Method, system and equipment for assisting inspiration process of designer and medium

Abstract

The invention relates to the related technical field of auxiliary tools for design, and discloses a method, a system, equipment and a medium for assisting the inspiration process of a designer, and the method comprises the following steps: S1, a task description and keyword generation stage: receiving design task description input by the designer, and extracting a keyword, a design target and an emotion demand of a design task through a natural language processing technology; s2, an inspiration generation and search stage: according to the extracted keywords, utilizing a generative AI tool to generate related design materials, performing intelligent search in a design drawing library and a platform through an AI search engine, and automatically extracting inspiration materials related to a design task; the advantages of different models are utilized for synergistic interaction: the large language model, the Midjurney generation model and the CLIP model integrated in the workflow respectively exert unique advantages and cooperate with one another, the efficiency and accuracy of the whole workflow are improved, and it is ensured that most valuable information and resources can be provided for designers in each link.

Description

Technical Field

[0001] The present invention belongs to the technical field related to design auxiliary tools, and more specifically, particularly relates to a method, system, device and medium for assisting a designer's inspiration process. Background Art

[0002] The design process is the core of creativity, and inspiration is the key driving force for innovation. Designers usually seek external stimulation in the conception stage to build and solve the problems they face. Traditional sources of inspiration include image search platforms such as Pinterest, which provide a large amount of visual materials, but most of these images are existing design cases, lacking pertinence and personalization, and it is difficult to obtain innovative results; In recent years, the rise of artificial intelligence generative (AIGC) technology has provided designers with new sources of inspiration. AIGC tools, such as Midjourney, can quickly generate a large number of design concepts based on the needs of designers, and create unprecedented design ideas by imitating and integrating different styles and elements. However, existing AIGC tools still have limitations in understanding the designer's intentions, matching the generated results with expectations, and exploring design possibilities. The solutions generated by AIGC tools can often only provide creative guidance, and lack consideration of implementation and feasibility; At present, research on the sources of inspiration for designers mostly focuses on the analysis of traditional sources of inspiration. Research on AIGC as an emerging source of inspiration is still in its infancy, and there is a lack of an effective workflow that combines the two sources of inspiration to assist designers in obtaining inspiration.

[0003] Therefore, in view of this, the existing structure and deficiencies are studied and improved, and a method, system, equipment and medium to assist the designer's inspiration process are provided, in order to achieve a more practical and valuable purpose. Summary of the invention

[0004] The present invention provides a method, system, device and medium to assist a designer's inspiration process, so as to overcome the above-mentioned defects in the prior art.

[0005] The purpose and effect of the method, system, device and medium for assisting the designer's inspiration process of the present invention are achieved by the following specific technical means: A method to assist the designer's inspiration process, including: S1: Task description and keyword generation stage, receiving the design task description input by the designer, and extracting the keywords, design goals and emotional needs of the design task through natural language processing technology; S2: Inspiration generation and search stage: Generative AI tools are used to generate relevant design materials based on the extracted keywords, and AI search engines are used to intelligently search in the design gallery and platform to automatically extract inspiration materials related to the design task; S3: Inspiration screening and deepening stage. Based on the designer’s choice of the generated and searched inspiration materials, the system helps the designer focus on the most interesting creative direction through an intelligent screening mechanism, and further generates relevant design optimization suggestions; S4: Design iteration and optimization stage. Based on the designer’s feedback, the system optimizes the design solution, provides design iteration suggestions, helps the designer optimize the design solution, and further improves the design details based on the feedback.

[0006] According to a further technical solution, the inspiration generation and search phase includes the following steps: Generate images, design sketches, or product renderings using generative AI tools; Using image recognition and semantic retrieval technology, intelligent searches are performed in design galleries and platforms to extract inspiration materials related to design tasks.

[0007] Further technical solutions, the inspiration screening and deepening stage is achieved by the following steps: Automatically generate design solutions related to the selected inspiration based on the feedback input by the designer; Further optimize or improve the design based on the feedback from the design plan and provide design optimization suggestions.

[0008] Further technical solutions, the design iteration and optimization stage is achieved by the following steps: Based on the designer's feedback, we continue to optimize the design plan and provide further design improvement suggestions.

