Product design generation method, system, device and medium

Abstract

The present disclosure provides a product design generation method, system, device and medium based on knowledge graph and cultural graph model, which receives the object input by the user and converts the input object into the root node of the knowledge graph to be constructed; constructs the knowledge graph based on the root node; extracts the attribute values ​​of the leaf nodes in the knowledge graph, expands the attribute values ​​through the large language model to generate image generation prompt words; generates the design corresponding to the object through the cultural graph model based on the image generation prompt words. By deeply combining the knowledge graph with the cultural graph model, the problem that the traditional AI generation method relies only on a single prompt word and lacks systematic creative expansion capabilities is solved, making the design generation process more hierarchical, logical and controllable. It also supports automated creative divergence, combines with the knowledge graph, and dynamically generates high-quality, controllable prompt words, supporting users to automatically generate new design solutions at different levels, making inspiration exploration more efficient.

Description

Technical Field

[0001] The present disclosure relates to the technical field of product design generation, and in particular to a product design generation method, system, device and medium based on a knowledge graph and a cultural graph model. Background Art

[0002] With the advancement of technology, product design is gradually evolving from traditional manual drawing and modeling tools to intelligent, data-driven design methods. Computer-aided design (CAD) software (such as Rhino3D, 3DMax, Blender, C4D, and Keyshot) has become widely used in the product development process. These tools, relying on geometric modeling and physical rendering techniques, provide designers with high-precision visualization capabilities. However, they are primarily used to digitally present established ideas and still have certain limitations in inspiring innovation and expanding the scope of design solutions.

[0003] In recent years, the application of artificial intelligence (AI)-driven generative technologies in product design has steadily gained momentum. The rapid development of generative adversarial networks (GANs) and diffusion models, in particular, has provided designers with new tools for creative exploration. Diffusion models, through a gradual noise reduction and restoration approach, can generate high-quality images from random noise, demonstrating significant advantages in terms of stylistic consistency and detailed representation. However, existing text-to-image (T2I) technologies often rely on a single prompt to guide generation and lack the ability to expand upon existing concepts. In the actual product design process, designers often need to explore multi-dimensional and multi-level creative development around a core concept. For example, they may wish to explore design possibilities based on different materials, styles, or functions. However, traditional prompt-driven generation methods struggle to decouple these dimensions, and even fail to form a systematic creative expansion path.

[0004] Existing image generation techniques have made some progress in modifying specific dimensions of images, such as methods based on generative adversarial networks (GANs) and control methods based on diffusion models. Generative adversarial network-based methods use GANs and their variants to manipulate specific dimensions of generated images by introducing specific control vectors into the generator. For example, StyleGAN uses style vectors to hierarchically control high-level image features (such as overall shape) and low-level features (such as texture details), thereby adjusting a single dimension. However, these methods typically limit their control to global characteristics and lack support for specific local or fine-grained dimensions (such as adjusting the texture of a specific object). Furthermore, the control process requires a large amount of training data, and the model's latent space has weak interpretability, making it difficult to meet the designer's demand for high-degree-of-freedom modification of specific dimensions. Diffusion model-based control methods have recently demonstrated outstanding performance in high-quality image generation. Models such as Stable Diffusion allow for image generation using text prompts and, combined with techniques such as ControlNet, control specific dimensions of the generated image. For example, designers can partially modify the target dimension by inputting prompts such as "change object color" or "adjust texture." However, this approach has limited control granularity, and the resulting effect depends on the accuracy of the prompt. Modifying a single dimension often leads to changes in other dimensions, making it difficult to achieve completely independent control. Furthermore, with the development and related research of large language models (LLMs), a growing number of approaches have emerged that combine large language models for image generation or modification. These methods often achieve excellent results on single images.

[0005] However, design is a process of divergent thinking, and designers usually hope to expand hierarchically based on a certain concept (such as starting from a "chair" to explore design possibilities of different styles, different materials, and different functions). The current AI generation method only supports "random exploration" or "local changes" based on similarity, and lacks a systematic concept expansion path, resulting in poor divergence and logic of design solutions. Or for a certain AI-generated image, the designer cannot trace back which concepts or logic the model is based on to derive this design, making it difficult to adjust and optimize. Existing methods are difficult to support further exploration of new design directions based on existing solutions, that is, they cannot extract information from the generated results and promote the next round of creative generation.

[0006] Therefore, existing AI generation technology is difficult to meet the requirements of multi-dimensionality, systematization, controllability and explainability in the product design process. There is an urgent need for a new method to combine knowledge graphs and diffusion models to build an iterative, inspiration-driven design generation system to enhance designers' creative exploration capabilities. Summary of the Invention

[0007] The present disclosure provides a product design generation method, system, device and storage medium based on knowledge graph and cultural graph model.

