Product model generation method and device, electronic equipment and readable storage medium

Abstract

The invention relates to a product model generation method and device, electronic equipment and a readable storage medium. The method comprises the following steps: obtaining product key elements from obtained product demand information, and constructing structured product demand data according to the product key elements; matching a target reference model from a preset reference model database based on the structured product demand data; matching a target reference parameter instruction from a preset reference instruction database according to the target reference model and historical design data corresponding to the target reference model; according to a preset parameter recommendation neural network, performing parameter mapping based on the structured product demand data, the target reference model and the reference parameter instruction set, and generating a target design instruction set; and generating a product model based on a parameter driving technology and the target design instruction set to obtain a first target product model. According to the scheme provided by the invention, product model generation can be automatically driven in a whole process, the design efficiency and the result consistency are improved, and then the demand of quickly responding to the market is met.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of product design and modeling, and particularly relates to a product model generation method and device, electronic equipment and a readable storage medium. BACKGROUND

[0002] In the field of non-standard mechanical equipment, parameterized design technology has been widely used, which significantly improves the design efficiency and consistency of specific product series.

[0003] In related technologies, engineers usually need to manually analyze user requirements, set or adjust design parameters according to experience, and drive the system to iterate and optimize. However, the above method is time-consuming and laborious, and the efficiency is low when facing the increasingly diversified and personalized user order requirements. In addition, the design quality is closely related to the personal experience and state of the engineer, which is difficult to realize standardization and scaling, and it is difficult to meet the needs of rapid market response. SUMMARY

[0004] To solve or partially solve the problems in the related art, the present application provides a product model generation method, device, electronic equipment and readable storage medium, which can automatically drive the product model generation in the whole process, thereby effectively shortening the product design cycle, improving the design efficiency and result consistency, and further meeting the needs of rapid market response in the product model generation process.

[0005] The first aspect of the present application provides a product model generation method, comprising obtaining product key elements from the obtained product requirement information, and constructing structured product requirement data according to the product key elements; matching a target reference model from a preset reference model database based on the structured product requirement data; matching a target reference parameter instruction from a preset reference instruction database according to the target reference model and historical design data corresponding to the target reference model; performing parameter mapping based on a preset parameter recommendation neural network, the structured product requirement data, the target reference model and the reference parameter instruction set to generate a target design instruction set; generating a product model based on parameter-driven technology and the target design instruction set to obtain a first target product model.

[0006] In some embodiments, the product key elements are obtained from the obtained product requirement information, and the structured product requirement data is constructed according to the product key elements, comprising: performing named entity recognition on the obtained product requirement information based on a semantic analysis model to obtain entity elements within a preset range; According to the entity elements, a logical relationship tree between the entity elements is established based on semantic role labeling rules, and structured product requirement data is generated according to the logical relationship tree.

[0007] In some embodiments, the matching of the target benchmark model from the preset benchmark model database based on the structured product requirement data comprises: Based on the structured product requirement data, a preset benchmark model database is called for product series similarity matching, and a matching result of the product series similarity matching is obtained. Based on the matching result of the product series similarity matching and based on a preset similarity threshold, a target benchmark model is determined from the preset benchmark model database. In some embodiments, the determination of the target benchmark model from the preset benchmark model database based on the matching result of the product series similarity matching and based on a preset similarity threshold comprises: Based on the matching result of the product series similarity matching and based on a preset similarity threshold, a plurality of recommended models are determined from the preset benchmark model database. According to the received determination instruction, a target benchmark model is determined from the plurality of recommended models.

[0008] In some embodiments, the generation of the product model based on the parameter-driven technology and the target design instruction set comprises: From a preset basic template database, basic model data associated with the target benchmark model is obtained. Based on the parameter-driven technology and the target design instruction set, the basic model data is adaptively modified to obtain target model data. According to the target model data, model generation is performed to obtain a first target product model.

[0009] In some embodiments, the method further comprises: Based on the received structured feedback data, the first target product model is iteratively optimized to obtain a second target product model.

[0010] The second aspect of the present application provides a product model generation device, comprising: A product requirement extraction module is configured to obtain product key elements from obtained product requirement information, and construct structured product requirement data according to the product key elements. A benchmark model matching module is configured to match a target benchmark model from a preset benchmark model database based on the structured product requirement data. The reference parameter instruction matching module is configured to match a target reference parameter instruction from a preset reference instruction database according to the target reference model and first historical design data corresponding to the target reference model. The design instruction set acquisition module is configured to perform parameter mapping based on a preset parameter recommendation neural network, the structured product requirement data, the target reference model, and the reference parameter instruction set, to generate a target design instruction set. The model generation module is configured to generate a product model based on a parameter driving technology and the target design instruction set, to obtain a first target product model.

[0011] In some embodiments, the apparatus further includes: The model optimization module is configured to iteratively optimize the first target product model based on the received structured feedback data, to obtain a second target product model.

