Intelligent furniture design and production method and system

Abstract

The invention discloses an intelligent furniture design production method and system, and relates to the technical field of furniture production, and the method comprises the steps: obtaining the design demand data of a customer, carrying out the semantic analysis of the design demand data based on a semantic analysis model, extracting the design elements of the design demand data of the customer, and importing a basic furniture model, setting an initial size of the basic furniture model according to the spatial data; dividing the plurality of design elements into a plurality of design element groups according to a design direction; adjusting the initial size of the basic furniture model based on the plurality of design element groups to generate a plurality of initial design schemes; and extracting process parameters of the initial design scheme, screening and analyzing based on production feasibility, and outputting a furniture design production scheme meeting the production feasibility. Design elements of customer design demand data are extracted through semantic analysis, production feasibility analysis is carried out in combination with furniture materials, efficient and full-automatic intelligent furniture customization operation is achieved, and the intelligence of furniture design production is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of furniture production, and particularly relates to an intelligent furniture design and production method and system. Background Art

[0002] Currently, furniture customization design mainly relies on designers to carry out customized design according to customers' needs, and relies on manual model splicing or adjustment to generate furniture model solutions that meet customers' needs. The current furniture customization system can only achieve simple feedback on users' design requirements, adjust dimensions and colors based on existing furniture designs, and cannot meet customers' actual design and usage requirements. Moreover, the labor cost invested in customized design is high, and the intelligent full-automatic customization effect cannot be achieved. Summary of the Invention

[0003] The purpose of the present invention is to overcome the deficiencies of the prior art. The present invention provides an intelligent furniture design and production method, which extracts design elements of customers' design requirement data through semantic analysis, adjusts the design of furniture models according to the design elements, combines with furniture materials for production feasibility analysis, realizes efficient and fully automatic intelligent furniture customization operations, and improves the intelligence of furniture design and production.

[0004] The present invention provides an intelligent furniture design and production method, and the intelligent furniture design and production method includes: Obtain customers' design requirement data, perform semantic analysis on the design requirement data based on a semantic analysis model, and extract design elements of the customers' design requirement data; Import a basic furniture model into the design system, obtain spatial data of furniture layout, and set the initial dimensions of the basic furniture model according to the spatial data; Classify several design elements according to design directions to obtain several groups of design element groups; Adjust the initial dimensions of the basic furniture model based on several groups of design element groups to generate several initial design schemes; Extract process parameters of the initial design schemes, combine with the basic furniture model for production feasibility screening analysis, and output furniture design and production schemes that meet production feasibility.

[0005] Further, the obtaining of customers' design requirement data, performing semantic analysis on the customers' design requirement data based on a semantic analysis model, and extracting design elements of the customers' design requirement data includes: Obtain the login signal of the furniture design system, and call and run a visual table file based on the login signal; Obtain an information input signal based on the visual table file, and extract the input information content according to the information input signal to generate design requirement data.

[0006] Further, the semantic analysis of the customer's design requirement data by the semantic analysis model to extract the design elements of the customer's design requirement data includes: Preprocess the design requirement data through the Jieba algorithm, mark the key words in the design requirement data, and perform word frequency statistics on the marked key words based on the TF-IDF algorithm.

[0007] Further, the calculation formula of the TF-IDF algorithm is: ; Wherein, is the word frequency ratio of the keyword, is the number of times the keyword appears in the design requirement data, is the word in the design requirement data, is the sum of all words in the design requirement data.

[0008] Further, importing the basic furniture model into the design system, obtaining the spatial data of the furniture layout, and setting the initial dimensions of the basic furniture model according to the spatial data include: Extract the structural feature data from the design requirement data, perform 3D construction on the structural feature data based on the B-Rep mechanism to obtain the initial geometric entity; Obtain the spatial data of the furniture layout, and set the dimension threshold of the initial geometric entity according to the spatial data; Extract the model data from the database according to the initial geometric entity, and adjust the dimension value of the model data based on the dimension threshold to generate the basic furniture model.

[0009] Further, classifying several design elements according to the design direction to obtain several groups of design element groups includes: Set the classification rules according to the type of the basic furniture model, and divide several design directions according to the classification rules; Classify several design elements based on several design directions to obtain several groups of design element groups.

