Information processing system and program

Abstract

An information processing system and program are provided that can assist in the creation of prompts to be input into an image generation AI system. [Solution] The information processing system 10 comprises a control means 20 and a memory means 21, and the control means 20 comprises an instruction acquisition unit 30 that acquires image generation instructions, a prompt generation unit 31 that generates a prompt to be input to the generation AI system 15, a prompt sending unit 32 that transmits the prompt, an AI output information acquisition unit 33 that acquires AI output information from the generation AI system 15, and an information output unit 34 that presents the AI ​​output information, and the prompt generation unit 31 generates a concretization instruction prompt including an instruction to complement information to concretize the image generation instructions as an image generation prompt, sends the concretization instruction prompt to the generation AI system 15 to acquire the image generation prompt, and the information output unit 34 presents the acquired image generation prompt to the user.

Description

[Technical field]

[0001] The present invention relates to an information processing system and a program that complements prompts sent to an image generation AI system and points out missing elements. [Background technology]

[0002] In recent years, services have been provided that generate text in a dialogue with users using generative AI systems that use large-scale language models (LLMs). Image generation AI systems are also available that generate images by inputting text that describes the image and conditions of the image to be generated. In order to obtain the desired output from such generative AI systems, users need to create appropriate prompts and input them to the generative AI system.

[0003] However, it is difficult for an inexperienced user to create an appropriate prompt. For this reason, a system that generates a prompt for a generative AI system is also known. For example, Patent Document 1 lists a system that generates a prompt to be input to a generative AI system using LLM. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 7313757 Summary of the Invention [Problem to be solved by the invention]

[0005] Images generated by image generation AI systems vary widely depending on the prompts input. For this reason, it is easier to output the desired image if the prompts input to the image generation AI system include clear instructions for information that is not normally specified when communicating instructions between people, and prerequisites that are taken for granted. Inexperienced users do not know how to configure the prompts to be input to image generation AI systems, so it is desirable to provide appropriate support in this regard.

[0006] The present invention has been made in consideration of the above-mentioned problems, and aims to provide an information processing system and program that can assist in the creation of prompts to be input into an image generation AI system. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems, an information processing system according to the present invention is an information processing system that generates an image generation prompt based on an image generation instruction input by a user to an image generation AI system, and is equipped with a control means and a storage means, wherein the control means is equipped with an instruction acquisition unit that acquires the image generation instruction, a prompt generation unit that generates a prompt to be input to the generative AI system using an LLM, a prompt transmission unit that transmits the prompt to the generative AI system, an AI output information acquisition unit that acquires AI output information from the generative AI system, and an information output unit that presents the AI ​​output information to the user, wherein the prompt generation unit generates a concretization instruction prompt including an instruction to supplement information so as to concretize the image generation instruction as the image generation prompt, the prompt transmission unit transmits the concretization instruction prompt to the generative AI system, and the information output unit presents to the user the image generation prompt in which information is supplemented to the image generation instruction acquired by the AI ​​output information acquisition unit. The prompt generation unit generates the concretization instruction prompt so as to include an instruction to extract an element missing from the image generation instruction, and the information output unit presents to the user information on the element missing from the image generation instruction acquired by the AI ​​output information acquisition unit. .

[0009] In addition, in the information processing system of the present invention, the prompt generation unit presents information on elements missing from the image generation instruction to the user, and then, when the missing elements are obtained from the user, re-generates the concretization instruction prompt based on information that adds the missing elements to the image generation instruction.

[0010] In addition, the information processing system according to the present invention comprises: An information processing system that generates an image generation prompt based on an image generation instruction input by a user to an image generation AI system, comprising a control means and a storage means, wherein the control means comprises an instruction acquisition unit that acquires the image generation instruction, a prompt generation unit that generates a prompt to be input to the generative AI system using an LLM, a prompt transmission unit that transmits the prompt to the generative AI system, an AI output information acquisition unit that acquires AI output information from the generative AI system, and an information output unit that presents the AI ​​output information to the user, wherein the prompt generation unit generates a concretization instruction prompt including an instruction to supplement information so as to concretize the image generation instruction as the image generation prompt, the prompt transmission unit transmits the concretization instruction prompt to the generative AI system, and the information output unit presents to the user the image generation prompt in which information is supplemented to the image generation instruction acquired by the AI ​​output information acquisition unit, When the image generation instruction includes an instruction for a person and no instruction is given for the nationality of the person, the prompt generation unit includes an instruction for specifying a specific nationality as an instruction for complementing the information.

[0011] In the information processing system according to the present invention, the prompt generation unit includes, as the instruction to complement the information, an instruction to complement background information based on an instruction included in the image generation instruction.

