Auxiliary system and method for generating dispensing path based on generative artificial intelligence and computing device

Abstract

The present application provides an auxiliary system, method and computing device for generating a dispensing path based on generative artificial intelligence. An auxiliary system for generating a dispensing path based on generative artificial intelligence includes a dispensing path auxiliary generation module, an image acquisition module, an image marking module, an interaction module and a dispensing path manual editing module. The dispensing path auxiliary generation module includes a pre-trained graphic model and a path image parsing unit. The image acquisition module is used to acquire the first installation surface image before forming the glue path; the image marking module is used to mark the key points of the path on the first installation surface image; the graphic model generates the first dispensing path image from the first installation surface image based on the prompt text and the key points of the path. The technical solution according to the present application can assist in the generation of the dispensing path, reduce the intensity and cost of manual labor, and is highly efficient.

Description

Technical Field

[0001] The present invention relates to the field of image processing and artificial intelligence application technology, and in particular to an auxiliary system and method and computing device for generating a dispensing path based on generative artificial intelligence. Background Art

[0002] With the development of intelligent manufacturing and the increasing demand for precision in the fields of electronics, medical, semiconductors, and automobiles, more and more components are assembled through dispensing to meet the requirements of compact structures. Before dispensing, it is necessary to draw the dispensing path in advance as a benchmark for the dispensing operation.

[0003] At present, the dispensing path is mainly generated by manual drawing, and the user draws the dispensing trajectory on the installation surface image. Specifically, the dispensing path editing method is similar to CAD drawing. After importing the installation surface image, select the command on the editing tool and select points on the image to draw the trajectory. The editing software has the ability to draw points, lines, arcs, circles, irregular curves and other graphics. After editing the dispensing path, the dispensing three-axis robot can automatically perform dispensing operations according to the edited dispensing path.

[0004] Although this path drawing method is mature and stable, it mainly relies on manual operation, which requires a certain period of time to learn and master, and is inefficient. Therefore, a technical solution is needed to efficiently generate dispensing paths. Summary of the invention

[0005] The present application aims to provide an auxiliary system and method for generating a dispensing path based on generative artificial intelligence, which can assist operators in quickly and efficiently generating a dispensing path.

[0006] According to one aspect of the present invention, an auxiliary system for generating a dispensing path based on generative artificial intelligence is provided, comprising a dispensing path auxiliary generation module, an image acquisition module, an image marking module, an interaction module, and a dispensing path manual editing module, wherein the dispensing path auxiliary generation module comprises a pre-trained graphic model and a path image parsing unit, wherein:

[0007] The image acquisition module is used to acquire the first installation surface image before the glue path is formed;

[0008] The image marking module is used to mark key points of the path on the first installation surface image;

[0009] The glue dispensing path auxiliary generation module is configured to construct a prompt text according to the first installation surface image, send the prompt text to the interactive module for user confirmation, and input the prompt text confirmed by the user, the first installation surface image and the key points of the path into the pre-trained text-image generation model, and the text-image generation model generates a first glue dispensing path image from the first installation surface image based on the prompt text and the key points of the path; the path image parsing unit parses the first glue dispensing path image into a first glue dispensing path file in a target format;

[0010] The manual dispensing path editing module reads the first dispensing path file and generates a second dispensing path file in response to user operations.

[0011] According to some embodiments, the image acquisition module, the interaction module and the dispensing path manual editing module are located in a client node, and the dispensing path auxiliary generation module is located in a server node.

[0012] According to some embodiments, the dispensing path auxiliary generation module includes a pre-trained image description model and a pre-trained prompt text construction model, and the dispensing path auxiliary generation module is configured as follows:

[0013] extracting image information from the first installation surface image using the pre-trained image description model;

[0014] The image information is fed into the pre-trained prompt text construction model to generate the prompt text.

[0015] According to some embodiments, the image information includes component information and blank boundary information.

[0016] According to some embodiments, the aforementioned system further comprises a prompt information input module, wherein the prompt information input module generates prompt information in response to user input, and the prompt information is sent together with the image information to the pre-trained prompt text construction model to generate the prompt text.

[0017] According to some embodiments, the pre-trained text-to-image model includes a ControlNet model based on a Stable Diffusion model.

[0018] According to another aspect of the present invention, there is provided a method for assisting in generating a dispensing path, comprising:

[0019] Acquire a first installation surface image before forming a glue path and key path points marked on the first installation surface image;

[0020] constructing a prompt text according to the first installation surface image;

[0021] Sending the prompt text to the client for user confirmation;

[0022] The prompt text returned by the client, the first installation surface image and the path key points are input into a pre-trained text-to-image model, and the text-to-image model generates a first dispensing path image from the first installation surface image based on the prompt text.