[0010] Further, adjusting the initial dimensions of the basic furniture model based on several groups of design element groups to generate several initial design schemes includes: Extract one design element from each group of design element groups, and adjust the initial dimensions of the basic furniture model based on the extracted design element to obtain the furniture adjustment model; Organize several design elements and the furniture adjustment model and save them as the initial design scheme.

[0011] Further, the permutation and combination calculation formula of several initial design schemes is: ; Among them, represents all cases of extracting one design element from the first group of design elements, and represents all cases of extracting one design element from the m-th group of design elements.

[0012] Furthermore, the process parameters for extracting the initial design plan are combined with the basic furniture model for production feasibility screening analysis, and the furniture design and production plan that meets the production feasibility is output, including: Mark the design key points for several initial design plans in sequence, and match the processing methods according to the design key points; Detect the processing methods in combination with the basic furniture model to detect the production feasibility of the initial design plan.

[0013] The present invention also provides an intelligent furniture design and production system, which is used to execute the above-mentioned intelligent furniture design and production method. The production system includes: Data acquisition module: used to acquire the design requirement data of customers and the spatial data of furniture layout; Model processing module: used to import the basic furniture model according to the spatial data of furniture layout and adjust the basic furniture model according to the design requirement data; Data analysis module: used to extract design elements according to the design requirement data and generate several initial design plans; Data detection module: used to perform production feasibility analysis on several initial design plans and sort out and output the furniture design and production plan.

[0014] The present invention provides an intelligent furniture design and production method and system. By semantically analyzing the design requirements input by customers, extracting the design elements of the design requirement data of customers, combining the design elements with the spatial model data, automatically analyzing the design requirements of customers, intelligently generating a variety of furniture design plans and detecting the production feasibility, it solves the problem of low efficiency of traditional customization relying on manual labor, has the advantages of improving the furniture customization efficiency, reducing the labor cost and meeting the personalized needs of customers, and realizes the intelligent full-automatic design of furniture design and production. Description of the Drawings

[0015] Figure 1 is the flowchart of the intelligent furniture design and production method in the embodiment of the present invention; Figure 2 is the structural schematic diagram of the intelligent furniture design and production system in the embodiment of the present invention. Detailed Embodiments

[0016] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0017] Embodiment 1: Figure 1 The flowchart of the intelligent furniture design and production method in the embodiments of the present invention is shown. The intelligent furniture design and production method includes: S11: Obtain the design requirement data of the customer, perform semantic analysis on the design requirement data based on the semantic analysis model, and extract the design elements of the customer design requirement data.

[0018] Specifically, based on the design requirement data input by the customer into the furniture design system, the design elements of the current furniture design task are extracted. The design requirement data can be voice data, text data, pattern data, etc. By analyzing the design requirement data, the furniture customization design requirements of the customer are obtained, so as to generate a furniture model solution that meets the customer's design requirements.

[0019] After the customer logs in to the furniture design system, a form file loading instruction is triggered, and a guiding form file is displayed on the display section of the system, enabling the customer to select home furnishing style types such as "Chinese style", "European and American style", "Japanese style", etc. through radio buttons in the style selection item, and check types such as "redwood", "metal inlay", "stone", etc. in the material option list, so that the furniture design system can obtain the customer's preliminary design requirements.

[0020] A standardized form file template is preset in the furniture design system. This template contains multiple predefined fields, such as furniture type, style preference, main material, color preference, size requirements, etc. After the customer logs in to the furniture design system, the system automatically pops up this form file to guide the customer to fill it in item by item. Each field in the form is equipped with a drop-down option or an input box, and the customer can select or input the corresponding information according to actual needs. After filling in, the system automatically collects and organizes these structured design requirement data to form a standardized data set.

[0021] Furthermore, the semantic analysis model refers to a computational model for natural language parsing of customer design requirements. Specifically, natural language processing algorithms such as Jieba segmentation combined with TF-IDF word frequency statistics method can be used to implement it. Its function is to convert unstructured customer requirements into design elements that can be quantitatively processed, avoiding the subjective deviation of manual interpretation.

[0022] Among them, the basic furniture model refers to the standardized three-dimensional model framework of furniture pre-set in the system, which can be specifically constructed using parametric modeling tools such as CAD or SolidWorks. Its role is to provide an initial design benchmark, and combined with spatial data, it can quickly adapt to the size constraints of the actual scene.

