Suggestions based on historical and large-scale language model knowledge

Abstract

In various implementations, a computer-implemented method for generating cue input describing a design modification includes: receiving a first cue input indicating a first modification to a three-dimensional (3D) design; determining a first context input based on one or more attributes of the 3D design; and causing a first generative machine learning (ML) model to generate a second cue input based on the first cue input and the first context input, wherein the second cue input indicates a second modification to the 3D design.

Description

[0001] Cross-reference to related applications This application claims priority to U.S. Provisional Patent Application No. 63 / 592,877, filed October 24, 2023, entitled "PROMPT SUGGESTIONS BASED ON HISTORY AND LARGE LANGUAGE MODEL KNOWLEDGE," and to U.S. Patent Application No. 18 / 924,169, filed October 23, 2024, entitled "PROMPT SUGGESTIONS BASED ON HISTORY AND LARGE LANGUAGE MODEL KNOWLEDGE." Subject matter of these related applications is incorporated herein by reference. Technical Field

[0002] The various implementation schemes generally involve computer-aided design and artificial intelligence, and more specifically, they involve suggestions based on historical and large-scale language model knowledge. Background Technology

[0003] Generative machine learning (ML) models are increasingly being integrated into regular software applications. Text prompts are a common way for users to interact with generative ML models to perform various actions within a given software application. In a typical interaction, the user inputs a text prompt to the generative ML model, and in response, the generative ML model performs an action on behalf of the user within the software application. Often, the action fails to meet the user's needs or malfunctions for other reasons. The user then typically provides additional text prompts to the generative ML model, causing it to respond by performing additional actions. This type of interaction can be repeated multiple times in a trial-and-error manner until the generative ML model performs an action that meets the user's needs.

[0004] The iterative trial-and-error process described above can become extremely complex because conventional generative ML models do not necessarily behave in a deterministic or predictable manner. Consequently, users often do not understand what types of prompts should be fed to the generative ML model to obtain a useful response. Furthermore, users typically cannot predict what actions the generative ML model will perform when given a given prompt. Therefore, continuous iteration of prompts does not necessarily produce progressively improving behavior. In summary, due to the inherent unpredictability of ML models, users often have to engage in a great deal of guesswork before performing meaningful actions.

[0005] One approach to improving the interactive trial-and-error prompting process described above is a technique called fine-tuning. Fine-tuning involves retraining the generative ML model using additional training data. Once the fine-tuning process is complete, users can sometimes write shorter and / or less detailed prompts and obtain satisfactory behavior. Sometimes users can even obtain useful behavior with less interaction. However, a drawback of fine-tuning is that the additional training data usually needs to be created manually by the user or model developer. Another drawback of fine-tuning is that, even after fine-tuning, the generative ML model may still be unable to perform certain types of operations that were not explicitly included in the additional training data.

[0006] As mentioned above, there is a need in the art for more efficient techniques for interacting with generative ML models. Summary of the Invention

[0007] In various implementations, a computer-implemented method for generating cue input describing a design modification includes: receiving a first cue input indicating a first modification to a three-dimensional (3D) design; determining a first context input based on one or more attributes of the 3D design; and causing a first generative machine learning (ML) model to generate a second cue input based on the first cue input and the first context input, wherein the second cue input indicates a second modification to the 3D design.

[0008] At least one technical advantage of the disclosed technique over existing technologies is that it enables generative ML models to generate detailed and accurate cues that specifically describe design modifications, without requiring users to iteratively refine the cues in an uncertain and unpredictable manner. Therefore, users receive cues that are more effective when interacting with the generative ML model to generate the desired design or design modifications. Another technical advantage of the disclosed technique is that it enables generative ML models to produce accurate responses to user cues without fine-tuning. Therefore, in implementing the disclosed technique, it is not necessary to create additional training data typically used in fine-tuning. These technical advantages provide one or more technical advancements superior to existing approaches. Attached Figure Description

[0009] To gain a more detailed understanding of the features described above in the various embodiments, reference can be made to the various embodiments for a more specific description of the inventive concept briefly outlined above, some of which are already illustrated in the accompanying drawings. However, it should be noted that the drawings only show typical embodiments of the inventive concept and should therefore not be considered as limiting the scope, and that other equally effective embodiments exist.

[0010] Figure 1 It is a conceptual diagram of a system configured to implement one or more aspects of various implementation schemes; Figure 2 It is based on various implementation plans. Figure 1 More detailed illustrations of design modifications and prompts for application modifications; Figures 3A to 3C It is based on various implementation plans. Figure 2 An exemplary illustration of the design space and prompt space; Figure 4 Flowcharts illustrating the method steps for generating prompts and design modifications based on prompt catalogs, according to various implementation schemes; and Figure 5 An architecture of a system in which various implementation schemes of this disclosure may be implemented is described. Detailed Implementation

[0011] In the following description, numerous specific details are set forth to provide a more thorough understanding of various embodiments. However, it will be apparent to those skilled in the art that the inventive concept can be practiced without one or more of these specific details.

[0012] System Overview Figure 1 This is a conceptual diagram of a system 100 configured to implement one or more aspects of various implementation schemes. As shown, in some implementations, system 100 includes, but is not limited to, a client device 110 and a server device 160. Client device 110 includes, but is not limited to, a processor 112, one or more input / output (I / O) devices 114, and memory 116. Memory 116 includes, but is not limited to, a graphical user interface (GUI) 120, a design modification application 130, and local data storage 140. Local data storage 140 includes, but is not limited to, design data 142, prompt input 144, and context input 146. Server device 160 includes, but is not limited to, a processor 162, one or more I / O devices 164, and memory 166. Memory 166 includes, but is not limited to, a prompt catalog 170, a prompt modification application 180, and a generative ML model 190. In some other implementations, system 100 may include any number and / or type of other client devices, server devices, additional ML models, or any combination thereof.

[0013] Any number of components of System 100 can be distributed across multiple geographical locations, or in any combination within one or more cloud computing environments. For exampleThis is implemented within encapsulated shared resources, software, and data. In some implementations, client device 110 and / or zero or more other client devices (not shown) may be implemented as one or more computing instances in a cloud computing environment, as part of any other distributed computing environment, or implemented independently. In various implementations, client device 110 may be used with any number and / or type of other devices (… For example (One or more other computing instances and / or display devices) are integrated into the user device. Some examples of user devices include, but are not limited to, desktop computers, laptop computers, smartphones, and tablet computers.

