Device and method

Abstract

The purpose of the present invention is to provide a device and a method with which it is possible to generate a floor plan according to a user's desire.　A reception unit 101 of a prompt generation server 100 according to the present disclosure receives, from a user terminal 500, input information for requesting generation of a floorplan image of a house. Then, a concept information acquisition unit 102 determines concept information of the house on the basis of the input information. Meanwhile, a reference floorplan image acquisition unit 103 acquires a reference floorplan image from a reference floorplan database 400 by using the concept information. A prompt generation unit 104 generates a prompt for indicating generation of a recommended floorplan image by using the concept information and the reference floorplan image.　Thus, a prompt can be generated from inputted images, and a recommended floorplan image can be generated by an image generation model such as DCGAN.

Description

Apparatus and method

[0001] The present invention relates to an apparatus and method for generating floor plans of a house or the like.

[0002] Patent Document 1 describes a device that can reduce the effort required to change the style of a floor plan. The device uses a trained model to convert input image information containing a floor plan image in a first style into image information containing a floor plan image in a second style in response to a request.

[0003] Japanese Patent Application Laid-Open No. 2020-155115

[0004] However, in Patent Document 1, the objects, patterns, etc. of items used, such as furniture, are changed without substantially changing the shape or size of the plot, and it is not possible to generate a floor plan that takes into account the size and shape of the lot on which the house is to be built.

[0005] Therefore, an object of the present disclosure is to provide an apparatus and method capable of generating a floor plan according to a user's wishes.

[0006] The device disclosed herein includes a reception unit that receives input information for a request to generate a floor plan image of a house, a concept information acquisition unit that acquires concept information of the house based on the input information, a reference floor plan image acquisition unit that acquires a reference floor plan image using the concept information, and a prompt generation unit that uses the concept information and the reference floor plan image to generate a prompt that instructs the generation of a recommended floor plan image.

[0007] According to the present disclosure, a floor plan image of a house can be easily generated.

[0008] FIG. 1 is a diagram showing a system configuration for generating floor plan images including a prompt generation server 100 according to the present disclosure. FIG. 2 is a diagram showing a specific example of information stored in a reference floor plan DB 400. FIG. 3 is a block diagram showing the functional configuration of the prompt generation server 100. FIG. 4 is a flowchart showing the operation of the prompt generation server 100. FIG. 5 is a diagram showing an overview of a process for deriving the importance of concept information according to the present disclosure. FIG. 6 is a diagram explaining a process for deriving the importance from concept information. FIG. 7 is a diagram showing a prompt generated based on input information (desired conditions and site conditions) and information in the reference floor plan DB 400. FIG. 8 is a diagram showing a floor plan image output in response to input information including desired conditions and site conditions. FIG. 9 is a diagram showing an example of the hardware configuration of a prompt generation server 100 according to an embodiment of the present disclosure.

[0009] The present disclosure will be described with reference to the accompanying drawings. Whenever possible, the same parts are designated by the same reference numerals and redundant description will be omitted.

[0010] 1 is a diagram showing the configuration of a system for generating floor plan images, including a prompt generation server 100 according to the present disclosure. As shown in the figure, this system includes the prompt generation server 100, a large-scale language model 200, an image generation model 300, and a reference floor plan DB 400. These servers and databases are configured to be communicatively connected via a network.

[0011] The user terminal 500 transmits input information for the user's house to the prompt generation server 100. This input information includes desired conditions and site conditions. The desired conditions are composed of text information. The desired conditions also include written information that describes the user's wishes for the house. The site conditions include information such as the site area and site shape. The site conditions are displayed as an image, but may also be displayed as text.

[0012] The prompt generation server 100 generates a prompt based on the desired conditions and the reference floor plan information stored in the reference floor plan DB 400, and transmits the generated prompt to the large-scale language model 200. The large-scale language model 200 selects one or more pieces of concept information from the plurality of pieces of concept information included in the reference floor plan information based on the prompt.