[0008] According to one aspect of the present disclosure, a method for generating product designs based on a knowledge graph and a cultural graph model is provided, comprising:

[0009] Receive an object input by a user and convert the input object into a root node of a knowledge graph to be constructed; wherein the object includes text and / or an image;

[0010] The knowledge graph is constructed based on the root node; wherein the knowledge graph is stored in the form of a node-dimension-attribute triple, the node represents the object, the dimension represents a specific attribute classification of the object, and the attribute is a specific description item under the dimension, and the knowledge graph forms a tree structure with the root node as the starting point;

[0011] Extracting attribute values ​​of leaf nodes in the knowledge graph, and expanding the attribute values ​​through a large language model to generate image generation prompt words;

[0012] A prompt word is generated based on the image and a design corresponding to the object is generated through a text graph model.

[0013] In the method according to some embodiments of the present disclosure, the method further includes:

[0014] The tree structure of the knowledge graph and the generated design are visualized to generate a visualization interface with the object as the root node and including multiple levels of dimensions and attributes.

[0015] In the method according to some embodiments of the present disclosure, any leaf node in the knowledge graph is used as a new root node, and an image generation prompt word is generated based on the new root node to expand the hierarchy of the knowledge graph.

[0016] In the method according to some embodiments of the present disclosure, when the object is an image, receiving the object input by the user and converting the input object into a root node of the knowledge graph to be constructed includes:

[0017] The image is analyzed by the text graph model or the large language model, the main object in the image is extracted and a corresponding text description is generated, and the text description is converted into a root node of the knowledge graph to be constructed.

[0018] In the method according to some embodiments of the present disclosure, constructing the knowledge graph based on the root node includes:

[0019] Based on the root node and the preset question template, construct the knowledge graph through the large language model;

[0020] The knowledge graph is stored in a hierarchical lightweight text representation format.

[0021] In the method according to some embodiments of the present disclosure, the preset question template adopts a parameterized input method, and defines the knowledge graph construction rules through the [Object, M, N] triple;

[0022] Where Object is the root node name, M is the number of dimension categories, and N is the minimum number of attribute items under each dimension category.

[0023] In the method according to some embodiments of the present disclosure, storing the knowledge graph in a hierarchical lightweight text representation format includes:

[0024] The knowledge graph is stored in JSON format, wherein the JSON format includes the root node, the dimensions, and the attribute values ​​under each dimension to form a data structure with a hierarchical relationship.

[0025] According to another aspect of the present disclosure, a product design generation system based on a knowledge graph and a cultural graph model is provided, the system comprising:

[0026] A receiving module, an object input by a user, and converting the input object into a root node of a knowledge graph to be constructed; wherein the object includes text and / or an image;

[0027] A construction module constructs the knowledge graph based on the root node; wherein the knowledge graph is stored in the form of a node-dimension-attribute triple, the node represents the object, the dimension represents a specific attribute classification of the object, and the attribute is a specific description item under the dimension, and the knowledge graph forms a tree structure with the root node as the starting point;

[0028] An expansion module extracts attribute values ​​of leaf nodes in the knowledge graph and expands the attribute values ​​to generate image generation prompt words through a large language model;

[0029] A generation module generates a prompt word based on the image and generates a design corresponding to the object through a text-based graph model.

[0030] According to another aspect of the present disclosure, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the above method when executing the computer program.

[0031] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0032] The present disclosure proposes a product design generation method, system, device, and medium based on a knowledge graph and a text graph model. The method includes: receiving an object input by a user and converting the input object into a root node of a knowledge graph to be constructed; wherein the object includes text and / or an image; constructing a knowledge graph based on the root node; wherein the knowledge graph is stored in the form of a node-dimension-attribute triple, wherein the node represents the object, the dimension represents the specific attribute classification of the object, and the attribute is a specific description item under the dimension, and the knowledge graph forms a tree structure with the root node as the starting point; extracting the attribute values ​​of the leaf nodes in the knowledge graph, and expanding the attribute values ​​through a large language model to generate image generation prompt words; based on the image generation prompt words, generating a design corresponding to the object through a text graph model. By deeply combining the knowledge graph and the text graph model, the problem of traditional AI generation methods relying only on a single prompt word and lacking systematic creative expansion capabilities is solved, making the design generation process more hierarchical, logical, and controllable. It also supports automated creative divergence, combining large language models and knowledge graphs to dynamically generate high-quality, controllable prompts, allowing designers to automatically generate new design solutions at different levels, making inspiration exploration more efficient. This effectively addresses the shortcomings of existing AI generation technologies in creative divergence, fine-grained control, and iterative optimization.