[0014] Generally, client device 110 is configured to implement one or more software applications. For illustrative purposes only, each software application is described as residing in memory 116 of client device 110 and executing on processor 112 of client device 110. In some embodiments, any number of instances of any number of software applications may reside in memory 116 and any number of other memories associated with any number of other computing instances, and execute in any combination on processor 112 of client device 110 and any number of other processors associated with any number of other computing instances. In the same or other embodiments, the functionality of any number of software applications may be distributed across any number of other software applications residing in memory 116 and any number of other memories associated with any number of other computing instances, and execute in any combination on processor 112 and any number of other processors associated with any number of other computing instances. Furthermore, subsets of the functionality of multiple software applications may be combined into a single software application.

[0015] Specifically, client device 110 is configured to implement design modification application 130, which allows a user to generate design modifications to a three-dimensional (3D) design defined by design data 142. In various embodiments, design data 142 may include any technically feasible definition of 3D geometry. In operation, design modification application 130 receives prompt input 144 from the user, wherein prompt input 144 describes one or more design modifications to the 3D design. Prompt modification application 180 then generates an alternative version of prompt input 144, which includes a higher level of detail. Based on the alternative version of prompt input 144, design modification application 130 can implement the desired design modifications.

[0016] In various embodiments, processor 112 can be any instruction execution system, device, or apparatus capable of executing instructions. For example, processor 112 may include a central processing unit (CPU), digital signal processing unit (DSP), microprocessor, application-specific integrated circuit (ASIC), neural processing unit (NPU), graphics processing unit (GPU), field-programmable gate array (FPGA), controller, microcontroller, state machine, or any combination thereof. In some embodiments, processor 112 is a programmable processor that executes program instructions to manipulate input data. In some embodiments, processor 112 may include any number of processing cores, memory, and other modules for facilitating program execution.

[0017] Input / output (I / O) device 114 includes devices configured to receive input, such as a keyboard, mouse, etc. In some embodiments, I / O device 114 also includes devices configured to provide output, such as a display device, speaker, etc. Additionally or alternatively, I / O device 114 may also include devices configured to receive and provide input and output, such as a touchscreen, Universal Serial Bus (USB) port, etc.

[0018] Memory 116 includes storage modules or a collection of storage modules. In some embodiments, memory 116 may include various computer-readable media selected for their size, relative performance, or other capabilities: volatile and / or non-volatile media, removable and / or non-removable media, etc. Memory 116 may include cache, random access memory (RAM), storage devices, etc. Memory 116 may include one or more discrete memory modules, such as dynamic RAM (DRAM) dual in-line memory modules (DIMMs). Of course, various memory chips, bandwidths, and form factors can be alternatively selected. Memory 116 stores content (such as software applications and data) for use by processor 112. In some embodiments, a storage device (not shown) supplements or replaces memory 116. The storage device may include any number and type of external memory accessible to the processor 112 of client device 110. For example, but not limited to, the storage device may include a secure digital card (SD card), external flash memory, portable optical disc read-only memory, optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0019] The non-volatile memory included in memory 116 typically stores one or more applications (including design modification application 130) and data for processing by processor 112 (e.g., design data 142, prompt input 144, and context input 146 stored in local data storage 140). In various embodiments, memory 116 may include non-volatile memory such as an optical disc drive, magnetic drive, flash drive, or other storage device. In some embodiments, separate data storage, such as one or more external data storage devices (“cloud storage”) connected via network 150, may supplement memory 116. In various embodiments, design modification application 130 within memory 116 may be executed by processor 112 to implement the overall functionality of client device 110 to coordinate the operation of system 100 as a whole.

[0020] In various embodiments, memory 116 may include one or more modules for performing the various functions or techniques described herein. In some embodiments, one or more of the modules and / or applications included in memory 116 may be implemented locally on client device 110 and / or via a cloud-based architecture. For example, any of the modules and / or applications included in memory 116 may execute on a remote device (e.g., a smartphone, server system, cloud computing platform, etc.) that communicates with client device 110 via a network interface or I / O device interface.

[0021] Design modification application 130 resides in memory 116 and executes on processor 112 of client device 110. Design modification application 130 interacts with the user via GUI 120. In some embodiments, design modification application 130 and one or more separate applications (not shown) interact with the same user via GUI 120. In various embodiments, design modification application 130 interacts with the user via GUI 120 to display a 3D model associated with design data 142 to the user.

[0022] GUI 120 receives prompt input 144 from the user and generates context input 146 based on one or more interactions between the user and GUI 120. Prompt input 144 includes text referencing a 3D design defined by design data 142. Context input 146 typically indicates one or more attributes of the 3D design. For example, but not limited to, context input 146 may include a portion of geometry associated with the 3D design and / or the current view from which GUI 120 generates a rendering of the 3D design. In various embodiments, context input 146 may further include a cursor position corresponding to a location within design data 142 and / or a selected area of ​​the 3D design. Design modification application 130 transmits prompt input 144 and context input 146 to prompt modification application 180 for further processing. In one embodiment, design modification application 130 may generate a composite prompt that includes both prompt input 144 and context input 146.

[0023] GUI 120 can be any type of user interface that allows a user to interact with one or more software applications via any number and / or type of GUI elements. GUI 120 can be displayed in any technically feasible manner on any number and / or type of stand-alone display devices, any number and / or type of displays integrated into any number and / or type of user devices, or any combination thereof. Design modification application 130 can perform any number and / or type of operations to directly and / or indirectly display and monitor any number and / or type of interactive GUI elements and / or any number and / or type of non-interactive GUI elements within GUI 120. In some embodiments, each interactive GUI element implements one or more types of user interactions that automatically trigger corresponding user events. Some examples of interactive GUI element types include, but are not limited to, scrollbars, buttons, text input boxes, drop-down lists, and sliders. In some embodiments, design modification application 130 organizes GUI elements into one or more container GUI elements (e.g., panels and / or panes).

