Product model construction method and device, computer program product and electronic equipment

Abstract

The invention discloses a product model construction method and device, a computer program product and electronic equipment. The method relates to the field of artificial intelligence, and comprises the following steps: determining a plurality of parts forming a target product, and for each part, receiving a part design demand input by a user; the part design requirements are input into a target model, a part model of the part is obtained, the target model is obtained through training of multiple sets of training samples, and each set of training samples comprise historical part design requirements and historical part models; determining assembly information of the part model of each part, and matching an assembly relationship and an assembly position between every two part models through the assembly information to obtain a matching result set; and assembling all the part models through the matching result set to obtain a product model of the target product. Through the method and the device, the problem of low construction efficiency of a product model in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and more specifically, to a method, device, computer program product, and electronic device for constructing a product model. Background Art

[0002] 3D CAD (Computer Aided Design) software has been widely used in the manufacturing industry. Users can reduce repetitive work by making customized product models in CAD software, thereby improving design efficiency, design stability and design accuracy, and achieving the goal of reducing costs and increasing efficiency.

[0003] However, the customization function of CAD in related technologies has problems such as low model utilization and high requirements on the professional quality of users. The parametric drive and intelligent assembly functions of CAD are only some basic functions. Parametric drive can only drive the modeling part of the model with variables, and intelligent assembly can only improve the accuracy and efficiency of assembly when assembling the model, but cannot provide users with the ability to customize logic and interactive behavior modes. It is impossible to directly allow users to customize some complex product models.

[0004] Currently, no effective solution has been proposed to the problem of low efficiency in building product models in related technologies. Summary of the invention

[0005] The main purpose of the present application is to provide a method, device, computer program product and electronic device for constructing a product model to solve the problem of low efficiency in constructing product models in related technologies.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for constructing a product model is provided. The method includes: determining multiple parts constituting a target product, and for each part, receiving a part design requirement input by a user; inputting the part design requirement into a target model to obtain a part model of the part, wherein the target model is obtained by training multiple sets of training samples, and each set of training samples includes historical part design requirements and historical part models; determining assembly information of the part model of each part, matching the assembly relationship and assembly position between each two part models through the assembly information, and obtaining a matching result set; assembling all part models through the matching result set to obtain a product model of the target product.

[0007] Optionally, the target model is obtained by: obtaining model building records for each product in a product database, extracting historical part models of multiple parts from the model building records, and determining the historical part design requirements when each historical part model was constructed; determining the historical part design requirements and historical part models of each part as a set of training samples to obtain multiple groups of training samples; and training a natural language processing model based on the multiple groups of training samples to obtain a target model.

[0008] Optionally, determining the assembly information of the part model of each part includes: extracting product model information of each product from a product database, wherein the product model information includes at least one of the following: part information constituting the product, product identification, geometric data information of the product model, and part attachment point position information; determining target part information corresponding to each part of the target product through the product model information; for each part, extracting size parameter information and spatial position information of the part relative to the product to which the part belongs from the target part information of the part, and determining at least one of the size parameter information, spatial position information and part attachment point position information of the part as the assembly information of the part.

[0009] Optionally, the assembly relationship and assembly position between every two part models are matched through assembly information to obtain a matching result set including: for each part model, multiple attachment points are determined from the part attachment point position information of the assembly information of the part model, and the number of each attachment point is determined, wherein the same numbers of the attachment points of different part models represent that the attachment points with corresponding numbers between the part models match each other; multiple part models with the same numbers are determined as a group of part model sets with an assembly relationship to obtain multiple groups of part model sets; the spatial position information in the assembly information of each part model is determined as the initial assembly position of the part model, and the surface of the part model in contact with other part models is calibrated based on the part attachment point position information to obtain the target assembly position of the part model, wherein the other part models are models other than the part model in the part model set to which the part model belongs; the target assembly positions of all part models are determined as the matching result set.

[0010] Optionally, assembling all part models through the matching result set to obtain the product model of the target product includes: receiving assembly data input by the user for each part model, wherein the assembly data includes at least one of the following: dimensional parameter data and constraint relationship data of the part model, the constraint relationship data is used to characterize the dimensional range and position data range of the part features on the part model; assembling all part models through the assembly data and the target assembly position to obtain the product model of the target product.

[0011] Optionally, after all part models are assembled through assembly data and target assembly positions, the method further includes: determining whether each part model is assembled successfully; when all part models are assembled successfully, issuing a first prompt message, wherein the first prompt message is used to prompt that the product model assembly is completed; when the part model assembly fails, determining the part model set to which the part model belongs as the model set to be adjusted; detecting whether there is an assembly data conflict between the part models in the model set to be adjusted, and when an assembly data conflict is detected, issuing a second prompt message, wherein the second prompt message is used to prompt the user to adjust the assembly data of the part model with the assembly data conflict.

