Property proposal system, property proposal method, and property proposal program

Abstract

To enable a user to easily materialize an image of a property desired by the user and to make a concrete sales proposal for the property. [Solution] A property proposal system 1 in which a processor executes a presentation step of presenting multiple candidate images showing an image of a property, a first reception step of accepting a user's selection from the multiple candidate images, an instruction step of instructing a first artificial intelligence to generate specifications for the property in the selected candidate image, and an output step of outputting contractors capable of carrying out construction according to the property specifications and an estimate of the costs required for the construction, and the first artificial intelligence has a learning model that receives a selected candidate image as input and outputs the specifications of the property shown in the selected candidate image.

Description

[Technical field]

[0001] The present invention relates to a property proposal system, a property proposal method, and a property proposal program. [Background technology]

[0002] When a real estate agent proposes selling a building that has not yet been built to a client, it is important that the client have a concrete image of the property, and it is also important to make sure that there will be no inconveniences when the client actually wants to build the property.

[0003] For example, Patent Document 1 proposes a device that allows a user to grasp a concrete image of what a building would look like when constructed on a piece of land by using a three-dimensional composite image. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2023-174766 A Summary of the Invention [Problem to be solved by the invention]

[0005] By the way, for those without any particular expertise in architecture, even if they have a vague image of the property they want to build or live in, it is difficult to convey this to a professional real estate agent, and even for a professional real estate agent, it is difficult to share that image accurately, so sharing an image involves a considerable communication cost. Also, customers often want to first simply know how much it would cost to build the building they want, rather than consulting a professional real estate agent straight away.

[0006] Therefore, one of the objects of the present invention is to enable a user to easily concretize an image of a desired property and to make a concrete sales proposal for the property. [Means for solving the problem]

[0007] In order to achieve the above-mentioned object, a property proposal system according to one aspect of the present invention is a property proposal system in which a processor executes a presentation step of presenting a plurality of candidate images representing an image of a property, a first reception step of accepting a user's selection from the plurality of candidate images, an instruction step of instructing a first artificial intelligence to generate specifications for the property in the selected candidate image, and an output step of outputting contractors capable of carrying out construction according to the specifications of the property and an estimate of the costs required for the construction, wherein the first artificial intelligence has a learning model that receives a selected candidate image as input and outputs the specifications of the property represented in the selected candidate image.

[0008] The system may include a contractor information storage means that associates contractors with information indicating the types of work that the contractors can perform, and information that serves as a basis for calculating the cost of each task, and in the output step, the second artificial intelligence may be caused to refer to the contractor information storage means and output contractors that can perform work according to the specifications of the property and an estimate of the cost required for the work.

[0009] The information indicating the type of work that the contractor can perform may be an image showing the content of the work that the contractor can perform.

[0010] The method may further include a second receiving step of receiving, from a contractor terminal used by the contractor, registration of an image showing the content of the work that the contractor can perform.

[0011] The learning model may be a model that is machine-learned from a contractor and an image representing the work content that the contractor can perform.

[0012] The image showing the work that the contractor can carry out may be the same image as the candidate image.

[0013] The method may further include a third reception step of receiving a request for special construction from a user, and in the instruction step, the first artificial intelligence may be instructed to generate specifications for an item that reflects the special construction received as a request from the user, in accordance with an object in a selected candidate image.

[0014] In the instruction step, the first artificial intelligence may be input with the selected image and refer to a land information storage means storing information on land for sale to select land for sale that corresponds to the selected image, and may be instructed to generate property specifications for when the property shown in the selected image is to be built on the selected land for sale, and in the output step, may output contractors capable of construction according to the property specifications, the costs required for construction, and an estimate of the cost of the selected land for sale.

[0015] A property proposing method according to another aspect of the present invention includes a computer that executes the following steps: a presentation step of presenting a plurality of candidate images representing an image of a property; a reception step of accepting a user's selection from the plurality of candidate images; an instruction step of instructing a first artificial intelligence to generate specifications for the property in the selected candidate image; and an output step of outputting contractors capable of performing construction according to the property specifications and an estimate of the costs required for the construction, wherein the first artificial intelligence has a learning model that receives the selected candidate image as input and outputs the specifications of the property represented in the selected candidate image.