[0024] Network 150 can be any technically feasible set of interconnected communication links, including a local area network (LAN), a wide area network (WAN), the World Wide Web, or the Internet. Network 150 enables communication between client device 110 and other devices in network 150 via wired and / or wireless communication protocols, including Bluetooth, Bluetooth Low Energy (BLE), Wi-Fi, cellular protocols, satellite networks, and / or Near Field Communication (NFC).

[0025] Server device 160 is configured to communicate with design modification application 130 to process cue input 144 and context input 146. In operation, server device 160 executes cue modification application 180 to generate one or more modified cue inputs based on cue input 144, context input 146, and cue catalog 170. The one or more modified cue inputs may represent alternative versions of cue input 144, which have a higher degree of descriptive detail and / or accuracy than cue input 144. In various embodiments, cue modification application 180 may implement generative ML model 190 to generate one or more modified cue inputs based on cue input 144, context input 146, and one or more related cue inputs derived from cue catalog 170, as described below. Figure 2 To describe in more detail.

[0026] In various embodiments, processor 162 can be any instruction execution system, device, or apparatus capable of executing instructions. For example, processor 162 may include a central processing unit (CPU), digital signal processing unit (DSP), microprocessor, application-specific integrated circuit (ASIC), neural processing unit (NPU), graphics processing unit (GPU), field-programmable gate array (FPGA), controller, microcontroller, state machine, or any combination thereof. In some embodiments, processor 162 is a programmable processor that executes program instructions to manipulate input data. In some embodiments, processor 162 may include any number of processing cores, memory, and other modules for facilitating program execution.

[0027] Input / output (I / O) device 164 includes devices configured to receive input, such as a keyboard, mouse, etc. In some embodiments, I / O device 164 also includes devices configured to provide output, such as a display device, speaker, etc. Alternatively or additionally, I / O device 164 may further include devices configured to receive and provide input and output, such as a touchscreen, Universal Serial Bus (USB) port, etc.

[0028] Memory 166 includes storage modules or a collection of storage modules. In some embodiments, memory 166 may include various computer-readable media selected for their size, relative performance, or other capabilities: volatile and / or non-volatile media, removable and / or non-removable media, etc. Memory 166 may include cache, random access memory (RAM), storage devices, etc. Memory 166 may include one or more discrete memory modules, such as dynamic RAM (DRAM) dual in-line memory modules (DIMMs). Of course, various memory chips, bandwidths, and form factors can be alternatively selected. Memory 166 stores content (such as software applications and data) for use by processor 162. In some embodiments, storage devices (not shown) supplement or replace memory 166. The storage device may include any number and type of external memory accessible to the processor 162 of server device 160. For example, but not limited to, the storage device may include a secure digital card (SD card), external flash memory, portable optical disc read-only memory, optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0029] The non-volatile memory included in memory 166 typically stores one or more applications (including prompt modification application 180 and generative ML model 190) and data for processing by processor 112 (e.g., prompt catalog 170). In various embodiments, memory 166 may include non-volatile memory such as an optical disc drive, magnetic drive, flash drive, or other storage device. In some embodiments, separate data storage, such as one or more external data storage devices connected via network 150, may supplement memory 166. In various embodiments, prompt modification application 180 and / or generative ML model 190 within memory 166 may be executed by processor 162 to enable the overall functionality of server device 160 to coordinate the operation of system 100 as a whole.

[0030] In various embodiments, memory 166 may include one or more modules for performing the various functions or techniques described herein. In some embodiments, one or more of the modules and / or applications included in memory 166 may be implemented locally on client device 110, server device 160, and / or via a cloud-based architecture. For example, any of the modules and / or applications included in memory 166 may execute on a remote device (e.g., a smartphone, server system, cloud computing platform, etc.) that communicates with server device 160 via a network interface or I / O device interface. Alternatively or additionally, prompting modification application 180 may execute on client device 110 and may communicate with generative ML model 190 operating at server device 160.

[0031] In various implementations, the prompt modification application 180 receives various inputs from the design modification application 130, including prompt input 144 and context input 146, and retrieves a set of relevant prompts from the prompt catalog 170 based on these inputs. The prompt catalog 170 typically includes a library of other prompts that may be context-related to the 3D design, such as, but not limited to, one or more recent prompts including user or other user input, a prompt history associated with the user's team, a set of commonly used prompts in the industry where the user typically operates, one or more prompts historically associated with the type of 3D design the user is currently generating, and so on.

[0032] The prompt modification application 180 inputs prompt input 144, context input 146, and one or more related prompts 170 into the generative ML model 190. In response, the generative ML model 190 generates modified prompt input that describes modifications to the 3D design described by design data 142. The given modified prompt input is a more detailed and potentially more accurate version of prompt input 144. In one embodiment, the modified prompt input may include prompt input 144 and additional context-related text generated by the generative ML model 190 to provide additional details about the desired modifications to the 3D design. In another embodiment, the modified prompt input may include a changed version of prompt input 144 modified by the generative ML model 190 to more accurately describe the modifications to the 3D design. Based on the modified prompt input, the design modification application 130 modifies the design data 142. The GUI 120 can then display an updated rendering of the 3D design associated with the design data 142.

[0033] In some implementations, one or more of the generative ML models 190 are trained to respond to specific types of input, such as ML models trained to generate text-based responses from combinations of specific modalities (e.g., text and images). In such instances, the prompting modification application 180 processes various inputs to determine the modality of the data included therein and identifies one or more of the ML models 190 that have been trained to respond to such combinations of modalities. After identifying one or more ML models 190, the prompting modification application 180 selects an ML model and inputs a prompt into the selected ML model 190.

[0034] Generative ML models 190 include one or more ML models that have been trained on relatively large amounts of existing data to perform any number and / or type of prediction tasks based on patterns detected in the existing data. In some implementations, a given trained ML model 190 is trained using various combinations of data from multiple modalities—such as text data, image data, sound data, etc. Generative ML models 190 trained using at least two data modalities are also referred to herein as multimodal ML models. For example, in some implementations, one or more trained ML models 190 may include a third-generation generative pre-trained transformer (GPT-3) model, a specialized version of the GPT-3 model referred to as the “DALL-E2” model, a fourth-generation generative pre-trained transformer (GPT-4) model, and so on.

