Design demand result generation method and system and computer medium

Abstract

The invention provides a design demand result generation method and system and a computer medium. The method comprises the steps of obtaining an original demand of a design project and performing preprocessing to obtain original demand data; vectorizing the original demand data through an artificial intelligence model to generate an original demand vector; obtaining design demand data from a design demand library, and vectorizing the design demand data through an artificial intelligence model to obtain a design demand vector; and matching the two types of vectors based on an artificial intelligence model, and outputting a design demand result matched with the original demand by the model. According to the scheme, a traditional manual demand analysis mode is replaced with artificial intelligence model automatic process processing, complex original demand texts are efficiently processed, potential demand points are automatically mined, demand identification omission and later rework risks caused by manual negligence are reduced, the mapping relation between original demands and design demands is accurately constructed, and the design efficiency is improved. And the design process can be efficiently propelled.

Description

Technical Field

[0001] The present invention relates to the field of industrial design, and in particular to a method, system and computer medium for generating design requirement results. Background Art

[0002] In complex industrial design fields (such as automotive and aerospace equipment design), requirements analysis remains a critical step in project success. Requirements analysis refers to the translation of raw user needs, typically expressed in natural language, into clear design requirements, typically expressed as design metrics. Accurately mapping raw requirements to design requirements is crucial for ensuring comprehensive requirements coverage, design compliance, and minimizing rework.

[0003] However, traditional requirements analysis typically requires manual review of requirements documents, capturing specific requirements from the original documents based on personal experience and then forming design requirements. However, this makes it easy to miss the original requirements and the requirements identification efficiency is low, often leading to project delays and the need for rework later. Summary of the Invention

[0004] In order to overcome the above technical defects, the purpose of the present invention is to provide a design requirement result generation method, system and computer medium.

[0005] The present invention discloses a method for generating design requirement results, comprising: Capture original requirements for input into design projects.

[0006] Preprocess the original demand to obtain the original demand data.

[0007] The original demand data is vectorized based on the artificial intelligence model to obtain the original demand vector.

[0008] Based on the design requirement library, obtain design requirement data for design project output.

[0009] The design requirement data is vectorized based on the artificial intelligence model to obtain the design requirement vector.

[0010] Match the original demand vector with the designed demand vector based on the artificial intelligence model.

[0011] Based on the matching results, the artificial intelligence model outputs the design requirement results that match the original requirements.

[0012] Preferably, after the artificial intelligence model outputs the design requirement results that match the original requirements based on the matching results, the method further includes: The original requirement includes a first tag, the design requirement result includes a second tag, the first tag and the second tag form a data link, and the first tag and the second tag can be bidirectionally connected through the data link.

[0013] Preferably, the original demand is preprocessed to obtain original demand data, including: Obtain the original demand, and use the artificial intelligence model to divide the original demand into the first demand and the second demand.

[0014] The first requirement includes the original design type and original design standard. The second requirement includes the original design requirements.

[0015] Preferably, the original demand data is vectorized based on the artificial intelligence model to obtain the original demand vector, including: The first demand and the second demand are respectively vectorized based on the artificial intelligence model to obtain a first demand vector and a second demand vector.

[0016] The artificial intelligence model matches the first demand vector and the second demand vector with the design demand vector respectively.

[0017] Preferably, the artificial intelligence model matches the first demand vector and the second demand vector with the design demand vector respectively, including: The first demand vector, the second demand vector and the design demand vector are cleaned using a data cleaning algorithm.

[0018] Preferably, the design requirement result generating method further includes: Upload the original demand data and design demand results to the artificial intelligence model, train the original demand data and design demand results through the artificial intelligence model, and strengthen the matching algorithm of the artificial intelligence model.

[0019] The present invention also provides a design requirement result generation system, which includes: Get the module to obtain the original requirements and design requirements data.

[0020] The data processing module pre-processes the original requirements and generates original requirement data. The original requirement data is vectorized based on the AI ​​model to obtain the original requirement vector. The design requirement data is vectorized based on the AI ​​model to obtain the design requirement vector. The original requirement vector and the design requirement vector are matched based on the AI ​​model.

