Information processing apparatus

Abstract

Disclosed is an information processing apparatus. The information processing apparatus includes: an acquisition unit that acquires a graphic structure input by a user as instruction data; a generation unit that generates an image based on the instruction data; a conversion unit that converts the generated image into a graphic structure; a calculation unit that calculates a difference between the graphic structure of the instruction data and the graphic structure converted from the generated image; a regeneration instruction unit that, in a case where the difference is equal to or greater than a predetermined value, instructs the generation unit to regenerate the image so as to make the difference smaller; and an output unit that, in a case where the difference is smaller than the predetermined value, outputs the generated image to the user.

Description

Technical Field

[0001] This disclosure relates to the technical field of information processing devices. Background Technology

[0002] As such a device, for example, a system has been proposed that enables Large Language Models (LLMs) to generate document-based query data, and uses the pairs of documents and query data to learn a retrieval model for a chatbot (see Japanese Patent Application Publication No. 2023-076413). Summary of the Invention

[0003] When using machine learning models to generate images, sometimes images are generated that do not conform to the user's intentions (e.g., images that deviate slightly from the user's instructions). In such cases, correcting the image requires repeated exchanges between the user and the device, necessitating new input from the user. This results in technical problems that increase user inconvenience and reduce convenience.

[0004] This disclosure was made in view of the above-mentioned problems, and the object of the disclosure is to provide an information processing apparatus capable of appropriately generating images desired by the user.

[0005] An information processing apparatus according to one aspect of this disclosure includes: an acquisition unit that acquires a graphic structure input by a user as instruction data; a generation unit that generates an image based on the instruction data; a transformation unit that transforms the generated image into a graphic structure; a calculation unit that calculates the difference between the graphic structure of the instruction data and the graphic structure transformed from the generated image; a regeneration instruction unit that, if the difference is greater than a predetermined value, instructs the generation unit to regenerate the image so that the difference is reduced; and an output unit that, if the difference is less than a predetermined value, outputs the generated image to the user. Attached Figure Description

[0006] The features, advantages, and technical and industrial significance of exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, wherein like symbols denote like elements, and wherein:

[0007] Figure 1 This is a block diagram illustrating the hardware structure of the information processing apparatus according to an embodiment;

[0008] Figure 2 This is a block diagram illustrating the functional structure of the information processing apparatus according to an embodiment;

[0009] Figure 3 This is a flowchart illustrating the operation flow of the information processing device according to an embodiment. Detailed Implementation

[0010] The embodiments of the information processing apparatus will now be described with reference to the accompanying drawings.

[0011] Hardware Structure

[0012] First, refer to Figure 1 The hardware structure of the information processing apparatus described in the embodiments is described. Figure 1 This is a block diagram illustrating the hardware structure of the information processing apparatus according to an embodiment.

[0013] exist Figure 1 In this embodiment, the information processing apparatus 10 is configured to include an arithmetic unit 110, a storage unit 120, a communication unit 130, an input unit 140, and an output unit 150. The arithmetic unit 110, the storage unit 120, the communication unit 130, the input unit 140, and the output unit 150 are interconnected via a data bus.

[0014] The arithmetic processing unit 110 is configured to perform various arithmetic operations in the information processing unit 10. The arithmetic processing unit 110 may have a processor. The arithmetic processing unit 110 may have a single processor or multiple processors. That is, the arithmetic processing unit 110 may have more than one processor. Furthermore, the processor may be a multi-core processor. In the case where the arithmetic processing unit 110 has a single processor that is a multi-core processor, it can be said that the arithmetic processing unit 110 logically has multiple processors.

[0015] The processor included in the computing device 110 may be at least one of a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a FPGA (Field Programmable Gate Array), and a TPU (Tensor Processing Unit).

[0016] Storage device 120 may be at least one of RAM (Random Access Memory), ROM (Read Only Memory), hard disk drive, optical disk drive, SSD (Solid State Drive), and optical disk array. That is, storage device 120 may be implemented by a single device or by multiple devices.

[0017] Storage device 120 is capable of storing desired data. The computer program CP executed by the arithmetic unit 110 can be stored in storage device 120. Storage device 120 can temporarily store data temporarily used by the arithmetic unit 110 while the arithmetic unit 110 is executing the computer program CP.

[0018] Furthermore, the computer program CP can also be recorded on a computer-readable and non-transitory recording medium. In this case, the recording medium can be read using a recording medium reading device (not shown) included in the information processing device 10, thereby storing the computer program CP in the storage device 120. Additionally, at least one of optical discs, magnetic media, optical disks, semiconductor memory, and other media capable of storing programs can be used as the recording medium. The computer program CP can be obtained from an external 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.

[0019] The arithmetic unit 110 (e.g., a processor) can perform the processing to be performed by the information processing unit 10 together with the storage device 120 storing the computer program CP (in other words, together with the storage device 120 and the computer program CP stored in the storage device 120). For example, the computer program CP can also be executed by the arithmetic unit 110, and logical function blocks for performing the processing to be performed by the information processing unit 10 can be implemented within the arithmetic unit 110 (e.g., within the processor).

