: a project management system, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the project management method described above is implemented.

[0010] Based on the above-mentioned project management method, the present invention also provides a computer-readable storage medium.

[0011] Another technical solution of the present invention to solve the above-mentioned technical problems is as follows: a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the project management method described above.

[0012] The beneficial effects of this invention are as follows: by preprocessing the original demand dataset to obtain a preprocessed demand dataset, analyzing the draft topics of the preprocessed demand dataset to obtain a draft topic, and analyzing the project establishment documents of the user application information and the draft topic to obtain the target project establishment document, this invention solves the technical problem of automatically extracting high-quality research topics from scattered business needs. It can efficiently and accurately output research topics that are available for project establishment and have business value, reduce the reliance on subjective experience in the project establishment process, improve the objectivity, efficiency, and scientific nature of the topic extraction process, significantly improve the efficiency of document preparation, ensure the structural integrity and professional format of the output content, and reduce repetitive work. Attached Figure Description

[0013] Figure 1 A flowchart illustrating the project management method provided in an embodiment of the present invention; Figure 2 A schematic diagram illustrating the analysis of a draft project for a project management method provided in an embodiment of the present invention; Figure 3 A schematic diagram illustrating the project initiation document analysis of the project management method provided in this embodiment of the invention; Figure 4 A block diagram of a project management device provided in an embodiment of the present invention. Detailed Implementation

[0014] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0015] Figure 1 This is a flowchart illustrating a project management method provided in an embodiment of the present invention.

[0016] like Figure 1 As shown, a project management method includes the following steps: S1: Import multiple scenario classification data, multiple business urgency data, multiple requirement description texts, multiple project submission times, and multiple department information, and combine all the scenario classification data, all the business urgency data, all the requirement description texts, all the project submission times, and all the department information to obtain the original requirement dataset; S2: Preprocess the original demand dataset to obtain a preprocessed demand dataset; S3: Analyze the preprocessed demand dataset to obtain a draft research topic for conducting research on the technological innovation projects of telecommunications operators; S4: Import multiple user application information used to provide user information for scientific research projects, analyze all the user application information and the project drafts to obtain the target project approval document used to approve the communication operator's scientific and technological innovation project.

[0017] It should be understood that two access methods are provided: Web form and API. It supports the input of structured fields (such as scenario classification and urgency level) (i.e. scenario classification data and business urgency level data) and unstructured text (requirement description) (i.e. requirement description text), and automatically records metadata such as submission time and department (i.e., project submission time and department information).

[0018] In the above embodiments, a preprocessed demand dataset is obtained by preprocessing the original demand dataset, a project draft is obtained by analyzing the project draft of the preprocessed demand dataset, and a target project establishment document is obtained by analyzing the user application information and the project draft. This solves the technical problem of automatically extracting high-quality scientific research topics from scattered business needs. It can efficiently and accurately output scientific research topics that are available for project establishment and have business value, reduce the reliance on subjective experience in the project establishment process, improve the objectivity, efficiency and scientific nature of the topic extraction process, greatly improve the efficiency of document preparation, ensure the structural integrity and professional format of the output content, and reduce repetitive work.

[0019] Optionally, as an embodiment of the present invention, the process of preprocessing the original demand dataset to obtain a preprocessed demand dataset includes: The original demand dataset is cleaned to obtain a cleaned demand dataset; The cleaned demand dataset is segmented into words to obtain a segmented demand dataset. The segmented demand dataset is standardized to obtain a preprocessed demand dataset.

[0020] Specifically, intelligent preprocessing is performed on the requirement text (i.e., the original requirement dataset) to remove invalid information such as names, addresses, emails, and phone numbers, and semantic word segmentation is performed. Finally, the segmented paragraph text (i.e. the segmented requirement dataset) is reorganized into more professional, systematic, and concise content, thus completing text cleaning and standardization.

[0021] In the above embodiments, the original demand dataset is preprocessed to obtain a preprocessed demand dataset, which solves the technical problem of automatically extracting high-quality scientific research topics from scattered business demands. It can efficiently and accurately output scientific research topics that are suitable for project initiation and have business value.