[0013] This large-scale language model 200 is a generative AI model that can respond to a request consisting of input information (text information). For example, it is a so-called interactive generative AI model, such as LMs such as chat GPT and Tsusumi. In this disclosure, the large-scale language model 200 is a language model that selects at least one concept information from multiple pieces of concept information. This generative AI model will be described later.

[0014] The reference floor plan DB 400 stores concept information and corresponding reference floor plan images in advance. This reference floor plan DB 400 is a pre-constructed database.

[0015] All or some of the large-scale language model 200 , the image generation model 300 , and the reference floor plan DB 400 may be located in the prompt generation server 100 or the user terminal 500 .

[0016] FIG. 2 is a diagram showing a specific example of information stored in the reference floor plan DB 400. As shown in the figure, the reference floor plan DB 400 stores concept information and image files in association with each other. The concept information is, for example, information indicating the functions or preferences of the house that the user intends to live in (or build). The image files are images showing reference floor plans corresponding to the concept information. The reference floor plan DB 400 is prepared in advance, and the concept information and the corresponding image files are associated with each other manually by, for example, the administrator who constructed the reference floor plan DB 400, based on the administrator's intuition.

[0017] The prompt generation server 100 acquires a reference floor plan image corresponding to the concept information from the reference floor plan DB 400, which is an external database, based on the concept information transmitted from the large-scale language model 200. That is, the prompt generation server 100 transmits the concept information to the reference floor plan DB 400 and acquires the corresponding reference floor plan image using the concept information as a key.

[0018] Furthermore, the prompt generation server 100 transmits the acquired reference floor plan image and concept information to the image generation model 300, thereby generating a floor plan image by correcting the reference floor plan image based on the concept information. Details will be described later.

[0019] This image generation model 300 is, for example, a DCGAN (Deep Convolutional Generative Adversarial Networks), which is a generative AI model that can generate images in response to requests. Note that DCGAN is just one example, and other image generation models may be used. For example, partial autoencoders (VAE), flow-based models, and diffusion models are available.

[0020] A generative AI model is a model that can generate content in response to a prompt containing input information, according to the instructions, context, question, and output format indicated by the prompt, and return the content as response information. The prompt can also include input information, in which case the generative AI model generates response information targeted at the input information. The generative AI model may be, for example, an interactive AI model that includes a large language model (LLM) and a user interface (UI) for interacting with the user, enabling text or voice chat with the user. Examples of such generative AI models include ChatGPT, GPT (registered trademark)-3.5, GPT-4V, PaLM2, etc. In this embodiment, the prompt generation server 100 is capable of providing content provision functions using interactive AI models, which are multiple types of models. These interactive AI models may be stored within the prompt generation server 100, or may be stored in another device connected to the prompt generation server 100 via a network and configured to enable information exchange with the user via the prompt generation server 100. Note that although only one prompt generation server 100 is shown in the figure, multiple prompt generation servers 100 may be included.

[0021] In this disclosure, a prompt is information indicating an instruction or question entered by a user in an interactive system such as an interaction with a generative AI model or a command line interface (CLI).

[0022] Next, the functions of the prompt generation server 100 of the present disclosure will be described. Fig. 3 is a block diagram showing the functional configuration of the prompt generation server 100. As shown in the figure, the prompt generation server 100 includes a reception unit 101, a concept information acquisition unit 102, a reference floor plan image acquisition unit 103, and a prompt generation unit 104.

[0023] The reception unit 101 receives input information and a request to generate a floor plan image from the user terminal 500, and extracts desired conditions and site conditions from the input information. That is, upon receiving the input information, the reception unit 101 extracts the desired conditions, which are comprised of text. These desired conditions are, for example, the user's desired conditions, such as the user's intended use or room functions. This extraction process is performed by analyzing the text of the input information, using algorithms such as segmentation by punctuation marks and rule-based sentence extraction using regular expressions.

[0024] In this disclosure, there are site conditions in addition to desired conditions. The site conditions are image files, but the site conditions may also be text information indicating the site area (size) and site shape.