[0012] In addition, the information processing system according to the present invention comprises: An information processing system that generates an image generation prompt based on an image generation instruction input by a user to an image generation AI system, comprising a control means and a storage means, wherein the control means comprises an instruction acquisition unit that acquires the image generation instruction, a prompt generation unit that generates a prompt to be input to the generative AI system using an LLM, a prompt transmission unit that transmits the prompt to the generative AI system, an AI output information acquisition unit that acquires AI output information from the generative AI system, and an information output unit that presents the AI ​​output information to the user, wherein the prompt generation unit generates a concretization instruction prompt including an instruction to supplement information so as to concretize the image generation instruction as the image generation prompt, the prompt transmission unit transmits the concretization instruction prompt to the generative AI system, and the information output unit presents to the user the image generation prompt in which information is supplemented to the image generation instruction acquired by the AI ​​output information acquisition unit, The prompt generating unit includes, as the instruction to complement the information, an instruction to increase visibility when the size of the generated image is small.

[0013] In the information processing system according to the present invention, the prompt generating unit includes an instruction to exclude a certain inappropriate element in the concrete instruction prompt.

[0014] In order to solve the above problems, the present invention provides a program that can be used from a user terminal, the program comprising: User-input image generation AI systemThe method executes an instruction acquisition process for acquiring an image generation instruction, a prompt generation process for generating a prompt to be input to a generative AI system using an LLM, a prompt transmission process for transmitting the prompt to the generative AI system, an AI output information acquisition process for acquiring AI output information from the generative AI system, and an information output process for presenting the AI ​​output information to the user, wherein the prompt generation process generates a concretization instruction prompt including an instruction to supplement information so as to concretize the image generation instruction as an image generation prompt, the prompt transmission process transmits the concretization instruction prompt to the generative AI system, and the information output process presents the image generation prompt, in which information is supplemented to the image generation instruction acquired in the AI ​​output information acquisition process, to the user. In the prompt generation process, the embodiment instruction prompt is generated so as to include an instruction to extract an element that is missing from the image generation instruction, and in the information output process, information on the element that is missing from the image generation instruction acquired in the AI ​​output information acquisition process is presented to the user. . Effect of the Invention

[0015] According to the information processing system and program of the present invention, a user can easily generate an image generation prompt for obtaining a stable image with little fluctuation or wobble in the generated image. [Brief description of the drawings]

[0016] [Figure 1] 1 shows a configuration diagram of an information processing system according to an embodiment of the present invention. [Diagram 2] 3 shows a detailed configuration diagram of a control means. [Diagram 3] 1 is a flowchart in an information processing system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] An embodiment of the present invention will be described in detail with reference to the drawings. The information processing system 10 of this embodiment is a system that, when generating an image with an image generation AI system, complements the image generation instruction input by the user and extracts missing elements to provide a more specific image generation prompt, thereby supporting the generation of an image closer to the user's desire. The information processing system 10 uses a generation AI system 15 using an LLM (large-scale language model) to complement the image generation instruction and extract the missing elements. The LLM is a language model constructed using a large amount of text data and deep learning technology. This allows the generation AI system 15 to perform natural language processing and generate natural dialogue and sentences like a human. The generation AI system 15 can receive a prompt from the information processing system 10 and transmit AI output information corresponding to the prompt.

[0018] As shown in Fig. 1, an information processing system 10 can be connected to a plurality of user terminals 12 via a communication network 17. This allows a plurality of users to log in and use the information processing system 10. Each user terminal 12 has a display means 13 such as a monitor. The user terminal 12 is a computer such as a PC, or a mobile information terminal such as a smartphone. However, the user terminal 12 is not limited to these.

[0019] The information processing system 10 can be connected to the generative AI system 15 and the image generation AI system 16 via a communication network 17. The information processing system 10 can obtain AI output information by sending a prompt to the generative AI system 15. The information processing system 10 can also obtain a generated image by sending an image generation prompt to the image generation AI system 16. The information processing system 10 may be capable of being connected to a plurality of generative AI systems 15 and image generation AI systems 16, or the information processing system 10 itself may include a generative AI system 15 and an image generation AI system 16.

[0020] In Figure 1, information processing system 10 is connected to multiple user terminals 12, generative AI system 15, and image generation AI system 16 via a single communication network 17, but information processing system 10 may also be connected to user terminals 12, generative AI system 15, and image generation AI system 16 via separate communication networks. For example, information processing system 10 can be connected to user terminals 12 via an in-house LAN, and to generative AI system 15 and image generation AI system 16 via the Internet.