[0022] Optionally, as an embodiment of the present invention, such as Figure 2As shown, the process of analyzing the preprocessed demand dataset to obtain a draft research topic for conducting research on the technological innovation projects of telecommunications operators includes: The preprocessed demand dataset is vectorized to obtain a demand semantic vector set, which includes multiple demand semantic vectors. Cluster analysis is performed on all the aforementioned requirement semantic vectors to obtain multiple requirement clusters; By calculating keyword weights for all the aforementioned demand clusters using a pre-built large model, weighted information for multiple demand clusters is obtained. Import a pre-defined scientific research domain knowledge base, and generate a project draft by weighting the pre-built large model with the pre-defined scientific research domain knowledge base and all the required clusters.

[0023] Understandably, relying on contextual semantic representation technology, the processed text is combined with the paragraph content context, and the paragraph-to-vector algorithm is used to transform the entire text paragraph (i.e., the preprocessed demand dataset) into a high-dimensional word vector (i.e., the demand semantic vector set) that is rich in deep semantic information and also contains paragraph context information, thus replacing the traditional feature engineering method.

[0024] Specifically, based on the extracted key demand clusters (i.e. demand clusters), the information in the demand clusters is assigned scores by relying on the keyword weight calculation capability of the large model, so as to accurately identify the core themes and key information of each demand cluster and provide high-quality data support for the subsequent generation of research topics.

[0025] Specifically, based on the analysis results of demand clusters (i.e., demand cluster weighted information), combined with a pre-set research field tag library (i.e., a pre-set research field knowledge base), and through the RAG knowledge base integration and structured generation capabilities of the large model, based on the core content information of demand clusters (i.e., demand cluster weighted information) and the existing research field knowledge base, relying on a "three-step" approach—confirming the core content of demand clusters, generating the core outline of the research topic, and filling in technical details and research field knowledge—automatically generates a draft research proposal (i.e., a research draft) containing the research topic name, core issues, research objectives, and preliminary technical routes.

[0026] In the above embodiments, the preprocessed demand dataset is analyzed to obtain a draft project proposal, which reduces the reliance on subjective experience in the project initiation process and improves the objectivity, efficiency, and scientific nature of the project formulation process.

[0027] Optionally, as an embodiment of the present invention, the process of performing cluster analysis on all the said demand semantic vectors to obtain multiple demand clusters includes: Calculate the vector similarity for each of the aforementioned demand semantic vectors and any remaining demand semantic vector to obtain multiple semantic vector similarities corresponding to each of the aforementioned demand semantic vectors. The similarity of each of the semantic vectors and the similarity of any remaining semantic vector are calculated separately to obtain multiple similarity differences corresponding to each of the required semantic vectors. All the aforementioned demand semantic vectors are clustered according to the classification rules to obtain multiple demand clusters. The classification rule is that if the similarity difference is less than or equal to a preset difference, the demand semantic vectors corresponding to the similarity difference are aggregated into a demand cluster.

[0028] It should be understood that by utilizing the fine-tuned clustering adaptation capability, semantic vectors (i.e. demand semantic vectors) are grouped based on vector similarity according to a large model, automatically forming demand clusters with close logical connections.

[0029] In the above embodiments, cluster analysis is performed on all demand semantic vectors to obtain multiple demand clusters, which reduces the reliance on subjective experience in the project initiation process and improves the objectivity, efficiency and scientific nature of the project formulation process.

[0030] Optionally, as an embodiment of the present invention, such as Figure 3 As shown, the process of analyzing all the user application information and the draft project proposals to obtain the target project proposal document for approving the telecommunications operator's technological innovation project includes: By integrating and analyzing all the user application information and the project drafts, a target project approval dataset is obtained. Based on the target project initiation dataset, an initial project initiation template is obtained from the preset template library; The initial project initiation template is mapped based on the target project initiation dataset to obtain the mapped project initiation dataset. The initial project initiation template is populated with the mapped project initiation dataset to obtain the original project initiation document; The original project proposal document was optimized and analyzed to obtain the target project proposal document.

[0031] Specifically, the process of analyzing the project draft forms a data and business closed loop: the structured dataset (i.e., project draft) including the output project proposal draft, core issues, research objectives, and technical routes is used as the basic data source of the present invention (i.e., project draft) and integrated with user application information to automatically generate standardized, high-quality project approval materials, solving the problems of low efficiency, non-standard format, and inconsistent content in the conversion of project results into project approval documents.