[0023] According to some embodiments, constructing a prompt text according to the first installation surface image includes:

[0024] Get the prompt information entered by the user.

[0025] extracting image information from the first installation surface image using a pre-trained image description model;

[0026] The image information and the prompt information are sent to the pre-trained prompt text construction model to generate the prompt text.

[0027] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, any of the above-mentioned methods is implemented.

[0028] According to another aspect of the present invention, there is provided a computing device, comprising:

[0029] Processor; and

[0030] A memory storing a computer program, which implements any of the above methods when the computer program is executed by the processor.

[0031] According to an embodiment of the present application, by constructing a prompt text based on the installation surface image and the key points of the path, and sending the prompt text and the installation surface image to a pre-trained graphic model to generate a dispensing path, a dispensing path image can be efficiently produced. The generated dispensing path image is parsed into a dispensing path file and loaded into a dispensing path editing tool, and the user can quickly generate a dispensing path file based on this. The solution of the present invention uses artificial intelligence technology to assist in the generation of the dispensing path, which is low in cost and high in efficiency, and is conducive to the rapid actual production of the dispensing system.

[0032] It should be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for describing the embodiments are briefly introduced below.

[0034] Figure 1 An architectural block diagram of an auxiliary system for generating a dispensing path based on generative artificial intelligence according to an example embodiment is shown.

[0035] Figure 2 A flow chart of a method for assisting in generating a dispensing path according to an example embodiment is shown.

[0036] Figure 3 A flow chart of a method for constructing a prompt text according to an exemplary embodiment is shown.

[0037] Figure 4 A block diagram of a computing device according to an example embodiment of the invention is shown. DETAILED DESCRIPTION

[0038] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this application will be comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0039] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0040] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0041] It should be understood that although the terms first, second, third, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another component. Therefore, the first component discussed below can be referred to as the second component without departing from the teachings of the concepts of the present application. As used herein, the term "and / or" includes any one of the associated listed items and all combinations of one or more.

[0042] Those skilled in the art will appreciate that the drawings are merely schematic diagrams of example embodiments, and the modules or processes in the drawings are not necessarily necessary for implementing the present application, and therefore cannot be used to limit the scope of protection of the present application.

[0043] With the increasing demand for precision in the fields of electronics, medical, semiconductors, and automobiles, dispensing assembly technology has become a trend. The market demand for dispensing systems is getting higher and higher.

[0044] To this end, the present application proposes an auxiliary system and method for generating a dispensing path based on generative artificial intelligence. By constructing a prompt text (prompt) according to the installation surface image, and sending the prompt text and the installation surface image to a pre-trained graphic model to generate a dispensing path, the dispensing path image can be efficiently produced. The technical solution according to the present invention is highly efficient, can assist in the rapid generation of a dispensing path, and greatly reduces manual labor intensity and labor costs.

[0045] Before describing the embodiments of the present application, some terms or concepts involved in the embodiments of the present application are explained.

[0046] Large Model: refers to all models with very large parameter scale in deep learning or machine learning. Such models usually involve hundreds of millions, billions or even hundreds of billions of parameters. Large models are not limited to the language field, but can also be applied to various tasks such as image processing, video analysis, speech recognition, and recommendation systems.

[0047] Large Language Model (LLM): A type of large model that is specifically designed to handle natural language understanding and generation tasks. Their training data is mainly large-scale text corpora, aiming to generate meaningful text output, answer questions, or perform language reasoning.

[0048] Generative AI (AIGC) refers to the process of generating content through artificial intelligence technology, covering various forms such as text, images, audio, video, etc. AIGC is different from traditional content generation methods. It relies on technologies such as deep learning models, natural language processing (NLP) and generative adversarial networks (GAN) to automatically generate content that meets user needs.

[0049] Diffusion Model: It is a probabilistic model used to generate data (such as images, audio, text, etc.). It generates data through a step-by-step inverse process. The core idea is to generate new content by simulating the process of data gradually changing from noise to clarity.

[0050] Stable Diffusion: is a tool for generating images from text based on a diffusion model. The core of StableDiffusion is to gradually generate images from noise, allowing users to enter text descriptions and automatically generate corresponding high-quality images. It is an open source project developed by Stability AI and other institutions, and is a milestone in AI image generation technology.