[0033] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0035] Figure 1 is a schematic diagram of a first process according to an exemplary embodiment of the present disclosure;

[0036] Figure 2 is a schematic diagram of a second process according to an exemplary embodiment of the present disclosure;

[0037] Figure 3 is a schematic diagram of a third flow chart according to an exemplary embodiment of the present disclosure;

[0038] Figure 4 is a schematic diagram of a visualization effect according to an exemplary embodiment of the present disclosure;

[0039] Figure 5This is a block diagram of a product design generation system based on a knowledge graph and a cultural graph model according to an exemplary embodiment of the present disclosure;

[0040] Figure 6 is a block diagram of an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0041] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0042] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0043] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0044] In recent years, the application of artificial intelligence-driven generation technology in the field of product design has gradually emerged, especially the rapid development of generative adversarial networks and diffusion models, which have provided designers with new creative exploration tools. The diffusion model can generate high-quality images from random noise by gradually reducing noise and restoring it, and shows great advantages in style consistency and detail expression. However, most of the existing text-based image technologies rely on a single prompt word to guide generation and lack the ability to expand thinking. In the actual product design process, designers usually need to carry out multi-dimensional and multi-level creative expansion around a core concept. For example, designers may want to explore design possibilities based on different materials, different styles, different functions, etc. However, traditional prompt-driven generation is difficult to decouple these dimensions, let alone form a systematic creative expansion path. For the above reasons, such as Figure 1 、 Figure 2 and Figure 3 As shown, this embodiment provides a product design generation method based on a knowledge graph and a cultural graph model, including:

[0045] S101. Receive an object input by a user and convert the input object into a root node of a knowledge graph to be constructed; wherein the object includes text and / or an image.

[0046] In the method according to some embodiments of the present disclosure, the object input by the user is accepted as the root node for executing the next step of constructing the knowledge graph. In this step, a specific product object name is usually obtained, which is recorded as Object.

[0047] In the method according to some embodiments of the present disclosure, when the object is an image, step S101 includes:

[0048] The image is analyzed through a text-based graph model or a large language model, the main object in the image is extracted and the corresponding text description is generated, and the text description is converted into the root node of the knowledge graph to be constructed.

[0049] If the user input is in text form, it can be directly recorded. If the user provides an image input, a graph-to-text model (for example, the Blip graph-to-text model) or a multimodal large language model (for example, ChatGPT4o) can be used to automatically generate the main object in the image and record it, thus completing the construction of the initial node (i.e., the root node) of the knowledge graph.

[0050] In a specific example, designer input is obtained, and the designer provides the product (for example, "chair") that he or she wishes to design.

[0051] Text input: The designer provides the product name Name, and the initial input object = Name.

[0052] Image input: The designer provides a product design image. The Blip image-to-text model is used to determine the initial object, i.e. object = Blip. I2T (Image).

[0053] S102. Construct a knowledge graph based on the root node; wherein the knowledge graph is stored in the form of a node-dimension-attribute triple, where the node represents the object, the dimension represents the specific attribute classification of the object, and the attribute is the specific description item under the dimension. The knowledge graph forms a tree structure with the root node as the starting point.

[0054] In one example, a knowledge graph, as a structured form of knowledge representation, is intended to describe things (entities) and their relationships so that computers can understand and reason. It is usually presented as a graph structure as a whole. The structured information of the knowledge graph is stored through triples (Subject-Predicate-Object), which include nodes, edges and attributes, where nodes represent entities (such as people, places, companies, products, etc.), edges represent the relationships between entities (such as "is a friend", "located in", "belongs to"), and attributes describe the characteristics of the entities (such as name, date of birth, location, etc.). In this embodiment, the idea of ​​knowledge graph is adopted to construct a node-dimension-attribute triple. Specifically, the node represents the product entity of the object input in step S101. It is the object to be explored in combination with the knowledge graph. The dimension represents a specific angle for this entity, which will be expanded later (such as the material, color, style, etc. of the product). The attribute is a specific representation under a specific dimension. This step will use a large language model (such as ChatGPT4o) to build a knowledge graph, so that this step can give full play to the thinking expansion ability of the large language model to expand the designer's thinking and explore inspiration more efficiently.

[0055] S103: Extract the attribute values ​​of the leaf nodes in the knowledge graph, and expand the attribute values ​​through the large language model to generate image generation prompt words.