[0021] The result output module outputs the design requirement results that match the original requirements based on the matching results.

[0022] Preferably, the data processing module includes: The preprocessing module is used to preprocess the original demand to obtain the original demand data.

[0023] Vectorization module, the vectorization module is used to vectorize the original demand data and design demand data based on the artificial intelligence model.

[0024] Matching module, the matching module matches the original demand vector with the design demand vector based on the artificial intelligence model, thereby obtaining the design demand data that best matches the original demand data.

[0025] Preferably, the system further includes a first server and a second server. The second server obtains the newly added demand data from the first server. The second server is in communication with a vectorization module, and the vectorization module vectorizes the newly added demand data and stores the vectorized data in a vector database of the second server.

[0026] The present invention also provides a computer storage medium storing a computer program for executing the design requirement result generating method of any of the aforementioned embodiments.

[0027] Compared with the existing technology, the above technical solution has the following beneficial effects: 1. The original requirements are automatically pre-processed and vectorized through artificial intelligence models, and then intelligently matched with the design requirements library that has also been vectorized. The automated processing of artificial intelligence models has changed the traditional model of relying on manual experience to identify and match one by one. It can quickly and on a large scale process complex original requirement texts and automatically mine potential demand points. On the one hand, this intelligent matching not only greatly shortens the demand analysis cycle, but also avoids identification omissions due to human negligence. It significantly reduces the risk of later design rework and the possibility of project delays due to deviations or omissions in the understanding of requirements, laying a solid demand foundation for the smooth progress of engineering projects. On the other hand, the mapping relationship between original requirements and design requirements is accurately established, and both can be traced in the computer system, which greatly reduces the tracing cost between original requirements and design requirements, and is more convenient for reference at any time during the implementation of the engineering project.

[0028] 2. Through the tagging mechanism and data chain, a strong association is established between the original requirements and the final output design requirements results, and two-way traceability is achieved through the data chain. This mechanism further enables users to clearly track the original requirements corresponding to each design requirement result, and can also trace back to which specific design requirements a certain original requirement was ultimately implemented. This not only greatly improves the transparency and auditability of the design process, but more importantly, when the original requirements change or the design requirements need to be adjusted, the data chain can quickly locate the parts that need to be linked, effectively supporting the change management of requirements and iterative updates of design versions, forming a closed-loop management of requirements, and significantly improving the maintainability of design results and the flexibility of project management.

[0029] 3. By dividing the original requirements into primary and secondary requirements and sequentially matching them with the design requirements in a vectorized manner, the original requirements are processed in a more refined and layered manner. This allows the AI ​​model to perform an initial screening based on the primary requirement vector and then more accurately match the specific requirements of the secondary requirement vector. This matching method improves both matching speed and matching accuracy. Furthermore, by incorporating data cleaning algorithms to clean the data and vectors, matching accuracy is further enhanced. The final output of the design requirement results not only meets the overall requirement framework but also accurately meets specific detailed requirements, effectively improving project quality and user satisfaction.

[0030] 4. By continuously feeding actual raw demand data and design demand data back to the AI ​​model for training, the AI ​​model can continuously learn from new project experiences, optimizing its vectorization capabilities and matching algorithms to adapt to changes in demand representation and the introduction of new domain knowledge. Furthermore, by regularly obtaining and vectorizing new demand data from the first server, the timeliness and completeness of the second server are ensured. This dynamic update and continuous learning mechanism enables the entire system to evolve over time and with the accumulation of projects, effectively leveraging historical data and maintaining long-term matching accuracy, effectively avoiding the problem of system performance degradation over time. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A flowchart of the design requirement result generation method provided for this application; Figure 2 This is a system framework diagram of the design requirement result generation method provided in this application. DETAILED DESCRIPTION

[0032] The advantages of the present invention are further described below with reference to the accompanying drawings and specific embodiments.

[0033] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0034] The terms used in this disclosure are for the purpose of describing specific embodiments only and are not intended to limit the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0035] It should be understood that although the terms first, second, third, etc. may be used in the present disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of the present disclosure, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" In the description of the present invention, it should be understood that the terms "longitudinal", "transverse", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention.