[0035] Figure 2 It is based on various implementation plans. Figure 1 A more detailed illustration of the design modification application 130 and the prompt modification application 180 is provided. As shown, in some embodiments, system 200 includes, but is not limited to, a GUI 120, a design modification application 130, and a server device 160. GUI 120 includes, but is not limited to, a prompt space 220 and a design space 230. Design modification application 130 includes, but is not limited to, a prompt manager 240 and a visualization module 250. Server device 160 includes, but is not limited to, a domain directory 170, a prompt modification application 180, and a generative ML model 190.

[0036] For illustrative purposes only, the functionality of the design modification application 130 and the prompt modification application 180 is described herein in the context of exemplary interactive and linear workflows. As those skilled in the art will recognize, the techniques described herein are illustrative and not limiting, and can be modified and applied in other contexts without departing from the broader spirit and scope of the inventive concepts described herein.

[0037] In operation, the visualization module 250 generates a GUI 120 including a prompt space 220 and a design space 230. The prompt space 220 typically includes GUI elements for receiving text input. The design space 230 typically includes GUI elements for displaying a 3D rendering of the 3D model described by design data 142. The design space 230 also includes GUI elements that allow the user to select portions of such an image, including a cursor, etc. The prompt manager 240 interacts with the prompt space 220 to obtain prompt input 144 from the user. The prompt manager 240 also interacts with the design space 230 to obtain contextual input 146, including user selections and view information associated with the 3D rendering.

[0038] Generally, the prompt input 144 is a textual prompt that describes, to some extent, what the design space 230 should display. In some embodiments, the prompt input 144 may describe a specific image that should be displayed. For example, but not limited to, the prompt input 144 may describe a specific scene that the design space 230 should display with a given level of detail. In other embodiments, the prompt input 144 may describe modifications that should be made to the 3D design displayed via the design space 230. For example, but not limited to, the prompt input 144 may describe, with a given level of detail, the placement of holes in the 3D design displayed via the design space 230.

[0039] Context input 146 includes contextual data derived from user interactions with design space 230. For example, but not limited to, context input 146 may include user selections for a portion of a 3D rendering, or a user-selected viewpoint, etc. In various embodiments, context input 146 may also include a set of applications recently used or currently being used by the user, a set of design tools recently used or currently being used by the user to modify the 3D design, a defined skill level associated with the user relative to a given task, or the current operating mode associated with the design modification application 130.

[0040] The cue manager 240 generates a composite cue 260 to include both cue input 144 and context input 146. In one embodiment, the composite cue 260 may be a multimodal cue that includes data associated with two different modalities. For example, but not limited to, cue input 144 may include text, while context input 146 may include one or more images. In various other embodiments, cue input 144 and context input 146 correspond to a single modality (e.g., text only).

[0041] The prompt modification application 180 is configured to access the prompt directory 170 and retrieve a set of prompts contextually related to the prompt input 144 and / or context input 146 within the composite prompt 260. As described, the prompt directory 170 typically includes other prompt libraries and may include, for example, but not limited to, one or more recent prompts entered by the user or other users, a prompt history associated with the user's team, a set of commonly used prompts in the industry where the user typically operates, one or more prompts historically associated with the type of 3D design the user is currently generating, and so on. In one embodiment, the set of related prompts 182 may be sorted according to a metric reflecting the frequency or success of each related prompt's previous use. The prompt modification application 180 accesses the prompt directory 170 based on the composite prompt 260 and extracts the related prompts 182.

[0042] Then, the prompt modification application 180 causes the generative ML model 190 to process the composite prompt 260 and the associated prompt 182 to generate the modified prompt input 192. The modified prompt input 192 includes one or more alternative text prompts that typically represent an improved version of the prompt input 144. The generative ML model 190 can generate the modified prompt input 192 by adding additional language to the prompt input 144 to add descriptive detail, or by modifying the prompt input 144 to improve descriptive precision, as illustrated below with examples. Figures 3A to 3B As stated above.

[0043] Figures 3A to 3C It is based on various implementation plans. Figure 2 An exemplary illustration of the prompt space and design space. For example... Figure 3A As shown, the cue space 220 includes cue input 144, which provides a general description of an image associated with the living room. In operation, the design modification application 130 receives cue input 144 and generates any relevant contextual input 146. The cue modification application 180 retrieves one or more relevant cue inputs 182 from the cue catalog 170, and then the generative ML model 190 generates modified cue inputs 192-0 and 192-1.

[0044] In the example shown, the modified prompt inputs 192-0 and 192-1 are alternative versions of prompt input 144, which are expanded with additional text to provide further details. In this way, the prompt modification application 180 helps the user generate descriptive prompts by providing a set of suggestions. The user can then choose between the modified prompt inputs 192, and the design modification application 130 can update the design space 230 based on the selected modified prompt input 192. Therefore, the design modification application 130 can implement a generative ML model 190 to generate specific design modifications. In addition to expanding the prompt inputs, the prompt modification application 180 can also generate different versions of the prompt inputs, as mentioned above and combined below. Figure 3B To describe in more detail.

[0045] like Figure 3BAs shown, the cue space 220 includes cue input 144, which typically describes a change in gear ratio associated with a 3D design 300 representing a set of mountain bike gears. In operation, the design modification application 130 receives cue input 144 and generates contextual input 146. In this example, contextual input 146 may include, but is not limited to, a portion of design data 142 describing the current gear ratio, a portion of geometry derived from the 3D design 300, or a portion of a rendering of the 3D design 300, without limitation. Contextual input 146 may further indicate a set of common mountain bike gear ratios associated with the mountain bike industry, or a team of mountain bike engineers interacting with the user. In one embodiment, the design modification application 130 or the cue modification application 180 may analyze cue input 144 and collect relevant context to resolve ambiguous or vague descriptive text. In the described example, the design modification application 130 or the cue modification application 180 may use various contextual factors as needed to resolve the text “a more common mountain bike gear ratio” to a specific gear ratio determined to be common. Based on the prompt input 144 and the context input 146, the prompt modification application 180 then retrieves one or more relevant prompts 182 from the prompt catalog 170. The generative ML model 190 then generates the modified prompt input 190.

[0046] The modified prompt input 192 in the example shown is a more detailed version of the updated prompt input 144 to include specific details of the mountain bike gear ratio. In this manner, the prompt modification application 180 helps the user generate prompts with greater accuracy and detail. The user can select the modified prompt input 192, and then the design modification application 130 can update the design data 142 with the specific design modifications expressed in the modified prompt input 192. The design modification application 130 can implement the generative ML model 190 in any technically feasible manner to generate these design modifications. Figure 3C This provides another example of how the Tip Modification App 180 can help users develop more detailed and accurate tips.