[0056] In one embodiment, the knowledge graph constructed by step S102 is a tree-like structure, in which the specific attributes of each dimension are recorded on the leaf nodes of the tree. In order to generate images for better reference by designers, this step performs a text-to-image generation operation. In the text graph, the quality of the prompt words often has a great impact on the generation results. In actual operation, if the designer is required to manually design the prompt words, the effect may be poor. Therefore, a large language model is used to expand the content on the leaf nodes to form image generation prompt words that are more in line with the requirements of text-to-image generation.

[0057] S104: Generate a design corresponding to the object through a text-based graph model based on the generated prompt words in the image.

[0058] This embodiment proposes a product design generation method based on a knowledge graph and a cultural graph model. By constructing a multi-level knowledge graph, using a large language model to expand prompt words, and combining the multi-dimensional control capabilities of a diffusion model, it realizes the intelligent generation and iterative optimization of product design. First, this embodiment solves the difficulties faced by designers in creative divergence and multi-dimensional control. By constructing a hierarchical knowledge graph of features such as style, material, and function, it provides structured guidance for the generation process, thereby improving the logic and controllability of the generation. Secondly, by dynamically expanding prompt words through a large language model, this embodiment can automatically generate high-quality, accurately described prompt words based on knowledge graph nodes, allowing users to obtain design solutions that meet their needs without manually adjusting complex text input. In addition, this embodiment combines cultural graph models or diffusion models for intelligent image generation, which not only meets the actual needs of product design, but also can perform iterative optimization without deviating from the initial creative direction, ultimately providing a more creative, systematic and efficient product design generation method.

[0059] In the methods according to some embodiments of the present disclosure, Figure 4 As shown, the product design generation method based on the knowledge graph and the cultural graph model disclosed in the present invention also includes:

[0060] S105. Visualize the tree structure of the knowledge graph and the generated design to generate a visualization interface with the object as the root node and containing multiple levels of dimensions and attributes.

[0061] The knowledge graph constructed in the above steps will be a tree structure with Object as the root node and at least three layers. * The layer is the thinking dimension when expanding the knowledge graph, the 2k+1,k∈N * The layers are some specific attributes in the 2kth dimension. Through the method of this embodiment, users can not only quickly generate multiple design solutions at the initial stage of inspiration, but also conduct systematic creative expansion by combining knowledge graphs, thereby improving the intelligent level of product design and the efficiency of creative exploration.

[0062] In the method according to some embodiments of the present disclosure, step S102 includes:

[0063] S1021. Based on the root node and preset question templates, a knowledge graph is constructed through a large language model.

[0064] S1022. Store the knowledge graph in a hierarchical lightweight text representation format.

[0065] In a specific embodiment, the knowledge graph is stored in a hierarchical lightweight text representation format, including:

[0066] The knowledge graph is stored in JSON format, which includes the root node, dimensions, and attribute values ​​under each dimension to form a data structure with a hierarchical relationship.

[0067] In one example, JSON, as a lightweight text representation format with a hierarchical structure, is completely independent of any programming language and is an ideal data exchange language. To facilitate storage and further development, this implementation uses the JSON format to store the knowledge graph. The specific format is as follows:

[0068]

[0069] In the format, "Object" is the root node, Dimensions_X represents X dimensions of divergent thinking, and the attribute_X values ​​under each Dimensions_X represent the specific attributes of that dimension.

[0070] In one embodiment, the preset question template uses a parameterized input method to define the knowledge graph construction rules through the [Object, M, N] triple. Where Object is the root node name, M is the number of dimension categories, and N is the minimum number of attribute items under each dimension category.

[0071] In one example, this step uses the large language model ChatGPT to construct the knowledge graph. To ensure that the structure described in the above steps is obtained, a preset question template is designed. By submitting this template to the large language model, a JSON text with the required format and content is obtained.

[0072] The question template is designed as follows:

[0073] Here is an idea to combine the knowledge graph and the text graphmodel.For example,given an initial prompt word and an initial image,we needto generate a knowledge graph based on the initial object.Each node of thegraph generates a new image after bringing new and different information.Allthe images generated finally form a graph structure,which is similar todivergent thinking for images.