[0025] The concept information acquisition unit 102 is a part that transmits a prompt including the desired conditions extracted by the reception unit 101 and an instruction requesting the generation of concept information to the large-scale language model 200, and obtains concept information that serves as a response. The large-scale language model 200 generates or selects concept information for houses that satisfy the required conditions, and the concept information acquisition unit 102 acquires the concept information generated or selected by the large-scale language model 200.

[0026] The reference floor plan image acquisition unit 103 is a part that transmits the concept information acquired by the concept information acquisition unit 102 to the reference floor plan DB 400 and acquires the corresponding reference floor plan image.

[0027] The prompt generation unit 104 is a unit that derives the importance of concept information based on concept information and desired conditions. The prompt generation unit 104 also generates a prompt based on the acquired reference floor plan image and concept information, transmits it to the image generation model 300, and causes the image generation model 300 to generate a recommended floor plan image that matches the concept information. In the present disclosure, the image generation model 300 generates a recommended floor plan image by modifying the reference floor plan image. The prompt generation unit 104 acquires the recommended floor plan image from the image generation model 300 and transmits it to the user terminal 500.

[0028] Next, the operation of the prompt generation server 100 configured as above will be described. Fig. 4 is a flowchart showing the operation of the prompt generation server 100. The reception unit 101 receives input information from the user terminal 500 (S101). Then, the reception unit 101 acquires, from the input information, desired conditions for the house / room and site conditions, which are image files indicating the size and shape of the site that will serve as the basis for the floor plan output image (S102).

[0029] The concept information acquisition unit 102 generates a prompt for selecting at least one concept information that meets the user's requirements from the plurality of concept information in the reference floor plan DB 400 based on the acquired desired conditions and the concept information stored in the reference floor plan DB 400 (S103). Then, the concept information acquisition unit 102 transmits the generated prompt to the large-scale language model 200 (S104). The concept information acquisition unit 102 acquires the concept information selected based on the desired conditions from the large-scale language model 200 (S105). The large-scale language model 200 refers to the concept information stored in the reference floor plan DB 400 and selects at least one concept information that meets the desired conditions, and the concept information acquisition unit 102 acquires this.

[0030] The prompt generation unit 104 then derives the importance of each piece of concept information based on the desired conditions and the concept information (S106). That is, the prompt generation unit 104 segments the desired conditions, which are made up of multiple sentences, associates the segmented sentences with the concept information, and derives the importance as the ratio of the number of sentences that correspond to each piece of concept information.

[0031] On the other hand, the reference floor plan image acquisition unit 103 acquires a corresponding reference floor plan image from the reference floor plan DB 400 based on the concept information acquired by the concept information acquisition unit 102 (S107).

[0032] The prompt generation unit 104 generates a prompt based on the concept information, the importance, the reference floor plan image, and the site conditions, and transmits the generated prompt to the image generation model 300 (S108). Then, the prompt generation unit 104 acquires, from the image generation model 300, a recommended floor plan image that meets the user's desired conditions and the site conditions (S109).

[0033] The prompt generating unit 104 transmits the acquired recommended floor plan image to the user terminal 500 (S109).

[0034] In this way, the prompt generation server 100 causes the large-scale language model 200 and the image generation model 300 to generate concept information and its importance, respectively, and generates a recommended floor plan image based on the concept information and its importance.

[0035] Here, an example of a prompt generated by the prompt generation server 100 will be described. Fig. 5 is a diagram showing an outline of the process for deriving the importance of concept information according to the present disclosure. In the prompt generation server 100, the reception unit 101 receives input information (including desired conditions and site conditions) from the user terminal 500 (Fig. 5(a)). This information is input into the user terminal 500.

[0036] The concept information acquisition unit 102 generates a prompt for causing the large-scale language model 200 to select at least one piece of concept information based on the concept information ( FIG. 5( b) ) stored in the reference floor plan DB 400 and the desired conditions. FIG. 5( c) shows an example of such a prompt. The concept information acquisition unit 102 acquires a list of concept information stored in the reference floor plan DB 400 and generates a prompt including the desired conditions and a list of that concept information. This prompt includes, as a task, content instructing the user to select concept information that matches the desired conditions from the concept information.