[0021] The information processing system 10 can be configured with a computer such as a server. The information processing system 10 includes at least a control means 20, a storage means 21, and a communication means 22. The control means 20 can be configured with a processor such as a CPU. The storage means 21 can be configured with, for example, a RAM, a DRAM, a HDD, an SSD, or an external cloud or distributed storage. The communication means 22 can be configured with, for example, a NIC or a wireless LAN connection device.

[0022] As shown in Figure 2, the control means 20 includes an instruction acquisition unit 30 that transmits and receives information between the user terminal 12 and acquires image generation instructions input by the user, a prompt generation unit 31 that generates a prompt to be input to the generation AI system 15, a prompt transmission unit 32 that transmits a prompt to the generation AI system 15 or the image generation AI system 16, an AI output information acquisition unit 33 that acquires AI output information from the generation AI system 15 or the image generation AI system 16, and an information output unit 34 that transmits AI output information to the user terminal 12 and presents it to the user.

[0023] Next, a flow of a user using the generation AI system 15 with the information processing system 10 will be described. As shown in Fig. 3, first, the user inputs an image generation instruction on the user terminal 12 (S1). The image generation instruction is a verbal expression of the image the user wants to generate. The image generation instruction is, for example, as follows: "Female image: A business woman in her late 30s with a confident expression Wearing a suit and holding a tablet It makes you think of a team leader or manager.

[0024] The instruction acquisition unit 30 receives and acquires an image generation instruction input by a user. Next, the prompt generation unit 31 generates an embodiment instruction prompt for further concretizing the image generation instruction as an image generation prompt based on the acquired image generation instruction (S2).

[0025] The concretization prompt is to make the abstract expressions of the image generation instructions entered by the user as concrete as possible, and to verbalize the requests that can be read from the image generation instructions. Also, if the image generation instructions include a purpose, the purpose is accurately understood and included in the image generation prompt. The concretization prompt includes an instruction to supplement information so as to concretize the image generation instruction as an image generation prompt. The information to be supplemented in this instruction is information that is usually not specified between people and is easily overlooked when creating an image generation instruction, such as prerequisites that are taken for granted.

[0026] Specifically, the instruction to supplement the information includes an instruction to specify a specific nationality, for example, Japan, when the image generation instruction specifies a person and the nationality of the person is not specified.

[0027] The instruction to complement information may include an instruction to complement background information based on other instructions included in the image generation instruction. The instruction to complement background information may include an instruction to specify a simple background when the image generation instruction does not include a specific background instruction.

[0028] The instruction to supplement information also includes an instruction to increase visibility when the size of the image to be generated is small. For example, when the size of the image to be generated is smaller than a certain value, a simple background or a simple composition is specified.

[0029] The concrete instruction prompt includes an instruction to exclude certain inappropriate elements. For example, if sexual depictions, violence, discriminatory expressions, copyright infringement, etc. are included in the generated image generation prompt as inappropriate elements, the system instructs the output to exclude these elements.

[0030] The concretization prompt includes an instruction to extract elements that are missing from the image generation instruction. The instruction includes a description that lists, as candidates for the missing elements, for example, a purpose, an image style, details of a person, a use of the image, a mood or atmosphere of the image, and elements that are unnecessary for the image, and if any of these are missing from the generated image generation prompt, presents the user with up to one element, as well as advice for improvement and a request to present multiple examples.

[0031] The instantiation prompt further includes an instruction to output the information generated from the above instruction sentence in a certain format, which outputs the image generation prompt in Japanese, the image generation prompt translated into English, the content and examples of missing elements, if any, and the content excluding inappropriate elements, if any, separately.

[0032] When the concretization instruction prompt is generated, the prompt sending unit 32 sends the concretization instruction prompt to the generation AI system 15 (S3). The generation AI system 15 generates an image generation prompt according to the instruction of the concretization instruction prompt (S4). As described above, the concretization instruction prompt includes an instruction to generate an image generation prompt by complementing information, as well as an instruction to extract missing elements, generate an improvement plan, and exclude inappropriate elements, so the generation AI system 15 generates information about these as well. In addition, the concretization instruction prompt instructs the generation AI system 15 to output the image generation prompt in English, so the generation AI system 15 translates the image generation prompt into English (S5). The generated information is sent from the generation AI system 15 to the information processing system 10, and the AI ​​output information acquisition unit 33 acquires the AI-generated information (S6).