[0074] Your current task is to generate a corresponding knowledge graph fora given object.For the main object,you need to diverge from M perspectives,and each perspective provides N specific different words or phrases underthis dimension.For example,I give the requirement:["Mobile Phone",3,3],and Iexpect to get a knowledge graph representedby JSON like this:

[0075] {

[0076] "Mobile Phone":{

[0077] "Material":["Glass","Aluminum","Plastic"],

[0078] "Style":["Modern","Vintage","Futuristic",],

[0079] "Usage":["Gaming Phone","Business Phone","PhotographyPhone"]

[0080] }

[0081] }

[0082] Your task is to return a JSON text with the structure above. Pleasenote that the JSON text above is only a format requirement. You can express your own content. All text should be in English. You only need return the JSON text. Here are my requirements:

[0083] [Object,M,N]

[0084] In the preset template, the idea of ​​the method of this embodiment is first introduced to the large language model so that it can understand the purpose and generate replies that are more in line with the expected results. In order to ensure that the reply is in the expected format, a specific example is provided in the template, requiring ChatGPT to follow the relevant format, and clearly indicating the relevant requirements, such as writing in English and only needing to reply to JSON without other descriptions. The final requirements are expressed in a formula: [Object, M, N]. Where Object is the initial object obtained in the above steps, M represents the number of dimensions, and N represents the number of specific attributes provided for each dimension. By integrating the requirements into three parameters and condensing them into this formula, future development can be facilitated. Of course, the above question template can also be used in Chinese, which will not be repeated here.

[0085] Modify the three parameters in the question template in the above step as needed and send them to the large language model to generate a JSON document, thus completing the construction of a three-layer knowledge graph. This step can also be implemented in the form of an API interface.

[0086] In the method according to some embodiments of the present disclosure, after steps S102 and S103, the method of the present disclosure further includes:

[0087] S1031. Use any leaf node in the knowledge graph as a new root node, and generate image generation prompt words based on the new root node to expand the hierarchy of the knowledge graph.

[0088] Specifically, in step S102, the knowledge graph is only constructed once for the initial input object, and a three-layer tree structure is obtained, in which the nodes contain relevant entries or images generated based on them. It should be noted that for each leaf node, it itself can be used as another initial input to generate another knowledge graph with it as the core. Therefore, the knowledge graph obtained in step S102 can be further expanded, and each leaf node can be extended again. Similarly, the newly added leaf nodes after the expansion can also be expanded again as needed, and iterated continuously. This method of hierarchical iteration using the structure of the knowledge graph automatically recommends new design directions through a large language model. Designers can choose new expansion paths based on existing generated images, making creative exploration more logical and traceable.

[0089] Attribute nodes in the knowledge graph are simple words or phrases. To apply them to the text graph model, it is best to further expand the prompt words to achieve better generation results. The text prompt word expansion is performed using the large language model ChatGPT. The second prompt word expansion question template is designed as follows:

[0090] Your task now is to write a prompt word for text-generated imagesbased on the keywords I give.The keywords are given in JSON,which contains the keywords and the model used by the text-generated image.You need to giveappropriate prompt words based on the text-generated image model.This is an example:

[0091] {

[0092] "KeyWords":["Mobile Phone","Futuristic"],

[0093] "Model":"StableDiffusionXL"

[0094] }

[0095] for this JSON, your answer maybe "A sleek futuristic mobile phone with a transparent holographic display, glowing neon edges, and a minimalist design, set in a high-tech environment with ambient cyberpunk lighting, highlydetailed textures".

[0096] All text should be in English.You only need to return the prompt.Hereis your task:

[0097] {

[0098] "KeyWords":["Object","attribute_i"],

[0099] "Model":"model_name"

[0100] }

[0101] The request to expand the prompt word is also written to a JSON file. The value of "KeyWords" is the keyword to be expanded. It comes from a leaf node and a root node in the knowledge graph, that is, a specific attribute and the initial object name. The value of "Model" is the name of the large model planned to be used in the subsequent text-based graph step. Because different large models have their own prompt word writing standards, this step can further improve the writing of prompt words.

[0102] Get the prompt word expansion results

[0103] Change the subject name and related attributes in the above template, select the model name, and send the task to ChatGPT to obtain a set of complete prompts for the text map.

[0104] Get Wenshengtu results

[0105] The expanded prompt word prompt is provided to the large model of the cultural graph StableDiffusion to generate a product design drawing corresponding to the node.

[0106] Knowledge graph expansion

[0107] For each attribute, a new knowledge graph can be generated as a new object, thereby expanding the depth and breadth of the original indication graph. This step requires changing the "Object" value of the prompt word template in the above step to a specific attribute on a leaf node.

[0108] Visual page layout

[0109] The knowledge graph ultimately forms a multi-layered tree structure, with nodes representing related attributes or generated images. Designers can see the thought process behind any node, which helps them think more divergently.

[0110] In combination with the above implementation methods, the following is a specific introduction using an example:

[0111] Step S1: Obtain designer input. The designer provides the product they wish to design (e.g., a chair).

[0112] Text input: The designer provides the product name Name, and the initial input object = Name.

[0113] Image input: The designer provides a product design image, and the Blip image-to-text model is first used to determine the initial object.