[0037] The concept information acquisition unit 102 then transmits the generated prompt to the large-scale language model 200, which selects one or more pieces of concept information. Figure 6(a) shows concept information 1 and concept information 2 selected by the large-scale language model 200. They represent the concepts of "a home where you can balance your hobbies and work from home" and "a home where you can live with pets," respectively.

[0038] 6B is a diagram showing a comparison between segmented desired conditions and corresponding concept information. The prompt generation unit 104 acquires concept information corresponding to the segmented desired conditions and associates the segmented content with the concept information. The prompt generation unit 104 counts the number of concept information items associated with each phrase and calculates the percentage of each item relative to the total. FIG. 6C is a diagram showing the percentage for each piece of concept information. In the present disclosure, this percentage is treated as the importance of the concept information.

[0039] FIG. 7 is a diagram showing a prompt generated based on input information (desired conditions and site conditions) and information from the reference floor plan DB 400. As shown in the figure, the prompt generation unit 104 generates a prompt to instruct the image generation model 300. This prompt includes the instruction content, such as a task, desired conditions, concept information, and information related to the concept information (importance, reference floor plan image, site conditions (site area and shape, image file)). The prompt generation unit 104 transmits this prompt to the image generation model 300. In accordance with the prompt, the image generation model 300 generates a recommended floor plan image that meets the desired conditions, taking into account the concept information, importance, reference floor plan image, and site conditions (site area and shape).

[0040] The prompt generation unit 104 receives the recommended floor plan image generated by the image generation model 300 and transmits it to the user terminal 500.

[0041] 8 is a diagram showing a recommended floor plan image output in response to input information including desired conditions and site conditions. As shown in the figure, by inputting desired conditions and site conditions, a user can obtain a recommended floor plan image according to the user's wishes and the site conditions.

[0042] The above description is an example of the present disclosure, and is not limited to the above description. For example, the concept information stored in the reference floor plan DB 400 described in the present disclosure is an example, and is not limited to the above. Possible concept information stored in the reference floor plan DB 400 includes a home where you can watch over your children growing up, an inorganic home with no sense of life, etc.

[0043] The input information may also be information that takes the following into consideration: The reference floor plan image stored in the reference floor plan DB 400 may include furniture, so that the image generation model 300 can generate a floor plan image that includes furniture.

[0044] The desired conditions among the input information may also be information indicating conditions related to the floor plan. For example, it may include wanting a larger kitchen or a larger living room. It may also include information indicating the floor plan and its purpose / function. For example, it may include wanting to watch movies in the living room, wanting a room where you can listen to music at a loud volume, wanting a room for teleworking, wanting to sleep in a room with a good view, etc.

[0045] It may also include information specifying the number of living rooms, kitchens, bathrooms, toilets, rooms, bedrooms, and storerooms, or the sizes of these rooms. It may also include information specifying the number of floors, etc.

[0046] The desired conditions may also include information about furniture requirements, such as a desire for a large sofa (which may be a specific size, or may include information specifying the number of seats, such as three).

[0047] The desired conditions may also include the number of rooms, and may specify sensory information such as whether the rooms are separated from each other or whether an open feeling is important.

[0048] The site conditions may include information on land conditions, such as information specifying the size and shape of the land (site), as well as information specifying restrictions on the height, size, shape, and color of the building.

[0049] The input information may also include user attribute information, such as the desired conditions and site conditions, including family structure, the user's gender, and age group. The attribute information may be received by the user entering it into the user terminal 500, or the prompt generation server 100 may function as a Retrieval-Augmented Generation (RAG) to search and retrieve information associated with the user account from another external database.

[0050] The attribute information may be included in a prompt input to the large-scale language model 200. The large-scale language model 200 may select concept information taking into account the attribute information. Furthermore, the attribute information may be included in a prompt input to the image generation model 300. The image generation model 300 may generate a floor plan image taking into account the attribute information.