[0032] It should be understood that the system includes built-in standardized templates (i.e., a preset template library) such as PPTs for general office meetings, investment review meetings, project application forms, and scientific research project application forms; it supports online editing, version control, and permission management of templates; it provides template variable and placeholder definition functions, clearly defining the data source, field type, filling rules, and format requirements of each placeholder, and can directly connect to the output project data structure (i.e., project draft).

[0033] It should be understood that the merged data (i.e., the target project initiation dataset) is automatically and accurately mapped to the template placeholders (i.e., the initial project initiation template), achieving a seamless conversion of research results into project content.

[0034] Specifically, based on the data mapping results, and in accordance with template logic and format requirements, the system automatically populates the content of text, tables, framework diagrams, and technology roadmaps.

[0035] In the above embodiments, project approval documents are analyzed for all user application information and project drafts to obtain target project approval documents, which solves the problems of low conversion efficiency, non-standard format, and inconsistent content in the conversion from project results to project approval documents.

[0036] Optionally, as an embodiment of the present invention, the process of fusing and analyzing all the user application information and the project draft to obtain the target project approval dataset includes: By combining all the user application information and the project drafts, the original project approval dataset is obtained. The original project initiation dataset is subjected to field alignment processing to obtain the aligned project initiation dataset; All aligned project initiation data in the aligned project initiation dataset are merged, and the merged results are combined to obtain the merged project initiation dataset. The merged project initiation dataset is augmented to obtain the target project initiation dataset.

[0037] In the above embodiments, all user application information and project drafts are integrated and analyzed to obtain the target project approval dataset, which solves the problems of low conversion efficiency, non-standard format, and inconsistent content in the conversion from project results to project approval documents.

[0038] Optionally, as an embodiment of the present invention, the process of optimizing and analyzing the original project proposal document to obtain the target project proposal document includes: The original project proposal document is standardized by using a pre-built large model to obtain a standardized project proposal document. The standardized project proposal document is professionalized by using a pre-built large model to obtain a professionalized project proposal document. The specialized project initiation document is processed according to the preset integrity rules to obtain the project initiation document to be processed. The specialized project initiation document is processed according to preset normative rules to obtain the processed project initiation document; The professionalized project initiation document is processed for format consistency according to the preset format consistency rules to obtain the target project initiation document.

[0039] It should be understood that, relying on the semantic understanding and text enhancement capabilities of the large model, the output topic content (i.e., the original project proposal document) is standardized and professionally optimized to improve the rigor of the proposal materials; it supports batch generation, incremental updates and parallel output of multiple versions to meet the needs of different review scenarios.

[0040] Specifically, the generated documents (i.e., the professionalized project initiation documents) are checked for completeness, standardization, and format consistency; issues such as font, line spacing, layout, and chart styles are automatically corrected to ensure that the output documents meet the standards of enterprises and scientific research applications.

[0041] In the above embodiments, the original project initiation document is optimized and analyzed to obtain the target project initiation document, which supports batch generation, incremental updates and parallel output of multiple versions, meeting the needs of different review scenarios.

[0042] Alternatively, as another embodiment of the present invention, the objective of the present invention is as follows: 1. Solved the technical problem of how to automatically extract high-quality research topics from scattered business needs: Established a mechanism and method that can automatically collect, intelligently cluster, and quantitatively evaluate massive amounts of front-line business needs, identify common pain points and strategic opportunities through large models, and thus efficiently and accurately output research topics that are suitable for project initiation and have business value, fundamentally opening up the transformation link from needs to research.

[0043] 2. Solved the technical problem of how to achieve data-driven intelligent selection and scientific project establishment: Constructed an automated analysis and priority ranking model for projects based on multi-dimensional quantitative indicators (such as business influence, technical feasibility, and resource input-output ratio), reducing the reliance on subjective experience in the project establishment process and improving the objectivity, efficiency, and scientific nature of the project formulation process.

[0044] 3. Solved the technical problem of how to efficiently and systematically generate and manage science and technology innovation project documents: Designed an intelligent document generation method and system, which uses a built-in standardized document template library (corresponding to different decision-making scenarios, such as general office meetings and investment review meetings), and automatically converts the structured form data filled in by users online during the project application process (such as project background, technical solutions, resource requirements, etc.) into standardized PPT presentation documents that meet the requirements of specific scenarios within minutes according to preset logic and templates, thereby greatly improving the efficiency of document preparation, ensuring the structural integrity and professional format of the output content, and reducing repetitive work.