[0033] The AI ​​output information generated by the generation AI system 15 is, for example, as follows: "Image Generation Prompt (Japanese) -Portraying Japanese business women in their late 30s - Look confident and look towards the camera Wearing a dark grey suit and a white blouse Hold the tablet in your right hand and assume a natural pose The surroundings depict a corner of an office, with blurred desks and laptops in the background. The background is simple and reflects the modern office space. - Emphasize a bright, professional and leadership-oriented mood Image generation prompt (English) ·Depict a Japanese businesswoman in her late 30s ·Confidence exuded through her facial expression, looking at the camera ·Wearing a dark gray suit and a white blouse ·The surroundings portray a corner of an office; blurred desks and a laptop in the background ·Background reflects a modern office space while keeping it simple ·Emphasize a bright, professional, and leadership-evoking mood Advice on missing elements Specifying the style and touch in detail can help you get closer to your image. For example, consider styles such as "Anime," "Semi-Realistic," and "Pop Art."

[0034] In this example, the image generation instructions do not specify the woman's nationality, details of her clothing, background, etc., so the image generation prompt is generated by the AI ​​system 15 supplementing these information. Also, the image generation instructions lack information on the style of the entire image, so the AI ​​system 15 extracts these missing elements and presents them together with an example in response to the prompt. Furthermore, the image generation prompt in Japanese is translated into English.

[0035] If the size of the image to be generated is specified in the image generation instructions and this is a small size, for example 150px x 150px, the concretization instruction prompt includes an instruction to specify a simple background and simple composition if the size of the image to be generated is smaller than a certain size, so the generation AI system 15 includes a specification in the image generation prompt to make the background simple, such as a solid color or a gradient.

[0036] Next, the information output unit 34 of the information processing system 10 determines whether the acquired AI output information contains information on missing elements (S7), and if there are no missing elements, the information output unit 34 transmits the generated image generation prompt to the user terminal 12, which displays it and presents it to the user (S8). If the user modifies the instructions in the image generation prompt (S9), the process repeats from step S5, where the modified image generation prompt is transmitted to the generation AI system 15 and translated into English. If the instructions are not modified in S9, the process proceeds to the next step.

[0037] If the AI ​​output information acquired in S7 contains information on missing elements, the information output unit 34 transmits the information on the missing elements together with the generated image generation prompt to the user terminal 12, and displays and presents it to the user (S10). If the user modifies the instruction content in the image generation prompt (S11), the process repeats from step S5, in which the modified image generation prompt is transmitted to the generation AI system 15 for translation into English. If the instruction content is not modified in S11, and the user modifies the image generation prompt to add the presented missing elements (S12), the process repeats from step S2, in which a concretization instruction prompt is generated based on the information in which the missing elements have been added to the initial image generation instruction. If the missing elements have not been added in S12, the process proceeds to the next step.

[0038] Next, the prompt sending unit 32 sends the image generation prompt to the image generation AI system 16 (S13). The AI ​​output information acquisition unit 33 acquires the image generated by the image generation AI system 16 in accordance with the image generation prompt, and the information output unit 34 sends the generated image to the user terminal 12 for display (S15). Note that the information processing system 10 may perform the process up to generating the image generation prompt, and the user may send the image generation prompt to the image generation AI system 16 and acquire the generated image at the user terminal 12.

[0039] In this way, the information processing system 10 generates a concretization instruction prompt to be input to the generation AI system 15 using LLM based on the image generation instructions input by the user, complements the image generation instructions, and presents missing elements, in order to support the creation of an image generation prompt to be input to the image generation AI system 16. This allows the user to easily generate an image generation prompt to obtain a stable image with little fluctuation or fluctuation in the generated image.

[0040] Also, the program used in the information processing system 10 of this embodiment can be provided alone. In this case, the program is a program available from the user terminal 12, and causes a computer to execute an instruction acquisition process for acquiring an image generation instruction, a prompt generation process for generating a prompt to be input to the generation AI system 15 using the LLM, a prompt transmission process for transmitting the prompt to the generation AI system 15, an AI output information acquisition process for acquiring AI output information from the generation AI system 15, and an information output process for presenting the AI ​​output information to the user, in which the prompt generation process generates a concretization instruction prompt including an instruction to complement information so as to concretize the image generation instruction as an image generation prompt, the prompt transmission process transmits the concretization instruction prompt to the generation AI system 15, and the information output process presents to the user an image generation prompt in which information is complemented to the image generation instruction acquired in the AI ​​output information acquisition process.