[0114] object=Blip I2T (Image)

[0115] Step S2: Modify the knowledge graph question template to:

[0116] Here is an idea to combine the knowledge graph and the text graphmodel. For example, given an initial prompt word and an initial image, we need to generate a knowledge graph based on the initial object. Each node of the graph generates a new image after bringing new and different information. All the images generated finally form a graph structure, which is similar to divergent thinking for images.

[0117] Your current task is to generate a corresponding knowledge graph fora given object.For the main object,you need to diverge from M perspectives,and each perspective provides N specific different words or phrases underthis dimension.For example,I give the requirement:["Mobile Phone",3,3],and Iexpect to get a knowledge graph representedby JSON like this:

[0118] {

[0119] "Mobile Phone":{

[0120] "Material":["Glass","Aluminum","Plastic"],

[0121] "Style":["Modern","Vintage","Futuristic",],

[0122] "Usage":["Gaming Phone","Business Phone","PhotographyPhone"]

[0123] }

[0124] }

[0125] Your task is to return a JSON text with the structure above.Pleasenote that the JSON text above is only a format requirement.You can expressyour own content.All text should be in English.You only need return the JSONtext.Here are my requirements:

[0126] [“Chair”,3,3]

[0127] The key to modifying the question template lies solely in the final question formula. The modification here, ["Chair", 3, 3], indicates that the question is considered from three different dimensions based on the "Chair" object, with each dimension providing three different attributes. Submitting the task to ChatGPT4o yields the following JSON response:

[0128]

[0129]

[0130] For each attribute obtained, you can choose to perform text-to-image operations, thereby entering step S3, or you can further expand and enter step S4. If you enter step S3, you need to expand the prompt words for text-to-image generation. Modify the question template in step S31 to the following:

[0131] Your task now is to write a prompt word for text-generated imagesbased on the keywords I give.The keywords are given in JSON,which contains the keywords and the model used by the text-generated image.You need to giveappropriate prompt words based on the text-generated image model.This is an example:

[0132] {

[0133] "Key Words":["Mobile Phone","Futuristic"],

[0134] "Model":"StableDiffusionXL"

[0135] }

[0136] for this JSON, your answer maybe "A sleek futuristic mobile phone with a transparent holographic display, glowing neon edges, and a minimalist design, set in a high-tech environment with ambient cyberpunk lighting, highlydetailed textures".

[0137] All text should be in English.You only need to return the prompt.Hereis your task:

[0138] {

[0139] "Key Words":["Chair","Vintage"],

[0140] "Model":"Flux"

[0141] }

[0142] Send the above task to ChatGPT4o and get the following expanded reply:

[0143] A vintage wooden chair with intricate carvings, aged leatherupholstery, and an antique finish, set in a cozy, dimly lit Victorian-styleroom–highly detailed, cinematic lighting

[0144] Enter this prompt into StableDiffusion to obtain the product design for this attribute. If you proceed to step S4, which involves recreating the knowledge graph for a particular attribute (for example, expanding the knowledge graph for the "Vintage" style), you can modify the final formula in the knowledge graph question template to ["Vintage", 3, 2], indicating divergent thinking about this attribute, requiring two different attribute descriptions for each dimension from three dimensions. Sending the task to ChatGPT4o yields the following JSON text:

[0145]

[0146] Thus, the second iteration of the overall knowledge graph is completed. For each node, whether it is generated when the knowledge graph is first constructed or obtained by subsequent expansion, you can choose to operate it arbitrarily in step S3 and step S4, and finally construct a divergent tree-like text / image set. The effect is as follows Figure 4 shown.

[0147] This embodiment addresses the problem of traditional AI generation methods relying solely on a single prompt word and lacking systematic creative expansion capabilities by deeply integrating knowledge graphs with cultural graph models. This makes the design generation process more hierarchical, logical, and controllable. This method supports automated creative divergence, leveraging LLM combined with knowledge graphs to dynamically generate high-quality, controllable prompt words. This allows designers to automatically generate new design solutions at different levels, making inspiration exploration more efficient and providing a new intelligent tool for product design.

[0148] The product design generation method based on the knowledge graph and the cultural graph model provided in this embodiment can be executed in an intelligent terminal, a computer terminal, a network device, a chip, a chip module or a similar computing device.

[0149] Corresponding to the product design generation method based on the knowledge graph and the cultural graph model described above, this embodiment also provides a product design generation system based on the knowledge graph and the cultural graph model. The following will introduce them separately. Specifically, Figure 5 As shown, the product design generation system based on the knowledge graph and cultural graph model of this embodiment includes:

[0150] Module 1 receives the object input by the user and converts the input object into the root node of the knowledge graph to be constructed; the object includes text and / or image;

[0151] Construction module 2: constructs a knowledge graph based on the root node. The knowledge graph is stored in the form of node-dimension-attribute triples. Nodes represent objects, dimensions represent specific attribute classifications of objects, and attributes are specific description items under dimensions. The knowledge graph forms a tree structure with the root node as the starting point.

