INFORMATION PROCESSING DEVICE

Abstract

An information processing device includes: a capture unit configured to capture a graph structure input from a user; a generation unit configured to generate an image based on the graph structure; and an output unit configured to output the generated image. The graph structure might include, for example, type information about an object and position information about the object. The graph structure might also include, for example, information about the object's shape or color.

Description

BACKGROUND OF THE INVENTION 1. Field of the invention This disclosure concerns the technical field of information processing devices. 2. Description of the state of the art As an example of this type of device, a system has been proposed in which a large language model (LLM) is used to generate query data based on documents, and pairs of documents and query data are used to train a retrieval model for a dialog bot (see JP 2023 - 076 413 A ). SUMMARY OF THE INVENTION When an image is generated using a machine-learned generative model, it can produce an image that does not match the user's intent (for example, an image that deviates slightly from the user's instructions). To avoid such a situation, it is desirable to give the generative model instructions that allow it to accurately understand the user's intent. However, it is not easy for the user to enter such instructions on their own. The present disclosure was made with regard to the above problems, and one of its objectives is to provide an information processing device capable of adequately generating an image intended by a user. An information processing device according to one aspect of the present disclosure includes: a capture unit configured to capture a graph structure inputted by a user; a generation unit configured to generate an image based on the graph structure; and an output unit configured to output the generated image. BRIEF DESCRIPTION OF THE DRAWINGS Features, advantages, and technical and industrial significance of exemplary embodiments of the invention are described below with reference to the accompanying drawings, in which the same reference numerals denote the same elements, and wherein: Fig. 1 is a block diagram illustrating a hardware configuration of an information processing device according to one embodiment; Fig. 2 is a block diagram illustrating a functional configuration of the information processing device according to the embodiment; and Fig. 3 is a flowchart illustrating the operational sequence of the information processing device according to the embodiment. DETAILED DESCRIPTION OF EXECUTION FORMS One embodiment of an information processing device is described below with reference to the drawings. Hardware configuration First, a hardware configuration of the information processing device according to the embodiment is described with reference to Fig. 1. Fig. 1 is a block diagram illustrating the hardware configuration of the information processing device according to the embodiment. In Fig. 1, an information processing device 10 according to the embodiment comprises a computing device 110, a storage device 120, a communication device 130, an input device 140 and an output device 150. The computing device 110, the storage device 120, the communication device 130, the input device 140 and the output device 150 are interconnected via a data bus. The computing device 110 is configured to perform various computing processes in the information processing device 10. The computing device 110 can include a processor. The computing device 110 can include a single processor or it can include a plurality of processors. In other words, the computing device 110 can include one or more processors. The processor can be a multi-core processor. If the computing device 110 includes a single processor that is a multi-core processor, the computing device 110 can logically be considered to include a plurality of processors. The processor included in the computing device 110 can be, for example, at least one of the following: a central processing unit (CPU), a graphics processing unit (GPU), a field-programmable gate array (FPGA) and a tensor processing unit (TPU). The storage device 120 can be, for example, at least one of the following: random access memory (RAM), read-only memory (ROM), a hard disk drive, a magneto-optical disk drive, a solid-state drive (SSD), and an optical disk array. That is, the storage device 120 can be implemented using a single device or it can be implemented using a variety of devices. The storage device 120 is capable of storing desired data. The storage device 120 can store a computer program CP that is executed by the computing device 110. When the computing device 110 executes the computer program CP, the storage device 120 can temporarily store data that is temporarily used by the computing device 110. The computer program CP can be recorded on a computer-readable and non-volatile recording medium. In this case, the computer program CP can be stored in the storage device 120 by reading the recording medium using a recording medium reader (not shown) included in the information processing device 10. At least one of the following media can be used as the recording medium: an optical disk, a magnetic medium, a magneto-optical disk, a semiconductor memory, and any other medium capable of storing programs. The computer program CP can be retrieved from a device (not shown) outside the information processing device 10 via the communication device 130.In other words, the computer program CP can be downloaded from an external device to the storage device 120 of the information processing device 10. The computing device 110 (e.g., a processor) can, together with the storage device 120, which stores the computer program CP (in other words, together with the storage device 120 and the computer program CP stored in the storage device 120), perform processing to be carried out by the information processing device 10. For example, logical function blocks for carrying out the processing to be carried out by the information processing device 10 can be implemented within the computing device 110 (e.g., within the processor) by the computing device 110, which executes the computer program CP. The communication device 130 is configured to communicate with a device outside the information processing device 10. The communication device 130 can perform wired or wireless communication. The input device 140 is a device capable of receiving information input from an external source into the information processing device 10. The input device 140 may include an operating device that can be operated by a user of the information processing device 10 (e.g., a keyboard, a mouse, a touch panel, etc.). The input device 140 may also include a recording medium reader capable of reading information recorded on a recording medium (such as a Universal Serial Bus (USB) storage device) that is attachable to and detachable from the information processing device 10.When information is entered into the information processing device 10 via the communication device 130 (in other words, when the information processing device 10 obtains information via the communication device 130), the communication device 130 can serve as an input device. The output device 150 is a device capable of outputting information outside the information processing device 10. The output device 150 may include a display device capable of outputting visual information such as text or images. The output device 150 may include a loudspeaker capable of outputting acoustic information such as sound. The output device 150 may be configured to output the above information (e.g., control information for other devices) to other devices. The output device 150 may be capable of outputting information to a recording medium that can be attached to and detached from the information processing device 10, such as a USB flash drive.If the information processing device 10 outputs information via the communication device 130, the communication device 130 can serve as an output device. Functional configuration Next, a functional configuration of the information processing device 10 according to the embodiment is described with reference to Fig. 2. Fig. 2 is a block diagram illustrating the functional configuration of the information processing device according to the embodiment. In Fig. 2, the information processing device 10 is configured as a