[0012] Optionally, after assembling all part models through the matching result set to obtain the product model of the target product, the method also includes: receiving a user's request for parameter adjustment of the product model, determining the parameters to be adjusted and the target data based on the parameter adjustment request, wherein the parameters to be adjusted include at least one of the following: dimensional parameters of the product model and assembly information of each part model; modifying the current data of the parameters to be adjusted of the product model to the target data to obtain an updated target model.

[0013] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a device for constructing a product model is provided. The device includes: a first determination unit, used to determine multiple parts constituting a target product, and for each part, receiving a part design requirement input by a user; an input unit, used to input the part design requirement into a target model to obtain a part model of the part, wherein the target model is obtained by training multiple groups of training samples, and each group of training samples includes historical part design requirements and historical part models; a second determination unit, used to determine the assembly information of the part model of each part, and match the assembly relationship and assembly position between each two part models through the assembly information to obtain a matching result set; an assembly unit, used to assemble all part models through the matching result set to obtain a product model of the target product.

[0014] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps of the method for constructing a product model described in each embodiment of the present application.

[0015] Through this application, the following steps are adopted: determine multiple parts constituting a target product, and for each part, receive the part design requirements input by the user; input the part design requirements into the target model to obtain the part model of the part, wherein the target model is trained by multiple sets of training samples, and each set of training samples includes historical part design requirements and historical part models; determine the assembly information of the part model of each part, match the assembly relationship and assembly position between every two part models through the assembly information, and obtain a matching result set; assemble all part models through the matching result set to obtain the product model of the target product, thereby solving the problem of low efficiency in building product models in related technologies. A target model that automatically inputs part design requirements and outputs part models is trained through a machine learning method, and the target model generates the part model of the target product according to the part design requirements input by the user, and then matches according to the assembly information of the part model, and assembles the part model based on the matching result set to obtain the product model, thereby achieving the effect of improving the building efficiency of the product model. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 is a flowchart of a method for constructing a product model provided in an embodiment of the present application;

[0018] Figure 2 is a schematic diagram of a system for constructing an optional product model provided according to an embodiment of the present application;

[0019] Figure 3 is a schematic diagram of a device for constructing a product model according to an embodiment of the present application;

[0020] Figure 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0025] It should be noted that the information collected is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0026] The present invention is described below in conjunction with preferred implementation steps. Figure 1 is a flowchart of a method for constructing a product model according to an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0027] Step S101, determining a plurality of parts constituting a target product, and receiving part design requirements input by a user for each part.

[0028] Specifically, the target product can be a product produced by a manufacturing enterprise. The target product can be composed of multiple parts or directly composed of a single part model. The user can be a product model designer. The parts can be threaded parts such as screws, nuts, etc., or mechanical parts such as shafts, wheels, gears, etc., or electronic parts such as circuit boards, sockets, connectors, etc., or structural parts such as beams, columns, beam-column connectors, etc., or pipeline parts such as pipelines, pipe joints, etc., or hydraulic parts such as hydraulic cylinders, valves, etc., or automotive parts such as engines, wheels, car bodies, etc., or building parts such as doors, windows, stairs, walls, etc. Part design requirements, such as "I want a helical gear with 12 teeth, 0.5 module, and 15 degree rotation angle", can also be a general requirement, such as "I want a three-piece forged steel ball valve".

[0029] Among them, receiving the part design requirements input by the user can be realized through a preset intelligent interaction plug-in. The intelligent interaction plug-in provides a window for the user to input information for intelligent interaction. This module can be developed by expanding the existing control library of CAD. Combining large model language processing with a graphical interface, the design instructions (i.e., part design requirements) input by the user can be conveyed to the product model construction system in an intuitive way. The intelligent interaction plug-in contains two main functional modules, namely the information input module and the artificial intelligence interaction module. The information input module receives user input information by adding a floating window in the design environment. The floating window supports user and artificial intelligence interaction, prompt word guidance and other functions. The artificial intelligence interaction module inputs the part design requirements into the target model for calculation according to the interface provided by the target model. At the same time, the target model is encapsulated as a service, which can be a local service or a network service.

[0030] Step S102, inputting the part design requirements into the target model to obtain the part model of the part, wherein the target model is trained by multiple groups of training samples, and each group of training samples includes historical part design requirements and historical part models.

[0031] Specifically, the target model can be a natural language processing model. The user inputs part design requirements through the artificial intelligence interaction module, and the target model outputs a file in a unified format according to user requirements to store part information, such as an XML (Extensible Markup Language) file.