[0045] Optionally, as another embodiment of the present invention, the present invention consists of three parts: a requirement collection interface, a text analysis engine, and a topic generator, aiming to solve the problem of scattered business requirements and difficulty in forming research topics. Specifically, the present invention innovatively constructs a new method with large model capabilities as its core, possessing semantic understanding and generation capabilities. This solves the problems of shallow semantic understanding, lack of context, and the need for more manual intervention in traditional methods, automatically and intelligently transforming scattered business requirements into high-quality research topics.

[0046] Alternatively, as another embodiment of the present invention, the technical implementation details of the present invention are as follows: I. Large-scale model implementation: The large-scale model simplifies and refines the requirement clusters through intelligent text segmentation, text cleaning, text vectorization, and keyword weight calculation. At the same time, it combines prompt word engineering to accurately process the requirement text based on semantic understanding rather than traditional word frequency statistics technology, and generates the project proposal draft step by step by relying on the RAG knowledge base and the preset workflow.

[0047] 2. Service Interface: The RESTful API is built using Spring Boot to support the data flow business process in requirement collection and intelligent analysis. It supports asynchronous processing of large-scale requirement analysis tasks. After the large model is processed, the output of each stage is transferred to the next stage of data processing or workflow. Finally, the analysis results are returned to the front end. III. Front-end Interaction: Based on the Vue.js framework, it provides functions for submitting requirements, viewing analysis progress, and previewing topic suggestions.

[0048] Optionally, as another embodiment of the present invention, the present invention consists of four sub-modules: template management, data mapping, document generation, and format validation, to realize the automatic conversion from form data to standardized documents.

[0049] Optionally, as another embodiment of the present invention, after the verification is passed, the present invention outputs PPT, Word, PDF and other format files, and supports previewing through kkfileview.

[0050] Alternatively, as another embodiment of the present invention, the key technology of the present invention is implemented as follows: (i) Data Fusion Engine: Connects to the output interface of the project generator, reads the structured dataset of the project proposal draft, and performs field alignment, fusion and enhancement with the user's application data to form a unified project establishment data layer.

[0051] (ii) Template engine: Based on the Apache FreeMarker extension, it supports logical control such as conditional judgment and loop and dynamic content generation, and can directly parse the output structured information such as technical route and research objectives.

[0052] (III) Document processing: Apache POI is used to process Office documents, and LibreOffice is used to process PDF document conversion; kkfileview provides online preview capabilities, supporting real-time viewing and confirmation of project documents.

[0053] Figure 4 This is a module block diagram of a project management device provided in an embodiment of the present invention.

[0054] Alternatively, as another embodiment of the present invention, such as Figure 4 As shown, a project management device includes: The import module is used to import data from multiple scenario categories, multiple business urgency levels, multiple requirement description texts, multiple project submission times, and multiple departmental information. The data set module is used to collect all the scenario classification data, all the business urgency data, all the requirement description texts, all the project submission times, and all the department information to obtain the original requirement dataset. The preprocessing module is used to preprocess the original requirement dataset to obtain a preprocessed requirement dataset. The project draft analysis module is used to analyze the preprocessed demand dataset to obtain project drafts for research on the technological innovation projects of telecommunications operators. The import module is also used to import multiple user application information for providing user information for scientific research projects; The project approval document acquisition module is used to analyze all the user application information and the project draft to obtain the target project approval document for the telecommunications operator's science and technology innovation project.

[0055] Optionally, another embodiment of the present invention provides a project management system, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the project management method described above. This system can be a computer or similar system.

[0056] Optionally, another embodiment of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the project management method described above.

[0057] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0058] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described apparatus and unit can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0059] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0060] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.

[0061] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0062] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0063] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A project management method, characterized in that, Includes the following steps: Import multiple scenario classification data, multiple business urgency data, multiple requirement description texts, multiple project submission times, and multiple department information, and combine all the aforementioned scenario classification data, all the aforementioned business urgency data, all the aforementioned requirement description texts, all the aforementioned project submission times, and all the aforementioned department information to obtain the original requirement dataset; The original demand dataset is preprocessed to obtain the preprocessed demand dataset; The preprocessed demand dataset is analyzed to obtain a draft research topic for conducting research on the technological innovation projects of telecommunications operators. Import multiple user application information used to provide user information for scientific research projects, analyze all the user application information and the project drafts to obtain the target project approval document for approving the scientific and technological innovation projects of the telecommunications operators.