[0047] like Figure 3CAs shown, the prompt space 220 includes prompt input 144, which typically describes additions the user wants to make to the 3D design. Here, the user wants to add fasteners to a mounting bracket, which are custom-designed to be compatible with a set of existing holes. In response to prompt input 144, the design modification application 130 generates context input 146. In this example, context input 146 may include, but is not limited to, a specific design geometry reflecting the existing placement of the holes. Based on prompt input 144 and context input 146, the prompt modification application 180 then retrieves one or more relevant prompts 182 from the prompt catalog 170. The generative ML model 190 then generates the modified prompt input 192.

[0048] The modified prompt input 192 is an alternative to prompt input 144, updated to include specific text describing the current placement of the hole on the mounting bracket. Therefore, the modified prompt input 192 more specifically indicates the desired positioning of the requested fastener. In this way, the prompt modification application 180 generates modified prompt inputs that describe design changes with greater accuracy than the prompt inputs received from the user. When the user selects the modified prompt input 192, the design modification application 130 then updates the design data 142 with the specific design modifications expressed in the modified prompt input 192. The design modification application 130 can implement the generative ML model 190 in any technically feasible manner to generate these design modifications and update the design data 142.

[0049] Overall reference Figures 3A to 3C Using the aforementioned techniques, design modification application 130 and prompt modification application 180 interoperate to generate modified prompts that more specifically describe a set of desired design modifications. These design modifications can then be applied to the 3D design. This approach simplifies the typical iterative prompting process by assisting the user with more detailed and descriptive prompts that are context-relevant and directly related to the 3D design.

[0050] Figure 4 Flowcharts illustrating the methodological steps for generating prompts and design modifications based on a prompt catalog, according to various implementation schemes, are presented. (Although references are provided...) Figures 1 to 3C The system describes the method steps, but those skilled in the art will understand that any system configured to implement the method steps in any order falls within the scope of the implementation.

[0051] As shown in the figure, method 400 begins at step 402, where design modification engine 130 receives prompt input 144 via GUI 120. Prompt input 144 typically corresponds to a 3D design described via design data 142. GUI 120 is configured to display a 3D rendering of the design to the user via design space 230. Prompt input 144 is received via prompt space 220 within GUI 120.

[0052] At step 404, the design modification engine 130 receives context input 146 via GUI 120. Context input 146 includes contextual information associated with the 3D design and / or various user interactions with the 3D design. For example, but not limited to, context input 146 may include user selection of a portion of the 3D design, the current viewpoint of the 3D design, a portion of the 3D design referenced by prompt input 144, or various metadata describing one or more attributes of the 3D design. In one embodiment, the design modification engine 130 generates a composite prompt 260 that includes prompt input 144 and context input 146 and transmits the composite prompt 260 to the prompt modification application 180 for further processing.

[0053] At step 406, the application 180 is prompted to access the prompt directory 170 to identify the group of related prompts 182. The prompt directory 170 typically includes other prompt libraries and may include, for example, but not limited to, one or more recent prompts entered by the user or other users, a prompt history associated with the user's team, a set of prompts commonly used in the industry where the user typically operates, one or more prompts historically associated with the type of 3D design currently generated by the user, and so on.

[0054] At step 408, the prompt modification application 180 causes one or more of the generative ML models 190 to generate modified prompt input 192 based on prompt input 144, context input 146, and / or the set of related prompts 182. In one embodiment, the prompt modification application 180 may select a domain-specific generative ML model 190 based on specific content and / or context associated with prompt input 144. For example, but not limited to, the prompt modification application 180 may select a generative ML model 190 specifically trained and / or fine-tuned using data related to electrical engineering to generate one or more modified prompt inputs 192 related to the prompt input 144 associated with electrical engineering.

[0055] At step 410, the design modifies application 130 so that GUI 120 displays the modified prompt input 192. GUI 120, within prompt space 220, utilizes... Figures 3A to 3CThe example in the diagram shows the modified prompt input 192. In various implementations, GUI 120 displays the modified prompt input 192 together with prompt input 144 as a suggested alternative to prompt input 144. GUI 120 may display the modified prompt input 192 as, for example, but not limited to, a dropdown list below prompt input 144.

[0056] At step 412, GUI 120 receives from the user a selection of one of the modified prompt inputs 192. The modified prompt input 192 selected by the user may describe a specific design modification the user wants to make to the 3D design displayed via design space 230. The modified prompt input 192 may include prompt input 144 along with additional descriptive text provided via prompt modification application 180, or alternatively may include an updated version of prompt input 144 modified to improve specificity, accuracy, and / or detail.

[0057] At step 412, the design modification application 130 generates a design modification based on the selected modification prompt input 192. In one embodiment, the design modification application 130 can implement one or more of the generative ML models 190 to generate design modifications based on the current state of the 3D design described via design data 142. At step 416, the design modification engine 130 applies the design modification to the design. Therefore, the design modification engine 130 can implement various generative techniques to produce 3D geometry representing an updated version of the 3D design. At step 418, the design modification engine 130 causes the GUI 120 to display the modified version of the design.

[0058] System Implementation Method Figure 5 An architecture of a system 500 in which embodiments of the present disclosure may be implemented is depicted. The accompanying drawings are in no way limiting or intended to limit the scope of the present disclosure. In various implementations, system 500 may be an augmented reality, virtual reality, or mixed reality system or device, a personal computer, a video game console, a personal digital assistant, a mobile phone, a mobile device, or any other device suitable for practicing one or more embodiments of the present disclosure. Furthermore, in various embodiments, any combination of two or more systems 500 may be coupled together to practice one or more aspects of the present disclosure.