[0032] Through the natural language processing technology of the large model, the design requirements expressed by the user in natural language are accurately parsed. Combining industry knowledge and practical experience, the optimal design part model is recommended through machine learning algorithms. The target model uses a large-scale neural network model to process and analyze a large amount of design-related data (i.e., training samples). Model training involves key information such as design technical parameters and rules to optimize the accuracy and efficiency of design predictions. In this way, the target model can not only provide specific design parameter recommendations, but also predict problems that may be encountered during the design process.

[0033] The natural language understanding module in the target model accurately analyzes design instructions, that is, part design requirements. This module collects and organizes professional terms and expressions in the field of industrial design, designs and implements NLP (Natural Language Processing) algorithms to accurately interpret and execute user instructions. By building a knowledge base containing design rules, design constraints, and historical cases, it is used to assist in analyzing the designer's intentions and making intelligent recommendations. The construction of the knowledge base is based on industry standards and successful cases of historical part models to ensure that the recommended product model solutions are practical and innovative.

[0034] Step S103, determining assembly information of the part model of each part, matching the assembly relationship and assembly position between every two part models through the assembly information, and obtaining a matching result set.

[0035] Specifically, the assembly information may include part information, product identification, geometric data information of the product model, and part attachment point position information that constitute the target product. For every two part models that constitute the target product, the assembly relationship and assembly position are matched through the assembly information. For example, part model a and part model b are attached to each other in the target product, indicating that there is an assembly relationship between part model a and part model b. For each part model, the attachment point position information of the part can be preset in advance according to the target product, and the same number is used for the attachment points between the part models that are attached to each other. For example, part model a and part model b have the same attachment point number 1, indicating that part model a and part model b are attached to each other at the attachment point position corresponding to number 1, thereby determining the assembly position of each part model relative to other part models.

[0036] Step S104, assembling all part models through the matching result set to obtain a product model of the target product.

[0037] Specifically, the matching result set can be the target assembly position of each part model in the product model. The target assembly position is determined by the spatial position information in the assembly information to determine the initial assembly position, and then the contact surface between each part model is calibrated according to the attachment point position information between each part model. After determining the target assembly position of each part model, the part model can be adjusted according to the part model size parameter data and constraint relationship data input by the user, so that the adjusted part models can match each other to obtain the product model of the target product.

[0038] The method for constructing a product model provided in the embodiment of the present application determines multiple parts constituting a target product, and for each part, receives a part design requirement input by a user; inputs the part design requirement into the target model to obtain a part model of the part, wherein the target model is obtained by training multiple sets of training samples, and each set of training samples includes historical part design requirements and historical part models; determines the assembly information of the part model of each part, matches the assembly relationship and assembly position between every two part models through the assembly information, and obtains a matching result set; assembles all part models through the matching result set to obtain a product model of the target product, thereby solving the problem of low efficiency in constructing product models in related technologies. A target model that automatically inputs part design requirements and outputs part models is trained through a machine learning method, and the target model generates a part model of the target product according to the part design requirements input by the user, and then matches according to the assembly information of the part model, and assembles the part model based on the matching result set to obtain a product model, thereby achieving the effect of improving the efficiency of constructing the product model.

[0039] In order to improve the user's design efficiency of product models, a target model is trained in advance. Optionally, in the product model construction method provided in the embodiment of the present application, the target model is obtained in the following way: obtaining model construction records of each product in the product database, extracting historical part models of multiple parts from the model construction records, and determining the historical part design requirements when each historical part model was constructed; determining the historical part design requirements and historical part models of each part as a group of training samples to obtain multiple groups of training samples; training a natural language processing model based on the multiple groups of training samples to obtain a target model.

[0040] Specifically, the product database may be a database of products produced by a manufacturing enterprise, which contains product model data of various products produced by the enterprise, and these product model data may include the bill of materials, attribute information, model space location information, model unique identification information, model geometry data information, parameter information, intelligent assembly point information (i.e., attachment point location information), etc. The historical part design requirements and historical part models of various parts for building products obtained from the product database are used as training samples, and the natural language processing model is trained through a large number of training samples, so as to obtain a trained target model that automatically outputs part models based on the part design requirements input by the user.

[0041] Among them, the part model can be created in the CAD software according to the calculation results output by the target model through the part generation tool. The part generation tool mainly includes two modules, namely the model library module and the parametric drive module. The model library module can be deployed to a local or local area network. Through the configuration interface, various standard models, active parameters of the model (that is, the parameters that can be directly modified by the part model without constraints), change rules (that is, the output expression of the part model results) and serialized data (parameters that cannot be directly modified due to constraints in the part model) can be entered to form a model library. CAD can search and call in the corresponding part model into the CAD design environment through the interface. The parametric drive module relies on the parametric mechanism of the CAD software to drive the key parameters of the model data, thereby realizing the series size changes or structural changes of the model.