[0009] A further technical solution is that the task description and keyword generation stage uses a large language model (such as GPT, BERT) to perform natural language processing on the design task, automatically extract keywords, design goals and emotional needs, and generate a keyword list for the design task.

[0010] As a further technical solution, the inspiration generation and search stage uses an AI search engine to intelligently analyze and recommend design materials related to designer needs, and generate customized inspiration images or sketches.

[0011] As a further technical solution, the design iteration and optimization stage automatically generates multiple design solutions through an artificial intelligence recommendation algorithm, and optimizes the design content based on the designer's feedback.

[0012] According to another aspect of the present disclosure, a system for assisting a designer's inspiration process is provided, comprising: Input module: used to receive the design task description input by the designer and generate corresponding keywords, design goals and emotional needs; Generation module: used to generate relevant design materials according to the design task description, and find relevant design inspiration in the design gallery through intelligent search engine; Screening module: used to screen and recommend design solutions related to the inspiration materials selected by the designer, and further generate design optimization suggestions; Optimization module: Used to continuously iterate and optimize the design plan based on designer feedback and provide further design improvement suggestions.

[0013] 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-described method when executing the computer program.

[0014] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that when the computer program is executed by a processor, the steps of the method described above are implemented.

[0015] Compared with the prior art, the present invention has the following beneficial effects: In the method, system, device and medium of the present invention for assisting the designer's inspiration process, the advantages of different models are used to synergize and enhance efficiency: the large language model, Midjourney generation model and CLIP model integrated in the workflow each play their unique advantages and work together. They perform well in understanding user intent, generating keywords and providing design ideas based on image descriptions; Midjourney can generate high-quality creative images based on converted instructions; and the CLIP model provides efficient indexing and retrieval capabilities for library images. This multi-model collaborative working mode gives full play to the expertise of each model in natural language processing, image generation and image-text matching, improves the efficiency and accuracy of the entire workflow, and ensures that the most valuable information and resources are provided to designers at every stage. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 is a flowchart according to an exemplary embodiment of the present disclosure; Figure 2is a system block diagram of an assisting designer inspiration process according to an exemplary embodiment of the present disclosure; Figure 3 is a block diagram of an electronic device according to an exemplary embodiment of the present disclosure; Figure 4 Detailed description of the invention is given in detail in the figure. DETAILED DESCRIPTION

[0018] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0019] In the description of the present invention, unless otherwise specified, "plurality" means two or more than two; the orientations or positional relationships indicated by the terms "upper", "lower", "left", "right", "inner", "outer", "front end", "rear end", "head", "tail", etc. are based on the orientations or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0020] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "connected" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0021] As attached Figure 1 To Attachment Figure 4 As shown: The present invention provides a method, system, device and medium for assisting a designer's inspiration process.

[0022] Refer to the attached Figure 1 ,include: 1. Task description and keyword generation stage; In this stage, designers input simple design task descriptions (such as product appearance, functional requirements, etc.) through natural language. The system processes the descriptions through large language models (such as GPT, BERT, etc.) and automatically extracts keywords, design goals, and emotional needs. These keywords include not only specific objects and forms, but also design styles, emotions, and background information, helping the system build a basic framework for inspiration generation.

[0023] The user first enters a design task description, which is defined as the variable {x}input_task. Subsequently, the workflow calls Doubao, a knowledge-enhanced large language model developed by ByteDance. The model performs well in language understanding, generation, and cross-language processing. It can accurately understand user intentions, emotions, and tone, and provide intelligent, accurate, and personalized answers and suggestions. With a lot of training and rich knowledge reserves, it can generate natural and fluent language content. Especially in Chinese understanding and expression, it has significant advantages over the GPT series models. When calling the Doubao model, the system's built-in instructions are: Please conceive inspiration keywords related to the task based on the design task {x}input_task entered by the user. The keywords should be as abstract as possible and considered from the level of emotion and atmosphere. The Doubao model outputs a series of keywords based on its algorithm and learning ability. For example, for the task of "Mars Survival Concept Design", keywords such as "Lonely Abyss", "Spiritual Frontier", and "Technology Dreamweaving" may be output, which will serve as the key basis for subsequent inspiration searches.

[0024] 2. Inspiration generation and search stage; In this stage, the system combines generative AI tools (such as Midjourney and DALL·E) and AI search engines to generate and search for inspirational materials related to the task based on the extracted keywords.

