CN-122020993-A - Product intelligent design method and system based on big data and axiom design

Abstract

The invention relates to the technical field of intelligent product design, and discloses an intelligent product design method and system based on big data and axiom design. The method comprises the steps of analyzing user comment data, constructing a quantization index which is integrated with the attention degree and the satisfaction degree and needs to be improved to determine the design priority, further taking the index as input, driving a axiom design theory to perform zigzag mapping and decomposition, guiding design decoupling according to the data priority in the process, outputting a design parameter set meeting the independence axiom, and finally quantitatively evaluating the effectiveness of different design elements through a layering generation scheme and user testing and feeding back to the front end to form a closed loop. The invention realizes the automatic and accurate conversion from subjective user feedback to objective and uncoupled design scheme, solves the core problems of fuzzy requirements, dependence on experience and difficult verification of the attribution in the traditional design flow, and remarkably improves the scientificity and efficiency of the design.

Inventors

• LI XUELIAN
• HUANG WENQIAN

Assignees

• 浙江理工大学

Dates

Publication Date

20260512

Application Date

20260113

Claims (10)

1. 1. The intelligent product design method based on big data and axiom design is characterized by comprising the following steps: determining a quantization index for indicating the design priority according to the user comment data of the target product; Mapping and decomposing the quantization indexes based on an axiom design theory to determine a design parameter set meeting an independence axiom; And generating product schemes of different optimization levels based on the design parameter set, and verifying each product scheme through user testing so as to evaluate the effectiveness of the design elements.
2. 2. The method of claim 1, wherein mapping and decomposing the quantization index based on axiom design theory comprises: converting the part meeting the preset condition in the quantization index into one or more top-layer function requirements; Based on the top-layer functional requirements, design parameters meeting the current functional requirements are searched layer by layer, decomposition and mapping are carried out in a mode of leading out the next-layer functional requirements according to the design parameters, and in the mapping process of each layer, the coupling relation between the functional requirements is analyzed.
3. 3. The method of claim 2, wherein analyzing the coupling relationship between functional requirements comprises: Constructing a design matrix for judgment; When judging that coupling exists, adjusting the setting of design parameters according to the priority sequence indicated by the quantization index so as to eliminate or reduce the coupling.
4. 4. A method according to claim 3, wherein said adjusting the setting of the design parameters according to the priority order indicated by the quantization index comprises: and preferentially adjusting design parameters corresponding to the parts with higher priority in the quantization indexes.
5. 5. The method of claim 1, wherein determining a quantization index for indicating design priority from user comment data comprises: Identifying a plurality of product features of interest to the user from the user comment data; and calculating the improvement degree value of each product characteristic based on the user comment data so as to form the quantitative index.
6. 6. The method of claim 5, wherein calculating a desired improvement value for each of the product features comprises: calculating the attention degree of the product features in comments; Calculating the satisfaction degree of the user on the product characteristics; And calculating a value of the degree of improvement according to the attention degree and the satisfaction degree.
7. 7. The method of claim 6, wherein the calculating user satisfaction with the product feature comprises: Constructing a dedicated emotion analysis model aiming at the product characteristics, wherein the model is obtained by training based on a reference word and word vector method matched with the product characteristics; And analyzing emotion tendencies about the product features in the comments by using the exclusive emotion analysis model so as to calculate satisfaction.
8. 8. The method according to claim 1, wherein the method further comprises: And dynamically adjusting the calculation logic or weight of the quantization index according to the effectiveness evaluation results of different design elements obtained by user test verification.
9. 9. A product intelligent design system based on big data and axiom design for performing the method of any of claims 1-8, the system comprising: The index determining module is used for determining a quantization index for indicating the design priority according to the user comment data; The theoretical mapping module is connected with the index determining module and is used for taking the quantization index as input, mapping and decomposing based on axiom design theory and outputting a design parameter set meeting the independence axiom; And the verification evaluation module is connected with the theoretical mapping module and is used for generating product schemes of different optimization levels based on the design parameter set and verifying each scheme through user test so as to evaluate the effectiveness of the design elements.
10. 10. The system according to claim 9, wherein: The theoretical mapping module further comprises a coupling analysis and decoupling unit, wherein the coupling analysis and decoupling unit is used for constructing a coupling relation between design matrix analysis function requirements in each layer of mapping process, and guiding setting and adjustment of design parameters to realize decoupling according to the priority indicated by the quantization index acquired from the index determination module when the coupling is judged to exist; The verification evaluation module is also connected with the index determination module and is used for feeding back the design element validity result obtained by quantitative evaluation to the index determination module so as to dynamically adjust the calculation logic or weight of the quantitative index.