[0042] This embodiment integrates the machine learning model with the CAD software to achieve seamless conversion from design intent to specific models. By transforming the CAD software to support data interaction with the target model, the product model can be directly generated and adjusted in the CAD software. Through the intelligent interaction between the target model and the designer, CAD is guided to quickly build the product model and output the design plan. The efficiency of the design process is improved and the dependence on the professional skills of engineers is reduced, so that non-professionals can also effectively participate in the design work.

[0043] In order to intelligently assemble part models, it is first necessary to determine the assembly information of the part models. Optionally, in the product model construction method provided in the embodiment of the present application, determining the assembly information of the part model of each part includes: extracting product model information of each product from a product database, wherein the product model information includes at least one of the following: part information constituting the product, product identification, geometric data information of the product model, and part attachment point position information; determining target part information corresponding to each part of the target product through the product model information; for each part, extracting size parameter information and spatial position information of the part relative to the product to which the part belongs from the target part information of the part, and determining at least one of the size parameter information, spatial position information and part attachment point position information of the part as the assembly information of the part.

[0044] Specifically, the part information constituting the product may be the various parts constituting the target product, as well as the size parameter information of each part and the spatial position information of the part relative to the target product. The product identification is also the unique authentication identification of the target product. The geometric data information may be the size parameter information of the target product such as length, width, height, diameter, distance, angle, etc. The part attachment point position information may be the contact point position information between the part model and other adjacent part models. The assembly information may include at least one of the size parameter information, spatial position information and part attachment point position information of the part. The assembly information of each part model is determined to match the assembly relationship and assembly position, thereby improving the assembly efficiency of the product model.

[0045] After determining the assembly information of each part model, a matching result set between the part models is determined based on the assembly information. Optionally, in the method for constructing a product model provided in an embodiment of the present application, the assembly relationship and assembly position between each two part models are matched through the assembly information to obtain a matching result set including: for each part model, multiple attachment points are determined from the part attachment point position information of the assembly information of the part model, and a label of each attachment point is determined, wherein the same labels of the attachment points of different part models represent that the attachment points corresponding to the labels between the part models match each other; multiple part models with the same labels are determined as a group of part model sets with an assembly relationship, to obtain multiple groups of part model sets; the spatial position information in the assembly information of each part model is determined as the initial assembly position of the part model, and the surface of the part model in contact with other part models is calibrated based on the part attachment point position information to obtain the target assembly position of the part model, wherein the other part models are models other than the part model in the part model set to which the part model belongs; the target assembly positions of all part models are determined as the matching result set.

[0046] Specifically, the assembly relationship can be determined based on the part attachment point position information in the assembly information. If there are attachment points with the same number in any two part models, it means that the two part models are attached to each other through the attachment points, that is, there is an assembly relationship. All part models with assembly relationships are combined into a group of part model sets, and the initial assembly position of the part model is determined based on the spatial position information of the part in the product model. Then, the contact surface between the mutually attached part models is determined according to the part attachment point position information, so as to obtain the target assembly position of each part model, and the target assembly position of all part models is used as the matching result set.

[0047] This embodiment implements intelligent assembly of product models by determining a set of matching results, thereby improving the assembly efficiency of product models.

[0048] After determining the matching result set, the part models are assembled based on the matching result set. Optionally, in the product model construction method provided in the embodiment of the present application, all part models are assembled through the matching result set to obtain the product model of the target product, including: receiving assembly data input by the user for each part model, wherein the assembly data includes at least one of the following: dimensional parameter data and constraint relationship data of the part model, the constraint relationship data is used to characterize the dimensional range and position data range of the part features on the part model; all part models are assembled through the assembly data and the target assembly position to obtain the product model of the target product.

[0049] Specifically, the dimensional parameter data of the part model can be the length, width, height, diameter, distance, angle, etc. of the part, as well as parameter information of features on the part such as threads, holes, etc. The constraint relationship data is also the size range and position data range of each part feature on the part model. For example, the size range of a hole on a part model needs to be smaller than the size range of the surface of the control, and the position of the hole needs to match the part features on other part models, for example, so that part features of other part models such as pins can be inserted into the hole.