[0051] Furthermore, the large-scale language model 200 is not necessarily required when selecting concept information. For example, in the present disclosure, the reference floor plan DB 400 may store a label for each piece of concept information as an in-house system. As mentioned above, the concept information is not limited to the above, and the following is also possible. At least one label is assigned to this concept information. For example, a "home where you can watch your children grow up" is assigned the labels: children, childcare, flexible, no blind spots, etc. (Example 1) A home where you can watch your children grow up: children, childcare, flexible, no blind spots, etc. (Example 2) A home where you can balance hobbies and working from home: hobbies, telework, (Example 3) An impersonal home with no sense of life: impersonal, exposed driving range, etc. (Example 4) A Brooklyn-style home that looks like it could be in a foreign TV drama: overseas, Brooklyn, etc.

[0052] That is, the reference floor plan DB 400 stores sets of concept information and related keywords or key sentences (labels). Furthermore, the prompt generation server 100 may be equipped with a learning model. This learning model learns (stores) the relationship between each label and a word (token). This learning model outputs information (e.g., a score) indicating the degree of relationship between the input token and each label. For example, specific examples of algorithms that calculate the degree of relationship between concept information and keywords include Word2Vec and BERT. These can be used to vectorize the meaning of the label and calculate the cosine similarity with the concept information.

[0053] The concept information acquisition unit 102 acquires concept information using this learning model. In the above disclosure, the large-scale language model 200 selects concept information using the reference floor plan DB 400, and the prompt generation server 100 acquires the selected concept information. However, the prompt generation server 100 may acquire concept information by the following process.

[0054] The receiving unit 101 performs morphological analysis on sentences included in the desired conditions in the input information, and inputs the multiple tokens (phrases) obtained by the morphological analysis into a learning model. The learning model outputs, for each of the multiple tokens, information (e.g., a score) indicating the degree of relationship with each label.

[0055] The concept information acquisition unit 102 may acquire concept information based on the information (score). There may also be one or more labels that have a certain relationship with the token. For example, there may be one or more labels whose scores exceed a predetermined threshold. In this case, the concept information acquisition unit 102 may determine that the concept information corresponding to the label is the concept information desired by the user.

[0056] For example, if the token extracted from the desired condition is "childcare," and the score with the label "children" is 0.86 and the score with the label "childcare" is 0.91, and the threshold is set to 0.8, the concept information acquisition unit 102 determines that there is a relationship. Then, the concept information acquisition unit 102 determines that "a home where you can watch over your children growing up" is the concept information.

[0057] In addition, if there are multiple pieces of concept information with a certain relationship (labels above a threshold), multiple pieces of concept information (e.g., a house where you can watch your children grow up, a house with no sense of life) may be selected. When multiple pieces of concept information are selected, information indicating the degree of desirability of the concept information calculated based on the score (e.g., the sum of the scores (0.86 + 0.91 + ...)) may be entered. Here, the sum of the scores for each label represents the degree of desirability for the concept information. (Example) A house where you can watch your children grow up, 2.41 A house with no sense of life, 1.63 By including this in the prompt, the image generation model 300 can be instructed to generate a house that is a house where you can watch your children grow up and that emphasizes a house with no sense of life. The image generation model 300 can generate a recommended floor plan image taking into account this degree value.

[0058] Here, a plurality of floor plan images corresponding to each piece of concept information may be prepared in the reference floor plan DB 400. In other words, a plurality of pieces of concept information may be associated with each floor plan image. (Example) Image 1: A house where you can watch your children grow up: childcare, flexible, no blind spots,... Image 2: A house where you can watch your children grow up: childcare, flexible, no blind spots,... Image 3: An impersonal house with no sense of life: impersonal, exposed concrete,...

[0059] In this way, the prompt generation unit 104 may select a floor plan image using the label and concept information as keys, and output information indicating this floor plan image to the prompt. If there are multiple floor plan images, some of the multiple floor plan images may be output, or a single randomly selected floor plan image may be output. For example, if image 1 is a floor plan of a detached house with an open feel, and image 3 is a floor plan of a designer apartment with exposed concrete, and these are output to the prompt, the image generation model 300 will generate a never-before-seen floor plan image using these two images as reference.