[0025] AI generation method: In view of the current restrictions on the input command format of generative AI tools, the user input content needs to be converted before being connected to the generation tool. The system prompts the user to enter a specific noun based on the design direction based on their own cognition, defined as the variable {x}input_word1, and combined with the inspiration atmosphere word selected in the keyword definition stage (defined as the variable {x}input_word2) to enter the Doubao model. The built-in command is: When conducting the inspiration divergence of {x}input_task, please generate 3 commands that can be input into the midjourney based on the desired design direction {x}input_word1 and the theme of {x}input_word2, such as: / imagine body Mars wearable equipment design, dark and desolate color palette dominated by deep grays and blacks, rough and textured surface, feature a unique helmet with a narrow visor that gives a sense of mystery and isolation, some dim red lights on the edges of the equipment indicating the life. This node outputs {x}output_prompt, and then connects to the midjourney generation tool, inputs the {x}output_prompt command to generate inspiration pictures and output them to users. Midjourney uses deep learning neural networks, trained on massive image and text description data sets, and with the help of advanced technologies such as diffusion technology and transformer models, it can understand user text descriptions and generate high-quality, diverse styles (realistic, cartoon, abstract, etc.) of visual images, which are widely used in many fields.

[0026] AI search method: In this link, AI search combines online search with knowledge base search, and collects pictures in batches on multiple designated websites (such as Pinterest, behance, etc.) through CrawlWorm Picture. Users can enter keywords based on their personal cognition, and the system collects according to the configuration parameters. At the same time, the system supports users to access the material library, in which the pictures are indexed by the CLIP model to form picture embeddings. As an advanced text-image pre-training model using contrastive learning launched by OpenAI, the CLIP model performs well in multiple key task areas. By learning a large number of text-image pairs, it can convert pictures into vector representations with rich semantic information, namely picture embeddings. When users enter keywords, the keywords are converted into text embeddings. The CLIP model then calculates the cosine similarity between the image embedding of the picture and each text embedding. This calculation method is based on the vector space model and can accurately measure the degree of association between pictures and keywords at the semantic level. Pictures with high similarity are accurately screened and output to users, realizing an efficient conversion from vague keyword input by users to accurate picture recommendations.

[0027] 3. Inspiration screening and deepening stage; Due to the huge amount of inspiration materials generated and searched, designers may face information overload. Therefore, the system helps designers quickly focus on the creative direction they are most interested in through intelligent screening and guidance mechanisms. Designers can further describe the selected inspiration, and the system automatically provides improvement or optimization suggestions based on the description to deepen the design details.

[0028] This stage mainly deals with the "information overload" problem that may be caused by the rich pictures generated in the first two stages. Too much information may hinder decision-making and creative thinking. The workflow helps designers refine the design direction by guiding users to describe inspirational pictures of interest and combining them with design goals.

[0029] The system prompts the designer to enter a description of an inspiration picture, which is defined as a variable {x}input_description and connected to the Doubao model. The built-in instruction is: Please conceive possible design directions based on my description {x}input_description, combined with the design task of {x}input_task, and output detailed design ideas to provide inspiration for users. For example, when the input description is "a helmet for survival on Mars, with a red warning light and a wasteland atmosphere", combined with the design task of "Mars concept survival", the system may output design directions such as environmental monitoring and warning enhancement: integrate advanced environmental monitoring sensors on the helmet, and the red warning light is not only used for emergency warnings, but its light color or flashing mode can provide real-time feedback on key information such as radiation, atmospheric composition, and temperature in the Martian environment. Normally, the warning light is a weak blue light, turns yellow and flashes when the radiation rises slightly, turns red and flashes when it exceeds the standard, and sends an alarm to the communication equipment. In this way, designers can filter and deepen their design ideas among many inspirations, and improve design efficiency and quality.

[0030] 4. Design iteration and optimization stage; In the later stages of the design process, the system continuously optimizes the design through continuous user feedback. Designers can modify and adjust the generated solutions, and the system will automatically provide matching design solutions based on the feedback information and suggest further optimization directions. This design iteration mechanism can greatly improve the creative output in the design process and quickly form a feasible design solution.

[0031] For example: After selecting the design of a smart home control console, the designer requires the system to adjust the layout of the control interface to make it more ergonomic.

