Research and development information generation method, system and device based on textile information and medium

Abstract

The invention discloses a research and development information generation method, system and device based on textile information and a medium, and the method comprises the steps: obtaining user question data and an enterprise type, and determining a target prompt word according to the enterprise type; performing database retrieval according to the user question data and the target prompt word to obtain a target retrieval result; and integrating the target retrieval results to generate research and development information. Subsequent information retrieval is carried out based on enterprise types, the requirements of users can be better met, then natural language expressions of the users and knowledge and technical terms of the enterprises are deeply fused, the retrieval quality is improved, finally, target retrieval results are integrated, and the retrieval efficiency is improved. According to the method, automatic analysis, induction and integration can be carried out on scattered and multi-source retrieval results, and target information can be accurately generated.

Description

Technical Field

[0001] This application relates to, but is not limited to, the field of information generation technology, and in particular to a method, system, device, and medium for generating research and development information based on textile information. Background Technology

[0002] In the current era of deep integration between artificial intelligence and industry informatization, the textile industry and various manufacturing sectors have an increasingly urgent need for accurate and efficient acquisition of enterprise information. Enterprise information serves as a core basis for industry decision-making, cooperation, and market analysis, and its sources include government directories, data released by industry associations, and third-party commercial databases. This crucial data is mostly stored in structured and semi-structured formats such as tables, static web pages, and PDF documents, resulting in a massive volume and dispersed distribution. Currently, in the textile industry, the mainstream method for obtaining textile information still relies on manual operation. This requires manually entering keywords, filtering search results item by item, and manually comparing, filtering, and verifying information from multiple data sources to obtain target information. This method is inefficient and easily affected by subjective factors in human operation, leading to omissions or errors and low reliability. Therefore, there is an urgent need for a research and development method for information generation based on textile information that can accurately generate target information. Summary of the Invention

[0003] This application provides a method, system, device, and medium for generating R&D information based on textile information, which can effectively improve the reliability of generating textile R&D information.

[0004] In a first aspect, embodiments of this application provide a method for generating R&D information based on textile information, including: Obtain user question data and company type, and determine target prompt words based on the company type; A database search is performed based on the user question data and the target prompt words to obtain the target search results; The search results for the target are integrated to generate R&D information.

[0005] The R&D information generation method based on textile information according to the first aspect of this application has at least the following beneficial effects: It acquires user query data and enterprise type to facilitate targeted and accurate information retrieval based on user needs. Different enterprise types correspond to different business processes and needs. Determining target prompts based on enterprise type, and fully integrating enterprise knowledge and professional terminology, allows for subsequent information retrieval based on enterprise type, better meeting user needs and achieving precise and scenario-based retrieval, effectively improving the relevance, practicality, and reliability of retrieval results. Database retrieval based on user query data and target prompts deeply integrates users' natural language expressions with enterprise knowledge and professional terminology to obtain target retrieval results, improving retrieval quality. Integrating the target retrieval results enables automated analysis, summarization, and integration of scattered and multi-source retrieval results, generating R&D information and forming structured, reliable information that can be directly used for decision support. This avoids secondary data processing issues and improves subsequent data processing efficiency.

[0006] According to some embodiments of the first aspect of this application, the step of performing a database search based on the user query data and the target prompt words to obtain target search results includes: The user's question data is interpreted using a text interpretation model to generate content. The generated content is then used to perform a database search to obtain the first search result. The user question data is used to extract target keywords, and a database search is performed based on the target keywords and the target prompt words to obtain a second search result; The first search result and the second search result are determined as the target search results.

[0007] According to some embodiments of the first aspect of this application, the step of integrating the target retrieval results to generate R&D information includes: Calculate the complexity of the generated content, and determine the first weight factor based on the complexity; Based on the accuracy of the target keywords, a second weighting factor is determined; Research and development information is generated based on the first search result, the second search result, the first weighting factor, and the second weighting factor.