[0023] Among them, the spatial data refers to the set of physical parameters of the furniture layout environment, which can be specifically obtained through a laser rangefinder or a three-dimensional scanning device. Its role is to match the design scheme with the real space and avoid design rework caused by size conflicts.

[0024] Among them, the design direction classification refers to the logical rule for dividing requirement elements according to the functional attributes of furniture. Specifically, a classification tree can be established according to dimensions such as structure, material, and style. Its role is to establish an association system among requirement elements and provide structured data support for subsequent scheme combination.

[0025] Specifically, semantic analysis is performed on the design requirement data of the customer based on the semantic analysis model, and the design elements of the customer design requirement data are extracted.

[0026] The design requirement data is input into the semantic analysis model for semantic recognition. Based on Jieba, preprocessing is performed on the design requirement data, part-of-speech tagging is performed in the design requirement data, and part-of-speech data such as nouns, verbs, and adjectives in the design requirement data are initially defined. Based on the tagged part-of-speech, the design requirement data is initially segmented for classifying the design requirement data.

[0027] Furthermore, the Jieba library is a word segmentation library. By calling the Jieba word segmentation library, sentences can be accurately segmented, and at the same time, fast sentence semantic analysis can be achieved.

[0028] Furthermore, the preprocessing also includes marking irrelevant words in the design requirement data, such as semantic word groups, prepositions, etc. When performing semantic analysis, the interference of irrelevant words can be reduced, thereby improving the convenience and accuracy of semantic analysis of the design requirement data.

[0029] Specifically, the high-frequency words in the design requirement data are detected, the high-frequency words in the design requirement data are identified and extracted based on the TF-IDF algorithm, preprocessing is performed on the design requirement data through the Jieba algorithm, keyword words are marked in the design requirement data, and word frequency statistics are performed on the marked keyword words based on the TF-IDF algorithm. Based on the word frequency analysis of the keyword words in the design requirement data, the design requirements of the customer can be accurately analyzed.

[0030] TF-IDF (term frequency–inverse document frequency) is a commonly used weighting technique for information retrieval and text mining. By detecting the term frequency of keywords in the design requirement data, it can estimate the importance of the keywords.

[0031] Specifically, the calculation formula of the TF-IDF algorithm is as follows: ; where is the term frequency ratio of the keyword, is the number of times the keyword appears in the design requirement data, is a word in the design requirement data, is the sum of all words in the design requirement data.

[0032] S12: Import the basic furniture model into the design system based on the design requirement data, obtain the spatial data of the furniture layout, and set the initial dimensions of the basic furniture model according to the spatial data.

[0033] Extract the structural feature data from the design requirement data, perform three-dimensional construction on the structural feature data based on the B-Rep mechanism to obtain the initial geometric entity, extract the structural feature parameters of the furniture design from the design requirement data through keyword extraction, and fit the structural features such as points, lines, and surfaces in the structural feature data through the B-Rep mechanism to construct the initial geometric entity.

[0034] Obtain the spatial data of the furniture layout, and set the size threshold of the initial geometric entity according to the spatial data, so that the overall size of the initial geometric entity occupies about 80% of the layout space.

[0035] Extract the model data from the database according to the initial geometric entity, and adjust the size value of the model data based on the size threshold to generate the basic furniture model.

[0036] Further, the design requirement data is processed by semantic analysis to generate a keyword set, and the keywords related to the furniture category are screened as type identifiers through word frequency statistics. The model library matches the corresponding basic models according to the type identifiers. For example, when the type identifier is "bookcase", a model framework including shelf spacing and load-bearing parameters is called. The spatial data generates wall boundary information through coordinate transformation, and the initial size of the basic model is scaled proportionally within this boundary. For example, the height of the bookcase is set to 0.8 times the floor height to avoid wasting the top space. By type matching, it is ensured that the model structure meets the functional requirements, and then the size parameters are adjusted through spatial constraints, thereby realizing the adaptation of the furniture model to the spatial environment at the scheme generation stage.

[0037] Further, based on the B-Rep mechanism, the dimension data in the design requirement data is extracted, and the dimensions of the basic furniture model are set according to the dimension data obtained from the design requirement data, that is, the geometric entity generated by the B-Rep mechanism is used to adjust the basic furniture model, so that the initial size of the basic furniture model can meet the design requirements of the customer.