[0036] See also Figure 1 , Figure 1 It is a flowchart of the design requirement result generation method provided in this application.

[0037] like Figure 1 As shown, this application provides a method for generating design requirement results, including: Capture original requirements for input into design projects.

[0038] Preprocess the original demand to obtain the original demand data.

[0039] The original demand data is vectorized based on the artificial intelligence model to obtain the original demand vector.

[0040] Based on the design requirement library, obtain design requirement data for design project output.

[0041] The design requirement data is vectorized based on the artificial intelligence model to obtain the design requirement vector.

[0042] Match the original demand vector with the designed demand vector based on the artificial intelligence model.

[0043] Based on the matching results, the artificial intelligence model outputs the design requirement results that match the original requirements.

[0044] Specifically, the system first obtains the original requirements input by the user for the design project. This can be a description provided by the user in natural language or by importing a document. The original requirements are then preprocessed to obtain several pieces of raw requirement data. These pieces of raw requirement data are then vectorized using an artificial intelligence model to accurately extract the smallest semantic units of the requirement description. The low-dimensional raw requirement data is then converted into high-dimensional raw requirement vectors, which are then stored in a vector database.

[0045] As for design requirements, similarly, the design requirement data for the output of the design project is obtained through the design requirement library, and the low-dimensional design requirement data is converted into several high-dimensional design requirement vectors through the artificial intelligence model, and the processed design requirement vectors are stored in the vector database. The design requirement library here can include structure tree style classification management of all the requirement data in it based on different business attributes, such as regulatory requirements, industry specifications, enterprise design specifications, historical archived design requirement data, etc. The design requirement library can also contain all original requirement data and the enterprise's design requirement data. The original requirement data and design requirement data are different data types, which facilitates classification and distinction during data processing.

[0046] The original requirement vector and the design requirement vector are then input into the AI ​​model for matching. By matching the high-dimensional vectors, a design requirement vector that matches the original requirement vector is obtained. Based on the matching results, the AI ​​model reversely converts the high-dimensional design requirement vector into low-dimensional design requirement data, ultimately outputting a design requirement result that matches the original requirement.

[0047] For example, a user's original requirement description is obtained as "I need a small drone with a long range, high flight, light weight, and good machinability." After pre-processing the original requirement, raw requirement data such as "small," "drone," "long range," "high flight," "light weight," and "good machinability" are obtained. Subsequently, an artificial intelligence model is used to vectorize these raw requirement data to obtain a high-dimensional raw requirement vector. After matching the design requirement vectors converted from the design requirement library, the final design requirement results are obtained: "Light drone, empty weight ≤ 4kg, maximum take-off weight ≤ 7kg," "Fuselage made of carbon fiber composite material," "Hybrid rotor / fixed-wing configuration," "Fuselage ≤ 800g, battery ≤ 1.2kg, power system ≤ 600g," "Battery uses ISO 24352:2023 standard power lithium battery with energy density ≥ 250Wh / kg," "Wing aspect ratio > 12," etc.

[0048] The above embodiments are only for illustrating the technical effects. In actual engineering projects, the original requirements are often more complex. In this case, the original requirements can be input by document import as described above. This application does not constitute any limitation here.

[0049] Therefore, it is understandable that the original requirements are automatically pre-processed and vectorized through the artificial intelligence model, and then intelligently matched with the design requirement library that has also been vectorized. The automated processing of the artificial intelligence model has changed the traditional model of relying on manual experience to identify and match one by one. It can quickly and on a large scale process complex original requirement texts and automatically mine potential demand points. On the one hand, this intelligent matching not only greatly shortens the demand analysis cycle and avoids identification omissions due to human negligence. It significantly reduces the risk of later design rework and the possibility of project delays due to deviations or omissions in the understanding of requirements, laying a solid demand foundation for the smooth progress of engineering projects. On the other hand, the mapping relationship between original requirements and design requirements is accurately established, and both can be traced in the computer system, thereby greatly reducing the tracing cost between original requirements and design requirements, and making it easier to check at any time during the implementation of the engineering project.

[0050] The above is an explanation of the basic concept and basic embodiments of the present application. Those skilled in the art will understand that the specific implementation of each of the aforementioned steps is not limited and may include more or fewer steps.