[0032] The system provides different interface layout designs based on feedback, including button arrangement, color matching, interactive functions, etc., and recommends ergonomic design solutions.

[0033] Embodiment 1: Design of smart sports shoes; User input design task: "Smart sports shoe design, suitable for urban running".

[0034] The system analyzes the task description and extracts the keywords: “smart,” “sports shoes,” and “city running.”

[0035] The system generates multiple sneaker design sketches through generative AI tools such as Midjourney, showing images of shoes that are modern, comfortable, and adapted to running environments.

[0036] The user selected one of the designs and further requested that the upper material be made more breathable and that a reflective design be considered.

[0037] The system adjusts the upper design as required and provides different reflective area distribution schemes, showing different reflective effects and color combinations.

[0038] The user finally selected a shoe with high breathability, reflective design and intelligent functions (such as cadence monitoring and foot pressure distribution analysis), and made final design optimization based on the feedback.

[0039] Example 2: Design of future home intelligent control system; User input design task: "Future home intelligent control system, suitable for multi-device control".

[0040] The system extracts keywords: "future home", "smart control", "multi-device control", and generates design inspirations, such as voice control, touch screen control, mobile phone APP remote control, etc.

[0041] The system automatically searches for design materials related to the task and finds similar design works that have been published by some designers.

[0042] The user chose a design that integrated a touch screen and voice assistant, and required the system to add control support for more devices, such as air conditioning, audio, etc.

[0043] The system provides different layout designs based on needs, and recommends interactive integration of the device control area with other home areas to improve the system's usability and visual aesthetics.

[0044] Example 3: Future office furniture design The user inputs the design task: "Future office furniture, combining comfort and technology."

[0045] The system generated keywords: "office furniture", "comfort", "sense of technology", and generated some design sketches, such as smart desks, adjustable chairs, and furniture with integrated wireless charging.

[0046] The system further optimizes the design based on user needs, such as "the design should have remote adjustment capabilities and can be adjusted through the APP."

[0047] The system generated optimized design sketches, showing multifunctional, intelligently adjustable desks and chairs, and optimized material selection, recommending environmentally friendly and durable synthetic materials.

[0048] This stage aims to provide designers with a wide range of sources of inspiration. The workflow supports two ways of obtaining inspirational images: AI search and AI generation. The method for assisting a designer's inspiration process provided in this embodiment may be executed in an intelligent terminal, a computer terminal, a network device, a chip, a chip module or a similar computing device.

[0049] Corresponding to the method for assisting the designer's inspiration process described above, this embodiment also provides a system for assisting the designer's inspiration process. The following will introduce each of them. Specifically, Figure 2 As shown, the system for assisting the designer inspiration process of this embodiment includes: Input module: used to receive the design task description input by the designer and generate corresponding keywords, design goals and emotional needs; Generation module: used to generate relevant design materials according to the design task description, and find relevant design inspiration in the design gallery through intelligent search engine; Screening module: used to screen and recommend design solutions related to the inspiration materials selected by the designer, and further generate design optimization suggestions; Optimization module: Used to continuously iterate and optimize the design plan based on designer feedback and provide further design improvement suggestions.

[0050] It should be noted that the system embodiment for assisting the designer's inspiration process provided in the embodiments of the present application and the method embodiment for assisting the designer's inspiration process described above are based on the same inventive concept.

[0051] It should be noted that the system for assisting the designer's inspiration process in this embodiment can be, for example: a separate chip, a chip module or an 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, or hardware modules / units, or they can be partially software modules / units and partially hardware modules / units. For example, for various devices and products applied to or integrated in 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 a 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 in 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 software programs. The software program runs on a processor integrated inside the chip, and the remaining (if any) 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.

[0052] The present invention provides 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, and the method of assisting the designer's inspiration process is implemented when the processor executes the program. Figure 3 The electronic device 30 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0053] like Figure 3 As shown, the electronic device 30 may be in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 30 may include, but are not limited to: at least one processor 31, at least one memory 32, and a bus 33 connecting different system components (including the memory 32 and the processor 31).

[0054] The bus 33 includes a data bus, an address bus, and a control bus.

[0055] 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 .

[0056] 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.