[0051] ControlNet: is an architecture extension specifically designed to enhance image generation models such as Stable Diffusion. It allows users to have more detailed control over the output of the model during the image generation process by introducing external conditional control. This architecture has a wide range of uses in generative artificial intelligence applications, especially for scenarios that require fine control, such as generating specific images based on posture, contours, edges, etc. In addition to text prompts, ControlNet can also accept structured information of the image, such as edge detection maps, human posture (skeleton), depth maps, line drawings, etc. These inputs can be used as additional constraints to guide the generation of results. ControlNet can work with existing diffusion models such as Stable Diffusion without requiring major modifications to the original model.

[0052] Image Captioning Model: It is a generative AI model that can generate a corresponding text description based on the input image. Image captioning models combine the technologies of computer vision and natural language processing to understand the visual content in the image and generate language expressions. The goal of this type of model is to automatically describe the objects, scenes, actions and other visual features in the image.

[0053] The exemplary embodiments of the present application are described below in conjunction with the accompanying drawings.

[0054] Figure 1 An architectural block diagram of an auxiliary system for generating a dispensing path based on generative artificial intelligence according to an example embodiment is shown.

[0055] See also Figure 1According to an example embodiment, an auxiliary system for generating a dispensing path based on generative artificial intelligence may include a dispensing path auxiliary generation module 210 located at a server node and an image acquisition module 221, an image marking module 223, an interaction module 225, and a dispensing path manual editing module 227 located at a client node. The dispensing path auxiliary generation module 210 may include a pre-trained image-text model 211 and a path image parsing unit 213. According to some embodiments, the dispensing path auxiliary generation module 210 may also include an image description model 215 and a prompt text construction model 217. According to some embodiments, the client node may also include a prompt information input module 229. Since the technical solution of the present invention is based on deep learning technology and requires large computing power, even if a simplified AI model deployed on the client is used, it still puts a certain pressure on the user in terms of cost. To this end, the technical solution of the present invention adopts a solution of deploying client nodes and server nodes separately. The server node may be located in a cloud service center or an edge computing node, and the AI ​​cloud computing service platform of a mature service provider may be rented.

[0056] See also Figure 1 The image acquisition module 221 deployed in the client node is used to acquire the first installation surface image before the glue path is formed. In an actual production environment, the first installation surface image can be acquired through a camera.

[0057] The image marking module 223 can be used to mark the key points of the path on the first installation surface image. In order to generate the dispensing path more efficiently, according to an embodiment, the key points of the path can be marked in advance on the first installation surface image. In this way, when generating the prompt text later, the relevant description can be added; the conditional diffusion model can use these restrictive conditions to generate the dispensing path passing through the key points. It is easy to understand that for simple images or common similar images, the marking of the key points of the path can be omitted; and for complex images and new images, adding the key points of the path can greatly improve the efficiency and accuracy of the dispensing path generation.

[0058] After obtaining the first installation surface image and the key points of the path, the dispensing path auxiliary generation module 210 can construct a prompt text according to the first installation surface image. For example, according to some embodiments, the pre-trained image description model 215 can be used to extract image information from the first installation surface image, and the image information can be sent to the pre-trained prompt text construction model 217 to generate a prompt text.

[0059] According to some embodiments, the prompt information input module 229 may generate prompt information in response to user input, and the prompt information may be sent together with the image information to the pre-trained prompt text construction model to generate the prompt text.

[0060] After generating the prompt text, in order to ensure accuracy, the dispensing path auxiliary generation module 210 may send the prompt text to the interaction module 225 for user confirmation. After the user confirms, the prompt text confirmed by the user and the first installation surface image and path key points may be input into the pre-trained text-image model 211. According to some embodiments, the interaction module 225 may be configured to provide an interface for modifying the prompt text, and may return the modified prompt text to the dispensing path auxiliary generation module 210.

[0061] The text-to-image model 211 generates a first dispensing path image from the first installation surface image based on the prompt text and the path key points. According to an example embodiment, the pre-trained text-to-image model 211 includes a ControlNet model based on a StableDiffusion model. Of course, the present invention is not limited to this, and other suitable text-to-image models may also be used.

[0062] The path image parsing unit 213 can parse the first glue dispensing path image into a first glue dispensing path file in a target format, and then send it to the client node. According to some embodiments, the graphic model 211 can directly generate a glue dispensing path on an independent layer, and the first glue dispensing path image can be directly obtained. According to other embodiments, the glue dispensing path is generated on the first mounting surface image. In this case, the first glue dispensing path image can be separated from the first mounting surface image by a binary mask. According to some embodiments, the first glue dispensing path image can be converted into a vector image format or a discrete point format, the former can be an SVG format or an EPS format, and the latter can be a CSV format or a JSON format.

