Information processing device, method, program and system
A program using a large-scale language model automates homepage creation by generating content from image inputs, addressing the burden of constructing comprehensive service websites.
Patent Information
- Application Number
- JP2024213020
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2024-12-06
- Publication Date
- 2026-02-03
- Estimated Expiration
- 2044-12-06
AI Technical Summary
Existing technologies, such as Patent Document 1, are specialized in constructing e-commerce sites for single products and do not support the creation of homepages for entire services, placing a heavy burden on those in charge of creating them.
A program executed by a computer with a processor and memory, utilizing a large-scale language model to generate homepage content by obtaining pre-set templates, requesting image-based inputs, and generating explanatory text to create a homepage.
Supports the creation of homepages and reduces the burden on individuals responsible for their creation by automating the process through image-based input and text generation.
Smart Images

Figure 0007810504000001_ABST
Abstract
Description
[Technical Field]
[0001] The present disclosure relates to an information processing device, a method, a program, and a system. [Background technology]
[0002] In today's world, it is common to gather information via the Internet, and it is important to have a website for the services you provide. However, when creating a website, the person in charge must prepare images and text related to the service, which places a heavy burden on the person in charge.
[0003] For example, Patent Document 1 discloses a technology that enables a user who is the owner of an e-commerce site to easily put items up for sale. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] Patent No. 7411137 Summary of the Invention [Problem to be solved by the invention]
[0005] However, Patent Document 1 is specialized in constructing an e-commerce site for a single product that a user puts up for sale, and does not create a homepage for the entire service to be provided.
[0006] An object of the present disclosure is to support the creation of homepages and reduce the burden on those in charge of creating homepages. [Means for solving the problem]
[0007] In order to solve the above problem, one aspect of the program of the present disclosure is a program to be executed by a computer having a processor and a memory, the program causing the processor to execute the following steps: obtaining a template in which multiple elements for creating a homepage are pre-set; requesting the provision of an image based on a specified element from the multiple elements; obtaining a prompt corresponding to the specified element in response to the provision of the image; inputting the provided image and the obtained prompt into a large-scale language model and outputting sentences related to the provided image from the large-scale language model; and generating content for the homepage based on the provided image and the output sentences. [Effects of the Invention]
[0008] According to the present disclosure, it is possible to support the creation of a homepage and reduce the burden on the person in charge of creating the homepage. [Brief explanation of the drawings]
[0009] [Figure 1] 1 is a block diagram showing an example of the overall configuration of a system 1. FIG. [Figure 2] 2 is a block diagram illustrating an example of the configuration of a terminal device 10 shown in FIG. [Figure 3] FIG. 2 is a diagram illustrating an example of the functional configuration of a server 20. [Figure 4] FIG. 2 is a diagram showing the data structure of a user information table 2021. [Figure 5] FIG. 2 shows the data structure of a classification table 2022. [Figure 6] FIG. 10 is a diagram showing the data structure of a template table 2023. [Figure 7] FIG. 20 is a diagram showing the data structure of a prompt table 2024. [Figure 8] 10 is a flowchart showing an example of the operation of the server 20 when supporting the creation of a homepage. [Figure 9]10 is a flowchart showing the editing and regeneration process in step S20. [Figure 10] 10 is a flowchart showing the retouching process in step S30. [Figure 11] 2 is a schematic diagram illustrating an example of a display screen of a display 141 of a terminal device 10. FIG. [Figure 12] 10 is a schematic diagram illustrating another example of the display screen of the display 141 of the terminal device 10. FIG. [Figure 13] 10 is a schematic diagram illustrating another example of the display screen of the display 141 of the terminal device 10. FIG. [Figure 14] 10 is a flowchart showing a modified example of the operation of the server 20 when supporting the creation of a homepage. [Figure 15] 10 is a schematic diagram showing a modified example of the display screen of the display 141 of the terminal device 10. FIG. [Figure 16] FIG. 2 is a block diagram showing the basic hardware configuration of a computer 90. DETAILED DESCRIPTION OF THE INVENTION
[0010] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In all drawings describing the embodiments, common components are designated by the same reference numerals, and repeated explanations will be omitted. Note that the following embodiments do not unduly limit the content of the present disclosure described in the claims. Furthermore, not all components shown in the embodiments are necessarily essential components of the present disclosure. Furthermore, each drawing is a schematic diagram and is not necessarily a precise illustration.
[0011] In the following description, a "processor" refers to one or more processors. The at least one processor is typically a microprocessor such as a CPU (Central Processing Unit), but may also be another type of processor such as a GPU (Graphics Processing Unit). The at least one processor may be single-core or multi-core.
[0012] Furthermore, the at least one processor may be a processor in the broad sense, such as a hardware circuit (for example, a field-programmable gate array (FPGA) or an application-specific integrated circuit (ASIC)) that performs part or all of the processing.
[0013] In the following explanation, information that produces an output for an input may be described using expressions such as "xxx table," but this information may be data of any structure, or may be a learning model such as a neural network that produces an output for an input. Therefore, an "xxx table" may be referred to as "xxx information."
[0014] Furthermore, in the following description, the configuration of each table is an example, and one table may be divided into two or more tables, or all or part of two or more tables may be one table.
[0015] In addition, in the following explanation, processing may be described using the "program" as the subject, but since a program is executed by a processor to perform specified processing while appropriately using a memory unit and / or an interface unit, etc., the subject of the processing may also be the processor (or a device such as a controller that has that processor).
[0016] The program may be installed in a device such as a computer, or may be stored in, for example, a program distribution server or a computer-readable (e.g., non-transitory) recording medium. Also, in the following description, two or more programs may be realized as one program, or one program may be realized as two or more programs.
[0017] Furthermore, in the following description, identification numbers are used as identification information for various objects, but other types of identification information (for example, identifiers including alphabetic characters or symbols) may also be used.
[0018] In addition, in the following description, when describing elements of the same type without distinguishing between them, reference symbols (or common symbols among the reference symbols) may be used, and when describing elements of the same type with distinction between them, the identification numbers (or reference symbols) of the elements may be used.
[0019] In the following description, the control lines and information lines are those that are considered necessary for the description, and do not necessarily represent all the control lines and information lines in the product. All components may be interconnected.
[0020] Each information processing device is configured by a computer equipped with an arithmetic unit and a storage device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by the hardware configuration will be described later. For each of the terminal device 10 and the server 20, descriptions that overlap with the basic hardware configuration and basic functional configuration of the computer will be omitted.
[0021] <Summary> The system according to this embodiment has a function for supporting the creation of a homepage related to a service to be provided. The system, for example, acquires a homepage template. The template has multiple elements for creating the homepage preset. The system inputs images provided by a user based on each element into large language models (LLMs), causing the LLM to output explanatory text related to the image. The system generates homepage content based on the images and explanatory text. The elements may be any element, such as the exterior, interior, or menu of a facility in the service to be provided. The system according to this embodiment makes it possible to easily create a homepage by simply uploading images for multiple elements in sequence, without the need to input text, etc.