[0059] As shown in the figure, system 500 includes a central processing unit (CPU) 502 and system memory 504 that communicate via a bus path, which may include a memory bridge 505. CPU 502 includes one or more processing cores and, in operation, is the main processor of system 500 that controls and coordinates the operation of other system components. System memory 504 stores software applications and data used by CPU 502. CPU 502 runs software applications and, optionally, an operating system. Memory bridge 505, which may be, for example, a northbridge chip, is connected to I / O (input / output) bridge 507 via a bus or other communication path (e.g., a hyperlink). I / O bridge 507, which may be, for example, a southbridge chip, receives user input from one or more user input devices 508 (e.g., keyboard, mouse, joystick, digitizer, touchpad, touchscreen, still or video camera, motion sensor, and / or microphone) and forwards the input to CPU 502 via memory bridge 505.

[0060] Display processor 512 is coupled to memory bridge 505 via a bus or other communication path (e.g., PCI Express, Accelerated Graphics Port, or HyperTransport Link); in one embodiment, display processor 512 is a graphics subsystem including at least one graphics processing unit (GPU) and graphics memory. Graphics memory includes display memory (e.g., a frame buffer) for storing pixel data for each pixel of the output image. Graphics memory may be integrated into the same device as the GPU, connected to the GPU as a separate device, and / or implemented within system memory 504.

[0061] Display processor 512 periodically delivers pixels to display device 5110 (e.g., a screen or a conventional CRT, plasma, OLED, SED, or LCD-based monitor or television). Additionally, display processor 512 can output pixels to a film recorder suitable for reproducing computer-generated images on photographic film. Display processor 512 can provide analog or digital signals to display device 510. In various embodiments, one or more of the various graphical user interfaces described in Appendix AJ appended herein are displayed to one or more users via display device 510, and one or more users can input data to and receive visual output from those various graphical user interfaces.

[0062] System disk 514 is also connected to I / O bridge 507 and can be configured to store content, applications, and data for use by CPU 502 and display processor 512. System disk 514 provides non-volatile storage for applications and data and may include fixed or removable hard disk drives, flash memory devices, and CD-ROMs, DVD-ROMs, Blu-ray, HD-DVDs, or other magnetic storage devices, optical storage devices, or solid-state storage devices.

[0063] Switch 516 provides I / O bridge 507 with other components such as network adapter 518 and various plug-in cards 520 and 521. Network adapter 518 allows system 500 to communicate with other systems via electronic communication networks and may include wired or wireless communication via local area networks and wide area networks (such as the Internet).

[0064] Other components (not shown), including USB or other port connections, film recording devices, etc., may also be connected to I / O bridge 507. For example, an audio processor can be used to generate analog or digital audio output from instructions and / or data provided by CPU 502, system memory 504, or system disk 514. Figure 1 The communication paths for interconnecting the various components in the device can be implemented using any suitable protocol such as PCI (Peripheral Component Interconnect), PCI Express (PCI-E), AGP (Accelerated Graphics Port), HyperTransport, or any other bus or point-to-point communication protocol, and connections between different devices can use different protocols, as known in the art.

[0065] In one embodiment, the display processor 512 includes circuitry optimized for graphics and video processing, including, for example, video output circuitry, and constitutes a graphics processing unit (GPU). In another embodiment, the display processor 512 includes circuitry optimized for general-purpose processing. In yet another embodiment, the display processor 512 may be integrated with one or more other system elements, such as memory bridge 505, CPU 502, and I / O bridge 507, to form a system-on-a-chip (SoC). In a further embodiment, the display processor 512 is omitted, and the functions of the display processor 512 are performed by software executed by the CPU 502.

[0066] Pixel data can be provided directly from CPU 502 to display processor 512. In some embodiments of this disclosure, instructions and / or data representing a scene are provided via network adapter 518 or system disk 514 to a rendering field or set of server computers, each similar to system 500. The rendering field uses the provided instructions and / or data to generate one or more rendered images of the scene. These rendered images can be stored in a digital format on a computer-readable medium and optionally returned to system 500 for display. Similarly, stereoscopic image pairs processed by display processor 512 can be output to other systems for display, stored on system disk 514, or stored in a digital format on a computer-readable medium.

[0067] Alternatively, CPU 502 provides display processor 512 with data and / or instructions defining the desired output image, and display processor 512 generates pixel data for one or more output images based on this data and / or instructions, including characterizing and / or adjusting the offset between stereoscopic image pairs. The data and / or instructions defining the desired output image may be stored in system memory 504 or graphics memory within display processor 512. In embodiments, display processor 512 includes 3D rendering capabilities for generating pixel data for output images based on instructions and data defining the geometry, lighting and shadows, texturing, motion, and / or camera parameters of a scene. Display processor 512 may also include one or more programmable execution units capable of executing shader programs, tone mapping programs, etc.

[0068] Furthermore, in other embodiments, CPU 502 or display processor 512 may be replaced or supplemented by any technically feasible form of processing device configured to process data and execute program code. Such processing device may be, for example, a central processing unit (CPU), a graphics processing unit (GPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), etc. In various embodiments, any of the operations and / or functions described herein may be performed by CPU 502, display processor 512, or one or more other processing devices or any combination of these different processors.

[0069] CPU 502, render field and / or display processor 512 may employ any surface or volume rendering technique known in the art to create one or more rendered images based on provided data and instructions, including rasterization, scanline rendering REYES or micropolygon rendering, ray casting, ray tracing, image-based rendering techniques and / or combinations of these techniques and any other rendering or image processing techniques known in the art.

[0070] In other envisioned embodiments, system 500 may be a robot or robotic device and may include CPU 502 and / or other processing units or devices, as well as system memory 504. In such embodiments, system 500 may or may not include... Figure 1 Other elements shown. System memory 504 and / or other memory units or devices in system 500 may include instructions that, when executed, cause the robot or robot device represented by system 500 to perform one or more operations, steps, tasks, etc.

[0071] It should be understood that the systems illustrated herein are illustrative, and variations and modifications are possible. The connection topology, including the number and arrangement of bridges, can be modified as desired. For example, in some embodiments, system memory 504 is connected directly to CPU 502 instead of via a bridge, and other devices communicate with system memory 504 via memory bridge 505 and CPU 502. In other alternative topologies, processor 512 is shown connected to I / O bridge 507 or directly to CPU 502, instead of to memory bridge 505. In other embodiments, I / O bridge 507 and memory bridge 505 may be integrated into a single chip. Certain components illustrated herein are optional; for example, any number of expansion cards or peripheral devices may be supported. In some embodiments, switch 516 is eliminated, and network adapter 518 and expansion cards 520, 521 are directly connected to I / O bridge 507.