[0152] Extension module 3 extracts the attribute values ​​of leaf nodes in the knowledge graph and expands the attribute values ​​through the large language model to generate image generation prompt words;

[0153] The generation module 4 generates prompt words based on the image and generates a design corresponding to the object through the text-graph model.

[0154] It should be noted that the product design generation system embodiment based on the knowledge graph and the cultural graph model provided in the embodiment of the present application and the above-mentioned product design generation method embodiment based on the knowledge graph and the cultural graph model are based on the same inventive concept.

[0155] It should be noted that the product design generation system based on the knowledge graph and literary graph model of this embodiment can be, for example: a separate chip, chip module or electronic device, or a chip or chip module integrated into an electronic device. Regarding the various modules / units contained in the various devices and products described in the above embodiments, they can be software modules / units, hardware modules / units, or partly software modules / units and partly hardware modules / units. For example, for various devices and products applied to or integrated into a chip, the various modules / units contained therein can all be implemented in the form of hardware such as circuits, or at least some of the modules / units can be implemented in the form of software programs, which run on the processor integrated inside the chip, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits; for various devices and products applied to or integrated into a chip module, the various modules / units contained therein can all be implemented in the form of hardware such as circuits, and different modules / units can be located in the same component (such as a chip, circuit module, etc.) or different components of the chip module, or at least some of the modules / units can be implemented in the form of hardware such as circuits. The element can be implemented in the form of a software program, which runs on the processor integrated inside the chip module, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits; for various devices and products applied to or integrated in the terminal, the various modules / units contained therein can be implemented in the form of hardware such as circuits, and different modules / units can be located in the same component (for example, chip, circuit module, etc.) or different components in the terminal, or, at least some modules / units can be implemented in the form of a software program, which runs on the processor integrated inside the terminal, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits.

[0156] This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements a product design generation method based on a knowledge graph and a cultural graph model. Figure 6 The electronic device 30 shown is only an example and should not limit the functionality and scope of use of the embodiments of the present invention.

[0157] like Figure 6As shown, the electronic device 30 may be a general-purpose computing device, such as a server device. Components of the electronic device 30 may include, but are not limited to, the at least one processor 31, the at least one memory 32, and a bus 33 connecting different system components (including the memory 32 and the processor 31).

[0158] The bus 33 includes a data bus, an address bus, and a control bus.

[0159] The memory 32 may include a volatile memory, such as a random access memory (RAM) 321 and / or a cache memory 322 , and may further include a read-only memory (ROM) 323 .

[0160] The memory 32 may also include a program / utility 325 having a set (at least one) of program modules 324, such program modules 324 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0161] The processor 31 executes various functional applications and data processing by running computer programs stored in the memory 32, such as the product design generation method based on the knowledge graph and cultural graph model disclosed in the present invention.

[0162] The electronic device 30 may also communicate with one or more external devices 34 (e.g., a keyboard, a pointing device, etc.). Such communication may be performed via an input / output (I / O) interface 35. Furthermore, the model generating device 30 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 36. Figure 6 As shown, the network adapter 36 communicates with the other modules of the model-generated device 30 via the bus 33. It should be understood that, although not shown in the figures, other hardware and / or software modules may be used in conjunction with the model-generated device 30, including but not limited to microcode, device drivers, redundant processors, external disk drive arrays, RAID (RAID) systems, tape drives, and data backup storage systems.

[0163] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more units / modules described above may be embodied in a single unit / module. Conversely, the features and functions of a single unit / module described above may be further divided and embodied by multiple units / modules.

[0164] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the steps in the product design generation method based on the knowledge graph and the cultural graph model are implemented.

[0165] The readable storage medium may include, but is not limited to, a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0166] In a possible implementation, the present invention can also be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps in the product design generation method based on the knowledge graph and literary graph model.

[0167] The program code for executing the present invention may be written in any combination of one or more programming languages, and may be executed entirely on the user device, partially on the user device, as a standalone software package, partially on the user device and partially on a remote device, or entirely on the remote device.

[0168] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This embodiment is not limited here.

[0169] It should be understood that the terms "system," "device," "unit," and / or "module" used in this embodiment are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, they can be replaced by other expressions.

[0170] In this embodiment, a flow chart is used to illustrate the operations performed by the system according to the embodiment of the present invention. It should be understood that the preceding or following operations do not necessarily need to be performed in exact order. Instead, each step can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more operations can be removed from these processes.