[0022] <1 Overall system configuration> Fig. 1 is a block diagram showing an example of the overall configuration of a system 1. The system 1 shown in Fig. 1 includes, for example, a terminal device 10, a server 20, and an LLM system 30. The terminal device 10, the server 20, and the LLM system 30 are communicatively connected via, for example, a network 80.
[0023] 1 shows an example in which the system 1 includes two terminal devices 10, but the number of terminal devices 10 included in the system 1 is not limited to two. The number of terminal devices 10 included in the system 1 may be less than three, or may be three or more.
[0024] 1 shows an example in which the system 1 includes one LLM system 30, but the number of LLM systems 30 included in the system 1 is not limited to one. The number of LLM systems 30 included in the system 1 may be two or more.
[0025] 1 shows an example in which the server 20 is independent of the LLM system 30, the server 20 may include the functionality of the LLM system 30. In other words, the server 20 may store the LLM.
[0026] In this embodiment, a collection of multiple devices may be considered as one server. The allocation of multiple functions required to realize the server 20 according to this embodiment to one or multiple pieces of hardware can be determined appropriately in consideration of the processing capacity of each piece of hardware and / or the specifications required for the server 20.
[0027] The terminal device 10 shown in Fig. 1 is an information processing device operated by a user who creates a homepage. The user is a person in charge of creating the homepage, and includes, for example, an employee of a facility that provides a service, a manager, or a management company staff member. The terminal device 10 is realized, for example, by a desktop personal computer (PC), a laptop PC, or the like. The terminal device 10 may also be realized by a mobile terminal such as a smartphone or a tablet.
[0028] The terminal device 10 includes a communication IF (Interface) 12, an input device 13, an output device 14, a memory 15, a storage 16, and a processor 19. The input device 13 is a device for receiving input operations from a user (for example, a touch panel, a touch pad, a pointing device such as a mouse, a keyboard, etc.). The output device 14 is a device for presenting information to a user (a display, a speaker, etc.).
[0029] The server 20 is, for example, an information processing device that uses LLM to provide a service that supports the creation of a homepage. The server 20 transmits images provided by the user and prompts for creating explanatory text (text) related to the images to the LLM system 30, and causes the LLM system 30 to output the text related to the images. The server 20 generates homepage content based on the images provided by the user and the text output from the LLM system 30, and presents it to the user.
[0030] The server 20 is, for example, an information processing device realized by a computer connected to a network 80. As shown in Fig. 1, the server 20 includes a communication IF 22, an input / output IF 23, a memory 25, a storage 26, and a processor 29. The input / output IF 23 functions as an interface with an input device for receiving input operations from a user and an output device for outputting information to the user.
[0031] The LLM system 30 is a system built with a large-scale artificial intelligence model (LLM) used in the field of natural language processing (NLP), for example. By learning from large amounts of text data (web pages, books, articles, etc.), the LLM can understand patterns in human language and effectively perform natural language generation (NLG) tasks.
[0032] LLMs are used in many NLP tasks, such as generating answers to specific questions, automatic sentence generation, text summarization, translation, and sentiment analysis. They can also be used in a variety of applications, including education, entertainment, customer service, and product development. Examples of LLMs include: GPT-4 (registered trademark) (OpenAI) PaLM2 (registered trademark) (Google Inc.) StableLM (StableAI) Llama 2 (Meta)
[0033] The LLM system 30 inputs text data and prompts from the server 20 to the LLM, and causes the LLM to output answers based on the input text data and prompts. The LLM system 30 transmits the answers output from the LLM to the server 20.
[0034] Each information processing device is configured by a computer equipped with an arithmetic unit and a storage device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by the hardware configuration will be described later. For each of the terminal device 10, the server 20, and the LLM system 30, explanations that overlap with the basic hardware configuration and basic functional configuration of the computer will be omitted.
[0035] <1.1 Terminal device configuration> Fig. 2 is a block diagram showing an example configuration of the terminal device 10 shown in Fig. 1. As shown in Fig. 2, the terminal device 10 includes a communication unit 120, an input device 13, an output device 14, an audio processing unit 17, a microphone 171, a speaker 172, a camera 160, a position information sensor 150, a storage unit 180, and a control unit 190. The blocks included in the terminal device 10 are electrically connected by, for example, a bus or the like.
[0036] The communication unit 120 performs processing such as modulation and demodulation for the terminal device 10 to communicate with other devices. The communication unit 120 performs transmission processing on the signal generated by the control unit 190 and transmits it to the outside (for example, the server 20). The communication unit 120 performs reception processing on the signal received from the outside and outputs it to the control unit 190.
[0037] The input device 13 is a device for inputting instructions or information by a user operating the terminal device 10. The input device 13 is realized, for example, by a touch-sensitive device 131 or the like, which inputs instructions by touching an operation surface. When the terminal device 10 is a PC or the like, the input device 13 may be realized by a reader, keyboard, mouse, or the like. The input device 13 converts instructions input by the user into electrical signals and outputs the electrical signals to the control unit 190. The input device 13 may include, for example, a receiving port that receives electrical signals input from an external input device.
[0038] The output device 14 is a device for presenting information to a user operating the terminal device 10. The output device 14 is realized, for example, by a display 141 or the like. The display 141 displays data according to the control of the control unit 190. The display 141 is realized, for example, by an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display or the like.
[0039] The audio processing unit 17 performs, for example, digital-to-analog conversion processing of an audio signal. The audio processing unit 17 converts a signal provided from the microphone 171 into a digital signal and provides the converted signal to the control unit 190. The audio processing unit 17 also provides the audio signal to the speaker 172. The audio processing unit 17 is realized, for example, by a processor for audio processing. The microphone 171 receives audio input and provides an audio signal corresponding to the audio input to the audio processing unit 17. The speaker 172 converts the audio signal provided from the audio processing unit 17 into audio and outputs the audio to the outside of the terminal device 10.
[0040] Camera 160 is a device that receives light with a light-receiving element and outputs the light as a photographing signal. When the user is requested by server 20 to provide an image for creating a homepage, the user may use camera 160 to take the necessary image.
[0041] The position information sensor 150 is a sensor that detects the position of the terminal device 10, and is, for example, a GPS (Global Positioning System) module. The GPS module is a receiving device used in a satellite positioning system. In the satellite positioning system, signals are received from at least three or four satellites, and the current position of the terminal device 10 equipped with the GPS module is detected based on the received signals. The position information sensor 150 may detect the current position of the terminal device 10 from the position of the wireless base station to which the terminal device 10 is connected.
[0042] The storage unit 180 is realized by, for example, the memory 15, the storage 16, etc., and stores data and programs used by the terminal device 10. The storage unit 180 stores, for example, user information 181 and image information 182.
[0043] The user information 181 includes, for example, information about the user who uses the terminal device 10. The information about the user includes, for example, the user's name, age, address, date of birth, and contact information.