2. The project management method according to claim 1, characterized in that, The process of preprocessing the original demand dataset to obtain the preprocessed demand dataset includes: The original demand dataset is cleaned to obtain a cleaned demand dataset; The cleaned demand dataset is segmented into words to obtain a segmented demand dataset. The segmented demand dataset is standardized to obtain a preprocessed demand dataset.

3. The project management method according to claim 1, characterized in that, The process of analyzing the preprocessed demand dataset to obtain draft research topics for conducting research on telecommunications operators' technological innovation projects includes: The preprocessed demand dataset is vectorized to obtain a demand semantic vector set, which includes multiple demand semantic vectors. Cluster analysis is performed on all the aforementioned requirement semantic vectors to obtain multiple requirement clusters; By calculating keyword weights for all the aforementioned demand clusters using a pre-built large model, weighted information for multiple demand clusters is obtained. Import a pre-defined scientific research domain knowledge base, and generate a project draft by weighting the pre-built large model with the pre-defined scientific research domain knowledge base and all the required clusters.

4. The project management method according to claim 3, characterized in that, The process of performing cluster analysis on all the aforementioned demand semantic vectors to obtain multiple demand clusters includes: Calculate the vector similarity for each of the aforementioned demand semantic vectors and any remaining demand semantic vector to obtain multiple semantic vector similarities corresponding to each of the aforementioned demand semantic vectors. The similarity of each of the semantic vectors and the similarity of any remaining semantic vector are calculated separately to obtain multiple similarity differences corresponding to each of the required semantic vectors. All the aforementioned demand semantic vectors are clustered according to the classification rules to obtain multiple demand clusters. The classification rule is that if the similarity difference is less than or equal to a preset difference, the demand semantic vectors corresponding to the similarity difference are aggregated into a demand cluster.

5. The project management method according to claim 1, characterized in that, The process of analyzing all the user application information and the draft research proposals to obtain the target project proposal document for approving the telecommunications operator's technological innovation project includes: By integrating and analyzing all the user application information and the project drafts, a target project approval dataset is obtained. Based on the target project initiation dataset, an initial project initiation template is obtained from the preset template library; The initial project initiation template is mapped based on the target project initiation dataset to obtain the mapped project initiation dataset. The initial project initiation template is populated with the mapped project initiation dataset to obtain the original project initiation document; The original project proposal document was optimized and analyzed to obtain the target project proposal document.

6. The project management method according to claim 5, characterized in that, The process of integrating and analyzing all the user application information and the project draft to obtain the target project approval dataset includes: By combining all the user application information and the project drafts, the original project approval dataset is obtained. The original project initiation dataset is subjected to field alignment processing to obtain the aligned project initiation dataset; All aligned project initiation data in the aligned project initiation dataset are merged, and the merged results are combined to obtain the merged project initiation dataset. The merged project initiation dataset is augmented to obtain the target project initiation dataset.

7. The project management method according to claim 5, characterized in that, The process of optimizing and analyzing the original project proposal document to obtain the target project proposal document includes: The original project proposal document is standardized by using a pre-built large model to obtain a standardized project proposal document. The standardized project proposal document is professionalized by using a pre-built large model to obtain a professionalized project proposal document. The specialized project initiation document is processed according to the preset integrity rules to obtain the project initiation document to be processed. The specialized project initiation document is processed according to preset normative rules to obtain the processed project initiation document; The professionalized project initiation document is processed for format consistency according to the preset format consistency rules to obtain the target project initiation document.

8. A project management device, characterized in that, include: The import module is used to import data from multiple scenario categories, multiple business urgency levels, multiple requirement description texts, multiple project submission times, and multiple departmental information. The data set module is used to collect all the scenario classification data, all the business urgency data, all the requirement description texts, all the project submission times, and all the department information to obtain the original requirement dataset. The preprocessing module is used to preprocess the original requirement dataset to obtain a preprocessed requirement dataset. The project draft analysis module is used to analyze the preprocessed demand dataset to obtain project drafts for research on the technological innovation projects of telecommunications operators. The import module is also used to import multiple user application information for providing user information for scientific research projects; The project approval document acquisition module is used to analyze all the user application information and the project draft to obtain the target project approval document for the telecommunications operator's science and technology innovation project.

9. A project management device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the project management method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the project management method as described in any one of claims 1 to 7.

Images