[0012] The third aspect of the present application provides an electronic device, including: a processor; and a memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the method as described above.

[0013] The fourth aspect of the present application provides a computer-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method as described above.

[0014] The technical solution provided by the present application can include the following beneficial effects: The technical solution of the present application, by automatically extracting key elements from product requirement information and constructing structured product requirement data after obtaining product requirement information, matching a target reference model and related historical design data based on structured data, performing precise parameter mapping to generate a target design instruction set using a parameter recommendation neural network, and finally realizing automatic generation of a product model based on a parameter driving technology, can effectively shorten the product design cycle, effectively reduce the dependence on individual experience and the subjective bias of manual screening, improve design efficiency and result consistency, and thus make the product model generation process meet the demand for rapid market response.

[0015] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0016] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description thereof taken in conjunction with the accompanying drawings, in which like reference characters designate like elements throughout the several views.

[0017] Figure 1 is a flowchart of a product model generation method according to an embodiment of the present application; Figure 2 is another flowchart of a product model generation method according to an embodiment of the present application; Figure 3 is a structural diagram of a product model generation apparatus according to an embodiment of the present application; Figure 4 is another structural diagram of a product model generation apparatus according to an embodiment of the present application; Figure 5 is a structural diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] Embodiments of the present application will be described more fully hereinafter with reference to the accompanying drawings, in which embodiments of the application are shown. This application may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art.

[0019] The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0020] It is to be understood that the singular forms "a", "an", and "the" include plural referents unless the context clearly dictates otherwise. It is to be further understood that the terms "comprise", "comprising", "comprises", "including", "includes" or "contain" or "containing" when used in this specification, specify the presence of stated features, integers, steps, operations, elements, or components but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or groups thereof.

[0021] In the traditional existing parametric design process for non-standard mechanical equipment, the customized requirements submitted by users usually contain unstructured natural language descriptions, requiring engineers to manually parse the requirement text to extract key elements such as functions, performance, and application scenarios. Due to the lack of an automated mechanism for structuring requirements, the manual parsing process is easily affected by subjective experience, resulting in insufficient completeness and accuracy in the extraction of requirement elements. When matching historical benchmark models, relying on manual experience to screen similar product lines makes it difficult to quantitatively evaluate the compatibility of the model with the requirements, and is prone to matching deviations. The parameter instruction generation stage requires engineers to manually adjust the design parameters based on historical data. The relevance of the parameter adjustment strategy to the current demand scenario depends on the accumulation of individual experience, resulting in low efficiency in the generation of design instruction sets and the risk of parameter redundancy or missing parameters.

[0022] In response to the above problems, an embodiment of the present application provides a product model generation method that can automatically drive product model generation throughout the entire process, thereby effectively shortening the product design cycle, improving design efficiency and result consistency, and enabling the product model generation process to meet the needs of rapid response to the market.

[0023] The technical solutions of the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0024] Figure 1 It is a flowchart of the product model generation method shown in an embodiment of the present application.

[0025] See also Figure 1 The product model generation method of the present application includes: S110, obtaining product key elements from the obtained product demand information, and constructing structured product demand data based on the product key elements.

[0026] In this step, product key elements are extracted from the product demand information received from the front end, and structured product demand data that matches user needs is constructed based on the extracted product key elements.

[0027] The product requirement information may be product requirement description text information input by the user through a graphical user interface.

[0028] Key product elements can refer to core entity elements such as functions, performance, and application scenarios extracted from product demand information. For example, a semantic analysis model can be used to perform named entity recognition and semantic role labeling on product demand information, thereby converting unstructured product demand information into structured product demand data that can be machine-readable.

[0029] S120 , matching a target benchmark model from a preset benchmark model database based on the structured product demand data.

[0030] In this step, after obtaining the structured product demand data, the target reference model data that matches the structured product demand data is matched through the pre-stored model data in the preset reference model data.

[0031] It should be understood that the target reference model can be used to show the user in the front end, and when the target reference model is determined and meets the user demand, the related parameters of the subsequent target product model are further designed according to the same or similar user demand as the target reference model, which effectively improves the fitting degree of the subsequent target product model and the user demand.

[0032] Among them, the target reference model can refer to the preset product model matched with the user demand corresponding to the structured product demand data.

[0033] Among them, the target reference model can be filtered and matched from the reference model database through similarity calculation. S130, according to the target reference model and the historical design data corresponding to the target reference model, the target reference parameter instruction is matched from the preset reference instruction database.

[0034] In this step, according to the obtained target reference model, the pre-stored historical design data corresponding to the target reference model is obtained, and the associated target reference parameter instruction is matched from the preset reference instruction database.

[0035] Among them, the historical design data can be a set of historical design data associated with the target reference model. The data type of the historical design data can include but is not limited to: historical design cases, industry specifications, material properties.