[0060] The input information may also include information instructing the layout to match the lot area, thereby generating a personalized floor plan image that matches the area of ​​each lot.

[0061] The input information may also include conditions for determining the style of the room, such as Brooklyn style.

[0062] If the input information includes information about furniture requirements, the furniture requirements may be output as a prompt, for example, a large sofa.

[0063] In addition, the user may be instructed to output information such as a sentence explaining the floor plan (for example, what concepts were emphasized).

[0064] Furthermore, the image generation model 300 outputs a recommended floor plan image, but the image may include furniture, and information indicating the names and types of rooms such as a living room and a kitchen may be added. Furthermore, a sentence explaining the floor plan may be added.

[0065] The input information may also include an instruction to create multiple recommended floor plan images.

[0066] Next, the effects of the prompt generation server 100 of the present disclosure will be described. In the prompt generation server 100 of the present disclosure, the reception unit 101 receives input information for a request to generate a floor plan image of a house from the user terminal 500. The concept information acquisition unit 102 then determines at least one piece of concept information for the house based on the input information. The reference floor plan image acquisition unit 103 then uses the concept information to acquire a reference floor plan image from the reference floor plan DB 400. The prompt generation unit 104 uses the concept information and the reference floor plan image to generate a prompt that instructs the user to generate a recommended floor plan image.

[0067] This allows prompts to be generated from the input image, and recommended floor plan images can be generated for image generation models such as DCGAN. In general rule-based processing, advice information is determined using a single concept. However, the generation AI can provide delicate advice based on multiple concept information, as if it were thought by a human. In the present disclosure, by creating prompts for the generation AI to generate recommended floor plan images, the generation AI can generate recommended floor plan images with the same delicate sensitivity as a human.

[0068] In the present disclosure, the receiving unit 101 acquires input information consisting of text from the user terminal 500 and acquires the user's desired conditions from the input information. The desired conditions are information consisting of multiple sentences that indicate the user's desires for the house. The input information also includes site conditions. The site conditions are the size and shape of the site.

[0069] The concept information acquisition unit 102 requests concept information based on desired conditions from the language model. In the present disclosure, the language model is requested to select at least one piece of concept information that meets the desired conditions from a plurality of pieces of concept information prepared in advance.

[0070] For example, if the language model is the large-scale language model 200, the concept information acquisition unit 102 generates a prompt for selecting at least one piece of concept information that meets the desired conditions from a list of multiple pieces of concept information, and transmits the prompt to the large-scale language model 200. This list of multiple pieces of concept information is information obtained from the concept information stored in the reference floor plan DB 400.

[0071] However, the present invention is not limited to this, and a language model that outputs similarities between words may also be used. In this case, a database called a concept information DB that stores concept information and its labels (words) may be prepared in advance, and the learning model may input words obtained from the input information, output a score for each label, and select a label based on the score. Concept information corresponding to the selected label may then be selected.

[0072] The input information may also include site conditions, such as the size of the site on which the house is to be constructed and the shape of the site. The site conditions may be expressed as an image file or as text.

[0073] Furthermore, the prompt generation unit 104 of the present disclosure may acquire the importance of the concept information based on the desired conditions and the concept information, and generate a prompt to be made to the image generation model 300 based on the importance in addition to the concept information and the reference floor plan image. This importance is calculated based on the number of pieces of concept information corresponding to each of a plurality of sentences obtained by segmenting the desired conditions.

[0074] As described above, when multiple pieces of concept information are used, the importance becomes meaningful information. In other words, when deciding advice information based on one piece of concept information, the importance is not particularly necessary, but it is necessary to take into account the level of each piece of concept information based on multiple pieces of concept information. In the present disclosure, by using the importance, it is possible to provide a recommended floor plan image or advice that is as detailed as if it were thought up by a human.