[0171] As shown in this embodiment, unless the context clearly indicates an exception, the words "a," "an," "an kind," and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or device may also include other steps or elements.

[0172] The definition of including in this embodiment, such as the terms "having", "may have", "including", or "may include" used herein, indicates the existence of the corresponding functions, operations, elements, etc. of this embodiment, and does not limit the existence of one or more other functions, operations, elements, etc. In addition, it should be understood that the terms "including" or "having" used herein indicate the existence of the characteristics, numbers, steps, operations, elements, parts, or a combination thereof described in the specification, and do not exclude the existence or addition of one or more other characteristics, numbers, steps, operations, elements, parts, or a combination thereof.

[0173] In the definition of and / or in this embodiment, as used herein, the term "A or B", "at least one of A and / or B", or "one or more of A and / or B" includes any and all combinations of the words listed therewith. For example, "A or B", "at least one of A and / or B", or "one or more of A and / or B" means (1) including at least one A, (2) including at least one B, or (3) including both at least one A and at least one B.

[0174] The definitions of "first" and "second" in this embodiment, and the descriptions of "first," "second," etc., appearing in this embodiment, are for illustrative purposes only and are intended to distinguish the objects being described. They are not to be considered in any particular order, nor do they represent any specific limitation on the number of devices in this embodiment, and do not constitute any limitation on this embodiment. For example, a first element may be referred to as a second element without departing from the scope of this disclosure. Similarly, a second element may be referred to as a first element.

[0175] Although specific embodiments of the present invention have been described above, those skilled in the art will appreciate that these are merely illustrative and that the scope of the present invention is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, and such changes and modifications are intended to fall within the scope of the present invention.

Claims

1. A product design generation method based on knowledge graph and cultural graph model, characterized in that: The method comprises: Receive an object input by a user and convert the input object into a root node of a knowledge graph to be constructed; wherein the object includes text and / or an image; The knowledge graph is constructed based on the root node; wherein the knowledge graph is stored in the form of a node-dimension-attribute triple, the node represents the object, the dimension represents a specific attribute classification of the object, and the attribute is a specific description item under the dimension, and the knowledge graph forms a tree structure with the root node as the starting point; Extracting attribute values ​​of leaf nodes in the knowledge graph, and expanding the attribute values ​​through a large language model to generate image generation prompt words; Generate a prompt word based on the image and generate a design corresponding to the object through a text graph model; The method further comprises: Visualizing the tree structure of the knowledge graph and the generated design to generate a visualization interface with the object as the root node and including multiple levels of dimensions and attributes; Taking any leaf node in the knowledge graph as a new root node, and generating an image generation prompt word based on the new root node to expand the hierarchy of the knowledge graph; When the object is an image, the step of receiving the object input by the user and converting the input object into a root node of the knowledge graph to be constructed includes: Analyze the image using the text graph model or the large language model, extract the main object in the image and generate a corresponding text description, and convert the text description into a root node of the knowledge graph to be constructed; The constructing the knowledge graph based on the root node includes: Based on the root node and the preset question template, construct the knowledge graph through the large language model; Storing the knowledge graph in a hierarchical lightweight text representation format; The preset question template adopts parameterized input mode and defines the knowledge graph construction rules through [Object, M, N] triples; Where Object is the root node name, M is the number of dimension categories, and N is the minimum number of attribute items under each dimension category.

2. The product design generation method based on the knowledge graph and cultural graph model according to claim 1 is characterized in that: The storing of the knowledge graph in a hierarchical lightweight text representation format includes: The knowledge graph is stored in JSON format, wherein the JSON format includes the root node, the dimensions, and the attribute values ​​under each dimension to form a data structure with a hierarchical relationship.

3. A product design generation system based on knowledge graph and cultural graph model, characterized by: For implementing the method according to any one of claims 1 to 2, the system comprises: A receiving module receives an object input by a user and converts the input object into a root node of a knowledge graph to be constructed; wherein the object includes text and / or an image; A construction module constructs the knowledge graph based on the root node; wherein the knowledge graph is stored in the form of a node-dimension-attribute triple, the node represents the object, the dimension represents a specific attribute classification of the object, and the attribute is a specific description item under the dimension, and the knowledge graph forms a tree structure with the root node as the starting point; An expansion module extracts attribute values ​​of leaf nodes in the knowledge graph and expands the attribute values ​​to generate image generation prompt words through a large language model; A generation module generates a prompt word based on the image and generates a design corresponding to the object through a text-based graph model.

4. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 2 is implemented.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 2 are implemented.

Images