[0038] Through the above technical solutions, the present application realizes the accurate import of the basic furniture model and the reasonable setting of the initial size. By extracting the furniture type from the customer requirements, it is ensured that the imported basic model matches the actual needs of the customer. Combining the spatial data to preliminarily adjust the model size improves the feasibility of the design scheme. This method reduces unnecessary model adjustment steps, improves the design efficiency, and at the same time increases the customer's satisfaction with the initial design scheme.

[0039] In some of the above solutions of the present application, it is proposed to classify the design elements according to the design direction to generate an initial design scheme. However, in this process, due to the lack of classification rules matching the type of the basic furniture model, the classification direction of the design elements is not clear, and the classification results are disjoint from the actual application scenarios of the furniture, thereby affecting the rationality and feasibility of the subsequent combined generation scheme.

[0040] S13: Classify the design elements according to the design direction to obtain several groups of design element groups.

[0041] Specifically, the classification of several design elements according to the design direction to obtain several groups of design element groups includes: Set classification rules according to the type of the basic furniture model, and divide several design directions according to the classification rules. When the basic furniture model is a sofa, the classification rules include two design directions: size adaptability and style matching degree. When the basic furniture model is a wardrobe, the classification rules include two design directions: structural stability and storage efficiency. The design directions are divided into independent categories, and each design direction corresponds to different furniture functional attributes. The design elements are classified into the corresponding design direction groups. For example, color and texture elements are classified into the style matching degree group, and board thickness and connection method are classified into the structural stability group. A data association is formed between the classification rules and the design elements extracted by semantic analysis. For example, the material elements corresponding to the keyword "modern minimalist" are classified into the style matching degree group through keyword matching.

[0042] Classify several design elements based on several of the said design directions to obtain several groups of design element groups. For example, design elements related to dimensions such as length, width, and height can be classified into the dimension direction group, and several sets of data with different dimension ratios can be set according to the model design of the basic furniture model; design elements related to appearance such as color, material, and texture can be classified into the style direction group, and several appearance design schemes can be automatically generated by integrating existing furniture appearance design elements to meet the design needs of customers; design elements related to usage experience such as backrest angle and seat cushion softness can be classified into the function direction group. Thus, several groups of design element groups are obtained. Based on the classification rules set according to the type of the basic furniture model, the classification direction of the design elements is made clear and systematic, avoiding the problem that the classification result is out of touch with the actual application scenario of the furniture. At the same time, by grouping the design elements in a targeted manner, the rationality and feasibility of the subsequent combined generation scheme are improved, providing a furniture design and production scheme that better meets the actual needs of customers.

[0043] S14: Adjust the initial dimensions of the basic furniture model based on several groups of design element groups to generate several initial design schemes.

[0044] The combination of several groups of design element groups to generate several initial design schemes includes: Extract one design element from each design element group, and form several initial design schemes by combining the design elements extracted from several groups of design element groups. Extract the design element combination from several groups of design element groups, so that several initial design schemes can cover several design elements of the customer and can simulate and combine the design styles required by the customer, in order to generate a design model, so that the customer can intuitively obtain the design effect of the furniture design model.

[0045] The permutation and combination calculation formula for several initial design schemes is: ; Among them, For all cases of extracting one design element from the first group of design elements, For all cases of extracting one design element from the m-th group of design elements, that is, a number of initial design schemes are formed by combining and arranging based on the design elements of a number of groups of design element groups, realizing the exhaustive combination operation of multi-dimensional design elements and accurately quantifying the generation scale of design schemes.

[0046] Furthermore, based on the classification groups and the method of permutation and combination, the problems of omission or repetition that may occur in the manual combination process are avoided, enabling the system to quickly construct a complete set of schemes under limited resources, significantly improving the scheme generation efficiency, and providing a traceable quantitative basis for subsequent scheme screening.

[0047] Specifically, the size of the basic furniture model is adjusted according to several of the said design element groups, so that the size of the basic furniture model can meet the design requirements of customers and can reflect the design requirements of customers.

[0048] S15: Extract the process parameters of the initial design scheme, combine with the basic furniture model for production feasibility screening analysis, and output the furniture design and production scheme that meets the production feasibility.

[0049] Specifically, outputting several furniture design and production schemes includes: sequentially marking the design key points of several initial design schemes, and matching the processing methods according to the design key points; combining with the basic furniture model to detect the processing methods, and detecting the production feasibility of the initial design scheme.