[0008] According to some embodiments of the first aspect of this application, the step of extracting target keywords from the user query data includes: Based on the enterprise type, keyword extraction is performed on the user question data to obtain target keywords corresponding to the enterprise type.

[0009] According to some embodiments of the first aspect of this application, the database is generated in the following manner: Acquire textile information data, and classify the textile information data into major categories to form a basic classification set; In each of the basic classification sets, cluster analysis is performed based on the frequency of product information in the textile information to obtain fine-grained subsets; A database is generated based on the basic classification set and the corresponding fine-grained subsets.

[0010] According to some embodiments of the first aspect of this application, the step of performing a database search based on the user query data and the target prompt words to obtain target search results includes: The user question data is broken down into multiple sub-question data. A database search is performed based on all sub-question data and the target prompts to obtain the target search results.

[0011] According to some embodiments of the first aspect of this application, the method for generating R&D information based on textile information further includes: Based on the user query data, a consistency check is performed on the target search results to determine the accuracy of the target search results; If the accuracy is lower than a preset threshold, the database is searched again based on the user's question data and the target prompt words to obtain new target search results.

[0012] Secondly, embodiments of this application provide an operation control device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the R&D information generation method based on textile information as described in the first aspect.

[0013] Thirdly, embodiments of this application provide a research and development information generation system based on textile information, including the operation control device as described in the second aspect.

[0014] Fourthly, embodiments of this application provide a computer storage medium storing computer-executable instructions for causing a computer to perform the research and development information generation method based on textile information as described in the first aspect. Attached Figure Description

[0015] The accompanying drawings are provided to further understand the technical solutions of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the technical solutions of the present invention, and do not constitute a limitation on the technical solutions of the present invention.

[0016] Figure 1This is a flowchart of the steps of a method for generating R&D information based on textile information provided in one embodiment of this application; Figure 2 This is a flowchart of the steps of a target retrieval result generation method provided in another embodiment of this application; Figure 3 This is a flowchart of the steps of a research and development information generation method provided in another embodiment of this application; Figure 4 This is a flowchart of the steps of a target keyword generation method provided in another embodiment of this application; Figure 5 This is a flowchart of the steps of a database generation method provided in another embodiment of this application; Figure 6 This is a flowchart of another method for generating target retrieval results provided in another embodiment of this application; Figure 7 This is a flowchart of another method for generating research and development information provided in another embodiment of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0018] It is understandable that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, or the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0019] This application provides a method, system, apparatus, and medium for generating R&D information based on textile information. It acquires user query data and enterprise types to facilitate targeted and precise information retrieval according to user needs. Different enterprise types correspond to different business processes and needs. Target keywords are determined based on enterprise type, fully integrating enterprise knowledge and professional terminology. Subsequent information retrieval based on enterprise type better meets user needs, achieving precise and scenario-based retrieval, and effectively improving the relevance, usability, and reliability of retrieval results. Database retrieval based on user query data and target keywords deeply integrates users' natural language expressions with enterprise knowledge and professional terminology to obtain target retrieval results, improving retrieval quality. Integrating the target retrieval results allows for automated analysis, summarization, and integration of scattered, multi-source retrieval results, generating R&D information. This results in structured, reliable information that can be directly used for decision support, avoiding secondary data processing issues and improving subsequent data processing efficiency.

[0020] The embodiments of this application will be further described below with reference to the accompanying drawings.

[0021] like Figure 1 As shown, Figure 1 This application provides a method for generating R&D information based on textile information, according to one embodiment. The method includes, but is not limited to, the following steps: Step S110: Obtain user question data and enterprise type, and determine target prompt words based on enterprise type; Step S120: Perform a database search based on user query data and target prompts to obtain target search results; Step S130: Integrate the target search results to generate R&D information.