[0051] In one possible implementation, after the artificial intelligence model outputs a design requirement result that matches the original requirement based on the matching result, the following steps are further included: The original requirement includes a first tag, the design requirement result includes a second tag, the first tag and the second tag form a data link, and the first tag and the second tag can be bidirectionally connected through the data link.

[0052] Specifically, the original requirement includes a first label, and the design requirement result includes a second label. After the design requirement result is output, the first label of the original requirement and the second label of the design requirement result are used to establish a strong association between the original requirement and the final output design requirement result through the label mechanism and data chain, and two-way traceability is achieved through the data chain. This mechanism further enables users to clearly trace the original requirement corresponding to each design requirement result, and can also trace back to which specific design requirements a certain original requirement is ultimately implemented on. This not only greatly improves the transparency and auditability of the design process, but more importantly, when the original requirement changes or the design requirement needs to be adjusted, the data chain can quickly locate the part that needs to be linked, effectively support the change management of requirements and the iterative update of the design version, form a closed-loop management of requirements, and significantly improve the maintainability of design results and the flexibility of project management.

[0053] Furthermore, those skilled in the art will appreciate that the first label and the second label here may be automatically assigned by the artificial intelligence model after outputting the results, or may be manually assigned by the user after obtaining the results, and this application does not impose any restrictions thereon.

[0054] The above is an explanation of the method for forming a traceable data chain in this application. The following will explain how this application pre-processes the original design data.

[0055] Preprocess the original demand to obtain the original demand data, including: The original requirements are obtained and divided into primary and secondary requirements by the AI ​​model. The primary requirements include the original design type and original design standard. The secondary requirements include the original design requirements.

[0056] Specifically, after obtaining the original requirements, the AI ​​model will initially categorize them into primary and secondary requirements. Primary requirements include the original design type and standard, often grouped into broad categories. Secondary requirements, on the other hand, primarily include original design requirements, addressing specific user needs beyond broad categories. This allows for a more refined stratification of the original requirements.

[0057] For example, as mentioned above, when the original demand is "I need a small drone with long range, high flying, light weight and good processability", "small" and "drone" are the first requirements, and "long range", "high flying", "light weight" and "good processability" are the second requirements.

[0058] Therefore, further, in a possible implementation, the original demand data is vectorized based on the artificial intelligence model to obtain the original demand vector, including: The first demand and the second demand are respectively vectorized based on the artificial intelligence model to obtain a first demand vector and a second demand vector.

[0059] The artificial intelligence model matches the first demand vector and the second demand vector with the design demand vector respectively.

[0060] Specifically, the original requirements are divided into a first and a second requirement, and then the first and second requirements are input into the AI ​​model for vectorization. These first and second requirement vectors are then matched against the design requirement vectors based on the AI ​​model, providing a more refined and layered approach to the original requirements. This allows the AI ​​to perform an initial screening based on the first requirement vector and then more accurately match the specific requirements of the second requirement vector. This layered matching approach improves both matching speed and accuracy.

[0061] Furthermore, during matching, the data can be further processed using a specific data cleaning algorithm.

[0062] In one possible implementation, the artificial intelligence model matches the first requirement vector and the second requirement vector with the design requirement vector respectively, including: The first demand vector, the second demand vector and the design demand vector are cleaned using a data cleaning algorithm.

[0063] Specifically, the data cleaning algorithm here may include but is not limited to one or more algorithms such as outlier processing, deduplication processing, and noise processing.

[0064] Among them, outliers, also known as outliers, refer to values ​​that are significantly different from the majority of data. The specific methods for handling outliers are: Statistical analysis: Use descriptive statistical indicators (mean, standard deviation, quartiles) to identify abnormal data entries and determine whether to remove them based on business needs.

[0065] Clustering-based clustering method: objects that do not belong to any cluster are considered as anomalies and eliminated.

[0066] Deduplication is used to identify and process duplicate records in requirement items, which may affect the accuracy and efficiency of matching results. The following methods are used to identify and process duplicate records in requirement items: Sort requirement items and detect duplicates based on similarity metrics of neighboring records (e.g., text similarity, feature value matching, etc.).