[0020] The communication device 130 is configured to communicate with devices outside the information processing device 10. The communication device 130 can perform wired communication or wireless communication.

[0021] Input device 140 is a device capable of receiving information input to information processing device 10 from an external source. Input device 140 may include user-operable operating devices of information processing device 10 (e.g., keyboard, mouse, touch panel, etc.). Input device 140 may include a recording medium reading device that reads information recorded on a recording medium, such as a Universal Serial Bus (USB) memory, that can be attached to and removed from information processing device 10. Note that when information is input to information processing device 10 via communication device 130 (in other words, when information processing device 10 obtains information via communication device 130), communication device 130 can function as an input device.

[0022] Output device 150 is a device capable of outputting information to the outside of information processing device 10. Output device 150 may have a display device capable of outputting visual information such as text or images as the aforementioned information. Output device 150 may have a speaker capable of outputting auditory information such as sound as the aforementioned information. Output device 150 may be configured to output the aforementioned information (e.g., control information for other devices) to other devices. Output device 150 can output information to a recording medium such as a USB memory that can be attached to and detached from information processing device 10. Note that when information processing device 10 outputs information via communication device 130, communication device 130 can function as an output device.

[0023] Functional structure

[0024] Next, we will refer to Figure 2 The functional structure of the information processing apparatus 10 according to the embodiment is described. Figure 2 This is a block diagram illustrating the functional structure of an information processing apparatus according to an embodiment.

[0025] exist Figure 2 In this embodiment, the information processing apparatus 10 is configured to generate an image based on instruction data input by a user. As constituent elements for realizing its functions, the information processing apparatus 10 includes an instruction data acquisition unit 210, an image generation unit 220, an image transformation unit 230, a difference calculation unit 240, a regeneration instruction unit 250, and an output unit 260. Furthermore, each of the instruction data acquisition unit 210, the image generation unit 220, the image transformation unit 230, the difference calculation unit 240, the regeneration instruction unit 250, and the output unit 260 can be a processing module implemented by the aforementioned arithmetic unit 110.

[0026] The instruction data acquisition unit 210 is configured to acquire instruction data input by the user. The instruction data is acquired as a graphical structure. Here, the graphical structure can mean relational data of various parts of an object in an image, which is constructed using node groups and edge groups representing relationships between nodes. The instruction data acquisition unit 210 may also have the function of vectorizing the acquired graphical structure features.

[0027] The image generation unit 220 is configured to generate an image based on the graphic structure acquired by the instruction data acquisition unit 210. That is, the image generation unit 220 transforms data representing a graphic structure to the user into an image. The image generator 220 can generate the image using a pre-machined image generation model 301. The image generation model 301 can be a model that takes a graphic structure (or a feature vector of the graphic structure) as input and outputs an image.

[0028] The image transformation unit 230 is configured to transform the image generated by the image generation unit 220 (hereinafter, appropriately referred to as the "generated image") into a graphic structure. That is, the image transformation unit 230 transforms the image obtained by the image generation unit 220 from the graphic structure transformation back into a graphic structure. The image transformation unit 230 can use a pre-machined image transformation model 302 to transform the image into a graphic structure. The image transformation model 302 can be a model that takes an image as input and outputs a graphic structure (or a feature vector of the graphic structure).

[0029] The difference calculation unit 240 is configured to calculate the difference between the graphic structure acquired by the instruction data acquisition unit 210 and the graphic structure transformed by the image transformation unit 230. That is, the difference calculation unit 240 calculates the difference between the graphic structure input by the user as instruction data and the graphic structure transformed from the image generated based on the instruction data. The difference calculation unit 240 can calculate the difference between the feature vectors of the graphic structure.

[0030] The regeneration instruction unit 250 is configured to provide a regeneration instruction to the image generation unit 220. Specifically, the regeneration instruction unit 250 provides a regeneration instruction to the image generation unit 220 when the difference calculated by the difference calculation unit 240 is above a predetermined value. Here, the "predetermined value" is a threshold used to determine that there is a difference between the graphic structure input by the user and the graphic structure obtained by transforming the generated image, to the extent that it can be determined that the image should be regenerated. When regenerating the image, the regeneration instruction unit 250 outputs an instruction to regenerate an image whose difference calculated by the difference calculation unit 240 has decreased.

[0031] The output unit 260 is configured to output the generated image produced by the image generation unit 220 to the user. Specifically, the output unit 260 outputs the generated image to the user when the difference calculated by the difference calculation unit 240 is less than a predetermined value. The output unit 260 may, for example, output the generated image in a manner that causes the display to show the image.

[0032] Action Flow

[0033] Next, we will refer to Figure 3 The flow of operation of the information processing apparatus 10 according to the embodiment is described. Figure 3 This is a flowchart illustrating the operation flow of the information processing device according to an embodiment.