[0050] Among them, the design key point marking converts the key features in the scheme into recognizable data tags through a structured annotation method. For example, the type of connecting parts is marked as metal mortise and tenon or plastic buckle. The matching of processing methods is realized based on a preset process database, which stores the types of processing equipment and process flows corresponding to different design parameters. The production feasibility detection is performed by parameter comparison. For example, the design size is compared with the assembly gap of the basic model, and it is determined to be infeasible when the dimensional tolerance exceeds ±2mm.

[0051] Specifically, in the initial design scheme, the physical parameters corresponding to each design element are extracted and converted into a standard data format. Combining with the processing requirements of the design key points, it is detected whether there are conflicts in the processing methods of multiple design key points, that is, the combination feasibility between each design element is detected to avoid the occurrence of unprocessable design schemes.

[0052] As a preferred embodiment, the solution of the present application is specifically implemented as follows: During the initial design solution detection and screening stage, the design points in each initial solution are first parameterized based on preset structured tags, for example, the modeling features are marked as surface parameters, and the connection structure is marked as mortise and tenon parameters. Subsequently, the processing methods corresponding to each design point are matched through the process database, where the mortise and tenon parameters are automatically associated with the CNC engraving process, and the surface parameters are associated with the three-dimensional hot bending process. Finally, the structural parameter library of the basic furniture model is called to verify the matching degree between the engraving tool path and the model joint surface, detect the inclusion relationship between the hot bending mold size and the model surface, and eliminate solutions with interference or tolerance exceeding the limit.

[0053] The above technical solution effectively solved the problem of unimplementable solutions due to the disconnection between design parameters and production processes. Digital representation of design elements was achieved through structured markup. Automatic matching of the process database was used to ensure compatibility between processing methods and production equipment. Basic model parameters were used to verify process feasibility. Ultimately, an optimized solution was selected that not only met customer customization requirements but could also be directly implemented on the production line, avoiding the design rework problem caused by the lack of process verification in traditional solutions.

[0054] The intelligent furniture design and production method works by obtaining customer design requirement data, performing semantic analysis on the data using a semantic analysis model, and extracting design elements. The semantic analysis model can utilize natural language processing technology, combined with a professional vocabulary in the field of furniture design, to accurately identify and extract key design elements.

[0055] Next, import the basic furniture model into the design system to obtain the spatial data for the furniture layout. This spatial data can include information such as room dimensions and door and window locations. The initial dimensions of the basic furniture model are automatically set based on this spatial data to ensure the model matches the actual space.

[0056] The extracted design elements are then classified by design direction, yielding several groups of design elements. Design direction can include dimensions such as material, style, and function. Through orthogonal classification methods, independent feature dimensions are established, providing a structured data foundation for subsequent combination.

[0057] Based on the design element groups, the system automatically combines and generates several initial design solutions. The combination process uses multi-dimensional feature cross-validation to achieve comprehensive coverage and innovative combinations of design elements.

[0058] Finally, the initial design is tested and screened, and a furniture design and production plan is output. This testing process, combined with the production process parameter library, verifies the production feasibility of the plan, ensuring that the output plan meets both customer needs and manufacturing requirements.

[0059] An embodiment of the present invention provides an intelligent furniture design and production method. By semantically analyzing the design requirements input by the customer, extracting the design elements of the customer's design requirement data, combining the design elements with the spatial model data, automatically analyzing the customer's design requirements, intelligently generating multiple furniture design schemes and detecting the production feasibility, it solves the problem of low efficiency of traditional customization relying on manual labor, has the advantages of improving furniture customization efficiency, reducing labor costs and meeting the personalized needs of customers, and realizes the intelligent full-automatic design of furniture design and production.

[0060] Embodiment 2: Figure 2 The schematic structural diagram of the intelligent furniture design and production system in the embodiment of the present invention is shown. The intelligent furniture design and production system is used to execute the intelligent furniture design and production method. The production system includes: Data acquisition module 10: It is used to collect the design requirement data of the customer and the spatial data of furniture layout.