[0067] According to business rules, retain the best records or merge duplicate records to ensure the uniqueness of data.

[0068] Noise processing is to deal with the situation where random errors or variances in the data may interfere with the matching performance of the artificial intelligence model. For noisy data, the following smoothing techniques are used: Binning method: Divide the data into several intervals (boxes) and smooth the data values ​​by calculating the mean, median and other statistics within the interval.

[0069] Linear regression fitting: Use the linear regression model to fit the data and eliminate the influence of random noise to obtain a smoother data distribution.

[0070] Through the above exemplary algorithm, this application can clean the data and vectors through the data cleaning algorithm, further improving the matching accuracy, so that the final output design requirement results not only meet the overall requirement framework, but also accurately meet the specific detail requirements, effectively improving the quality of the engineering project and user satisfaction.

[0071] The above is a complete design requirement result generation method process provided by this application. It can be understood by those skilled in the art that after the design requirement result is generated, the artificial intelligence model can be further trained with historically generated data to further improve the generated effect.

[0072] In a possible implementation, the design requirement result generating method further includes: Upload the original demand data and design demand results to the artificial intelligence model, train the original demand data and design demand results through the artificial intelligence model, and strengthen the matching algorithm of the artificial intelligence model.

[0073] By continuously feeding back the actual original demand data and design demand results to the artificial intelligence model for training, the artificial intelligence model can continuously learn from new project experiences, optimize its vectorization representation capabilities and matching algorithms, thereby adapting to changes in demand expressions and the introduction of new domain knowledge, and further improving the generation effect.

[0074] The above is an explanation of various possible implementations of the design requirement result generation method provided by this application. The following will explain the design requirement result generation system provided by this application and possible implementations.

[0075] On the other hand, the present application also provides a design requirement result generation system for implementing the aforementioned design requirement result generation method. Figure 2 , Figure 2 A system framework diagram of the design requirement results generation method for the engineering project provided in this application.

[0076] like Figure 2 As shown, combined with Figure 1It is understood that the design requirement result generation system includes: Get the module to obtain the original requirements and design requirements data.

[0077] The data processing module pre-processes the original requirements and generates original requirement data. The original requirement data is vectorized based on the AI ​​model to obtain the original requirement vector. The design requirement data is vectorized based on the AI ​​model to obtain the design requirement vector. The original requirement vector and the design requirement vector are matched based on the AI ​​model.

[0078] The result output module outputs the design requirement results that match the original requirements based on the matching results.

[0079] By providing these modules, the design requirement result generation system can execute the aforementioned design requirement result generation method.

[0080] Furthermore, the data processing module includes: The preprocessing module is used to preprocess the original demand to obtain the original demand data.

[0081] Vectorization module, the vectorization module is used to vectorize the original demand data and design demand data based on the artificial intelligence model.

[0082] Matching module, the matching module matches the original demand vector with the design demand vector based on the artificial intelligence model, thereby obtaining the design demand data that best matches the original demand data.

[0083] It should be noted that the specific deployment locations of the preprocessing module, vectorization module, and matching module are not limited. In one possible implementation, the vectorization module, preprocessing module, and matching module are deployed on different servers. In another possible implementation, the vectorization module, preprocessing module, and matching module can be deployed on the same server, which is not a limitation in this application.

[0084] Once the vectorization module is deployed independently, it can independently perform vectorization processing for design requirements. Therefore, in one possible implementation, the design requirement result generation system also includes a first server and a second server, where the second server obtains the newly added requirement data from the first server. The second server is communicatively connected to the vectorization module, or the vectorization module is directly deployed on the second server. The vectorization module then vectorizes the newly added requirement data and stores the vectorized data in a vector database on the second server.