[0044] Image information 182 includes, for example, images necessary for creating a homepage. The images include, for example, exterior images, interior images, menu images, etc. of the facility providing the service. For example, when the user is requested by server 20 to provide an image for creating a homepage, the user may provide a pre-stored image or may provide an image newly captured by camera 160.
[0045] The control unit 190 is realized by the processor 19 reading a program stored in the storage unit 180 and executing instructions included in the program. The control unit 190 controls the operation of the terminal device 10. The control unit 190 functions as an operation reception unit 191, a transmission / reception unit 192, and a presentation control unit 193 by operating in accordance with the program.
[0046] The operation reception unit 191 performs processing for receiving instructions or information input from the input device 13. Specifically, for example, the operation reception unit 191 receives instructions or information input from the touch-sensitive device 131 or the like.
[0047] Furthermore, the operation reception unit 191 receives voice instructions input from the microphone 171. Specifically, for example, the operation reception unit 191 receives a voice signal that is input from the microphone 171 and converted into a digital signal by the voice processing unit 17. For example, the operation reception unit 191 analyzes the received voice signal and extracts a predetermined noun, thereby acquiring an instruction from the user.
[0048] The transmitting / receiving unit 192 performs processing for the terminal device 10 to transmit and receive data to and from an external device such as the server 20 in accordance with a communication protocol. Specifically, for example, the transmitting / receiving unit 192 transmits information input by a user or instructions from a user to the server 20. In addition, the transmitting / receiving unit 192 receives information provided by the server 20.
[0049] The presentation control unit 193 controls the output device 14 to present information provided from the server 20 to the user. Specifically, for example, the presentation control unit 194 displays information such as a request instruction transmitted from the server 20 or the contents of a homepage on the display 141. In addition, the presentation control unit 194 outputs the information transmitted from the server 20 from the speaker 172.
[0050] <1.2 Functional configuration of the server> 3 is a diagram showing an example of the functional configuration of the server 20. As shown in FIG. 3, the server 20 functions as a communication unit 201, a storage unit 202, and a control unit 203.
[0051] The communication unit 201 performs processing for the server 20 to communicate with external devices.
[0052] The storage unit 202 includes, for example, a user information table 2021, a classification table 2022, a template table 2023, and a prompt table 2024. The tables stored in the storage unit 202 are not limited to these.
[0053] The user information table 2021 is a table that stores information about users, and will be described in detail later.
[0054] The category table 2022 is a table that stores information about the categories (genres) of services published on the homepage, as will be described in detail later.
[0055] The template table 2023 is a table that stores information about the homepage template, as will be described in detail later.
[0056] The prompt table 2024 is a table that stores information about prompts that serve as input statements to the LLM system 30. Details will be described later.
[0057] The control unit 203 is realized by the processor 29 reading a program stored in the storage unit 202 and executing instructions included in the program. The program includes an application such as a web browser application. The program includes an interpreted programming language such as JavaScript (registered trademark) that is executed on a web browser application stored in the terminal device 10. The control unit 203 operates in accordance with the program to perform functions shown as a reception control module 2031, a transmission control module 2032, a service processing module 2033, and a presentation control module 2034.
[0058] The reception control module 2031 controls the process by which the server 20 receives signals from external devices in accordance with a communication protocol. The transmission control module 2032 controls the process by which the server 20 transmits signals to external devices in accordance with a communication protocol. The service processing module 2033 controls the process of creating a homepage in response to user operations. The presentation control module 2034 controls the process of presenting information to the user.
[0059] Specifically, for example, the reception control module 2031 accepts from the user a selection of a service category for which a homepage is to be created. The service processing module 2033 obtains a template corresponding to the selected category from the category table 2022. The service processing module 2033 references the template table 2023 and identifies multiple elements preset in the template. The service processing module 2033 then references the prompt table 2024 and requests the user to provide an image based on a specific element from the multiple elements. At this time, the presentation control module 2034 may read and present a reference image for the requested image from the prompt table 2024. When the user provides an image, the service processing module 2033 obtains a prompt corresponding to the specific element from the prompt table 2024. The prompt differs for each element. The transmission control module 2032 transmits the provided image and the obtained prompt to the LLM system 30. The reception control module 2031 receives text output from the LLM system 30. This text is an explanatory text related to the image. The service processing module 2033 generates homepage content based on the images and text, for example by synthesizing them. The presentation control module 2034 presents the generated homepage content on the user's terminal device 10.
[0060] Furthermore, the reception control module 2031 receives, for example, an edit instruction from the user for the text output from the LLM system 30. The edit instruction may be executed, for example, by the user operating the terminal device 10. Upon receiving the edit instruction, the service processing module 2033 further receives edited text from the user and edits the content in accordance with the edited text.
[0061] Furthermore, the reception control module 2031 receives, for example, a regeneration instruction for the output text from the user. When the service processing module 2033 receives the regeneration instruction, the transmission control module 2032 transmits the received regeneration instruction to the LLM system 30. The regeneration instruction is a prompt that instructs the LLM included in the LLM system 30 to regenerate the text. At this time, for example, the prompt may be stored in a second prompt table (not shown) stored in the storage unit 202. The reception control module 2031 receives the text output from the LLM system 30 in response to the transmitted regeneration instruction. This text is a regenerated explanatory text related to the image. The service processing module 2033 regenerates the content of the homepage based on the image and the regenerated text. The presentation control module 2034 presents the regenerated content of the homepage on the user's terminal device 10.
[0062] Furthermore, the service processing module 2033 may terminate the creation of the homepage when content has been generated based on images and text for all elements set in the template. Alternatively, the service processing module 2033 may terminate the creation of the homepage when the reception control module 2031 receives an instruction to terminate from the user, regardless of whether content for all elements has been generated.
[0063] Furthermore, for example, when homepage content has been generated for all elements, the reception control module 2031 receives a retouching instruction for the generated homepage content from the user. When the service processing module 2033 receives the retouching instruction, the transmission control module 2032 transmits the generated homepage content and the received retouching instruction to the LLM system 30. The retouching instruction is a prompt that instructs the LLM included in the LLM system 30 to retouch the homepage content. At this time, for example, the prompt may be stored in a second prompt table (not shown) stored in the storage unit 202. The reception control module 2031 receives retouching candidates output from the LLM system 30 in response to the transmitted retouching instruction. The presentation control module 2034 presents the retouching candidates for the homepage content to the user's terminal device 10.
[0064] The retouching candidates may include, for example, at least one of the layout, design, text, and images of the created homepage, and may include multiple candidates for each. The layout may include, for example, the positional relationship of content among multiple elements, the positional relationship between images and text in each content, etc. The design may include, for example, a logo or font for text such as the facility name or menu, etc. The design may also include a background design.
[0065] When receiving retouching instructions from a user, the reception control module 2031 may, for example, receive one or more additional images. The additional images may be different from the previously provided image, for example, they may include images from different angles or of different subjects. The transmission control module 2032 may transmit the additional images along with the received retouching instructions to the LLM system 30.