[0036] S140, according to the preset parameter recommendation neural network, the parameter mapping is performed based on the structured product demand data, the target reference model and the reference parameter instruction set, and the target design instruction set is generated.

[0037] In this step, the preset parameter recommendation neural network is used to perform parameter mapping based on the structured product demand data, the target reference model and the reference parameter instruction set, and generate the target design instruction set that meets the current user demand.

[0038] Among them, the preset parameter recommendation neural network can refer to a machine learning model used to generate design instructions and obtained through pre-construction and pre-training. Among them, the historical design data can be used to train the neural network to obtain the preset parameter recommendation neural network, so that the preset parameter recommendation neural network can automatically generate the design instruction set that meets the current demand through parameter mapping based on the input structured product demand data, target reference model and reference parameter instruction set.

[0039] The target design instruction set can refer to a same set of predefined rules and algorithms for controlling the relationship between parameters. The target design instruction set can be automatically executed by a modeling system or software.

[0040] For example, the target design instruction set can include the following: Geometric constraint: "cylinder height = diameter x 2"; Performance constraint: "material thickness >= load calculation value x safety factor"; Logical rule: "if product type = outdoor equipment, then protection level >= IP67".

[0041] S150, generating a product model based on the parameter-driven technology and the target design instruction set, to obtain a first target product model.

[0042] In this step, a product model that meets the user's requirements is generated based on the parameter-driven technology and the obtained target design instruction set, to obtain a first target product model.

[0043] It should be understood that the first target product model can include, but is not limited to, at least one of product BOM structure data, product modeling data, and engineering drawing data. The first target product model incorporates the rules or algorithms corresponding to the target design instruction set.

[0044] The parameter-driven technology can refer to a technology for automatically modifying model parameters based on a design instruction set. For example, the base model can be adaptively adjusted by calling a parameterized modeling tool.

[0045] In this embodiment, the product model generation method of the present application automatically extracts key elements from product requirement information and constructs structured product requirement data based on the obtained product requirement information. The target reference model and related historical design data are matched based on the structured data, and the target design instruction set is generated by precise parameter mapping using a parameter recommendation neural network. Finally, the product model is automatically generated based on the parameter-driven technology. Through the above product model generation method, the product model is generated through full-process automation driving, thereby effectively shortening the product design cycle, effectively reducing the dependence on individual experience and the subjective bias of manual screening, improving design efficiency and result consistency, and thus making the product model generation process meet the needs of rapid market response.

[0046] Figure 2 Another flowchart of the product model generation method according to an embodiment of the present application is shown.

[0047] Referring to Figure 2 The product model generation method of the present application includes: S210: Perform named entity recognition on the acquired product demand information based on a semantic analysis model to obtain entity elements within a preset range.

[0048] In this step, named entity recognition is performed on the obtained product demand information by completing the pre-trained semantic analysis model to obtain entity elements that meet the preset range.

[0049] Among them, the semantic analysis model can be a natural language processing model based on deep learning. The natural language processing model can process the input product requirement text, thereby identifying entity elements within a preset range by understanding the contextual semantics of the text. Of course, the semantic analysis model can also adopt AI models in related technologies. For example, the semantic analysis model can adopt the BERT (Bidirectional Encoder Representations from Transformers) model or the GPT (Generative Pre-trained Transformer) model, which is not limited here.

[0050] The preset scope of the entity elements may include at least functions, performance, and application scenarios. Functions may refer to the core roles or tasks undertaken by the product, such as load-bearing support, material handling, material cutting, etc. Performance may refer to the quantitative or qualitative levels achieved by the product when achieving its functions, such as load-bearing capacity, operating speed, cutting accuracy, etc. Application scenarios may refer to the specific use environment, industry, or working conditions targeted by the product, such as industrial automation production lines, aerospace fields, and automobile manufacturing.

[0051] As an example, for the product demand information corresponding to industrial robots, the semantic analysis model can identify "welding" as a functional entity, "cutting accuracy 0.05mm" as a performance entity, and "automobile manufacturing" as an application scenario entity.

[0052] S220 , establishing a logical relationship tree between entity elements based on semantic role labeling rules according to the entity elements, and generating structured product demand data according to the logical relationship tree.

[0053] In this step, according to the acquired entity elements and based on the pre-set semantic role labeling rules, a logical relationship tree corresponding to the preset relationship types between the entity elements is established, and then structured product demand data that can be directly processed by the computer is generated based on the logical relationship tree.

[0054] Among them, the semantic role labeling rules can be configured to identify the grammatical relationships and semantic roles between entity elements.

[0055] For example, in the requirement of "cutting in a high-temperature environment to achieve a cutting accuracy of 5 microns", it can be identified that "cutting" is the action subject, "5-micron cutting accuracy" is the aforementioned limit condition corresponding to the action subject, and "high-temperature environment" is the application scenario corresponding to the action subject and the limit condition.