[0057] The processor 31 executes various functional applications and data processing by running the computer programs stored in the memory 32, such as the method of assisting the designer inspiration process of the first embodiment of the present invention.

[0058] The electronic device 30 may also communicate with one or more external devices 34 (e.g., keyboards, pointing devices, 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 3 As shown, the network adapter 36 communicates with other modules of the model-generated device 30 via the bus 33. It should be understood that, although not shown in the figure, other hardware and / or software modules can 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 (disk array) systems, tape drives, and data backup storage systems, etc.

[0059] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0060] This embodiment provides a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the steps in the method of assisting a designer's inspiration process are implemented.

[0061] 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 of the above.

[0062] In a possible implementation manner, the present invention may also be implemented in the form of a program product, which includes program codes. When the program product is run on a terminal device, the program codes are used to enable the terminal device to execute the steps of the system method for implementing an aided designer inspiration process.

[0063] Among them, the program code for executing the present invention can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0064] Principle of the invention: In order to assist the designer's inspiration process and overcome the defects of traditional inspiration acquisition methods, the present invention introduces a large language model to optimize the designer's inspiration process.

[0065] The first is the inspiration generation mechanism of multimodal fusion The workflow uses multiple methods to acquire and transform keywords: In the keyword definition stage, the workflow uses the powerful semantic understanding and generation capabilities of the large language model to generate abstract and emotional keywords from the design task description input by the user. This keyword generation method starting from the abstract level avoids the problem of design solidification caused by traditional specific keywords and provides a broader space for subsequent inspiration expansion. At the same time, the specific design direction nouns input by the user are combined with abstract atmosphere words and converted into an instruction format suitable for generative AI tools such as Midjourney, realizing the effective conversion from natural language descriptions to instructions that can generate creative images, and fully tapping the conversion potential of user intentions between different modalities (text to image).

[0066] In the inspiration search phase, this workflow innovatively integrates AI generation and AI search to obtain inspiration images. The AI ​​generation method uses tools such as Midjourney to generate high-quality, diverse styles of creative images that meet user-specific needs (combined with design direction and atmosphere), providing designers with new visual inspiration. The AI ​​search method combines online search and knowledge base search, which can not only collect images from a wide range of online resources (such as Pinterest, behance, etc.), but also use the image resources indexed by the CLIP model in the material library, realizing the comprehensive integration of multiple types of image resources to meet designers' needs for inspiration materials of different styles and sources.

[0067] In the inspiration selection stage, designers are guided to describe inspiration pictures of interest and input them into the big language model in combination with the design task to obtain detailed design ideas. This method effectively utilizes the big language model's deep understanding of text and creative generation capabilities, transforming the designer's perceptual understanding of a single picture into a specific and actionable design direction, helping designers to quickly focus on and deepen creative concepts related to design tasks when faced with many inspiration pictures, overcoming the decision-making difficulties caused by "information overload" and improving the conversion efficiency from inspiration acquisition to design decision-making.

[0068] At the same time, the entire workflow can dynamically adjust the output results based on the user's input at different stages (such as design task description, design direction noun, inspiration picture description, etc.). Whether it is keywords, inspiration pictures or design ideas, they are all closely centered around the user's personalized needs and specific design tasks. This feature enables the workflow to adapt to the diverse needs of different designers in different design scenarios, providing customized inspiration support and design guidance, significantly improving the flexibility and pertinence of the design process.

[0069] This workflow uses the advantages of different models to achieve synergy: the large language model, Midjourney generative model, and CLIP model integrated in the workflow each play their own unique advantages and work together. Doubao performs well in understanding user intent, generating keywords, and providing design ideas based on image descriptions; Midjourney can generate high-quality creative images based on converted instructions; and the CLIP model provides efficient indexing and retrieval capabilities for library images. This multi-model collaborative working mode fully utilizes the expertise of each model in natural language processing, image generation, and image-text matching, improves the efficiency and accuracy of the entire workflow, and ensures that the most valuable information and resources are provided to designers at every stage.

[0070] 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 recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this embodiment is not limited here.