[0066] Furthermore, when receiving a retouching instruction from a user, the reception control module 2031 may also receive summary information about the homepage content. The summary information may include, for example, information indicating an outline of the content that the user wants to change or add to the generated homepage content. The summary information is not limited to information about the generated homepage content, but may also include information about new content that the user wants to generate. The transmission control module 2032 may transmit the summary information about the homepage content to the LLM system 30 along with the received retouching instruction.
[0067] <2 Data Structure> 4 to 7 are diagrams showing the data structures of tables stored in the server 20. Note that Figures 4 to 7 are merely examples and do not exclude data that is not listed. Furthermore, even data that is listed in the same table may be stored in separate storage areas in the storage unit 202.
[0068] Fig. 4 is a diagram showing the data structure of the user information table 2021. The user information table 2021 shown in Fig. 4 is a table having columns of name, age, sex, date of birth, and contact information, with the user ID as a key.
[0069] The user ID is an item that stores an identifier for uniquely identifying a user. The name is an item that stores the name of the user. The age is an item that stores the age of the user. The gender is an item that stores the gender of the user. The date of birth is an item that stores the date of birth of the user. The contact information is an item that stores the contact information (e.g., telephone number, email address, etc.) of the terminal device 10 that the user has.
[0070] Fig. 5 is a diagram showing the data structure of the category table 2022. The category table 2022 shown in Fig. 5 is a table having columns of user ID, genre, and template ID, with category ID as a key.
[0071] The category ID is an item for storing an identifier for uniquely identifying the category (genre) of the service for which the homepage is to be created.
[0072] The user ID is an item that stores an identifier for uniquely identifying the person who selected the category. The information stored in the user ID corresponds to the user ID stored in the user information table 2021, for example. Note that the name of the homepage creator may be stored instead of the user ID.
[0073] The genre is an item that stores the genre of the service that is the target of the homepage to be created. The item "genre" stores, for example, the facility genre that provides the service. Facility genres include, for example, restaurants, accommodations, tourist facilities, etc. Furthermore, each facility genre may include genres of lower concepts. For example, restaurants may include the cuisine genre, accommodations may include the accommodation genre, and tourist facilities may include the tourist facility genre. Furthermore, each facility genre may include, for example, a price range, etc.
[0074] The template ID is an item that stores an identifier for uniquely identifying a template for creating a homepage. The item "template ID" is uniquely determined according to the item "category ID." In other words, homepage templates are preset according to the service classification.
[0075] Fig. 6 is a diagram showing the data structure of the template table 2023. The template table 2023 shown in Fig. 6 is a table having columns of template data and element IDs, with the template ID as a key.
[0076] The template ID is an item for storing an identifier for uniquely identifying a template for creating a homepage. The item "template ID" corresponds to the template ID in the classification table 2022.
[0077] The template data is an item that stores data related to a template for a homepage. The template data may be stored in advance or may be additionally stored in response to editing by a user, etc. The template data may, for example, store different templates depending on the classification of the homepage. The template data may include, for example, multiple elements. The template data may also include, for example, the layout, fonts, images, and text of multiple elements on the homepage.
[0078] The element ID is an item that stores an identifier for uniquely identifying an element required to create a homepage. Each "element ID" item corresponding to each "template ID" item stores multiple element IDs. Furthermore, the "element ID" item is uniquely determined according to the "template ID" item.
[0079] Fig. 7 is a diagram showing the data structure of the prompt table 2024. The prompt table 2024 shown in Fig. 7 is a table having columns of prompt data, element ID, element, and reference image, with a prompt ID as a key.
[0080] The prompt ID is an item that stores an identifier for uniquely identifying a prompt. The prompt data is an item that stores data related to a prompt, which is an input statement (instruction statement) to the LLM system 30. The data related to the prompt is, for example, text information related to the prompt. The text information related to the prompt is, for example, an input statement that causes the LLM system 30 to create an explanation of an image based on elements related to creating a homepage, and differs for each element. The text information related to the prompt includes, for example, the following content: "The image you entered is related to element ____. Please write a description of this image."
[0081] The item "prompt data" may store, for example, reference information (path) for a prompt data file stored in another storage area.
[0082] The element ID is an item that stores an identifier for uniquely identifying an element required to create a homepage. The "element ID" item is uniquely determined according to the "prompt ID" item. The "element ID" item also corresponds to the element ID in the template table 2023.
[0083] The element is an item that stores elements necessary for the homepage to be created. The item "element" is content related to the services to be made public on the homepage. In FIG. 7, an example is described in which the facility genre is a restaurant, but this embodiment is not limited to this. If the facility genre is a restaurant, the item "element" stores, for example, the exterior, interior, menu, etc. of the facility.
[0084] The "reference image" is an item that stores reference images for images required for creating a homepage. The "reference image" item stores reference images corresponding to each element. If the facility genre is a restaurant, the "reference image" item stores, for example, exterior images, interior images, menu images, etc. of the facility that can be used as reference for the user.
[0085] <3 operations> The operation of the server 20 when assisting a user in creating a homepage will now be described.
[0086] Fig. 8 is a flowchart showing an example of the operation of the server 20 when supporting the creation of a homepage. In the explanation of Fig. 8, the server 20 provides a service that supports the creation of a homepage as SaaS (Software as a Service). Here, an example will be explained in which the service category for the homepage is a restaurant.
[0087] First, a user who wants to create a homepage accesses the server 20. The user logs in to a service that supports homepage creation provided by the server 20, for example, by entering their own user ID and password.
[0088] In step S11, the server 20 accepts the selection of a category of the homepage to be created. Specifically, the presentation control module 2034 displays a homepage category selection screen on the display 141 of the terminal device 10. The user operates the terminal device 10 to select the category of the homepage they want to create. The category is, for example, a facility genre that provides services, including restaurants, accommodations, tourist facilities, etc. Each facility genre may also include a subordinate genre. For example, a restaurant may include a cuisine genre, an accommodation may include an accommodation genre, and a tourist facility may include a tourist facility genre. Each facility genre may also include a genre such as a price range. That is, the user may select, for example, a restaurant as a category and then select a cuisine genre. The transmitter / receiver 192 transmits the category ID of the category selected by the user to the server 20. The reception control module 2031 receives the category ID transmitted from the terminal device 10. As a result, the server 20 accepts the user's category selection.
[0089] In step S12, the server 20 acquires a template for the homepage. Specifically, the service processing module 2033 identifies a template ID corresponding to the category ID of the homepage category selected by the user from the category table 2022. The service processing module 2033 reads template data from the template table 2023 based on the identified template ID. The template data includes, for example, different templates depending on the category of the homepage. The template data also includes, for example, multiple elements. For example, if the category is a restaurant, the multiple elements include the exterior, interior, menu, etc. The template data also includes, for example, the layout, font, images, text, etc. of the multiple elements on the homepage.