[0016] A property proposal program according to another aspect of the present invention causes a computer to execute the following steps: a presentation step of presenting a plurality of candidate images representing an image of a property; a reception step of accepting a user's selection from the plurality of candidate images; an instruction step of instructing a first artificial intelligence to generate specifications for the property in the selected candidate image; and an output step of outputting contractors capable of carrying out construction according to the specifications of the property and an estimate of the costs required for the construction, wherein the first artificial intelligence has a learning model that receives a selected candidate image as input and outputs the specifications of the property represented in the selected candidate image. The computer program may be provided as a non-transitory computer-readable medium, or may be provided so as to be downloadable from an external server, or may be provided so that the program is launched on an external computer and its functions are realized on a client terminal (so-called cloud computing). Effect of the Invention

[0017] According to the present invention, a user can easily concretize an image of a desired property and make a proposal for the sale of a specific property, etc. [Brief description of the drawings]

[0018] [Figure 1] 1 is a diagram showing an overall configuration and a functional configuration of a property proposal system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a sequence diagram showing an example of a processing flow executed by the property proposal system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0019] Hereinafter, a property proposal system 1 according to an embodiment of the present invention will be described with reference to the drawings.

[0020] System Configuration FIG. 1 shows an embodiment of the present invention. Property Proposal System 1 and 1 shows the configuration of the server device 10. 。

[0021] thing The item proposal system 1 is configured to be capable of communicating with each other via a network NW and includes a server device 10 and a user terminal 20. The server device 10 may be configured by a hardware device, or some or all of the functions may be realized by a cloud computer. Furthermore, each component of the server device 10 may be realized by an API (Application Programming Interface). The communication between the server device 10 and the user terminal 20 may be wireless or wired. Furthermore, the server device 10 may be configured with a plurality of hardware components. In this case, the plurality of hardware components may be connected by wire or wirelessly to transmit and receive information to and from each other.

[0022] ● User terminal 20 The user terminal 20 is a terminal operated by a user, such as a smartphone, a tablet terminal, or a personal computer. The user terminal 20 mainly comprises functional blocks including an output unit 21, an operation reception unit 22, and a communication processing unit 23, and is configured by a CPU (Central Processing Unit), a computer program executed by the CPU, a RAM (Random Access Memory) and a ROM (Read Only Memory) for storing the computer program and predetermined data.

[0023] The output unit 21 is a so-called display unit that is realized by, for example, a display for displaying data. Information for the user received from the server device 10 is displayed on the output unit 21. The output unit 21 may also include a speaker for outputting sound.

[0024] The operation reception unit 22 is realized by a touch panel, a keyboard, a mouse, a microphone, or the like for inputting data.

[0025] The communication processing unit 23 is a processing unit that enables data transmission and reception processing to and from the server device 10 in accordance with a predetermined protocol via a network NW such as the Internet, and is realized by an application, a Web browser, or the like.

[0026] ●Server device 10 Here, the configuration of the server device 10 will be described with reference to Fig. 1. The server device 10 is an information processing device that executes a property proposal process while exchanging data with a user terminal 20 via a network NW. The server device 10 stores an image database DB1, a land information database DB2, and a contractor information database DB3.

[0027] The image database DB1 stores candidate images that represent images of properties. The properties referred to here are land and buildings constructed on the land. The image of a property represents the specific contents of the property, for example, the appearance of the land and the building constructed on the land.

[0028] The candidate images may be photographic data of an actual building, or may be composite images, illustration images, etc. Furthermore, the candidate images may be collected from the Internet or the like, or may be provided by a user. A candidate image showing an image of a property may be composed of multiple images. For example, a candidate image showing a property may be composed of two images showing the exterior and interior of the property. Each candidate image may be provided with information explaining the contents of the property shown in the candidate image. The data format of the candidate images is not particularly limited as long as the data format is a format that the server device 10 can read.

[0029] The land information database DB2 stores information on land that is actually for sale. The land information includes a wide range of information required for constructing a building on the land and information that a customer who purchases the land needs to confirm, such as the address, area, shape of the land, selling price, and information related to the surrounding environment. It may also include two-dimensional or three-dimensional images of the land.