[0022] It is understandable that obtaining user query data and company types is crucial for targeted and precise information retrieval based on user needs. Different company types correspond to different business processes and requirements. Determining target keywords based on company type, and fully integrating company knowledge and professional terminology, allows for subsequent information retrieval based on company type, better meeting user needs and achieving more precise and contextualized retrieval, effectively improving the relevance, usability, and reliability of search results. Database retrieval based on user query data and target keywords deeply integrates users' natural language expressions with company knowledge and professional terminology to obtain target search results. Existing technical solutions employ full-text search engines or keyword matching algorithms, which still have significant limitations in processing natural language queries, recognizing users' multi-condition complex intentions, and understanding industry-specific terminology. For example, when a user enters "distribution of companies producing high-performance textile materials," traditional retrieval systems often struggle to accurately parse and combine multiple query conditions, resulting in incomplete search results or the inclusion of a large amount of irrelevant information. Compared to existing technical solutions, the embodiments of this application improve the quality of retrieval. Integrating the target search results enables automated analysis, summarization, and consolidation of scattered and multi-source search results, generating R&D information and forming structured, reliable information that can be directly used for decision support. This avoids the problem of secondary data processing and is beneficial to the efficiency of subsequent data processing.

[0023] It is understood that, in one embodiment, the R&D information may include industry-related patents, news, and other R&D information about the relevant products, and this is not limited thereto.

[0024] It is understood that, in one embodiment, the R&D information generation method based on textile information can be applied to the Dify platform, utilizing the workflow orchestration and model management capabilities of the Dify platform to construct a dynamic analysis process adapted to information query in the textile industry.

[0025] Understandably, in one embodiment, enterprise types can be categorized into three types: upstream enterprises, midstream enterprises, and downstream enterprises. Upstream enterprises may include suppliers of raw materials or basic inputs for textile production, such as natural fibers, chemical fibers, dyes, and auxiliary materials. Midstream enterprises may include enterprises engaged in semi-finished product manufacturing, including spinning, weaving, dyeing, and printing, processing raw materials into fabrics or semi-finished products. Downstream enterprise data may include enterprises that process, sell, or export finished products based on semi-finished products or fabrics. Different tag prompts can be set for different enterprise types to facilitate precise retrieval based on enterprise type. For example, target prompts for midstream enterprises tend to focus on content such as process flow, production capacity, and equipment type during retrieval.

[0026] Additionally, refer to Figure 2In one embodiment, Figure 1 Step S120 in the illustrated embodiment also includes, but is not limited to, the following steps: Step S210: Based on the text interpretation model, the user's question data is interpreted to obtain generated content. Based on the generated content and target prompt words, a database search is performed to obtain the first search result. Step S220: Extract keywords from user query data to obtain target keywords, and perform database retrieval based on target keywords and target prompts to obtain the second search result; Step S230: The first search result and the second search result are determined as the target search result.

[0027] Understandably, most information retrieval platforms can only perform queries targeting a single dimension, such as company directories or product information, lacking the ability to identify and analyze specific product structures and their components. This results in search results that fail to comprehensively cover user needs. By using a text interpretation model to interpret user query data and generate content, the overall semantics and contextual intent of the query data are analyzed. When user query data is ambiguous, lengthy, or contains technical terms, single search methods are prone to failure. Text interpretation can translate or summarize user query data, transforming it into more standardized content and generating query content that is closer to natural language description. This generated content can be a data query statement used for database queries. For example, if the user's query data is "I want to make a waterproof jacket," then the generated content obtained based on the text interpretation model can be a data query statement for "waterproof jacket." Then, a database search is performed based on the generated content and target keywords to obtain the first search result, ensuring that the search results are more closely related to the user's query data. In existing technologies, retrieval processes generally rely on simple keyword matching or preset rules, which are insufficient to effectively handle complex queries in natural language, especially when multiple conditions are combined or industry-specific terminology is involved. Retrieval results are often incomplete or contain a large amount of irrelevant information. Extracting target keywords from user query data allows for precise identification of core entities and key terms in the question, facilitating direct and accurate matching. Database retrieval based on target keywords and prompts yields a second set of search results, ensuring greater accuracy and completeness. For example, if a user's query is "I want to make a waterproof jacket," keyword extraction could yield target keywords such as polyester fiber and nylon. Combining the first and second search results as the target retrieval results balances semantic generalization and precise matching, achieving a balance between relevance, completeness, and accuracy, reducing information omissions. By combining deep semantic understanding-based text interpretation retrieval with precise matching-based keyword retrieval, the system significantly improves its ability to interpret the intent of complex natural language queries, enhancing the comprehensiveness and accuracy of the target retrieval results. The database can be an online knowledge base, and the data in the online knowledge base will be continuously updated to avoid data lag.