[0090] In step S13, the server 20 requests the user to provide an image. Specifically, the service processing module 2033 obtains a plurality of element IDs corresponding to the template ID from the template table 2023. The service processing module 2033 reads an element corresponding to the element ID from the prompt table 2024. The presentation control module 2034 displays a screen on the display 141 of the terminal device 10 requesting the provision of an image based on a predetermined element (for example, appearance, etc.). At this time, the presentation control module 2034 may read a reference image corresponding to the element (for example, a reference image of appearance, etc.) from the prompt table 2024 and present it on the display 141 of the terminal device 10.
[0091] In step S14, the server 20 acquires a prompt. Specifically, when an image is provided by the user operating the terminal device 10, the transmitter / receiver 192 transmits the image provided by the user to the server 20. The reception control module 2031 receives the image transmitted from the terminal device 10. In response to the image provided, the service processing module 2033 acquires a prompt corresponding to a predetermined element from the prompt table 2024. At this time, the text information related to the prompt is, for example, an input sentence for causing the LLM system 30 to create a description of the image based on the predetermined element, and differs for each element. The text information related to the prompt includes, for example, the following content: "The image you entered is related to element ____. Please write a description of this image."
[0092] In step S15, the server 20 transmits data for creating a sentence related to the image to the LLM system 30. Specifically, the transmission control module 2032 transmits an image provided by the user and a prompt obtained from the prompt table 2024 to the LLM system 30. For example, if the predetermined element is an appearance, the transmission control module 2032 transmits an appearance image provided by the user and a prompt corresponding to the appearance.
[0093] The LLM system 30 inputs the image received from the server 20 and prompt data for creating a description of the image into the LLM. The LLM system 30 causes the LLM to output text based on the input image data and prompt data. This text is a description related to the image. For example, if the image is an exterior image, the description related to the image may be a sentence that summarises information about the restaurant in one sentence, such as "a casual and relaxing izakaya." For example, if the image is an interior image, the description may be a sentence that describes the atmosphere inside the restaurant. For example, if the image is a menu image, the description may be a sentence that describes the taste of the menu, the origin of the ingredients, etc. The LLM system 30 outputs the description output from the LLM to the server 20.
[0094] In step S16, the server 20 receives the output result of the LLM system 30. Specifically, for example, the reception control module 2031 receives the text sent from the LLM system 30.
[0095] In step S17, the server 20 generates homepage content and presents it to the user. Specifically, the service processing module 2033 generates homepage content, for example, by combining images provided by the user and text transmitted from the LLM system 30. The presentation control module 2034 displays the generated homepage content screen on the display 141 of the user's terminal device 10.
[0096] In step S20, the server 20 edits and regenerates the content of the generated homepage, as will be described in detail later.
[0097] In step S18, if content relating to all elements included in the template has been created (Yes in step S18), the server 20 executes retouching processing in step S20, the details of which will be described later.
[0098] On the other hand, if content relating to all elements included in the template has not been created in step S18 (No in step S18), server 20 requests the user to provide an image relating to the next predetermined element in step S13. For example, if content relating to the exterior has been created, the next predetermined element would be the interior, etc.
[0099] 9 is a flowchart showing the editing and regeneration processing in step S20. The editing and regeneration processing is a process for executing editing or regeneration processing on the generated content of a homepage in response to an editing instruction or a regeneration instruction from a user.
[0100] As shown in Fig. 9, in step S21, the server 20 receives an instruction to edit or regenerate the content of the homepage from the user. Specifically, the presentation control module 2034 causes the display 141 of the terminal device 10 to display a screen for receiving an instruction to edit or regenerate the content of the homepage. The user operates the terminal device 10 to select, for example, an instruction to edit, an instruction to regenerate, or no instruction (content confirmed). The transmitter / receiver 192 transmits the instruction selected by the user to the server 20. The reception control module 2031 receives the instruction transmitted from the terminal device 10. As a result, the server 20 receives the instruction from the user.
[0101] If an editing instruction is received in step S21 (if an editing instruction is received in step S21), the server 20 receives edited text from the user in step S22. Specifically, the presentation control module 2034 causes the display 141 of the terminal device 10 to display a text screen on which the text of the homepage content can be edited. The user, for example, operates the terminal device 10 and inputs any text into the text screen. The transmission / reception unit 192 transmits the text input by the user to the server 20. The reception control module 2031 receives the text transmitted from the terminal device 10. Then, the service processing module 2033 reflects the received text in the homepage content.
[0102] If a regeneration instruction is received in step S21 (if a regeneration instruction is received in step S21), then in step S23 the server 20 transmits the regeneration instruction to the LLM system 30. Specifically, the transmission control module 2032 transmits the received regeneration instruction to the LLM system 30. The regeneration instruction is a prompt that instructs the LLM included in the LLM system 30 to regenerate the sentence. At this time, for example, the prompt may be stored in a second prompt table (not shown) stored in the storage unit 202.
[0103] The LLM system 30 inputs prompt data from the server 20 to the LLM for regenerating the sentence. The LLM system 30 causes the LLM to output the regenerated sentence based on the input prompt data. The LLM system 30 transmits the regenerated sentence output from the LLM to the server 20.
[0104] In step S24, the server 20 receives the output result of the LLM system 30 and presents it to the user. Specifically, for example, the reception control module 2031 receives the text sent from the LLM system 30. The service processing module 2033 regenerates the content of the homepage based on the image and the regenerated text. The presentation control module 2034 displays the content screen of the regenerated homepage on the display 141 of the user's terminal device 10.
[0105] In step S26, if the content of the homepage has been decided (Yes in step S26), the editing and regeneration process ends.
[0106] On the other hand, if the content of the homepage has not been decided in step S26 (No in step S26), the server 20 receives the next edit instruction and regeneration instruction for the homepage content from the user in step S21.
[0107] Moreover, if neither an instruction to edit nor an instruction to regenerate is accepted in step S21 and the content is decided (if no instruction is accepted in step S21), the editing and regeneration process ends.
[0108] 10 is a flowchart showing the retouching process in step S30. The retouching process is a process of executing retouching processes on all elements of the generated homepage content in response to retouching instructions from the user.
[0109] As shown in FIG. 10 , in step S31, the server 20 accepts a retouching instruction for the homepage content from the user. Specifically, the presentation control module 2034 displays a screen for accepting a retouching instruction for the homepage content on the display 141 of the terminal device 10. The user operates the terminal device 10 to input, for example, a retouching instruction. The retouching instruction includes, for example, an instruction to change the background or an instruction to change the layout. The instruction to change the background is an instruction to change the background of the homepage content. The instruction to change the layout is, for example, an instruction to change the layout of the homepage content. The retouching instruction may be an instruction for the entire homepage content or an instruction for each piece of content. The transmitting / receiving unit 192 transmits the retouching instruction input by the user to the server 20. The reception control module 2031 receives the retouching instruction transmitted from the terminal device 10. As a result, the server 20 accepts the retouching instruction from the user.