device that generates an image based on a graph structure input by a user. The information processing device 10 includes, as components for implementing its functions, a graph structure acquisition unit 210, an image generation unit 220, an image output unit 230, and a graph structure modification unit 240. Each of the graph structure acquisition unit 210, the image generation unit 220, the image output unit 230, and the graph structure modification unit 240 can be a processing block implemented by the computing device 110 described above. The Graph Structure Capture Unit 210 is configured to capture a graph structure entered by a user. The graph structure can refer to data consisting of a group of nodes representing parts of an object contained in an image that relates to an image data element, and a group of edges indicating relationships between the nodes. The Graph Structure Capture Unit 210 can include a function to convert the captured graph structure into a feature vector. The graph structure can include type information about an object and position information about the object. Alternatively, the graph structure can include information about the shape or color of an object. The image generation unit 220 is configured to generate an image from the graph structure captured by the graph structure capture unit 210. That is, the image generation unit 220 converts a user-specified graph structure into an image. The image generation unit 220 can generate an image using a model that has been pre-trained using machine learning. The model can be one that takes the graph structure (or the feature vector of the graph structure) as input and outputs an image. The image output unit 230 is configured to output an image generated by the image generation unit 220 (hereinafter referred to as the "generated image") to the user. For example, the image output unit 230 can display the image generated by the image generation unit 220 on a display. In addition to the generated image, the image output unit 230 can also display the graph structure used to generate the generated image (in other words, the graph structure input by the user). The graph structure modification unit 240 is configured to modify the graph structure captured by the graph structure acquisition unit 210 based on a modification input provided by the user. The modification input can, for example, include an instruction to modify a portion of the graph structure. For instance, the user can select a section of the graph structure to be modified and enter information to rewrite the selected section as the modification input. The graph structure modified by the graph structure modification unit 240 is output to the image generation unit 220. Therefore, when the graph structure modification unit 240 modifies the graph structure, the image generation unit 220 regenerates an image based on the modified graph structure. Operational process Next, the operating sequence of the information processing device 10 according to the embodiment will be described with reference to Fig. 3. Fig. 3 is a flowchart illustrating the operating sequence of the information processing device according to the embodiment. As shown in Fig. 3, when the operation of the information processing device 10 is started according to the embodiment, the graph structure acquisition unit 210 first acquires a graph structure from a user (step S101). The image generation unit 220 then generates an image from the graph structure acquired by the graph structure acquisition unit 210 (step S102). Next, the image output unit 230 outputs the image generated by the image generation unit 220 (step S103). Then, the graph structure modification unit 240 determines whether any modification input has been provided by the user (step S104). If it is determined that no modification input has been provided (step S104: NO), the sequence of operations can end. If a modification input is received (step S104: YES), the graph structure modification unit 240 modifies the graph structure based on the modification input (step S105). The process then returns to step S102, where processing is performed using the modified graph structure. In this way, an image is generated and output based on the modified graph structure. Technical effects Next, technical effects obtained by the information processing device 10 according to the embodiment are described. As described with reference to Figures 1, 2 to 3, in the information processing device 10 according to the embodiment, an image is generated from a graph structure entered by a user. The graph structure is easy for a machine to interpret. Therefore, by using the graph structure to generate an image, it is possible to output an image that corresponds to the user's intention. In the case of a graph structure, it is easy to modify some of the information. For example, suppose the user inputs a graph structure "tree-leaf (color: green)-person-person" and the image generator 220 produces an image "of a summer scene with people around a tree". After this image has been output, if the user modifies the information about the leaf color and changes the graph structure to "tree-leaf (color: yellow)-person-person", the image generator 220 will produce an image "of an autumn scene with people around a tree". Aspects of the invention derived from the above embodiment are described below. An information processing device according to one aspect of the present disclosure comprises: a capture unit configured to capture a graph structure inputted by a user; a generation unit configured to generate an image based on the graph structure; and an output unit configured to output the generated image. In the embodiment above, the “graph structure capture unit 210” is an example of the “capture unit”, the “image generation unit 220” is an example of the “generation unit”, and the “image output unit 230” is an example of the “output unit”. In the information processing device, as described above, the graph structure can contain type information and position information of an object. This makes it possible to generate a more appropriate image based on the object's type and position information contained in the graph structure. In the information processing device, as described above, the graph structure can contain information about the object's shape or color. This makes it possible to generate a more appropriate image based on the information about the object's shape or color contained in the graph structure. The information processing device according to the above aspect can further include a modification unit configured to modify a portion of the graph structure input by the user in response to user input. The generation unit can be configured to regenerate an image based on the graph structure resulting from the modification once the portion of the graph structure has been modified. In this way, the generated image can be easily modified. In the above embodiment, the "Graph Structure Modification Unit 240" is an example of the "Modification Unit". The present disclosure is not limited to the embodiment described above, and various modifications can be made as needed without departing from the core or concept of the invention, as is evident from the claims and the entire description. Information processing devices incorporating such modifications also fall within the technical scope of the present invention. QUOTES INCLUDED IN THE DESCRIPTION This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature JP 2023 - 076 413 A

[0002]

Claims

Information processing device comprising: a capture unit configured to capture a graph structure entered by a user; a generation unit configured to generate an image based on the graph structure; and an output unit configured to output the generated image. Information processing device according to claim 1, wherein the graph structure comprises type information of an object and position information of the object. Information processing device according to claim 2, wherein the graph structure contains information about a shape or a color of the object. Information processing device according to one of claims 1 to 3, further comprising a modification unit configured to modify a part of the graph structure entered by the user in response to user input, wherein the generation unit is configured to regenerate an image based on the graph structure resulting from the modification when the part of the graph structure has been modified.

Images