[0063] The manual glue path editing module 227 of the client node reads the first glue path file, and generates a second glue path file in response to the user operation. As mentioned above, the glue path editing method using the manual glue path editing module 227 is similar to ordinary drawing, and the editing software has the ability to draw points, lines, arcs, circles, irregular curves and other graphics. Selecting a command on the editing tool can visually modify the first glue path file, generate and save it as a second glue path file, so that the glue three-axis robot can perform automatic glue dispensing operations according to the path file.

[0064] According to an embodiment of the present application, by constructing a prompt text based on the installation surface image and the key points of the path, and sending the prompt text, the installation surface image and the key points of the path into a pre-trained graphic model to generate a dispensing path, a dispensing path image can be efficiently produced. The generated dispensing path image is parsed into a dispensing path file and loaded into the dispensing path editing tool, and the user can quickly generate a dispensing path file based on this. The solution of the present invention uses artificial intelligence technology to assist in the generation of the dispensing path, which is low in cost and high in efficiency, and is conducive to the rapid actual production of the dispensing system.

[0065] Figure 2 A flow chart of a method for assisting in generating a dispensing path according to an example embodiment is shown.

[0066] Figure 2 The method shown can be run on the dispensing path auxiliary generation module 210 of the service end node.

[0067] See also Figure 2 In S301, a first installation surface image and path key points before forming a glue path are obtained.

[0068] According to an example embodiment, path key points are pre-marked on the first installation surface image.

[0069] In S303, a prompt text is constructed according to the first installation surface image.

[0070] According to an example embodiment, a pre-trained image description model may be used to extract image information from the first installation surface image, and the image information may be fed into a pre-trained prompt text construction model to generate a prompt text.

[0071] For example, some of the tooltips may be similar to "The drawn line is smooth and passes through or near key points" and "The drawn line surrounds the board boundary."

[0072] In S305, the prompt text is sent to the client for user confirmation.

[0073] According to some embodiments, the interaction module of the client node may be configured to provide an interface for modifying the prompt text, and may return the modified prompt text to the dispensing path auxiliary generation module.

[0074] In S307, the prompt text returned by the client, the first installation surface image and the key points of the path are input into a pre-trained text-to-image model, and the text-to-image model generates a first dispensing path image from the first installation surface image based on the prompt text and the key points of the path.

[0075] According to some embodiments, a ControlNet model is used as a model for generating images from images, a first installation surface image and path key points are used as image inputs, and a prompt text is used as prompt text inputs, and a pre-trained ControlNet model generates a first dispensing path image from the first installation surface image based on the prompt text and path key points. For example, the first installation surface image and an image including path key points may be used as image inputs separately, or the first installation surface image marked with the path key points may be used as image input.

[0076] Figure 3 A flow chart of a method for constructing a prompt text according to an exemplary embodiment is shown.

[0077] See also Figure 3 , in S401, the prompt information input by the user is obtained.

[0078] According to some embodiments, the user may input some prompt information in advance. For example, for complex images and new types of images, providing some prompt information in advance may help improve the efficiency and accuracy of dispensing path generation. The prompt information input in advance by the user may be, for example, "add a dotted dispensing array on the central blank surface".

[0079] In S403, image information is extracted from the first installation surface image using a pre-trained image description model.

[0080] According to some embodiments, the image information includes component information and blank boundary information.

[0081] Image description models can achieve translation mapping between images and descriptions through end-to-end learning methods. Deep learning methods can learn the mapping from images to description sentences from a large amount of data and generate more accurate descriptions.

[0082] According to some embodiments, the image description model may adopt an encoder-decoder based solution, an attention mechanism based solution, or a generative adversarial network based solution, etc., and the present application does not impose any particular limitation on this.

[0083] In the solution of the present application, the main image information extracted by the image description model, such as component composition and layout and boundary information, is encapsulated as prompt text, which can guide the subsequent dispensing path generation.

[0084] In S405, the image information and the prompt information are sent to the pre-trained prompt text construction model to generate the prompt text.

[0085] According to some embodiments, the prompt information provided by the user may be fused with the image information constructed by the image description model, thereby providing further information for subsequent dispensing path generation, making the path generation more efficient and accurate.

[0086] Figure 4 A block diagram of a computing device according to an example embodiment of the invention is shown.

[0087] like Figure 4 As shown, computing device 30 includes processor 12 and memory 14. Computing device 30 may also include bus 22, network interface 16, and I / O interface 18. Processor 12, memory 14, network interface 16, and I / O interface 18 may communicate with each other via bus 22.