[0041] Although the embodiment of the present invention has been described above, the application of the present invention is not limited to the embodiment, and the present invention can be applied in various ways within the scope of its technical concept. [Explanation of symbols]

[0042] 10. Information Processing Systems 12 User terminals 13 Display means 15 Generative AI System 16 Image generation AI system 17. Communications Networks 20 Control Means 21 Memory means 22 Means of communication 30 Instruction acquisition part 31 Prompt Generation Unit 32 Prompt sending section 33 AI output information acquisition section 34 Information output section

Claims

1. An information processing system that creates an image generation prompt based on an image generation instruction input by a user to an image generation AI system, A control means and a storage means are provided, The control means An instruction acquisition unit that acquires the image generation instruction; A prompt generation unit that generates a prompt to be input to a generation AI system using the LLM; a prompt sending unit that sends the prompt to the generating AI system; An AI output information acquisition unit that acquires AI output information from the generation AI system; An information output unit that presents the AI ​​output information to the user; Equipped with The prompt generation unit generates an embodiment instruction prompt including an instruction to supplement information so as to embody the image generation instruction as the image generation prompt; The prompt sending unit sends the instantiation instruction prompt to the generating AI system; The information output unit presents to the user the image generation prompt in which information is supplemented to the image generation instruction acquired by the AI ​​output information acquisition unit, the prompt generation unit generates the instantiation instruction prompt so as to include an instruction for extracting an element that is missing from the image generation instruction; The information output unit is an information processing system that presents to the user information on elements that are missing from the image generation instructions acquired by the AI ​​output information acquisition unit.

2. The information processing system of claim 1, wherein the prompt generation unit presents information of elements missing from the image generation instruction to the user, and then, when the prompt generation unit obtains the missing elements from the user, regenerates the concretization instruction prompt based on information that adds the missing elements to the image generation instruction.

3. An information processing system that creates an image generation prompt based on an image generation instruction input by a user to an image generation AI system, A control means and a storage means are provided, The control means An instruction acquisition unit that acquires the image generation instruction; A prompt generation unit that generates a prompt to be input to a generation AI system using the LLM; a prompt sending unit that sends the prompt to the generating AI system; An AI output information acquisition unit that acquires AI output information from the generation AI system; An information output unit that presents the AI ​​output information to the user; Equipped with The prompt generation unit generates an embodiment instruction prompt including an instruction to supplement information so as to embody the image generation instruction as the image generation prompt; The prompt sending unit sends the instantiation instruction prompt to the generating AI system; The information output unit presents to the user the image generation prompt in which information is supplemented to the image generation instruction acquired by the AI ​​output information acquisition unit, The information processing system includes, as an instruction to complement the information, an instruction to specify a specific nationality when the image generation instruction includes an instruction for a person and no specification of the nationality of the person.

4. The information processing system according to any one of claims 1 to 3, wherein the prompt generation unit includes, as an instruction to complement the information, an instruction to complement background information based on an instruction contained in the image generation instruction.

5. An information processing system that creates an image generation prompt based on an image generation instruction input by a user to an image generation AI system, A control means and a storage means are provided, The control means An instruction acquisition unit that acquires the image generation instruction; A prompt generation unit that generates a prompt to be input to a generation AI system using the LLM; a prompt sending unit that sends the prompt to the generating AI system; An AI output information acquisition unit that acquires AI output information from the generation AI system; An information output unit that presents the AI ​​output information to the user; Equipped with The prompt generation unit generates an embodiment instruction prompt including an instruction to supplement information so as to embody the image generation instruction as the image generation prompt; The prompt sending unit sends the instantiation instruction prompt to the generating AI system; The information output unit presents to the user the image generation prompt in which information is supplemented to the image generation instruction acquired by the AI ​​output information acquisition unit, The prompt generation unit includes, as an instruction to complement the information, an instruction to increase visibility when a size of an image to be generated is small.

6. 6. The information processing system according to claim 1, wherein the prompt generating unit includes, in the concretization instruction prompt, an instruction for excluding a certain inappropriate element.

7. A program available from a user terminal, On the computer, An instruction acquisition process for acquiring an image generation instruction input by a user to the image generation AI system; A prompt generation process that generates a prompt to be input to a generation AI system using the LLM; a prompt sending process for sending the prompt to the generating AI system; An AI output information acquisition process for acquiring AI output information from the generation AI system; An information output process for presenting the AI ​​output information to the user; Run the command, In the prompt generation process, an embodiment instruction prompt is generated, the embodiment instruction prompt including an instruction to supplement information so as to embody the image generation instruction as an image generation prompt; In the prompt sending process, the instantiation instruction prompt is sent to the generating AI system; In the information output process, the image generation prompt in which information is supplemented to the image generation instruction acquired in the AI ​​output information acquisition process is presented to the user; In the prompt generation process, the instantiation instruction prompt is generated so as to include an instruction for extracting an element that is missing from the image generation instruction; In the information output process, a program presents to the user information on elements missing from the image generation instructions acquired in the AI ​​output information acquisition process.

Images