[0061] Specifically, the customer fills in the furniture design requirements through an online form, and the system obtains the design requirement data. Among them, the form file contains pre-defined parameter category fields, including style selection items, material option lists, size range input boxes, and function requirement check boxes. Each parameter category field is set with a mandatory verification rule. When the customer has not completed the specified field, the system automatically blocks the form submission operation. The interactive interface of the form file integrates a drop-down menu control and a numerical slider control. Among them, the drop-down menu control limits the style options to three preset types: modern, Chinese, and European. The data storage format of the form file adopts a two-dimensional array structure. The row data corresponds to the single parameter value input by the customer, and the column data corresponds to the parameter category field identifier, so that the data analysis module 30 can perform semantic recognition and analysis on the design requirement data.

[0062] Model processing module 20: It is used to import the basic furniture model according to the spatial data of furniture layout and adjust the basic furniture model according to the design requirement data.

[0063] Specifically, according to the design requirement data filled in by the customer, the spatial dimensions of furniture layout are obtained, so as to set the basic dimensions of the basic furniture model according to the dimensions of furniture placement, and ensure that the furniture design model can meet the furniture placement requirements.

[0064] Data analysis module 30: It is used to extract design elements according to the design requirement data and generate several initial design schemes.

[0065] The design requirement data is analyzed through a semantic analysis model to extract relevant design elements. A natural language processing algorithm optimized for the furniture design field is used to segment and part-of-speech tag the requirement data to extract key design elements.

[0066] In the preprocessing stage, the Jieba algorithm is used to segment continuous natural language text into independent word units, solving the problem of fuzzy word boundaries. During the word segmentation process, the segmentation granularity can be adjusted based on dictionary expansion or custom word libraries. For example, the compound word "Nordic style" can be recognized as a whole unit to improve the accuracy of design styles.

[0067] The weights of words are calculated through the TF-IDF algorithm. The term frequency ratio is determined by the ratio of the number of times a word appears in a single document to the total number of words in the document. The inverse document frequency is calculated by taking the logarithm of the ratio of the total number of documents in the corpus to the number of documents containing the word. This not only retains the key information in the customer's personalized expressions but also eliminates the interference of common vocabulary on feature extraction, effectively improving the extraction accuracy of design elements.

[0068] Data detection module 40: Used to conduct production feasibility analysis on a number of initial design schemes and organize and output furniture design production schemes.

[0069] Mark the design key points for a number of initial design schemes in sequence, match the processing methods according to the design key points, and based on the initial design schemes formed by combining multiple design key points, match the processing methods according to the type of design key points, and combine with the basic furniture model to detect the production feasibility of the initial design scheme. Detect whether there are conflicting situations among the processing methods of a number of design key points for parameters such as the material and size of the basic furniture model, so as to ensure the process feasibility of the furniture design production scheme. Finally, filter out the optimized scheme that not only meets the customer's customization requirements but can also be directly imported into the production line for implementation, avoiding the design rework problem caused by the lack of process verification in traditional schemes.

[0070] Specifically, in the initial design scheme, the physical parameters corresponding to each design element are extracted and converted into a standard data format. For example, the board thickness is marked as 18mm ± 0.5mm. During the processing method matching process, the processing precision parameters of the numerical control cutting machine are automatically compared with the dimensional tolerance requirements of the design key points, and a process adjustment instruction is triggered when the equipment precision cannot meet the tolerance requirements. In the production feasibility detection stage, the load-bearing structure parameters of the basic furniture model are called. For example, the load-bearing capacity of the shelf support beam is compared with the estimated load in the design scheme, and a structure strengthening suggestion is generated when the load exceeds 85% of the support capacity. Through triple data verification with the production process database and the basic model parameter database, the schemes with process conflicts or structural defects are effectively screened out, and the final output customized scheme can be directly connected to the processing parameter settings of the production line.

[0071] An embodiment of the present invention provides an intelligent furniture design and production system. By performing semantic analysis on the design requirements input by the customer, extracting the design elements of the customer's design requirement data, combining the design elements with the spatial model data, automatically analyzing the customer's design requirements, intelligently generating multiple furniture design schemes and detecting the production feasibility, the problem of low efficiency of traditional customization relying on manual labor is solved. It has the advantages of improving the furniture customization efficiency, reducing the labor cost and meeting the personalized needs of customers, and realizing the intelligent full-automatic design of furniture design and production.

[0072] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the relevant hardware through a program. The program can be stored in a computer-readable storage medium, and the storage medium can include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, etc.