[0072] In summary, the design modification application and the prompt modification application interoperate to generate one or more modified prompt inputs describing various modifications to the 3D design. The design modification application receives prompt input from the user, which describes the various design modifications with a certain degree of accuracy. The design modification application collects contextual input associated with the design and then enables the prompt modification application to obtain a set of relevant prompts contextually related to the prompt input. The prompt modification application then uses a generative ML model to analyze the prompt input, contextual input, and the set of relevant prompts to generate one or more modified prompt inputs. The given modified prompt inputs describe the various design modifications with greater accuracy. The user can choose between different modified prompt inputs. Based on the given choice, the design modification application then updates the 3D design to reflect the various design modifications.

[0073] At least one technical advantage of the disclosed technique over existing technologies is that it enables generative ML models to generate detailed and accurate cues that specifically describe design modifications, without requiring users to iteratively refine the cues in an uncertain and unpredictable manner. Therefore, users receive cues that are more effective when interacting with the generative ML model to generate the desired design or design modifications. Another technical advantage of the disclosed technique is that it enables generative ML models to produce accurate responses to user cues without fine-tuning. Therefore, in implementing the disclosed technique, it is not necessary to create additional training data typically used in fine-tuning. These technical advantages provide one or more technical advancements superior to existing approaches.

[0074] 1. Some implementations include a computer-implemented method for generating cue input describing a design modification, the method comprising: receiving a first cue input indicating a first modification to a three-dimensional (3D) design; determining a first context input based on one or more attributes of the 3D design; and causing a first generative machine learning (ML) model to generate a second cue input based on the first cue input and the first context input, wherein the second cue input indicates a second modification to the 3D design.

[0075] 2. The computer-implemented method as described in Clause 1, wherein determining the first context input includes determining a viewing location implemented via a graphical user interface to display the 3D design.

[0076] 3. A computer-implemented method as described in any one of Clauses 1 to 2, wherein determining the first context input includes receiving a user selection of a portion of the 3D design via a GUI that displays the 3D design.

[0077] 4. A computer-implemented method as described in any one of Clauses 1 to 3, wherein determining the first context input includes identifying a first portion of the 3D design based on the first prompt input.

[0078] 5. A computer-implemented method as described in any one of Clauses 1 to 4, wherein determining the first context input includes determining at least one design tool implemented by the user to generate the 3D design.

[0079] 6. The computer-implemented method of any one of Clauses 1 to 5, further comprising obtaining one or more additional prompts from a prompt directory based on the first prompt input and the first context input, wherein the prompt directory includes a plurality of historical prompts, and wherein the second prompt is further generated based on the one or more additional prompts.

[0080] 7. The computer-implemented method of any one of Clauses 1 to 6, wherein the second prompt is further generated based on a prompt history associated with the user.

[0081] 8. A computer-implemented method as described in any one of Clauses 1 to 7, wherein the second prompt input includes the first prompt input and further includes additional descriptive text describing the second modification to the 3D design.

[0082] 9. A computer-implemented method as described in any one of Clauses 1 to 8, wherein generating the second prompt input includes modifying at least a portion of the first prompt input based on the first context input.

[0083] 10. The computer-implemented method of any one of Clauses 1 to 9, further comprising causing a second generative ML model to modify the 3D design based on the second prompt input to achieve a second design modification.

[0084] 11. Various embodiments include one or more non-transitory computer-readable media, the one or more non-transitory computer-readable media including instructions that, when executed by one or more processors, cause the one or more processors to generate a cue input describing a design modification by performing the following steps: receiving a first cue input indicating a first modification to a three-dimensional (3D) design; determining a first context input based on one or more attributes of the 3D design; and causing a first generative machine learning (ML) model to generate a second cue input based on the first cue input and the first context input, wherein the second cue input indicates a second modification to the 3D design.

[0085] 12. One or more non-transitory computer-readable media as described in Clause 11, wherein the step of determining the first context input includes determining a viewing location implemented via a graphical user interface to display the 3D design.

[0086] 13. One or more non-transitory computer-readable media as described in any one of Clauses 11 to 12, wherein the step of determining the first context input includes receiving a user selection of a portion of the 3D design via a GUI displaying the 3D design.

[0087] 14. One or more non-transitory computer-readable media as described in any one of clauses 11 to 13, wherein the step of determining the first context input includes identifying a first portion of the 3D design based on the first prompt input.

[0088] 15. One or more non-transitory computer-readable media as described in any one of Clauses 11 to 14, wherein the step of determining the first context input includes determining at least one design tool implemented by the user to generate the 3D design.

[0089] 16. One or more non-transitory computer-readable media as described in any one of Clauses 11 to 15, further comprising the step of obtaining one or more additional prompts from a prompt directory based on the first prompt input and the first context input, wherein the prompt directory includes a prompt history associated with the user who provided the first prompt input, and wherein the second prompt is further generated based on the one or more additional prompts.

[0090] 17. One or more non-transitory computer-readable media as described in any one of Clauses 11 to 16, further comprising the step of causing a second generative ML model to modify the 3D design based on the second prompt input to achieve the second design modification.

[0091] 18. One or more non-transitory computer-readable media as described in any one of clauses 11 to 17, further comprising the steps of: causing the first generative ML model to generate a third prompt input based on the first prompt input and the first context input, wherein the third prompt input indicates a third modification to the 3D design; causing a graphical user interface to display the first prompt input, the second prompt input, and the third prompt input; and receiving from the user a selection of at least one of the first prompt input, the second prompt input, or the third prompt input.

[0092] 19. One or more non-transitory computer-readable media as described in any one of clauses 11 to 18, wherein the second prompt input comprises a greater number of characters than the first prompt input.

[0093] 20. Some embodiments include a system comprising: one or more memories storing instructions; and one or more processors coupled to the one or more memories, the one or more processors performing the following steps when executing the instructions: receiving a first cue input indicating a first modification to a three-dimensional (3D) design; determining a first context input based on one or more attributes of the 3D design; and causing a first generative machine learning (ML) model to generate a second cue input based on the first cue input and the first context input, wherein the second cue input indicates a second modification to the 3D design.

[0094] Any and all combinations of any element of any claim and / or any element described in this application, in any manner, fall within the scope of the invention and protection.