[0110] In step S32, the server 20 transmits the data required for retouching to the LLM system 30. Specifically, the transmission control module 2032 transmits the received retouching instruction and the generated homepage content to the LLM system 30. The retouching instruction is a prompt that instructs the LLM included in the LLM system 30 to retouch the homepage content. At this time, for example, the prompt may be stored in a second prompt table (not shown) stored in the storage unit 202.
[0111] The LLM system 30 inputs the homepage content and prompt data for retouching the homepage content into the LLM. The LLM system 30 causes the LLM to output retouching candidates for the homepage content based on the input homepage content and prompt data. The LLM system 30 transmits the retouching candidates output from the LLM to the server 20.
[0112] In step S33, the server 20 receives the output result of the LLM system 30 and presents it to the user. Specifically, for example, the reception control module 2031 receives the retouching candidates transmitted from the LLM system 30. The presentation control module 2034 displays the retouching candidates on the display 141 of the user's terminal device 10.
[0113] In step S31, the retouching instruction may be an instruction to add or change a photo. The instruction to add or change a photo is an instruction to add or change various images and explanatory text by adding or changing the photo. In this case, when receiving the retouching instruction from the user, the service processing module 2033 may, for example, receive one or more additional images. The additional images are images different from the previously provided image, and may include, for example, images of different angles or different objects. The transmission control module 2032 may transmit the additional images to the LLM system 30 together with the received retouching instruction.
[0114] Furthermore, in step S31, the retouching instruction may be an instruction for a content summary. The content summary instruction is any instruction regarding the subject (service) of the homepage content, such as what to explain, what to change, or what to add. In this case, when receiving the retouching instruction from the user, the service processing module 2033 may also receive summary information about the homepage content. The transmission control module 2032 may transmit the summary information about the homepage content together with the received retouching instruction to the LLM system 30.
[0115] <4 Screen example> Fig. 11 is a schematic diagram showing an example of a display screen of the display 141 of the terminal device 10. Fig. 11 shows, for example, a screen for requesting image provision in step S13 shown in Fig. 8. Note that Fig. 11 explains an example in which the target of the homepage service is a restaurant.
[0116] The screen shown in FIG. 11 includes a first area 1411 and a second area 1412.
[0117] The first area 1411 is an area where, for example, a reference image of an image requested in response to an element of the homepage is displayed. In FIG. 11, the instruction is to provide the exterior of a store, so the reference image is an image related to the exterior of the store. The information displayed in the first area 1411 is, for example, information read from the prompt table 2024 by the presentation control module 2035.
[0118] The second area 1412 is an area where operation buttons are displayed. The operation buttons may include, for example, a back button, a capture button, a skip button, a select from library button, etc. The back button is a button for returning to the previous page. The capture button is a button for switching to the camera 160 and enabling an image to be captured. The skip button is a button for proceeding to the next page. The select from library button is a button for reading out image information 182 from the storage unit 180.
[0119] The user checks the instruction text and the information displayed in the first area 1411, and presses the operation button in the second area 1412 that the user wants to execute. When the operation button is pressed, the operation receiving unit 191 receives an instruction corresponding to the operation button.
[0120] Fig. 12 is a schematic diagram showing another example of the display screen of the display 141 of the terminal device 10. Fig. 12 shows, for example, a screen presenting the content of the homepage generated in step S17 shown in Fig. 8. Fig. 12 also shows, for example, a screen accepting an instruction to edit and an instruction to regenerate in step S21 shown in Fig. 9. Note that Fig. 12 will be described taking as an example a case where the homepage service is for restaurants.
[0121] The screen shown in FIG. 12 includes a first area 1421, a second area 1422, and a third area 1423.
[0122] The first area 1421 is an area where an image provided by a user in response to an element of the homepage is displayed. In Fig. 12, since the instruction is to provide the exterior of a store, the image is an image related to the exterior of the store provided by the user.
[0123] The second area 1422 is an area where, for example, text output from the LLM system 30 is displayed. The displayed text is an explanatory text related to the image.
[0124] Third area 1423 is an area where operation buttons are displayed. The operation buttons may include, for example, a regenerate button, an edit button, a confirm button, etc. The regenerate button is a button that instructs the regeneration of the content of the homepage. The edit button is a button that instructs the editing of the content of the homepage. The confirm button is a button that confirms the content of the homepage.
[0125] The user checks the information displayed in the first area 1421 and the second area 1422, and presses the operation button in the third area 1423 that the user wants to execute. When the operation button is pressed, the operation reception unit 191 receives an instruction corresponding to the operation button. The transmission / reception unit 192 transmits the instruction corresponding to the operation button to the server 20.
[0126] Fig. 13 is a schematic diagram showing another example of the display screen of the display 141 of the terminal device 10. Fig. 13 shows, for example, a screen for accepting retouching instructions in step S31 shown in Fig. 10. Note that Fig. 13 explains an example in which the target of the homepage service is a restaurant.
[0127] The screen shown in FIG. 13 includes a first area 1431 and a second area 1432.
[0128] The first area 1431 is an area where all the contents of the homepage created based on each element are displayed. If the homepage service is for a restaurant, the first area 1431 includes, for example, an exterior image, an exterior description, an interior image, an interior description, a menu image, and a menu description.
[0129] The second area 1432 is an area where operation buttons are displayed. The operation buttons may include, for example, a button to change the background, a button to change the layout, a button to add or change a photo, a button to input a content summary, and a confirm button. The button to change the background is a button that instructs changing the background of the homepage content. The layout button is a button that instructs changing the layout of the homepage content. The button to add or change a photo is a button that adds or changes various images and descriptions by adding or changing a photo. The button to input a content summary is a button that arbitrarily inputs the content that you want to explain, change, or add for the subject (service) of the homepage content. The confirm button is a button that confirms the homepage content.
[0130] The user checks the information displayed in the first area 1431 and presses the operation button in the second area 1432 that the user wants to execute. When the operation button is pressed, the operation reception unit 191 receives an instruction corresponding to the operation button. The transmission / reception unit 192 transmits the instruction corresponding to the operation button to the server 20.
[0131] <5 Summary> As described above, in this embodiment, the service processing module 2033 acquires a template in which multiple elements for creating a homepage are preset. The presentation control module 2035 requests the provision of an image based on a specific element from among the multiple elements, and acquires a prompt corresponding to the specific element in response to the image provision. The service processing module 2033 inputs the provided image and the acquired prompt into a large-scale language model and causes the large-scale language model to output a sentence related to the provided image. The service processing module 2033 generates homepage content based on the provided image and the output sentence. This allows the person creating the homepage to easily create a homepage by simply uploading images for multiple elements in sequence, without having to input text, etc. This reduces the burden on the person creating the homepage.
[0132] In this embodiment, the reception control module 2031 receives the selection of the homepage category, and the service processing module 2033 acquires a template corresponding to the selected category. This allows an appropriate homepage to be created according to the category of the service target.