[0056] The logical relationship tree can be used to store the preset relationships between entities through a tree data structure. The root node of the logical relationship tree can be a core function, the child nodes of the logical relationship tree can be performance parameters and application scenarios, and the edges of the logical relationship tree represent the logical association between the core function, the performance parameters, and the application scenarios. The structured product requirement data can be in a standardized format that can be directly processed by a computer, such as JSON or XML.

[0057] In this step, based on the structured product requirement data, a preset benchmark model database is called to perform product series similarity matching, and a matching result of the product series similarity matching is obtained.

[0058] In this step, after obtaining the structured product requirement data, a preset benchmark model database that stores historical model data is called, and historical model data corresponding to the structured product requirement data is matched from the preset benchmark model database based on a similarity algorithm as a matching result.

[0059] The product series similarity matching process can include the following steps: The functional elements, performance elements, and application scenarios in the structured product requirement data are converted into multi-dimensional vectors, and the obtained multi-dimensional vectors are compared with corresponding feature vectors in the historical model data in the preset benchmark model database through a cosine similarity algorithm to output a similarity score.

[0060] The similarity score can be in numerical or percentage format.

[0061] The logical relationship tree in the structured product requirement data can be used to provide hierarchical weight distribution basis for similarity matching. For example, the functional element weight accounts for 60%, the performance element accounts for 30%, and the application scenario accounts for 10%. In this way, the relevance of the matching criteria in the matching process and the product technical characteristics can be ensured.

[0062] S240, based on the matching result of the product series similarity matching and based on a preset similarity threshold, a target benchmark model is determined from the preset benchmark model database.

[0063] In this step, according to the matching result of the product series similarity matching and the preset similarity threshold, a target benchmark model is determined from the preset benchmark model database.

[0064] The matching result of the product series similarity matching can correspond to all models in the preset reference model database. That is, the matching result of the product series similarity matching can have a similarity matching score corresponding to all models in the preset reference model database.

[0065] For example, the preset similarity threshold can be set to 0.8. After the matching result of the product series similarity matching, the reference models with a similarity score greater than or equal to 0.8 are screened out as candidate target reference models, and finally the model with the highest similarity is selected from these candidate models as the final target reference model.

[0066] In some embodiments, the matching process of obtaining the target reference model can include: S241, determining a plurality of recommended models from the preset reference model database based on a preset similarity threshold.

[0067] In this step, a plurality of recommended models of a preset number or meeting a preset condition are determined from the preset reference model database based on the obtained matching result of the product series similarity matching and the preset similarity threshold.

[0068] The plurality of recommended models can meet a preset association condition. The preset association condition can include at least one of similar functions, similar target user groups, similar core technologies, and the same product category. It should be understood that each of the similar functions, the similar target user groups, the similar core technologies, and the same product category can be applied alone or in combination. Of course, the preset association condition can also include other adaptive setting conditions, which are not limited here.

[0069] The similar function condition can be determined by comparing the function keywords extracted by the semantic matching algorithm, such as calculating the similarity between “precision transmission” and “power transmission”. The similar target user group condition can be determined by clustering analysis based on user portrait labels, such as distinguishing between medical device user groups and industrial device user groups. The similar core technology condition can be determined by calculating the cosine similarity of the technology feature vector, such as comparing the technical parameters of hydraulic drive and electric drive. The same product category condition can be determined by matching the pre-set classification code, such as classifying “industrial robots” and “service robots” into different product categories.

[0070] It should be understood that the plurality of recommended models can be product models of the same series or similar series. The same series or similar series satisfy the pre-associated condition, and the plurality of recommended models are determined from the product models of the same series or similar series that satisfy the pre-associated condition under the premise of meeting the preset similarity threshold. For example, variant products of different stroke specifications in the same series of hydraulic cylinder models.

[0071] As an example, the preset similarity threshold is set to 0.8, and the number of models is 5. Based on the preset similarity threshold and the preset association condition, 5 recommended models are selected from the preset reference model database, wherein the preset association condition includes similar functions, similar target user groups, similar core technologies, and the same product category, and respectively corresponds to weights 0.4, 0.3, 0.2, 0.1. The selection process is as follows: First, by comparing the matching degree of the function description keywords, the model that meets the similar function condition is selected. For example, if the target product demand contains the "automatic production line" function, the model with the same or similar function description is selected.

[0072] Second, on the basis of the first step, the user portrait features are compared to select the model that meets the similar target user group condition. For example, if the target product is aimed at the "manufacturing enterprise" user group, the model suitable for the same or similar user group is selected.

[0073] Third, on the basis of the second step, the technology field classification is compared to select the model that meets the similar core technology condition. For example, if the target product involves "machine vision" technology, the model that applies the same or similar core technology is selected.

[0074] Fourth, on the basis of the third step, the product category is compared to select the model that meets the same product category condition. For example, if the target product belongs to the "industrial robot" category, the model that belongs to the same category is selected.