[0095] Various embodiments have been described for illustrative purposes; however, these descriptions are not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments.

[0096] Various aspects of embodiments of this invention may be embodied as systems, methods, or computer program products. Therefore, aspects of this disclosure may take the form of entirely hardware implementations, entirely software implementations (including firmware, resident software, microcode, etc.), or implementations combining software and hardware aspects, all of which may be generally referred to herein as “modules,” “systems,” or “computers.” Furthermore, any hardware and / or software techniques, processes, functions, components, engines, modules, or systems described in this disclosure may be implemented as circuits or sets of circuits. Additionally, aspects of this disclosure may take the form of computer program products embodied on one or more computer-readable media having computer-readable program code embodied thereon.

[0097] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or apparatuses, or any suitable combination thereof. More specific examples (not an exhaustive list) of computer-readable storage media will include: electrical connections having one or more wires, portable computer floppy disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable optical disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the context of this document, a computer-readable storage medium can be any tangible medium that can contain or store programs for use with or in connection with an instruction execution system, device, or apparatus.

[0098] The foregoing description of aspects of this disclosure is based on flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine. When executed via a processor of a computer or other programmable data processing apparatus, the instructions enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such processors can be, but are not limited to, general-purpose processors, special-purpose processors, application-specific processors, or field-programmable gate arrays.

[0099] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each box in a flowchart or block diagram may represent a module, segment, or portion of code comprising one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the boxes may not occur in the order shown in the drawings. For example, two boxes shown consecutively may actually be executed substantially simultaneously, or the boxes may sometimes be executed in reverse order, depending on the functionality involved. It should also be noted that each box in the block diagram and / or flowchart illustrations, and combinations of boxes in the block diagram and / or flowchart illustrations, may be implemented by a system based on special-purpose hardware or a combination of special-purpose hardware and computer instructions that performs the specified function or action.

[0100] While the foregoing describes an embodiment of this disclosure, other and additional embodiments of this disclosure may be designed without departing from the basic scope of this disclosure, the scope of which is defined by the appended claims.

Claims

1. A computer-implemented method for generating prompt input describing design modifications, the method comprising: Receive the first prompt input indicating the first modification to the three-dimensional (3D) design; The first context input is determined based on one or more properties of the 3D design; as well as The first generative machine learning (ML) model generates a second cue input based on the first cue input and the first context input, wherein the second cue input indicates a second modification to the 3D design.

2. The computer-implemented method of claim 1, wherein determining the first context input includes determining a viewing location implemented via a graphical user interface to display the 3D design.

3. The computer-implemented method of claim 1, wherein determining the first context input includes receiving a user selection of a portion of the 3D design via a GUI that displays the 3D design.

4. The computer-implemented method of claim 1, wherein determining the first context input includes identifying a first portion of the 3D design based on the first prompt input.

5. The computer-implemented method of claim 1, wherein determining the first context input includes determining at least one design tool implemented by the user to generate the 3D design.

6. The computer-implemented method of claim 1, further comprising obtaining one or more additional prompts from a prompt directory based on the first prompt input and the first context input, wherein the prompt directory includes a plurality of historical prompts, and wherein the second prompt is further generated based on the one or more additional prompts.

7. The computer-implemented method of claim 1, wherein the second prompt is further generated based on a prompt history associated with the user.

8. The computer-implemented method of claim 1, wherein the second prompt input includes the first prompt input, and further includes additional descriptive text describing the second modification to the 3D design.

9. The computer-implemented method of claim 1, wherein generating the second prompt input includes modifying at least a portion of the first prompt input based on the first context input.

10. The computer-implemented method of claim 1, further comprising causing a second generative ML model to modify the 3D design based on the second prompt input to achieve a second design modification.

11. One or more non-transitory computer-readable media, the one or more non-transitory computer-readable media comprising instructions that, when executed by one or more processors, cause the one or more processors to generate a prompt input describing a design modification by performing the following steps: Receive the first prompt input indicating the first modification to the three-dimensional (3D) design; The first context input is determined based on one or more properties of the 3D design; as well as The first generative machine learning (ML) model generates a second cue input based on the first cue input and the first context input, wherein the second cue input indicates a second modification to the 3D design.

12. One or more non-transitory computer-readable media as claimed in claim 11, wherein the step of determining the first context input includes determining a viewing location implemented via a graphical user interface to display the 3D design.

13. One or more non-transitory computer-readable media as claimed in claim 11, wherein the step of determining the first context input includes receiving a user selection of a portion of the 3D design via a GUI displaying the 3D design.

14. One or more non-transitory computer-readable media as claimed in claim 11, wherein the step of determining the first context input includes identifying a first portion of the 3D design based on the first prompt input.

15. One or more non-transitory computer-readable media as claimed in claim 11, wherein the step of determining the first context input includes determining at least one design tool implemented by the user to generate the 3D design.

16. The one or more non-transitory computer-readable media of claim 11, further comprising the step of obtaining one or more additional prompts from a prompt directory based on the first prompt input and the first context input, wherein the prompt directory includes a prompt history associated with the user who provided the first prompt input, and wherein the second prompt is further generated based on the one or more additional prompts.

17. The one or more non-transitory computer-readable media of claim 11, further comprising the step of causing a second generative ML model to modify the 3D design based on the second prompt input to achieve the second design modification.

18. The one or more non-transitory computer-readable media of claim 11, further comprising the following steps: The first generative ML model generates a third prompt input based on the first prompt input and the first context input, wherein the third prompt input indicates a third modification to the 3D design; The graphical user interface is made to display the first prompt input, the second prompt input, and the third prompt input; as well as The user receives a selection from at least one of the first prompt input, the second prompt input, or the third prompt input.

19. One or more non-transitory computer-readable media as claimed in claim 11, wherein the second prompt input comprises a greater number of characters than the first prompt input.

20. A system comprising: One or more memories, wherein the one or more memories store instructions; as well as One or more processors, coupled to one or more memories, wherein the one or more processors perform the following steps when executing the instructions: Receive the first prompt input indicating the first modification to the three-dimensional (3D) design; The first context input is determined based on one or more properties of the 3D design; as well as The first generative machine learning (ML) model generates a second cue input based on the first cue input and the first context input, wherein the second cue input indicates a second modification to the 3D design.

Images