[0073] In addition, the above has introduced in detail the intelligent furniture design and production method and system provided by the embodiments of the present invention. Specific examples have been used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. An intelligent furniture design and production method, characterized in that, The intelligent furniture design and production method includes: Obtain the design requirement data of the customer, perform semantic analysis on the design requirement data based on the semantic analysis model, and extract the design elements of the design requirement data; Import the basic furniture model into the design system based on the design requirement data, obtain the spatial data of the furniture layout, and set the initial dimensions of the basic furniture model according to the spatial data; Classify several design elements according to the design direction to obtain several groups of design element groups; Adjust the initial dimensions of the basic furniture model based on several groups of design element groups to generate several initial design schemes; Extract the process parameters of the initial design scheme, combine with the basic furniture model to conduct a production feasibility screening analysis, and output a furniture design and production scheme that meets the production feasibility.

2. The intelligent furniture design and production method according to claim 1, characterized in that, The obtaining of the design requirement data of the customer, performing semantic analysis on the design requirement data of the customer based on the semantic analysis model, and extracting the design elements of the design requirement data of the customer includes: Obtain the login signal of the furniture design system, and call and run the visual table file based on the login signal; Obtain the information input signal based on the visual table file, and extract the input information content according to the information input signal to generate the design requirement data.

3. The intelligent furniture design and production method according to claim 2, characterized in that The performing semantic analysis on the design requirement data of the customer based on the semantic analysis model, and extracting the design elements of the design requirement data of the customer includes: Preprocess the design requirement data through the Jieba algorithm, mark the keyword phrases in the design requirement data, and perform word frequency statistics on the marked keyword phrases based on the TF-IDF algorithm.

4. The intelligent furniture design and production method according to claim 3, wherein, The calculation formula of the TF-IDF algorithm is: ； Among them, is the word frequency ratio of the keyword, is the number of times the keyword appears in the design requirement data, is a word in the design requirement data, is the sum of the words in the design requirement data.

5. The intelligent furniture design and production method according to claim 1, characterized in that The importing the basic furniture model into the design system based on the design requirement data, obtaining the spatial data of the furniture layout, and setting the initial dimensions of the basic furniture model according to the spatial data includes: Extract the structural feature data from the design requirement data, perform three-dimensional construction on the structural feature data based on the B-Rep mechanism to obtain the initial geometric entity; Obtain the spatial data of the furniture layout, and set the dimension threshold of the initial geometric entity according to the spatial data; Extract the model data from the database according to the initial geometric entity, and adjust the dimension value of the model data based on the dimension threshold to generate the basic furniture model.

6. The intelligent furniture design and production method according to claim 1, characterized in that The classifying several design elements according to the design direction to obtain several groups of design element groups includes: Set the classification rules according to the type of the basic furniture model, and divide several design directions according to the classification rules; Classify several design elements based on several design directions to obtain several groups of design element groups.

7. The intelligent furniture design and production method according to claim 1, characterized in that The adjusting the initial dimensions of the basic furniture model based on several groups of design element groups to generate several initial design schemes includes: Extract one design element from each design element group, and adjust the initial dimensions of the basic furniture model based on the extracted design element to obtain the furniture adjustment model; Sort out several design elements and the furniture adjustment model and save them as the initial design scheme.

8. The intelligent furniture design and production method according to claim 7, wherein, The permutation and combination calculation formula of several initial design schemes is: ； Among them, represents all cases of extracting one design element from the first group of design elements, represents all cases of extracting one design element from the m-th group of design elements.

9. The intelligent furniture design and production method according to claim 1, wherein, The process parameters for extracting the initial design scheme are combined with the basic furniture model for production feasibility screening analysis, and the furniture design and production scheme that meets the production feasibility includes: Mark the design key points for several initial design schemes in sequence, and match the processing methods according to the design key points; Combine the basic furniture model to detect the processing methods and detect the production feasibility of the initial design scheme.

10. An intelligent furniture design and production system, characterized in that, The intelligent furniture design and production system is used to execute the intelligent furniture design and production method as described in any one of claims 1 to 9. The production system includes: Data acquisition module: used to acquire the design requirement data of customers and the spatial data of furniture layout; Model processing module: used to import the basic furniture model according to the spatial data of furniture layout and adjust the basic furniture model according to the design requirement data; Data analysis module: used to extract design elements according to the design requirement data and generate several initial design schemes; Data detection module: used to conduct production feasibility analysis on several initial design schemes and sort out and output the furniture design and production scheme.

Images