[0075] Fifth, on the basis of the fourth step, the comprehensive matching score of the selected model is calculated according to the weight of the preset corresponding association condition, and the model whose comprehensive matching score exceeds the preset similarity threshold 0.8 and the number of which is more than 5 is selected as the recommended model.

[0076] It can be known that by setting the preset association condition and the preset similarity threshold, the accuracy and efficiency of the target reference model matching can be further improved, and a more reliable and applicable basis is provided for subsequent product model generation.

[0077] Among them, multiple recommended models can be displayed in the same interactive interface at the same time, so that the user can obtain information of multiple recommended models from the same interactive interface.

[0078] S242, according to the received determination instruction, determine the target reference model from the multiple recommended models.

[0079] In this step, the determination instruction received through the interactive interface is used to determine the target reference model from the multiple recommended models according to the determination instruction.

[0080] It should be understood that the determination instruction can be a user check operation on the candidate model list or a click confirmation action on any model from the interactive interface.

[0081] As an example, when the user demand corresponds to a 50-ton hydraulic machine, according to the corresponding structured product demand data, the reference model database is preliminarily screened through a preset similarity threshold, five reference models of the same series with a working pressure range of 45-55 tons are screened out, and then the recommended model set is pushed to the interactive interface of the user terminal for visual display. After receiving the user's selection operation on a specific model, the model corresponding to the selection operation is determined as the target reference model. Through the above-mentioned manner, the user decision-making link is introduced, and the final determination of the candidate model is made through the artificial confirmation instruction, which can effectively make up for the possible semantic understanding deviation of pure algorithm matching.

[0082] S250, according to the target reference model and the historical design data corresponding to the target reference model, matching the target reference parameter instruction from the preset reference instruction database.

[0083] In this step, according to the obtained target reference model, the pre-stored historical design data corresponding to the target reference model is obtained, and the associated target reference parameter instruction is matched from the preset reference instruction database.

[0084] S260, according to the preset parameter recommendation neural network, based on the structured product demand data, the target reference model and the reference parameter instruction set, performing parameter mapping to generate a target design instruction set.

[0085] In this step, the preset parameter recommendation neural network is used to perform parameter mapping based on the structured product demand data, the target reference model and the reference parameter instruction set to generate a target design instruction set that meets the current user demand.

[0086] In some embodiments, the preset parameter recommendation neural network can be obtained by: pre-training the preset recommendation neural network according to all reference models in the preset reference model database, historical design data corresponding to all reference models and the preset reference instruction database, to obtain a trained preset recommendation neural network.

[0087] It can be understood that through the pre-training process of multi-dimensional training data, the obtained preset recommendation neural network can complete the establishment of the end-to-end mapping relationship from product demand features to parameter instruction sets. For example, when the input structured demand data contains "high torque, low speed", the preset recommendation neural network can automatically generate a matched gear modulus and reduction ratio parameter combination, and recommend the optimal value. Therefore, the instruction set generated by the preset parameter recommendation neural network can adapt to the optimal parameter recommendation demand in different scenarios. The plurality of benchmark models in the benchmark model database can cover different product series, for example, including at least three core models of mechanical structures, each model corresponding to a different range of functional parameters.

[0088] The historical design data corresponding to all benchmark models can include parameter adjustment records in a preset number of actual design cases corresponding to all benchmark models, for example, the correspondence between material strength parameters and load conditions. It should be understood that the user's preference for parameter adjustment in actual application can be analyzed through the historical design data corresponding to all benchmark models.

[0089] The instruction set in the preset benchmark instruction database can be stored according to an industry standard format. For example, all instruction sets in the benchmark instruction database are stored by including an instruction template with ISO standard encoding.

[0090] During the pre-training process, the neural network optimizes the weight parameters through a back propagation algorithm. For example, the training period can be set to 500 rounds, and the loss function adopts a combined form of mean square error and cross entropy for training optimization.

[0091] S270, obtaining the basic model data associated with the target benchmark model from the preset basic template database.

[0092] In this step, when the target benchmark model is determined, the basic model data with the same topological structure as the target benchmark model is matched from the preset basic template database.

[0093] The preset basic template database can include basic model data of multiple product series, wherein each basic model data is associated with one or more target benchmark models.

[0094] The preset basic template database can establish the association between the basic model data and the target benchmark model through a hash index or a metadata tag. In this way, the matching degree between the model feature vector and the benchmark model parameters can be calculated by a cosine similarity algorithm, so as to realize the matching between the basic model data and the target benchmark model.

[0095] All basic model data in the preset basic template database can be pre-associated with the target benchmark model, and the corresponding basic model data can be directly obtained by querying the identifier of the target benchmark model in the subsequent matching process.

[0096] For example, the identifier of the target benchmark model is used as a query condition to obtain the corresponding basic model data by querying the preset basic template database using the identifier.