[0088] The processor 12 may include one or more general-purpose CPUs (Central Processing Units, processors), microprocessors, or application-specific integrated circuits, etc., for executing relevant program instructions. According to some embodiments, the computing device 30 may also include a high-performance graphics card (GPU) 20 for accelerating the processor 12.

[0089] The memory 14 may include a machine system readable medium in the form of a volatile memory, such as a random access memory (RAM), a read-only memory (ROM) and / or a cache memory. The memory 14 is used to store one or more programs including instructions and data. The processor 12 may read the instructions stored in the memory 14 to execute the above-mentioned method according to the embodiment of the present invention.

[0090] The computing device 30 may also communicate with one or more networks via the network interface 16. The network interface 16 may be a wireless network interface.

[0091] The bus 22 may include an address bus, a data bus, a control bus, etc. The bus 22 provides a path for exchanging information between components.

[0092] It should be noted that, in the specific implementation process, the computing device 30 may also include other components necessary for normal operation. In addition, those skilled in the art may understand that the above device may only include components necessary for implementing the embodiments of this specification, and need not include all components shown in the figure.

[0093] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above method when the program is executed by a processor. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), a network storage device, a cloud storage device, or any type of medium or device suitable for storing instructions and / or data.

[0094] An embodiment of the present invention also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any method recorded in the above method embodiments.

[0095] Those skilled in the art can clearly understand that the technical solution of the present invention can be implemented with the help of software and / or hardware. "Unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array, an integrated circuit, etc.

[0096] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0097] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0098] In the several embodiments provided by the present invention, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0099] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0100] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0101] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention.

[0102] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0103] The exemplary embodiments of the present invention are specifically shown and described above. It should be understood that the present invention is not limited to the detailed structures, configurations or implementations described herein; on the contrary, the present invention is intended to cover various modifications and equivalent configurations included in the spirit and scope of the appended clauses.

Claims

1. An auxiliary system for generating dispensing paths based on generative artificial intelligence, characterized in that: It includes a dispensing path auxiliary generation module, an image acquisition module, an image marking module, an interaction module, a dispensing path manual editing module, and a prompt information input module. The dispensing path auxiliary generation module includes a pre-trained image-text model and a path image parsing unit, a pre-trained image description model, and a pre-trained prompt text construction model, wherein: The image acquisition module is used to acquire the first installation surface image before the glue path is formed; The image marking module is used to mark key points of the path on the first installation surface image; The prompt information input module generates prompt information in response to user input; The glue dispensing path auxiliary generation module is configured to extract image information from the first installation surface image using the pre-trained image description model, send the prompt information together with the image information into the pre-trained prompt text construction model to generate a prompt text, send the prompt text to the interactive module for user confirmation, and input the prompt text confirmed by the user and the first installation surface image and path key points into the pre-trained graphic-text generation model, and the graphic-text generation model generates a first glue dispensing path image from the first installation surface image based on the prompt text and the path key points; the path image parsing unit parses the first glue dispensing path image into a first glue dispensing path file in a target format; The manual dispensing path editing module reads the first dispensing path file and generates a second dispensing path file in response to user operations.

2. The auxiliary system according to claim 1, characterized in that: The image acquisition module, the interaction module and the manual editing module of the dispensing path are located in the client node, and the auxiliary generation module of the dispensing path is located in the server node.

3. The auxiliary system according to claim 1, characterized in that: The image information includes component information and blank boundary information.

4. The auxiliary system according to claim 1, characterized in that: The pre-trained image-text model includes a ControlNet model based on a Stable Diffusion model.

5. A method for assisting in generating a dispensing path, characterized in that: include: Acquire a first installation surface image before forming a glue path and key path points marked on the first installation surface image; constructing a prompt text according to the first installation surface image; Sending the prompt text to the client for user confirmation; Inputting the prompt text returned by the client, the first installation surface image and the key points of the path into a pre-trained text-to-image model, wherein the text-to-image model generates a first dispensing path image from the first installation surface image based on the prompt text; The step of constructing a prompt text according to the first installation surface image includes: Get the prompt information entered by the user. extracting image information from the first installation surface image using a pre-trained image description model; The image information and the prompt information are sent to the pre-trained prompt text construction model to generate the prompt text.

6. A computer program product, characterized in that The method comprises a computer program which, when executed by a processor, implements the method as claimed in claim 5.

7. A computing device, characterized in that include: processor; as well as A memory storing a computer program, which implements the method according to claim 5 when the computer program is executed by the processor.

Images