[0075] In the present disclosure, the reference floor plan image acquisition unit 103 accesses a reference floor plan DB 400, which is an external database that stores concept information and reference floor plan images in association with each other. The reference floor plan image acquisition unit 103 then acquires the reference floor plan image from the reference floor plan DB 400 based on the concept information determined by the concept information acquisition unit 102.

[0076] According to this configuration, the reference floor plan image acquisition unit 103 can acquire a reference floor plan image corresponding to the concept information, and can issue an instruction to generate a recommended floor plan image using this reference floor plan image.

[0077] The prompt generation unit 104 also transmits the generated prompt to the image generation model 300 and acquires the recommended floor plan image generated by the image generation model 300 .

[0078] According to this configuration, the layout of a house can be easily and automatically generated in the image generation model 300 based on input information.

[0079] The device and method of the present disclosure include the following configuration.

[0080] [1] A device comprising: a receiving unit that receives input information for a request to generate a floor plan image of a house; a concept information acquisition unit that determines at least one concept information of the house based on the input information; a reference floor plan image acquisition unit that acquires a reference floor plan image using the concept information; and a prompt generation unit that generates a prompt that instructs the user to generate a recommended floor plan image using the concept information and the reference floor plan image.

[0081] [2] The device according to [1], wherein the reception unit receives input information consisting of text from a user terminal, and obtains the user's desired conditions from the input information.

[0082] [3] The device according to [2], wherein the desired conditions are information consisting of a plurality of sentences indicating the user's desires for the house.

[0083] [4] The device according to [2] or [3], wherein the concept information acquisition unit requests concept information based on the desired conditions from a language model.

[0084] [5] The device according to [4], wherein the concept information acquisition unit requests the language model to select at least one piece of concept information that meets the desired conditions from a plurality of pieces of concept information prepared in advance.

[0085] [6] The device according to any one of [1] to [5], wherein the input information includes the size of the lot on which the house is to be constructed and the shape of the lot.

[0086] [7] The device described in [3], wherein the prompt generation unit acquires the importance of the concept information based on the desired conditions and the concept information, and generates the prompt based on the importance in addition to the concept information and the reference floor plan image.

[0087] [8] The device described in any one of [1] to [7], wherein the reference floor plan image acquisition unit accesses an external database that stores concept information and reference floor plan images in association with each other, and acquires the reference floor plan image from the external database based on the concept information determined by the concept information acquisition unit.

[0088] [9] The device according to any one of [1] to [8], wherein the prompt generation unit transmits the generated prompt to an image generation model and acquires a recommended floor plan image generated by the image generation model.

[0089]

[10] A method including: a receiving step of receiving input information for a request to generate a floor plan image of a house; a determining step of determining concept information of the house based on the input information; an acquiring step of acquiring a reference floor plan image using the concept information; and a control step of generating a prompt that instructs the generation of a recommended floor plan image using the concept information and the reference floor plan image.

[0090] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of hardware and / or software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are connected directly or indirectly (e.g., via wire, wirelessly, etc.) and these multiple devices. The functional block may also be realized by combining the single device or multiple devices with software.

[0091] Functions include, but are not limited to, judgment, determination, assessment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0092] For example, the prompt generation server 100 according to an embodiment of the present disclosure may function as a computer that performs processing of the prompt generation method of the present disclosure. Fig. 9 is a diagram illustrating an example of the hardware configuration of the prompt generation server 100 according to an embodiment of the present disclosure. The prompt generation server 100 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage device 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

[0093] In the following description, the term "apparatus" may be interpreted as a circuit, device, unit, etc. The hardware configuration of the prompt generation server 100 may be configured to include one or more of the apparatuses shown in the figure, or may be configured to exclude some of the apparatuses.

[0094] Each function in the prompt generation server 100 is realized by loading specified software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0095] The processor 1001, for example, runs an operating system to control the entire computer. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, the above-mentioned concept information acquisition unit 102, reference floor plan image acquisition unit 103, and prompt generation unit 104 may be realized by the processor 1001.