[0097] S280, adaptively modifying the basic model data based on the parameter-driven technology and the target design instruction set to obtain target model data.

[0098] In this step, the obtained target design instruction set is disassembled into multiple parameter groups based on a parameter-driven technology, and a parameter mapping table is established. Based on the parameter mapping table, corresponding parameters on the basic model data are one-to-one corresponding and adaptively modified.

[0099] In the adaptive modification process, the hierarchical optimization strategy can be adopted, and the key parameters affecting the function implementation of the model are adjusted first, and then the secondary parameters are optimized. For example, in the hydraulic system design, the cylinder stroke parameter is adjusted first, and then the sealing material parameter is optimized.

[0100] In the adaptive modification process, the corresponding parameters of the basic model data can be adaptively adjusted according to the pre-set priority type. For example, the priority type includes core feature parameters and non-core feature parameters. In the adaptive modification process, the core feature parameters of the basic model data can be retained, and only the non-core parameters of the basic model data are dynamically adjusted according to the target design instruction set. For example, in the design of the transmission mechanism of the non-standard mechanical equipment, the core parameters such as gear modulus and center distance are retained, and the non-core parameters such as tooth width coefficient and lubrication mode are adjusted. Further, the adaptive modification process can include but is not limited to updating, adding, and deleting operations on the parameters of the basic model data.

[0101] S290, generating a model according to the target model data to obtain a first target product model.

[0102] In this step, a model is generated according to the target model data which is adaptively modified based on the basic model data and the target design instruction set, to obtain a first target product model.

[0103] In the model generation process, the application program interface of the three-dimensional modeling software can be used to convert the target model data into a three-dimensional geometric model. It can be understood that the generated first target product model can include complete data associated with the product model, such as geometric information, material properties, and assembly relationship.

[0104] In some embodiments, after obtaining the first target product model, the product model generation method of the present application can further include the following steps: S2100, iteratively optimizing the first target product model based on the received structured feedback data to obtain a second target product model.

[0105] In this step, after obtaining the first target product model, the structured feedback data fed back by the user or the designer is received from the pre-set data interface, and the first target product model is iteratively optimized based on the structured feedback data.

[0106] It should be understood that the first target product model, as the initially generated product model, may not be able to fully meet the actual needs or there may be room for local optimization. If only relying on the initial design process, the product model will still not be able to meet the actual needs of users. After the first target product model is generated, based on the structured feedback data from users or designers, the model is further optimized and adjusted on the basis of the first target product model, so that the final product model can better meet the actual needs of users and be more market-adaptable.

[0107] The structured feedback data may include parameter adjustment instructions, wherein the parameter adjustment instructions are used to instruct to perform corresponding adjustment operations on corresponding parameters of the first target product model.

[0108] The iterative optimization process can employ a reinforcement learning algorithm, using structured feedback data as a reward function input to dynamically adjust the direction of model parameter updates for iterative optimization of the first target product model. The iterative optimization process can be implemented using related technologies and will not be further elaborated here.

[0109] Among them, when iteratively optimizing the first target product model, it is also possible to first determine whether the parameter adjustment instructions in the received structured feedback data exceed the preset template parameter range of the first target product model. When the parameter adjustment instructions in the received structured feedback data are determined to exceed the preset template parameter range of the first target product model, the model is iteratively optimized using the basic model data corresponding to the first target product model to obtain the third target product model.

[0110] It is not difficult to understand that when the iterative optimization of the first target product model may cause the design parameters to deviate from the reasonable constraint range of the baseline model, if iterative optimization is still performed, the stability of the original product model design logic may be destroyed. Therefore, when it is judged that the iterative optimization process of the current model may cause the design parameters to deviate from the reasonable constraint range of the baseline model, re-iterative optimization of the model based on the basic model data can effectively ensure the stability of the product model design.

[0111] The third target product model obtained in the above manner not only retains the user's personalized needs for the product model, but also avoids the imbalance of model performance caused by parameters exceeding the range in the final generation effect of the product model by returning to the basic design framework, and effectively avoids the impact of parameter adjustments beyond the preset range on the stability of the product model.

[0112] In this embodiment, the product model generation method of the present application realizes automatic construction of logical relationship trees between entity elements based on product demand information by performing named entity recognition and semantic role labeling based on a semantic analysis model, so as to match a target reference model according to the logical relationship trees for user selection, which can effectively improve the understanding accuracy of structured product demand data, thereby improving the fitting degree of the obtained target reference model and the actual demand of the user; and the target reference model can be effectively quantified in objectivity in the matching process by relying on a product series similarity matching algorithm combined with a preset threshold to filter the target reference model, which eliminates the interference of artificial experience on model selection and ensures the accuracy and repeatability of the reference model matching; in addition, a process of automatically iterating and optimizing the model by using structured feedback data is set, forming a closed-loop mechanism of design-feedback-optimization, which can further improve the model quality while reducing manual intervention, and further enhance the adaptability and market response agility of product design.