[0133] In this embodiment, when an image is requested, the presentation control module 2035 presents a reference image for the requested image. This allows the person creating the homepage to provide the image without having to carefully consider the angle of the image, thereby further reducing the workload.
[0134] In this embodiment, the reception control module 2031 also accepts instructions to edit or regenerate the output text, allowing the person creating the homepage to accurately reflect their own intentions for the homepage.
[0135] In this embodiment, the reception control module 2031 also receives instructions for retouching the content of a homepage. The service processing module 2033 inputs the received instructions for retouching into the large-scale language model and outputs the generated retouching options for the homepage content. This allows the person creating the homepage to create a more attractive homepage.
[0136] <6 Variations> 14 is a flowchart showing a modified example of the operation of the server 20 when supporting homepage creation. As shown in FIG. 14, for example, steps S41 and S42 may be executed after step S12 in FIG.
[0137] In step S41, the server 20 presents a template to the user. Specifically, the service processing module 2033 obtains template data corresponding to the template ID from the template table 2023. The template includes, for example, multiple regions corresponding to multiple elements. The presentation control module 2034 displays a screen of the template data including the multiple regions on the display 141 of the terminal device 10.
[0138] In step S42, the server 20 accepts the selection of a template area from the user. Specifically, the presentation control module 2034 causes the display 141 of the terminal device 10 to display a screen for accepting the selection of an area in the template. The user operates the terminal device 10 to select an area of the template for creating homepage content. The transmitter / receiver 192 transmits the area selected by the user to the server 20. The reception control module 2031 receives the area transmitted from the terminal device 10. As a result, the server 20 accepts the selection of the template area by the user. Thereafter, as in the above embodiment, in step S13, the server 20 requests the user to provide an image corresponding to the area (element).
[0139] Fig. 15 is a schematic diagram showing a modified example of the display screen of the display 141 of the terminal device 10. Fig. 15 shows, for example, a template presentation screen for step S41 shown in Fig. 14. Note that Fig. 15 explains an example in which the target of the homepage service is restaurants.
[0140] The screen shown in FIG.
[0141] First area 1441 is an area where, for example, a template of a homepage is displayed. The template includes a plurality of areas corresponding to a plurality of elements. Here, the template includes, for example, an appearance area, an interior area, a menu area, etc.
[0142] Each area in first area 1441 is, for example, an operation button. That is, by pressing each area in first area 1441, a screen requesting image provision is displayed. As in FIG. 11, the screen requesting image provision includes, for example, first area 1451 including a reference image and second area 1452 including operation buttons.
[0143] In the above embodiment, the retouching candidates are presented only for the created homepage. However, the retouching candidates may be presented for an existing homepage by inputting an existing homepage that has been created in advance.
[0144] Furthermore, in the above embodiment, an example of a configuration in which each function is provided by the terminal device 10 or the server 20 is described, but this is not limited to this form, and some or all of the functions may be provided by the terminal device 10, the server 20, or both the terminal device 10 and the server 20 in a configuration different from the above embodiment.
[0145] <7 Basic computer hardware configuration> 16 is a block diagram showing the basic hardware configuration of a computer 90. The computer 90 includes at least a processor 91, a main memory device 92, an auxiliary memory device 93, and a communication IF (interface) 99. These are electrically connected to one another by a bus.
[0146] The processor 91 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, registers, peripheral circuits, and the like.
[0147] The main storage device 92 is used to temporarily store programs, data to be processed by the programs, etc. For example, it is a volatile memory such as a DRAM (Dynamic Random Access Memory).
[0148] The auxiliary storage device 93 is a storage device for saving data and programs, such as a flash memory, a hard disk drive (HDD), a magneto-optical disk, a CD-ROM, a DVD-ROM, or a semiconductor memory.
[0149] The communication IF 99 is an interface for inputting and outputting signals for communicating with other computers via a network using wired or wireless communication standards.
[0150] The network is composed of the Internet, a LAN, various mobile communication systems constructed by wireless base stations, etc. For example, the network includes 3G, 4G, and 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks (e.g., Wi-Fi (registered trademark)) that can connect to the Internet via a predetermined access point. In the case of a wireless connection, communication protocols include, for example, Z-Wave (registered trademark), ZigBee (registered trademark), and Bluetooth (registered trademark). In the case of a wired connection, the network also includes a direct connection using a USB (Universal Serial Bus) cable, etc.
[0151] It should be noted that the computer 90 can be virtually realized by distributing all or part of each hardware configuration across multiple computers 90 and interconnecting them via a network. In this way, the computer 90 is a concept that includes not only a computer 90 housed in a single housing or case, but also a virtualized computer system.
[0152] <Basic functional configuration of computer 90> A description will be given of the functional configuration of a computer realized by the basic hardware configuration of a computer 90 shown in Fig. 10. The computer includes at least the functional units of a control unit, a storage unit, and a communication unit.
[0153] The functional units of the computer 90 can also be realized by distributing all or part of the functional units among multiple computers 90 interconnected via a network. The computer 90 is a concept that includes not only a single computer 90 but also a virtualized computer system.
[0154] The control unit is realized by the processor 91 reading various programs stored in the auxiliary storage device 93, expanding them in the main storage device 92, and executing processing in accordance with the programs. The control unit can realize functional units that perform various types of information processing depending on the type of program. In this way, the computer is realized as an information processing device that processes information.
[0155] The storage unit is realized by a main storage device 92 and an auxiliary storage device 93. The storage unit stores data, various programs, and various databases. Furthermore, the processor 91 can allocate a storage area corresponding to the storage unit in the main storage device 92 or the auxiliary storage device 93 in accordance with the programs. Furthermore, the control unit can cause the processor 91 to execute processes for adding, updating, and deleting data stored in the storage unit in accordance with the various programs.
[0156] A database refers to a relational database, which manages data sets called tables, which are structured by rows and columns, by relating them to each other. In a database, a table is called a table, a column in a table is called a column, and a row in a table is called a record. In a relational database, relationships between tables can be set and associated.
[0157] Typically, each table has a column set as a key for uniquely identifying a record, but setting a key to a column is not essential. The control unit can cause the processor 91 to add, delete, or update records in a specific table stored in the storage unit according to various programs.
[0158] The communication unit is realized by the communication IF 99. The communication unit realizes the function of communicating with other computers 90 via a network. The communication unit can receive information transmitted from other computers 90 and input the information to the control unit. The control unit can cause the processor 91 to execute information processing on the received information in accordance with various programs. In addition, the communication unit can transmit information output from the control unit to other computers 90.
[0159] Furthermore, the above-described configurations, functions, processing units, processing means, etc. may be partially or entirely implemented in hardware, for example, by designing them as integrated circuits. The present invention can also be realized by software program code that implements the functions of the embodiments. In this case, a storage medium on which the program code is recorded is provided to a computer, and a processor included in the computer reads the program code stored in the storage medium. In this case, the program code itself read from the storage medium implements the functions of the above-described embodiments, and the program code itself and the storage medium on which it is stored constitute the present invention. Examples of storage media for providing such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs, optical disks, magneto-optical disks, CD-Rs, magnetic tape, non-volatile memory cards, and ROMs.