[0028] Additionally, refer to Figure 3 In one embodiment, Figure 1 Step S130 in the illustrated embodiment also includes, but is not limited to, the following steps: Step S310: Calculate the complexity of the generated content and determine the first weight factor based on the complexity; Step S320: Determine the second weighting factor based on the accuracy of the target keywords; Step S330: Generate R&D information based on the first search result, the second search result, the first weighting factor, and the second weighting factor.

[0029] Understandably, calculating the complexity of the generated content provides a direct understanding of the complexity of user query data. A first weighting factor is determined based on this complexity; the more complex the user query data, the higher the corresponding weighting factor, facilitating weighted fusion based on the first weighting factor and the first search result. A second weighting factor is determined based on the accuracy of the target keywords, providing a direct understanding of their precision; the more specific and directly relevant the target keywords, the higher the corresponding weighting factor. Weighted fusion is then performed based on the second weighting factor and the second search result. Based on the first search result, the second search result, the first weighting factor, and the second weighting factor, R&D information is generated. Different weighting factors correspond to different search results, avoiding simple result merging. If the generated content is too complex or uncertain, the weight can be reduced to prevent unreliable search results from excessively influencing the final R&D information. For clearly defined target keywords, the corresponding weighting factor can be increased, ensuring the reliability of the subsequent R&D information while saving computing resources and improving data processing speed. Dynamic weighted fusion based on different content complexity and usage scenarios allows for adaptive fusion, making the R&D information more scientific and better suited to user needs.

[0030] Additionally, refer to Figure 4 In one embodiment, Figure 2 Step S220 in the illustrated embodiment also includes, but is not limited to, the following steps: Step S410: Extract keywords from user query data based on enterprise type to obtain target keywords corresponding to the enterprise type.

[0031] Understandably, different types of enterprises have different business data. Extracting keywords from user query data based on enterprise type yields target keywords corresponding to that enterprise type. This allows for keyword extraction based on upstream, midstream, and downstream enterprise types, enabling more accurate identification of the core intent and key entities related to the enterprise type in user questions. This ensures that target keywords are more aligned with industry business characteristics, facilitating the relevance of subsequent R&D information to user needs. Processing user query data based on enterprise type also enables searching across different links in the industry chain, narrowing the search scope and effectively improving search efficiency.

[0032] Additionally, refer to Figure 5 In one embodiment, the generation of the database includes, but is not limited to, the following steps: Step S510: Obtain textile information data and classify it into basic classification sets based on the textile information data. Step S520: In each basic classification set, cluster analysis is performed based on the frequency of product information in textile information to obtain fine-grained subsets; Step S530: Generate a database based on the basic classification set and the corresponding fine-grained subsets.

[0033] Understandably, acquiring textile information data allows for broad categorization to form basic classification sets, creating a clear and logical framework that improves retrieval efficiency and accuracy. Within each basic classification set, cluster analysis is performed based on the frequency of product information occurrences, enabling refined data analysis and yielding fine-grained subsets. These subsets accurately reflect the relationships between various textile products, prioritizing the retrieval of frequently occurring product information, thus enhancing the relevance and accuracy of search results. A database is generated based on the basic classification sets and corresponding fine-grained subsets, allowing subsequent searches to prioritize highly relevant data areas and flexibly respond to dynamic changes in textile industry data and the expansion of business scope. By utilizing broad categorization and cluster analysis to obtain basic classifications and fine-grained subsets, the raw data is transformed into a hierarchical, easily searchable, and adaptively optimized textile product information database, further improving retrieval efficiency and accuracy.