[0113] Corresponding to the foregoing application function implementation method embodiments, the present application further provides a product model generation device, an electronic device and corresponding embodiments.

[0114] Figure 3 FIG. 1 is a structural schematic diagram of a product model generation device according to an embodiment of the present application.

[0115] Referring to FIG. 1, Figure 3 the product model generation device 300 of the present application comprises a product demand extraction module 310, a reference model matching module 320, a reference parameter instruction matching module 330, a design instruction set acquisition module 340 and a model generation module 350.

[0116] The product demand extraction module 310 is configured to obtain product key elements from the obtained product demand information and construct structured product demand data according to the product key elements.

[0117] In some embodiments, the product demand extraction module 310 can further perform named entity recognition on the obtained product demand information based on a semantic analysis model to obtain entity elements within a preset range; establish a logical relationship tree between each entity element based on a semantic role labeling rule, and generate structured product demand data according to the logical relationship tree.

[0118] The reference model matching module 320 is configured to match a target reference model from a preset reference model database based on the structured product demand data.

[0119] In some embodiments, the benchmark model matching module 320 can further call the preset benchmark model database based on the structured product demand data to perform product series similarity matching, and obtain a matching result of the product series similarity matching; and determine the target benchmark model from the preset benchmark model database based on the matching result of the product series similarity matching and based on a preset similarity threshold.

[0120] In some embodiments, the benchmark model matching module 320 can further determine a plurality of recommended models from the preset benchmark model database based on the matching result of the product series similarity matching and based on the preset similarity threshold; and determine the target benchmark model from the plurality of recommended models according to a received determination instruction.

[0121] The benchmark parameter instruction matching module 330 is configured to match the target benchmark parameter instruction from the preset benchmark instruction database according to the target benchmark model and historical design data corresponding to the target benchmark model.

[0122] The design instruction set acquisition module 340 is configured to perform parameter mapping based on the structured product demand data, the target benchmark model, and the benchmark parameter instruction set according to the preset parameter recommendation neural network, and generate the target design instruction set.

[0123] The model generation module 350 is configured to generate a product model based on a parameter-driven technology and the target design instruction set, and obtain a first target product model.

[0124] In some embodiments, the model generation module 350 can further obtain basic model data associated with the target benchmark model from a preset basic template database; perform adaptive modification on the basic model data based on a parameter-driven technology and the target design instruction set, and obtain target model data; and perform model generation according to the target model data, and obtain the first target product model.

[0125] Figure 4 FIG. 7 is another structural schematic diagram of a product model generation device according to an embodiment of the present application.

[0126] Referring to FIG. 7, Figure 4 The product model generation device 300 according to the present application includes a product demand extraction module 310, a benchmark model matching module 320, a benchmark parameter instruction matching module 330, a design instruction set acquisition module 340, a model generation module 350, and a model iteration module 360.

[0127] The model iteration module 360 is configured to perform iterative optimization on the first target product model based on received structured feedback data, and obtain a second target product model.

[0128] In this embodiment, the product model generation method of the present application automatically extracts key elements from product demand information and constructs structured product demand data after obtaining product demand information, matches target reference models and related historical design data based on structured data, uses a parameter recommendation neural network to perform precise parameter mapping to generate target design instruction sets, and finally realizes automatic generation of product models based on parameter driving technology. Through the above product model generation method, the product model generation is driven by full-process automation, thereby effectively shortening the product design cycle and effectively reducing the dependence on individual experience and the subjective bias of manual screening, improving design efficiency and result consistency, and thus making the product model generation process meet the needs of rapid market response.

[0129] As to the apparatus in the above-mentioned embodiments, the specific manners in which various modules perform operations have been described in detail in the embodiments about the method, and thus will not be described in detail here.

[0130] Figure 5 FIG. 1 is a structural schematic diagram of an electronic device according to an embodiment of the present application.

[0131] Referring to FIG. 1, Figure 5 The electronic device 1000 includes a memory 1010 and a processor 1020.

[0132] The processor 1020 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0133] The memory 1010 can include various types of storage units such as a system memory, a read-only memory (ROM), and a permanent storage device. Among them, the ROM can store static data or instructions required by the processor 1020 or other modules of the computer. The permanent storage device can be a rewritable storage device. The permanent storage device can be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device employs a mass storage device (e.g., a magnetic or optical disk, a flash memory) as a permanent storage device. In some other embodiments, the permanent storage device can be a removable storage device (e.g., a floppy disk, an optical drive). The system memory can be a readable and writable storage device or a volatile readable and writable storage device such as a dynamic random access memory. The system memory can store some or all of the instructions and data required by the processor during runtime. In addition, the memory 1010 can include a combination of any computer readable storage media, including various types of semiconductor storage chips (e.g., DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), magnetic disks and / or optical disks. In some embodiments, the memory 1010 can include a readable and / or writable removable storage device such as a compact disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (e.g., SD card, min SD card, Micro-SD card, etc.), a magnetic floppy disk, etc. The computer readable storage medium does not include a carrier wave and an instantaneous electronic signal transmitted by wireless or wired transmission.