[0096] The processor 1001 also reads programs (program code), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with these programs. The programs used are programs that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, the concept information acquisition unit 102, the reference floor plan image acquisition unit 103, and the prompt generation unit 104 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and similar implementations may be used for other functional blocks. While the above-described various processes have been described as being executed by a single processor 1001, they may also be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may also be transmitted from a network via a telecommunications line.

[0097] The memory 1002 is a computer-readable recording medium and may be configured, for example, by at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be referred to as a register, a cache, a main memory (primary storage device), etc. The memory 1002 may store executable programs (program codes), software modules, etc. for implementing a prompt generation method according to one embodiment of the present disclosure.

[0098] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0099] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, or a communication module. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the above-mentioned reception unit 101 may be realized by the communication device 1004. The communication device 1004 may be implemented with a transmission unit and a reception unit that are physically or logically separated.

[0100] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. Note that the input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0101] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0102] The prompt generation server 100 may also be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0103] The notification of information is not limited to the aspects / embodiments described in the present disclosure and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI) and Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB) and System Information Block (SIB))), other signals, or a combination thereof. Furthermore, the RRC signaling may be referred to as an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

[0104] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0105] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be sent to another device.

[0106] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0107] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0108] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0109] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0110] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0111] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0112] Note that terms described in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of a channel and a symbol may be a signal (signaling). Furthermore, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, a cell, a frequency carrier, etc.

[0113] Furthermore, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information. For example, a radio resource may be indicated by an index.

[0114] The names used for the above-described parameters are not intended to be limiting in any way. Furthermore, the mathematical expressions using these parameters may differ from those explicitly disclosed in this disclosure. The various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not intended to be limiting in any way.

[0115] In this disclosure, the terms "Mobile Station (MS)," "user terminal," "User Equipment (UE)," "terminal," and the like may be used interchangeably.

[0116] A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable terminology.

[0117] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0118] The terms "connected," "coupled," or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using one or more wires, cables, and / or printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0119] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0120] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0121] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0122] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0123] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0124] 100...prompt generation server, 200...large-scale language model, 300...image generation model, 400...reference floor plan DB, 500...user terminal, 101...reception unit, 102...concept information acquisition unit, 103...reference floor plan image acquisition unit, 104...prompt generation unit.

Claims

1. A device comprising: a reception unit that receives input information for a request to generate a floor plan image of a house; a concept information acquisition unit that acquires at least one concept information of the house based on the input information; a reference floor plan image acquisition unit that acquires a reference floor plan image using the concept information; and a prompt generation unit that generates a prompt that instructs the user to generate a recommended floor plan image using the concept information and the reference floor plan image.

2. The device according to claim 1, wherein the reception unit receives input information consisting of text from a user terminal and obtains the user's desired conditions from the input information.

3. The device according to claim 2, wherein the desired conditions are information consisting of a plurality of sentences indicating the user's desires for the house.

4. The device according to claim 2, wherein the concept information acquisition unit requests concept information based on the desired conditions from a language model.

5. The device according to claim 4, wherein the concept information acquisition unit requests the language model to select at least one piece of concept information that meets the desired conditions from a plurality of pieces of concept information prepared in advance.

6. The device according to claim 1, wherein the input information includes the size of the lot on which the house is to be constructed and the shape of the lot.

7. The device described in claim 3, wherein the prompt generation unit obtains the importance of the concept information based on the desired conditions and the concept information, and generates the prompt based on the importance in addition to the concept information and the reference floor plan image.

8. The device described in claim 1, wherein the reference floor plan image acquisition unit accesses an external database that stores concept information and reference floor plan images in association with each other, and acquires the reference floor plan image from the external database based on the concept information acquired by the concept information acquisition unit.

9. The device according to claim 1, wherein the prompt generation unit transmits the generated prompt to an image generation model and obtains a recommended floor plan image generated by the image generation model.

10. A method comprising: a receiving step of receiving input information for a request to generate a floor plan image of a house; a concept information acquisition step of acquiring concept information of the house based on the input information; a reference floor plan image acquisition step of acquiring a reference floor plan image using the concept information; and a prompt generation step of generating a prompt that instructs the user to generate a recommended floor plan image using the concept information and the reference floor plan image.