[0050] Among them, the assembly of product models based on part models can be realized through intelligent assembly tools, which include the construction of intelligent assembly point matching mechanism, intelligent assembly drive, and constraint relationship construction. First, a set of intelligent assembly point matching mechanism is established. This matching mechanism defines assembly rules (i.e. assembly relationship) and behaviors by setting assembly point data (i.e. part attachment point position information) at key assembly positions of the model, and simple constraint relationship rules can also be set. The intelligent assembly drive process will match and associate the generated CAD model through assembly point data and complete the defined assembly rules, thereby realizing intelligent automatic assembly of the model. The assembly log is recorded for the assembly process so that the assembly results can be checked and verified later. The assembly process will also rely on the constraint capability of the CAD system to add constraint relationships to key model positions to ensure the stability of the relative position relationship of the model.

[0051] This embodiment improves the assembly efficiency of product models by intelligently assembling various part models to form a product model, improves the speed and accuracy of design data processing, shortens the design cycle, and reduces the error rate. In addition, by making it easier for non-professionals to participate in complex design tasks, it will expand the scope of work of the design team and promote innovation and collaboration. The application of this process is expected to accelerate the transformation process from concept to product for enterprises and enhance their market competitiveness.

[0052] For part models that fail to assemble, it is necessary to promptly prompt the user to make modifications through prompt information. Optionally, in the method for constructing a product model provided in an embodiment of the present application, after all part models are assembled through assembly data and target assembly positions, the method also includes: determining whether each part model is assembled successfully; when all part models are assembled successfully, issuing a first prompt information, wherein the first prompt information is used to prompt that the assembly of the product model is completed; when the assembly of the part model fails, determining the part model set to which the part model belongs as the model set to be adjusted; detecting whether there is an assembly data conflict between the part models in the model set to be adjusted, and when an assembly data conflict is detected, issuing a second prompt information, wherein the second prompt information is used to prompt the user to adjust the assembly data of the part model with the assembly data conflict.

[0053] Specifically, if all part models are assembled successfully, the first prompt message will be used to prompt the user that the product model assembly is complete, so that the user can perform the next operation on the product model. If there is a part model assembly failure, it may be due to unreasonable assembly data input, resulting in assembly data conflicts between part models. For example, the control on part model a and the pin on part model b do not correspond and cannot be inserted, resulting in an assembly data conflict. At this time, the second prompt message will be used to prompt the user to adjust the assembly data.

[0054] This embodiment improves the design efficiency of the product model by promptly notifying the user of a successful assembly or promptly reminding the user to adjust assembly data when an assembly fails.

[0055] After the product model is generated, the product model can also be adjusted in time through parameter adjustment requests. Optionally, in the product model construction method provided in the embodiment of the present application, after all part models are assembled through the matching result set to obtain the product model of the target product, the method also includes: receiving the user's parameter adjustment request for the product model, determining the parameters to be adjusted and the target data based on the parameter adjustment request, wherein the parameters to be adjusted include at least one of the following: the size parameters of the product model and the assembly information of each part model; modifying the current data of the parameters to be adjusted of the product model to the target data to obtain an updated target model.

[0056] Specifically, based on the parametric drive function of the CAD software, the parameters of the assembled target model can be adjusted through the user's parameter adjustment request, such as adjusting the size parameters of the entire product model or adjusting the size parameters of a part model, or adjusting the assembly data, etc. This embodiment adjusts the product model based on the parameter adjustment request, which facilitates the user to modify the product model and improves the efficiency of product model design.

[0057] According to another embodiment of the present application, a system for constructing a product model is also provided. Figure 2 Schematic diagram of a system for constructing an optional product model according to an embodiment of the present application. Figure 2 As shown, the system includes: data preparation tools, intelligent interactive plug-ins, part generation tools, intelligent assembly tools and intelligent auxiliary design modules.

[0058] Specifically, the data preparation tool is used to provide basic data for large model training. The tool will provide relevant data according to the needs of model training. In the CAD system, all basic data related to the model can be obtained, including the model's BOM structure, attribute information, model spatial location information, model unique identification information, model geometric data information, parameter information, intelligent assembly point information, etc. Develop plug-ins in the CAD environment and output relevant information in a unified format through interfaces according to the needs of model training.

[0059] The intelligent interaction plug-in combines the language processing of the big model with the graphical interface, so that the design instructions can be conveyed to the system in an intuitive way. The intelligent interaction plug-in includes an information input module and an intelligent interaction module. The information input module receives user input information by adding a floating window in the design environment. The floating window supports functions such as user and artificial intelligence interaction and prompt word guidance. The intelligent interaction module inputs key information into the big model for calculation according to the interface provided by the big model. At the same time, the big model is encapsulated as a service. The service can be a local service or a network service, which is mainly determined by the capabilities provided by the big model.