[0034] Understandably, in one embodiment, textile information data is categorized into basic classification sets based on broad categories. This can be done by dividing the textile information data into three categories based on enterprise type: upstream enterprise data, midstream enterprise data, and downstream enterprise data. Upstream enterprise data can include data on suppliers of raw materials or basic inputs for textile production, such as natural fibers, chemical fibers, dyes, and accessories. Midstream enterprise data can include data on enterprises engaged in semi-finished product manufacturing, including spinning, weaving, dyeing, and printing, processing raw materials into fabrics or semi-finished products. Downstream enterprise data can include data on enterprises that process, sell, or export finished products based on semi-finished products or fabrics.

[0035] Understandably, in one embodiment, for textile information data, data segments are extracted sequentially using 4, 8, and 16 rows as data reading units. Based on data segments of different lengths, a large language model is used to generate corresponding question-and-answer pairs from different perspectives, and these pairs are processed according to three scales: 4 rows, 8 rows, and 16 rows. To improve the quality of the database, some lower-quality textile information sample data are used as negative examples to optimize the subsequent data generation process. Utilizing multi-scale data to represent the detailed features of tabular data at different granularities, obtaining fine-grained subsets, can effectively improve the diversity and reliability of the database.

[0036] Additionally, refer to Figure 6 In one embodiment, Figure 1 Step S120 in the illustrated embodiment also includes, but is not limited to, the following steps: Step S610: Decompose the user question data into multiple sub-question data. Step S620: Perform a database search based on all sub-question data and target prompts to obtain the target search results.

[0037] Understandably, breaking down user query data into multiple sub-question data points avoids single-dimensional searching, reduces the complexity of individual data retrieval, and makes subsequent database searches more accurate and reliable. Performing database searches based on all sub-question data and target keywords yields targeted search results, enabling modular processing and parallel searching of multiple sub-question data points, effectively improving search efficiency. Searching based on sub-question data makes the search process more goal-oriented, allowing for in-depth searching from different dimensions, resulting in more reliable targeted search results and avoiding information omissions or biases that may arise from simple keyword matching.

[0038] Understandably, in one embodiment, synonym substitution and semantic transformation are performed on user query data to obtain multiple similar sub-question data. For example, if the user query data is "What are the legal representatives of dyeing and finishing factories in Shaoxing?", it can generate sub-question data such as "What are the persons in charge of dyeing and finishing factories in Shaoxing?", "What is the name of the owner of a printing and dyeing factory in Shaoxing?", etc. Retrieving based on multiple sub-question data can make the target retrieval results richer and more comprehensive.

[0039] Additionally, refer to Figure 7 In one embodiment, the method further includes, but is not limited to, the following steps: Step S710: Based on the user query data, perform consistency verification on the target search results to determine the accuracy of the target search results; Step S720: If the accuracy is lower than the preset threshold, re-search the database based on the user's question data and target prompts to obtain new target search results.

[0040] Understandably, performing consistency checks on target search results based on user query data can determine the relevance between the target search results and the user query data, thereby determining the accuracy of the target search results. If the accuracy is lower than a preset threshold, it indicates a low relevance between the target search results and the user query data. Re-searching the database based on the user query data and target keywords can effectively identify and correct search errors, obtain new target search results, and effectively improve the accuracy and credibility of the target search results.

[0041] In addition, one embodiment of this application provides an operation control device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor.

[0042] The processor and memory can be connected via a bus or other means.