[0071] It should be understood that the "system", "device", "unit" and / or "module" used in this embodiment is a method for distinguishing different components, elements, parts, parts or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0072] In this embodiment, a flow chart is used to illustrate the operations performed by the system according to the embodiment of the present embodiment. It should be understood that the preceding or following operations are not necessarily performed precisely in order. On the contrary, each step can be processed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0073] As shown in this embodiment, unless the context clearly indicates an exception, the words "a", "an", "a kind" and / or "the" do not specifically refer to the singular, but may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate that the steps and elements that have been clearly identified are included, and these steps and elements do not constitute an exclusive list, and the method or device may also include other steps or elements.

[0074] The definition of including in this embodiment, as used herein, the terms "having", "may have", "including", or "may include" indicate the existence of the corresponding functions, operations, elements, etc. of this embodiment, and do 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" as used herein indicate the existence of the features, 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 features, numbers, steps, operations, elements, parts, or a combination thereof.

[0075] In the definition of and / or in this embodiment, the terms "A or B", "at least one of A and / or B" or "one or more of A and / or B" as used herein include 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.

[0076] The definitions of first and second in this embodiment, and the descriptions of first, second, etc. in this embodiment are only used for illustration and distinction of the described objects, and have no order, nor do they represent a special limitation on the number of devices in this embodiment, and cannot 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, and similarly, a second element may be referred to as a first element.

[0077] Although the specific embodiments of the present invention are described above, it should be understood by those skilled in the art that this is only for illustration and the protection 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, but these changes and modifications all fall within the protection scope of the present invention.

Claims

1. A method for assisting a designer's inspiration process, characterized in that: include: S1: Task description and keyword generation stage, receiving the design task description input by the designer, and extracting the keywords, design goals and emotional needs of the design task through natural language processing technology; S2: Inspiration generation and search stage: Generative AI tools are used to generate relevant design materials based on the extracted keywords, and AI search engines are used to intelligently search in the design gallery and platform to automatically extract inspiration materials related to the design task; S3: Inspiration screening and deepening stage. Based on the designer’s choice of the generated and searched inspiration materials, the system helps the designer focus on the most interesting creative direction through an intelligent screening mechanism, and further generates relevant design optimization suggestions; S4: Design iteration and optimization stage. Based on the designer’s feedback, the system optimizes the design solution, provides design iteration suggestions, helps the designer optimize the design solution, and further improves the design details based on the feedback.

2. The method for assisting a designer's inspiration process as claimed in claim 1, characterized in that: The inspiration generation and search phase includes the following steps: Generate images, design sketches, or product renderings using generative AI tools; Using image recognition and semantic retrieval technology, intelligent searches are performed in design galleries and platforms to extract inspiration materials related to design tasks.

3. The method for assisting a designer's inspiration process as claimed in claim 1, characterized in that: The inspiration screening and deepening stage is achieved through the following steps: Automatically generate design solutions related to the selected inspiration based on the feedback input by the designer; Further optimize or improve the design based on the feedback from the design plan and provide design optimization suggestions.

4. The method for assisting a designer's inspiration process as claimed in claim 1, characterized in that: The design iteration and optimization phase is achieved through the following steps: Based on the designer's feedback, we continue to optimize the design plan and provide further design improvement suggestions.

5. The method for assisting a designer's inspiration process as claimed in claim 1, characterized in that: The task description and keyword generation stage uses a large language model (such as GPT, BERT) to perform natural language processing on the design task, automatically extract keywords, design goals and emotional needs, and generate a keyword list for the design task.

6. The method for assisting a designer's inspiration process as claimed in claim 1, characterized in that: The inspiration generation and search stage uses an AI search engine to intelligently analyze and recommend design materials related to designer needs, and generate customized inspiration images or sketches.

7. The method for assisting a designer's inspiration process as claimed in claim 1, characterized in that: The design iteration and optimization stage automatically generates multiple design solutions through an artificial intelligence recommendation algorithm, and optimizes the design content based on the designer's feedback.

8. A system to assist designers in their inspiration process, characterized in that: include: Input module: used to receive the design task description input by the designer and generate corresponding keywords, design goals and emotional needs; Generation module: used to generate relevant design materials according to the design task description, and find relevant design inspiration in the design gallery through intelligent search engine; Screening module: used to screen and recommend design solutions related to the inspiration materials selected by the designer, and further generate design optimization suggestions; Optimization module: Used to continuously iterate and optimize the design plan based on designer feedback and provide further design improvement suggestions.

9. A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. 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 7 are implemented.

Images