[0060] The part generation tool creates the corresponding model data in the CAD software based on the calculation results output by the large model. This tool mainly includes two modules, namely the model library module and the parametric drive module. The model library module can be deployed to a local or local area network. Through the configuration interface, various standard models, active parameters of the model, change rules and serialized data can be entered to form a model library. CAD can search and call the corresponding model into the CAD design environment through the interface. The parametric drive module relies on the parametric mechanism of the CAD software to drive the key parameters of the model data, thereby realizing the series size changes or structural changes of the model.

[0061] The implementation of intelligent assembly tools includes the construction of intelligent assembly point matching mechanism, intelligent assembly drive, and constraint relationship construction. By establishing a set of intelligent assembly point matching mechanism, this matching mechanism defines assembly rules and behaviors by setting assembly point data at key assembly positions of the model, and can also set simple constraint relationship rules. The intelligent assembly drive process will match and associate the generated CAD model through assembly point data and complete the defined assembly rules, thereby realizing intelligent automatic assembly of the model. The assembly log is recorded for the assembly process so that the assembly results can be checked and verified later. The assembly process will also rely on the constraint capability of the CAD system to add constraint relationships to key model positions to ensure the stability of the relative position relationship of the model.

[0062] The intelligent assisted design module includes a natural language understanding module and knowledge base construction. The natural language understanding module accurately parses design instructions by developing an efficient natural language understanding module. This module includes collecting and organizing professional terms and expressions in the field of industrial design, designing and implementing natural language processing algorithms, so as to accurately interpret and execute the designer's instructions. The knowledge base construction includes a knowledge base of design rules, design constraints, and historical cases, which is used to assist in parsing the designer's intentions and make intelligent recommendations. The construction of the knowledge base is based on industry standards and past successful cases to ensure that the recommended practice solutions are practical and innovative.

[0063] The intelligent assisted design module, also known as the large model, generates calculation results by receiving the part design requirements of the intelligent interactive plug-in, sends the calculation results to the part generation tool to generate a part model, and the intelligent assembly tool assembles the part model to output a product model that meets user needs.

[0064] This embodiment improves the speed and accuracy of data processing when designing models through the product model construction system, shortens the design cycle, and reduces the error rate. In addition, by making it easier for non-professionals to participate in complex design tasks, it will expand the scope of work of the design team and promote innovation and collaboration. The application of this process is expected to accelerate the transformation process from concept to product for enterprises and enhance their market competitiveness.

[0065] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0066] The embodiment of the present application also provides a device for constructing a product model. It should be noted that the device for constructing a product model in the embodiment of the present application can be used to execute the method for constructing a product model provided in the embodiment of the present application. The device for constructing a product model provided in the embodiment of the present application is introduced below.

[0067] Figure 3 Schematic diagram of a device for constructing a product model according to an embodiment of the present application. Figure 3 As shown, the device comprises:

[0068] The first determining unit 301 is used to determine a plurality of parts constituting a target product, and for each part, receive a part design requirement input by a user;

[0069] An input unit 302 is used to input the part design requirements into a target model to obtain a part model of the part, wherein the target model is obtained by training multiple sets of training samples, each set of training samples includes historical part design requirements and historical part models;

[0070] The second determining unit 303 is used to determine the assembly information of the part model of each part, and match the assembly relationship and assembly position between every two part models through the assembly information to obtain a matching result set;

[0071] The assembly unit 304 is used to assemble all the part models through the matching result set to obtain the product model of the target product.

[0072] The device for constructing a product model provided in the embodiment of the present application determines multiple parts constituting a target product through a first determination unit 301, and receives a part design requirement input by a user for each part; an input unit 302 inputs the part design requirement into a target model to obtain a part model of the part, wherein the target model is obtained by training multiple groups of training samples, and each group of training samples includes historical part design requirements and historical part models; a second determination unit 303 determines assembly information of the part model of each part, and matches the assembly relationship and assembly position between every two part models through the assembly information to obtain a matching result set; an assembly unit 304 assembles all part models through the matching result set to obtain a product model of the target product, thereby solving the problem of low efficiency in constructing product models in related technologies, and training a target model that automatically inputs part design requirements and outputs part models through a machine learning method, and the target model generates a part model of the target product according to the part design requirements input by the user, and then matches according to the assembly information of the part model, and assembles the part model based on the matching result set to obtain a product model, thereby achieving the effect of improving the efficiency of constructing the product model.