[0160] Furthermore, the program code that realizes the functions described in this embodiment can be implemented in a wide range of program or script languages, such as assembler, C / C++, perl, Shell, PHP, and Java (registered trademark).
[0161] Furthermore, the program code of the software that realizes the functions of the embodiments may be distributed via a network and stored in a storage means such as a computer's hard disk or memory, or in a storage medium such as a CD-RW or CD-R, and the processor of the computer may read and execute the program code stored in the storage means or storage medium.
[0162] The functions performed by the components described herein may be implemented in circuitry or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), a CPU (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to perform the described functions. A processor includes transistors and other circuits and is considered to be circuitry or processing circuitry. A processor may also be a programmed processor that executes programs stored in memory. In this specification, a circuitry, unit, or means is hardware that is programmed to realize or performs the described functions, which may be any hardware disclosed herein or any hardware known to be programmed to realize or perform the described functions. If the hardware is a processor considered to be a type of circuitry, the circuitry, means, or unit is a combination of the hardware and software used to configure the hardware and / or processor.
[0163] Although several embodiments of the present disclosure have been described above, these embodiments can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and modifications are intended to be included in the scope of the inventions and their equivalents as defined in the claims, as well as in the scope and spirit of the inventions.
[0164] (Addendum) The matters described in the above embodiments will be supplemented below.
[0165] (Appendix 1) A program to be executed by a computer having a processor and a memory, the program causing the processor to: A step of obtaining a template in which a plurality of elements for creating a homepage are preset; requesting provision of an image based on a predetermined element of the plurality of elements; In response to providing the image, obtaining a prompt corresponding to the predetermined element; inputting the provided image and the obtained prompt into a large-scale language model, and outputting a sentence related to the provided image from the large-scale language model; generating content for the homepage based on the provided image and the output text; A program that executes the following.
[0166] (Appendix 2) having the processor perform a step of accepting a selection of a category of the home page; In the step of acquiring the template, the template corresponding to the selected classification is acquired. (Appendix 1) describes the program.
[0167] (Appendix 3) The program according to claim 1, wherein in the step of obtaining a prompt, a different prompt is obtained for each of the plurality of elements.
[0168] (Appendix 4) The program according to claim 1, wherein in the step of requesting provision of the image, a reference image for the requested image is presented.
[0169] (Appendix 5) The program according to claim 1, wherein the program causes the processor to execute a step of accepting an instruction to edit the output text.
[0170] (Appendix 6) receiving a regeneration instruction for the outputted sentence; inputting the received regeneration instruction into the large-scale language model and outputting the regenerated sentence from the large-scale language model; The program according to claim 1, which causes the processor to execute the above.
[0171] (Appendix 7) receiving a retouching instruction for the content of the generated homepage; inputting the generated content of the homepage and the received retouching instructions into the large-scale language model, and outputting retouching candidates for the generated content of the homepage; The program according to claim 1, which causes the processor to execute the above.
[0172] (Appendix 8) In the step of receiving a retouching instruction, an image different from the image provided in the second step is received; The program according to claim 7, wherein in the step of outputting the retouching candidates, the received image is input to the large-scale language model.
[0173] (Appendix 9) In the step of receiving a retouching instruction, summary information on the content of the generated homepage is received; The program according to claim 7, wherein in the step of outputting the retouching candidates, the received summary information is input to the large-scale language model.
[0174] (Appendix 10) The program according to claim 7, wherein the retouching candidates to be output are at least one of the layout, design, text, and images of the homepage.
[0175] (Appendix 11) A method executed by a computer having a processor and a memory, wherein the processor executes all of the steps performed in any of the inventions according to (Appendix 1) to (Appendix 10).
[0176] (Appendix 12) An information processing device comprising a control unit and a memory unit, wherein the control unit executes all of the steps executed in the invention according to any one of (Appendix 1) to (Appendix 10).
[0177] (Appendix 13) A system comprising means for executing all steps performed in any of the inventions according to (Appendix 1) to (Appendix 10). [Explanation of symbols]
[0178] 1. System 10...Terminal device 120…Communications Department 13...Input device 131...Touch-sensitive devices 14...Output device 15...Memory 16…Storage 19...Processor 20...Server 22...Communication IF 23...Input / output interface 25…Memory 26…Storage 29...Processor
Claims
1. A program to be executed by a computer having a processor and a memory, the program causing the processor to: A step of obtaining a template in which a plurality of elements for creating a homepage are preset; requesting provision of an image based on a predetermined element of the plurality of elements; In response to providing the image, obtaining a prompt corresponding to the predetermined element; inputting the provided image and the obtained prompt into a large-scale language model, and outputting a sentence related to the provided image from the large-scale language model; generating content for the homepage based on the provided image and the output text; receiving an instruction to edit the output text; When the content of the homepage relating to all of the plurality of elements has been generated, receiving a retouching instruction for the content of the homepage relating to all of the generated elements; inputting the generated content of the homepage and the received retouching instructions into the large-scale language model, and outputting retouching candidates for the generated content of the homepage; A program that executes the following.
2. having the processor perform a step of accepting a selection of a category of the home page; In the step of acquiring the template, the template corresponding to the selected classification is acquired. The program according to claim 1.
3. 2. The program according to claim 1, wherein in the step of obtaining a prompt, a different prompt is obtained for each of the plurality of elements.
4. receiving a regeneration instruction for the outputted sentence; inputting the received regeneration instruction into the large-scale language model and outputting the regenerated sentence from the large-scale language model; The program according to claim 1 , which causes the processor to execute the following steps.
5. In the step of receiving the retouching instruction, an image different from the image provided in the step of requesting provision of the image is received; The program according to claim 1 , wherein the step of outputting the retouching candidates includes inputting the received image into the large-scale language model.
6. In the step of receiving a retouching instruction, summary information on the content of the generated homepage is received; The program according to claim 1 , wherein the step of outputting the retouching candidates includes inputting the received summary information into the large-scale language model.
7. The program according to claim 1 , wherein the retouching candidates output are at least one of the layout, design, text, and images of the homepage.
8. A method implemented on a computer having a processor and a memory, wherein the processor performs all of the steps performed in the invention according to any one of claims 1 to 7.
9. 8. An information processing device comprising a control unit and a storage unit, wherein the control unit executes all of the steps executed in the invention according to any one of claims 1 to 7.
10. A system comprising means for executing all steps performed in the invention according to any one of claims 1 to 7.
Citation Information
Patent Citations
Multimedia page generation method and device, equipment, medium and program product
CN117011875A
Page display method, client, transaction platform and related device
CN117474628A
Information processing system, information processor and information processing method, recording medium, and program
JP2005198139A
System and method for enhanced model interaction integration within a website building system
US20240386197A1
PROGRAM, INFORMATION PROCESSING APPARATUS, METHOD AND SYSTEM
JP7411137B1