[0134] The memory 1010 stores executable code, which, when processed by the processor 1020, can cause the processor 1020 to perform part or all of the above-mentioned methods.

[0135] In addition, the method according to the present application can also be implemented as a computer program or a computer program product, which includes computer program code instructions for performing part or all of the steps of the above-mentioned methods of the present application.

[0136] Alternatively, the present application can also be implemented as a computer readable storage medium (or non-transitory machine readable storage medium or machine readable storage medium) having executable code (or computer program or computer instruction code) stored thereon, which, when executed by a processor of an electronic device (or a server, etc.), causes the processor to perform part or all of the steps of the above-mentioned methods according to the present application.

[0137] Having described various embodiments of the application, it is to be understood that the above description is meant not to limit and not to encompass all of the possible embodiments. Many modifications and variations of this application can be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. It is intended that the scope of the application be defined by the scope of the patent and by the claims as allowed by the patent office, which can include adaptations based on the description, equivalents, and / or substitutions of elements individually or collectively to the entire disclosure.

Claims

1. A product model generation method, characterized in that: include Acquire product key elements from the acquired product demand information, and construct structured product demand data based on the product key elements; matching a target benchmark model from a preset benchmark model database based on the structured product demand data; matching target reference parameter instructions from a preset reference instruction database according to the target reference model and historical design data corresponding to the target reference model; Recommending a neural network to perform parameter mapping based on the structured product requirement data, the target benchmark model, and the benchmark parameter instruction set according to preset parameters to generate a target design instruction set; A product model is generated based on parameter-driven technology and the target design instruction set to obtain a first target product model.

2. The method according to claim 1, characterized in that The step of obtaining product key elements from the obtained product demand information and constructing structured product demand data based on the product key elements includes: Performing named entity recognition on the acquired product demand information based on a semantic analysis model to obtain entity elements within a preset range; A logical relationship tree between the entity elements is established based on semantic role labeling rules according to the entity elements, and structured product demand data is generated according to the logical relationship tree.

3. The method according to claim 1, characterized in that The matching of the target benchmark model from a preset benchmark model database based on the structured product demand data includes: Based on the structured product demand data, calling a preset benchmark model database to perform product series similarity matching to obtain a matching result of the product series similarity matching; A target reference model is determined from the preset reference model database based on the matching result of the product series similarity matching and a preset similarity threshold.

4. The method according to claim 3, characterized in that The determining of a target reference model from the preset reference model database based on the matching result of the product series similarity matching and a preset similarity threshold comprises: Determining a plurality of recommendation models from the preset benchmark model database based on the matching results of the product series similarity matching and based on a preset similarity threshold; A target reference model is determined from the plurality of recommended models according to the received determination instruction.

5. The method according to claim 1, wherein The generating of a product model based on the parameter-driven technology and the target design instruction set to obtain a first target product model includes: Acquire basic model data associated with the target reference model from a preset basic template database; Adaptively modifying the basic model data based on parameter-driven technology and the target design instruction set to obtain target model data; Model generation is performed according to the target model data to obtain a first target product model.

6. The method according to any one of claims 1 to 5, characterized in that The method further includes: The first target product model is iteratively optimized based on the received structured feedback data to obtain a second target product model.

7. A product model generation device, characterized in that: include: A product demand extraction module is used to obtain product key elements from the obtained product demand information and construct structured product demand data based on the product key elements; A benchmark model matching module, configured to match a target benchmark model from a preset benchmark model database based on the structured product requirement data; a benchmark parameter instruction matching module, configured to match a target benchmark parameter instruction from a preset benchmark instruction database according to the target benchmark model and first historical design data corresponding to the target benchmark model; A design instruction set acquisition module is used to recommend a neural network based on preset parameters to perform parameter mapping based on the structured product requirement data, the target benchmark model and the benchmark parameter instruction set to generate a target design instruction set; The model generation module is used to generate a product model based on parameter-driven technology and the target design instruction set to obtain a first target product model.

8. The device according to claim 7, characterized in that The device also includes: The model optimization module is used to iteratively optimize the first target product model based on the received structured feedback data to obtain a second target product model.

9. An electronic device, characterized in that: include: processor; as well as A memory having executable codes stored thereon, which, when executed by the processor, causes the processor to execute the method according to any one of claims 1 to 6.

10. A computer-readable storage medium having executable code stored thereon, characterized in that: When the executable code is executed by a processor of an electronic device, the processor is caused to perform the method according to any one of claims 1 to 6.

Images