[0073] Optionally, in the product model construction device provided in the embodiment of the present application, the device also includes: an acquisition unit, used to obtain model construction records of each product in a product database, extract historical part models of multiple parts from the model construction records, and determine the historical part design requirements when each historical part model is constructed; a third determination unit, used to determine the historical part design requirements and historical part models of each part as a group of training samples to obtain multiple groups of training samples; a training unit, used to train a natural language processing model based on the multiple groups of training samples to obtain a target model.

[0074] Optionally, in the product model construction device provided in the embodiment of the present application, the second determination unit 303 includes: a first extraction module, used to extract product model information of each product from a product database, wherein the product model information includes at least one of the following: part information constituting the product, product identification, geometric data information of the product model, and part attachment point position information; a first determination module, used to determine the target part information corresponding to each part of the target product through the product model information; a second extraction module, used to extract size parameter information and spatial position information of the part relative to the product to which the part belongs from the target part information of each part, and determine at least one of the size parameter information, spatial position information and part attachment point position information of the part as the assembly information of the part.

[0075] Optionally, in the product model construction device provided in the embodiment of the present application, the second determination unit 303 includes: a second determination module, for determining, for each part model, multiple attachment points from the part attachment point position information of the assembly information of the part model, and determining the number of each attachment point, wherein the same numbers of the attachment points of different part models represent that the attachment points corresponding to the numbers between the part models match each other; a third determination module, for determining multiple part models with the same numbers as a group of part model sets with an assembly relationship, to obtain multiple groups of part model sets; a fourth determination module, for determining the spatial position information in the assembly information of each part model as the initial assembly position of the part model, and calibrating the surface of the part model in contact with other part models based on the part attachment point position information, to obtain the target assembly position of the part model, wherein the other part models are models other than the part model in the part model set to which the part model belongs; a fifth determination module, for determining the target assembly positions of all part models as a matching result set.

[0076] Optionally, in the product model construction device provided in the embodiment of the present application, the assembly unit 304 includes: a receiving module, used to receive assembly data input by the user for each part model, wherein the assembly data includes at least one of the following: dimensional parameter data and constraint relationship data of the part model, the constraint relationship data is used to characterize the dimensional range and position data range of the part features on the part model; an assembly module, used to assemble all part models through the assembly data and the target assembly position to obtain a product model of the target product.

[0077] Optionally, in the product model construction device provided in the embodiment of the present application, the device also includes: a judgment unit, used to judge whether each part model is assembled successfully; a first prompt unit, used to issue a first prompt message when all part models are assembled successfully, wherein the first prompt message is used to prompt that the product model assembly is completed; a fourth determination unit, used to determine the part model set to which the part model belongs as the model set to be adjusted when the part model assembly fails; a detection unit, used to detect whether there is an assembly data conflict between the part models in the model set to be adjusted, and when the assembly data conflict is detected, issuing a second prompt message, wherein the second prompt message is used to prompt the user to adjust the assembly data of the part model with the assembly data conflict.

[0078] Optionally, in the product model construction device provided in the embodiment of the present application, the device also includes: a receiving unit, used to receive a user's request for parameter adjustment of the product model, and determine the parameters to be adjusted and the target data based on the parameter adjustment request, wherein the parameters to be adjusted include at least one of the following: dimensional parameters of the product model and assembly information of each part model; a modifying unit, used to modify the current data of the parameters to be adjusted of the product model to the target data, so as to obtain an updated target model.

[0079] The device for constructing a product model includes a processor and a memory. The first determination unit 301, input unit 302, second determination unit 303 and assembly unit 304 are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions.

[0080] The processor contains a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the efficiency of building the product model can be improved by adjusting the kernel parameters.

[0081] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0082] An embodiment of the present invention provides a computer-readable storage medium on which a program is stored. When the program is executed by a processor, a method for constructing a product model is implemented.

[0083] An embodiment of the present invention provides a processor, which is used to run a program, wherein the method for constructing a product model is executed when the program is running.

[0084] Figure 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application. Figure 4 As shown, the electronic device 401 includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: determining multiple parts constituting a target product, and for each part, receiving a part design requirement input by a user; inputting the part design requirement into a target model to obtain a part model of the part, wherein the target model is obtained by training multiple sets of training samples, and each set of training samples includes historical part design requirements and historical part models; determining assembly information of the part model of each part, matching the assembly relationship and assembly position between each two part models through the assembly information, and obtaining a matching result set; assembling all part models through the matching result set to obtain a product model of the target product. The device in this article may be a server, a PC, a PAD, a mobile phone, etc.

[0085] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the following method steps: determining multiple parts that constitute a target product, and for each part, receiving part design requirements input by a user; inputting the part design requirements into a target model to obtain a part model of the part, wherein the target model is trained by multiple groups of training samples, and each group of training samples includes historical part design requirements and historical part models; determining assembly information of the part model of each part, and matching the assembly relationship and assembly position between each two part models through the assembly information to obtain a matching result set; assembling all part models through the matching result set to obtain a product model of the target product.