[0085] Those skilled in the art will appreciate that the specific types of the first server and the second processing server are not limited. For example, the first server can be a full-life cycle industrial design data management platform server, such as a 3DE platform (3DEXPERIENCE Platform) server. The first server is provided with a design requirement library, which stores a large amount of design requirement data and updates new requirement data in real time based on user usage. The new requirement data includes original requirement data and design requirement data. The second server can be deployed locally or in the cloud. Its main function is to retrieve the aforementioned new requirement data from the first server regularly or irregularly, and call the vectorization module (specifically, an embedded model can be used) to vectorize the new requirement data, and finally save it in the vector database of the second server. By obtaining and vectorizing the new requirement data from the first server, the timeliness and completeness of the design requirement data in the second server are ensured.

[0086] The present application also provides a computer storage medium storing a computer program for executing the design requirement result generation method of any of the aforementioned embodiments. It should be noted that the embodiments of the present invention have better feasibility and do not limit the present invention in any form. Any technician familiar with the field may use the technical content disclosed above to change or modify it into an equivalent effective embodiment. However, any modification or equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of the technical solution of the present invention.

Claims

1. A method for generating project design requirement results, characterized in that: The design requirement result generating method comprises: Obtain original requirements for design project input; Preprocessing the original demand to obtain original demand data; Vectorizing the original demand data based on an artificial intelligence model to obtain an original demand vector; Based on the design requirement library, obtain the design requirement data for the design project output; Vectorizing the design requirement data based on the artificial intelligence model to obtain a design requirement vector; Matching the original demand vector with the design demand vector based on the artificial intelligence model; Based on the matching results, the artificial intelligence model outputs a design requirement result that matches the original requirement.

2. The method for generating design requirement results according to claim 1, wherein: After the artificial intelligence model outputs a design requirement result that matches the original requirement based on the matching result, the method further includes: The original requirement includes a first tag, and the design requirement result includes a second tag. The first tag and the second tag form a data link, and the first tag and the second tag can be bidirectionally connected through the data link.

3. The method for generating design requirement results according to claim 1, wherein: The preprocessing of the original demand to obtain original demand data includes: Acquire the original demand, and divide the original demand into a first demand and a second demand by the artificial intelligence model; The first requirement includes the original design type and the original design standard; the second requirement includes the original design requirement.

4. The method for generating design requirement results according to claim 3, wherein: The original demand data is vectorized based on the artificial intelligence model to obtain an original demand vector, including: Vectorizing the first demand and the second demand based on an artificial intelligence model to obtain a first demand vector and a second demand vector; The artificial intelligence model matches the first demand vector and the second demand vector with the design demand vector respectively and successively.

5. The method for generating design requirement results according to claim 4, wherein: Matching the first requirement vector and the second requirement vector with the design requirement vector respectively by the artificial intelligence model includes: The first requirement vector, the second requirement vector and the design requirement vector are cleaned using a data cleaning algorithm.

6. The method for generating design requirement results according to claim 1, wherein: The design requirement result generating method further includes: The original demand data and the design demand results are uploaded to the artificial intelligence model, and the original demand data and the design demand results are trained by the artificial intelligence model to strengthen the matching algorithm of the artificial intelligence model.

7. A design requirement result generation system, characterized in that: The design requirement result generating system includes: Get the module to obtain the original requirements and design requirements data; a data processing module that preprocesses the original demand to generate original demand data; vectorizes the original demand data based on an artificial intelligence model to obtain an original demand vector; vectorizes the design demand data based on the artificial intelligence model to obtain a design demand vector; and matches the original demand vector with the design demand vector based on the artificial intelligence model; The result output module outputs the design requirement results that match the original requirements based on the matching results.

8. The design requirement result generating system according to claim 7, characterized in that: The data processing module includes: A preprocessing module, configured to preprocess the original demand to obtain the original demand data; A vectorization module, configured to perform vectorization processing on the original requirement data and the design requirement data based on an artificial intelligence model; A matching module is used to match the original requirement vector with the design requirement vector based on an artificial intelligence model, thereby obtaining the design requirement data that best matches the original requirement data.

9. The design requirement result generating system according to claim 8, characterized in that: It also includes a first server and a second server; the second server obtains the new demand data from the first server; the second server is communicated with the vectorization module, and the vectorization module vectorizes the new demand data and stores the vectorized data in the vector database of the second server.

10. A computer storage medium storing a computer program, wherein the computer program is used to execute the design requirement result generating method according to any one of claims 1 to 6.

Images