[0034] like Figure 3 As shown, when the information processing apparatus 10 according to the implementation method begins operation, firstly, the instruction data acquisition unit 210 acquires the graphic structure input by the user as instruction data (step S101). Then, the image generation unit 220 generates an image based on the graphic structure acquired by the instruction data acquisition unit 210 (step S102).

[0035] Next, the image transformation unit 230 transforms the image generated by the image generation unit 220 into a graphic structure (step S103). Then, the difference calculation unit 240 calculates the difference between the graphic structure acquired by the instruction data acquisition unit 210 and the graphic structure transformed by the image transformation unit 230 (step S104).

[0036] If the difference calculated by the difference calculation unit 240 is above a predetermined value (step S105: Yes), the regeneration instruction unit 250 instructs the image generation unit 220 to regenerate the image (step S106). In this case, the processing of step S103 is performed again using the regenerated image. Thus, the image regeneration is repeatedly performed until the difference is less than the predetermined value.

[0037] On the other hand, if the difference calculated by the difference calculation unit 240 is less than a predetermined value (step S105: No), the output unit 260 outputs the image generated by the image generation unit 220 (step S107). Furthermore, if the image is regenerated, the output unit 260 outputs the regenerated image (specifically, the image when the difference is less than the predetermined value).

[0038] Technical effect

[0039] Next, the technical effects obtained by the information processing apparatus 10 according to the embodiments will be described.

[0040] like Figures 1 to 3 As explained, in the information processing apparatus 10 of the embodiment, an image is generated based on a graphic structure input as instruction data. Then, if the difference between the graphic structure used as instruction data and the graphic structure obtained by transforming the generated image is greater than or equal to a predetermined value, the image is regenerated. In this way, an image that conforms to the user's intention (i.e., an image that accurately transforms the graphic structure used as instruction data) can be output. Specifically, even if the image generation unit 220 cannot transform the graphic structure into an appropriate image in one go, an image that is closer to the user's desired image can be obtained by regenerating an image where the difference between the graphic structure used as instruction data and the graphic structure of the generated image is smaller.

[0041] Furthermore, in cases where a suitable image is not generated, a method of re-entering new instruction data is considered. However, this presents the inconvenience of the user inputting a new graphic structure. Moreover, even if a new graphic structure is input, a suitable image may not be generated. In such cases, multiple exchanges occur between the user and the device. However, according to the information processing apparatus 10 of this embodiment, the image is automatically regenerated based on the difference in the graphic structure. Therefore, an image that matches the user's intent can be generated without increasing the user's inconvenience.

[0042] The present invention, derived from the embodiments described above, will now be described.

[0043] An information processing apparatus according to one aspect of this disclosure includes: an acquisition unit that acquires a graphic structure input by a user as instruction data; a generation unit that generates an image based on the instruction data; a transformation unit that transforms the generated image into a graphic structure; a calculation unit that calculates the difference between the graphic structure of the instruction data and the graphic structure obtained by transformation from the generated image; a regeneration instruction unit that, if the difference is greater than or equal to a predetermined value, instructs the generation unit to regenerate the image so that the difference is reduced; and an output unit that, if the difference is less than a predetermined value, outputs the generated image to the user. In the above embodiment, "instruction data acquisition unit 210" corresponds to an example of "acquisition unit", "image generation unit 220" corresponds to an example of "generation unit", "image transformation unit 230" corresponds to an example of "transformation unit", "difference calculation unit 240" corresponds to an example of "calculation unit", "regeneration instruction unit 250" corresponds to an example of "regeneration instruction unit", and "output unit 260" corresponds to an example of "output unit".

[0044] In the information processing apparatus described above, the generation unit may include a first machine learning model that takes a graphical structure, which is the indicator data, as input and outputs an image, and the transformation unit may include a second machine learning model that takes the generated image as input and outputs a graphical structure. In this way, since the model used to generate the image from the graphical structure and the model used to transform the image into the graphical structure are different, the regeneration of the indicator image can be more reliably indicated.

[0045] This disclosure is not limited to the embodiments described above. Appropriate modifications may be made without departing from the spirit or spirit of the invention as read in its entirety from the claims and description. Information processing apparatuses that accompany such modifications are also included within the technical scope of this invention.

Claims

1. Information processing device, equipped with: The acquisition unit acquires the graphical structure input by the user as indicator data; The generation unit generates an image based on the indicated data; The transformation unit transforms the generated image into a graphic structure; The calculation unit calculates the difference between the graphic structure of the indicated data and the graphic structure obtained from the generated image transformation; The regeneration instruction unit instructs the generation unit to regenerate the image when the difference is above a predetermined value, so as to reduce the difference. as well as The output unit outputs the generated image to the user when the difference is less than a predetermined value.

2. The information processing apparatus according to claim 1, wherein, The generation unit includes a first machine learning model, which takes the graphical structure of the indicated data as input and outputs an image. The transformation unit includes a second machine learning model that takes the generated image as input and outputs a graphical structure.

Images