[0086] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0087] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0088] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0089] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0090] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0091] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0092] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0093] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0094] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0095] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for constructing a product model, characterized in that: include: Determine a plurality of parts constituting a target product, and for each part, receive part design requirements input by a user; Inputting the part design requirements into a target model to obtain a part model of the part, wherein the target model is obtained by training multiple groups of training samples, each group of training samples including historical part design requirements and historical part models; Determine assembly information of the part model of each part, match the assembly relationship and assembly position between every two part models according to the assembly information, and obtain a matching result set; All part models are assembled through the matching result set to obtain the product model of the target product.

2. The method according to claim 1, characterized in that The target model is obtained by: Obtaining model building records of each product in a product database, extracting historical part models of multiple parts from the model building records, and determining historical part design requirements when each historical part model was built; Determine the historical part design requirements and historical part models of each part as a group of training samples, and obtain multiple groups of training samples; A natural language processing model is trained based on the multiple groups of training samples to obtain the target model.

3. The method according to claim 1, characterized in that The assembly information that determines the part model of each part includes: Extracting product model information of each product from a product database, wherein the product model information includes at least one of the following: part information constituting the product, product identification, geometric data information of the product model, and part attachment point location information; Determine target part information corresponding to each part of the target product through the product model information; For each part, the size parameter information and the spatial position information of the part relative to the product to which the part belongs are extracted from the target part information of the part, and at least one of the size parameter information, the spatial position information and the part attachment point position information of the part is determined as the assembly information of the part.

4. The method according to claim 1, characterized in that: The assembly relationship and assembly position between each two part models are matched by the assembly information, and a matching result set is obtained including: For each part model, multiple attachment points are determined from the part attachment point position information of the assembly information of the part model, and a label of each attachment point is determined, wherein the attachment points of different part models have the same labels, indicating that the attachment points corresponding to the labels between the part models match each other; Determine multiple part models with the same label as a set of part model sets with an assembly relationship, and obtain multiple sets of part model sets; Determine the spatial position information in the assembly information of each part model as the initial assembly position of the part model, and calibrate the surface of the part model in contact with other part models based on the part attachment point position information to obtain the target assembly position of the part model, wherein the other part models are models other than the part model in the part model set to which the part model belongs; The target assembly positions of all the part models are determined as the matching result set.

5. The method according to claim 4, characterized in that Assembling all part models through the matching result set to obtain the product model of the target product includes: Receiving assembly data input by the user for each part model, wherein the assembly data includes at least one of the following: dimension parameter data and constraint relationship data of the part model, the constraint relationship data being used to characterize the dimension range and position data range of the part feature on the part model; All part models are assembled according to the assembly data and the target assembly position to obtain a product model of the target product.

6. The method according to claim 5, characterized in that After all the part models are assembled using the assembly data and the target assembly position, the method further includes: Determine whether each part model is assembled successfully; When all the part models are assembled successfully, a first prompt message is issued, wherein the first prompt message is used to prompt that the assembly of the product model is completed; In the case where the assembly of the part model fails, determining the part model set to which the part model belongs as the model set to be adjusted; Detect whether there is an assembly data conflict between the part models in the set of models to be adjusted, and issue a second prompt message when an assembly data conflict is detected, wherein the second prompt message is used to prompt the user to adjust the assembly data of the part model with the assembly data conflict.

7. The method according to claim 1, characterized in that After all the part models are assembled through the matching result set to obtain the product model of the target product, the method further includes: receiving a parameter adjustment request from the user for the product model, and determining a parameter to be adjusted and target data based on the parameter adjustment request, wherein the parameter to be adjusted includes at least one of the following: a size parameter of the product model and assembly information of each part model; The current data of the to-be-adjusted parameter of the product model is modified to the target data to obtain an updated target model.

8. A device for constructing a product model, characterized in that: include: A first determining unit is used to determine a plurality of parts constituting a target product, and for each part, receive a part design requirement input by a user; An input unit, used for inputting the part design requirements into a target model to obtain a part model of the part, wherein the target model is obtained by training multiple sets of training samples, each set of training samples including historical part design requirements and historical part models; A second determination unit is used to determine assembly information of a part model of each part, and match the assembly relationship and assembly position between every two part models through the assembly information to obtain a matching result set; An assembly unit is used to assemble all part models through the matching result set to obtain a product model of the target product.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for constructing a product model according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for constructing a product model as described in any one of claims 1 to 7.

Images