[0043] The non-transient software program and instructions required to implement the textile information-based R&D information generation method of the above embodiments are stored in memory. When executed by a processor, the textile information-based R&D information generation method of the above embodiments is executed, for example, the method described above is executed. Figure 1 Method steps S110 to S130 in the middle Figure 2 Method steps S210 to S230 in the middle Figure 3 Method steps S310 to S330 in the middle Figure 4 Method steps S410, Figure 5 Method steps S510 to S530 in the middle Figure 6 Method steps S610 to S620 in the middle Figure 7 Method steps S710 to S720.

[0044] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0045] Furthermore, one embodiment of this application also provides a computer-readable storage medium storing computer-executable instructions that are executed by a processor or controller, for example, by a processor in the above-described operation control device embodiment, causing the processor to execute the R&D information generation method based on textile information in the above-described embodiment, for example, executing the above-described... Figure 1 Method steps S110 to S130 in the middle Figure 2 Method steps S210 to S230 in the middle Figure 3 Method steps S310 to S330 in the middle Figure 4 Method steps S410, Figure 5 Method steps S510 to S530 in the middle Figure 6 Method steps S610 to S620 in the middle Figure 7Method steps S710 to S720 are described above. Those skilled in the art will understand that all or some of the steps in the methods disclosed above, and the system, can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible by a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0046] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0047] The above is a detailed description of the preferred embodiments of this application. However, this application is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A method for generating R&D information based on textile information, characterized in that, include: Obtain user question data and company type, and determine target prompt words based on the company type; A database search is performed based on the user question data and the target prompt words to obtain the target search results; The search results for the target are integrated to generate R&D information.

2. The method for generating R&D information based on textile information according to claim 1, characterized in that, The step of performing a database search based on the user question data and the target prompt words to obtain the target search results includes: The user's question data is interpreted using a text interpretation model to generate content. The generated content is then used to perform a database search to obtain the first search result. The user question data is used to extract target keywords, and a database search is performed based on the target keywords and the target prompt words to obtain a second search result; The first search result and the second search result are determined as the target search results.

3. The method for generating R&D information based on textile information according to claim 2, characterized in that, The process of integrating the target search results to generate R&D information includes: Calculate the complexity of the generated content, and determine the first weight factor based on the complexity; Based on the accuracy of the target keywords, a second weighting factor is determined; Research and development information is generated based on the first search result, the second search result, the first weighting factor, and the second weighting factor.

4. The method for generating R&D information based on textile information according to claim 2, characterized in that, The step of extracting target keywords from the user question data includes: Based on the enterprise type, keyword extraction is performed on the user question data to obtain target keywords corresponding to the enterprise type.

5. The method for generating R&D information based on textile information according to claim 1, characterized in that, The database is generated in the following manner: Acquire textile information data, and classify the textile information data into major categories to form a basic classification set; In each of the basic classification sets, cluster analysis is performed based on the frequency of product information in the textile information to obtain fine-grained subsets; A database is generated based on the basic classification set and the corresponding fine-grained subsets.

6. The method for generating R&D information based on textile information according to claim 1, characterized in that, The step of performing a database search based on the user question data and the target prompt words to obtain the target search results includes: The user question data is broken down into multiple sub-question data. A database search is performed based on all sub-question data and the target prompts to obtain the target search results.

7. The method for generating R&D information based on textile information according to claim 1, characterized in that, The method for generating R&D information based on textile information also includes: Based on the user query data, a consistency check is performed on the target search results to determine the accuracy of the target search results; If the accuracy is lower than a preset threshold, the database is searched again based on the user's question data and the target prompt words to obtain new target search results.

8. An operation control device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for generating R&D information based on textile information as described in any one of claims 1 to 7.

9. A research and development information generation system based on textile information, characterized in that, Includes the operation control device as described in claim 8.

10. A computer storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions for causing a computer to perform the research and development information generation method based on textile information as described in any one of claims 1 to 7.

Images