Description

Product intelligent design method and system based on big data and axiom design Technical Field The invention relates to the field of design optimization, in particular to a product intelligent design method and system based on big data and axiom design. Background With the development of big data and artificial intelligence technology, data-driven design has become an important trend in product development. At present, methods for guiding design optimization by using user comments, market feedback and other data mainly comprise two types, namely a demand recognition technology based on emotion analysis and hot spot mining, aiming at extracting user attention points and emotion tendencies from massive texts, and a scheme generation technology based on parameterized modeling and intelligent optimization algorithms, and automatically generating candidate schemes by searching a design space. These techniques improve the objectivity of the design to some extent, but still have significant limitations. The problems of the prior art are mainly manifested in the following three aspects: Firstly, in the demand conversion stage, the traditional emotion analysis outputs a plurality of discrete emotion labels or macroscopic heat scores, and a quantitative index system capable of integrating the 'dissatisfaction degree' and the 'attention intensity' of a user is lacked, so that the design priority is accurately indicated, and the design input is still fuzzy. In the design generation stage, no matter the numerical optimization of an algorithm is relied on, or the experience decision of a designer is relied on, the harmony and the conflict-free property of the internal parameters of the final design scheme are difficult to systematically ensure, namely, the independence axiom is satisfied, and the realization difficulty of subsequent engineering is often caused. Finally, in the verification stage, the existing method focuses on the evaluation of the overall scheme, and cannot quantitatively strip and attribute specific contributions of different design elements to user experience, so that the design iteration lacks accurate direction guidance. Therefore, how to construct an intelligent design system capable of penetrating the whole flow of ' accurate quantization of requirements-generation of design logic-attribution verification of effects ', and closely coupling and mutually enhancing each link ' has become a key technical problem to be solved in the art. Disclosure of Invention In order to solve the problems in the prior art, the invention provides an intelligent product design method and system based on big data and axiom design. According to a first aspect of the present invention, a product intelligent design method based on big data and axiom design is provided, comprising: determining a quantization index for indicating the design priority according to the user comment data of the target product; mapping and decomposing the quantization index based on an axiom design theory to determine a design parameter set meeting an independence axiom; And generating product schemes of different optimization levels based on the design parameter set, and verifying each product scheme through user testing so as to evaluate the effectiveness of the design elements. According to some embodiments, in the method of the first aspect of the present invention, mapping and decomposing the quantization index based on axiom design theory includes: The method comprises the steps of obtaining a quantization index, converting a part meeting preset conditions in the quantization index into one or more top-layer functional requirements, searching design parameters meeting current functional requirements layer by layer based on the top-layer functional requirements, decomposing and mapping in a mode that the design parameters extend out of the next-layer functional requirements, and analyzing the coupling relation between the functional requirements in the mapping process of each layer. According to some embodiments, in the method of the first aspect of the present invention, analyzing the coupling relation between the functional requirements includes: And when judging that coupling exists, adjusting the setting of design parameters according to the priority order indicated by the quantization index so as to eliminate or reduce the coupling. According to some embodiments, in the method of the first aspect of the present invention, the setting of the design parameters is adjusted according to the priority order indicated by the quantization index, which specifically includes preferentially adjusting the design parameters corresponding to the portions with higher priority in the quantization index. According to some embodiments, in the method of the first aspect of the present invention, determining a quantization index for indicating a design priority according to user comment data includes: and calculating the value of the degree of improvemen