[0030] The contractor information database DB3 stores information about contractors who carry out various construction work according to the specifications of the building to be constructed. The contractor information includes basic information such as the contractor's name and address, as well as information that serves as the basis for estimating the cost of a particular task, such as the types of work that each contractor can perform and the unit price that serves as the basis for calculating the cost of each task. It may also include information regarding the contractor's schedule and the time required for the work, which allows you to know when the contractor will be able to accept the work and the time it will take if a specific work is ordered from the contractor.

[0031] In addition, as information indicating the type of work that each contractor can perform, images showing the work that the contractor actually performed or images showing the work that the contractor can perform may be registered. The registration of such images may be accepted from a terminal used by the contractor on a specified web page. In addition, the images may be prepared by the contractor himself and registered in the contractor information database DB3 via a specified web page, or images showing various types of work that have been prepared in advance may be selected by the contractor, and the image may be associated with the contractor who made the selection and registered. In addition, the same image as the image selected by the user as the candidate image may be used as the image registered as the image showing the work that the contractor can actually perform.

[0032] As shown in FIG. 1, the server device 10 is configured with functional blocks mainly consisting of a display control unit 11, a memory control unit 12, an AI control unit 13, an artificial intelligence unit 14, and a communication processing unit 15, which are configured with a CPU (Central Processing Unit, which is an example of a processor in the claims), a computer program executed by the CPU, a RAM (Random Access Memory) and a ROM (Read Only Memory) for storing the computer program and specified data, etc.

[0033] The display control unit 11 executes processing for displaying a screen related to the property proposal system 1 on the user terminal 20. The display control unit 11 performs processing such as generating and transmitting an HTML (Hyper Text Markup Language) file, and displays on the user terminal 20 a web page as a screen that the user views when receiving property proposals in this system. The display control unit 11 may also perform processing such as generating and transmitting display data for an application for using the property proposal system 1.

[0034] The storage control unit 12 is a functional unit that controls an appropriate storage device provided in the server device 10 and writes and reads data. The storage control unit 12 stores information received via a predetermined registration screen, for example, in each of the databases DB1, DB2, and DB3.

[0035] The AI ​​control unit 13 is a functional unit that controls input to the artificial intelligence unit 14. The AI ​​control unit 13 receives a candidate image representing an image of a property selected and input by a user, and generates a prompt that commands the output of the specifications of the property shown in the candidate image. The AI ​​control unit 13 also generates a prompt that commands the output of a contractor capable of performing construction according to the property specifications and an estimate of the cost required for construction. The prompt is information that instructs the artificial intelligence unit 14 on the content to be generated, and is, for example, a character string written in a natural language.

[0036] The artificial intelligence unit 14 is an AI equipped with a language model such as a transformer including BART (Bidirectional and Auto-regressive Transformer), BERT (Bidirectional Encoder Representations from Transformers), or GPT (Generative Pretrained Transformer, including GPT-1, GPT-2, and GPT-3), in particular a learning model such as a large-scale language model (LLM, Large Language Models). A learning model (also called a machine learning model) refers to a learning model based on a machine learning algorithm. Specific examples of machine learning algorithms include nearest neighbor methods, naive Bayes methods, decision trees, and support vector machines. Another example is deep learning, which uses a neural network to generate features and connection weighting coefficients for learning. The artificial intelligence unit 14 can apply the above algorithms as appropriate.

[0037] The artificial intelligence unit 14 has, as artificial intelligence, a trained model constructed by a learning method such as supervised learning, unsupervised learning, or self-supervised learning. In supervised learning, machine learning is performed using training data (training data). The training data is composed of a pair of input data for learning and output data (correct answer data). In addition, the language model may not only be one trained for a specific task, but also a general-purpose model that can be used for a wide range of tasks.

[0038] The artificial intelligence included in the artificial intelligence unit 14 has obtained appropriate learning data in advance, but can perform additional learning. For example, only images showing the image of the property may be given as input data in large quantities. Fine tuning may also be performed using a teacher data set that pairs an image showing the image of the property with the specifications of the property in the image. Furthermore, while the property proposal system 1 is actually operating, a correction data set may be prepared as feedback for the property specifications generated by the artificial intelligence unit 14 in response to a candidate image selected by the user, and fine tuning may be performed. This optimizes the content output from the learning model. In addition, the server device 10 may refer to the contractor information database DB3 and perform machine learning of contractors and images showing the construction content that the contractors can perform. This allows the presence or absence of contractors who can perform the construction of the property shown in the construction image to be appropriately determined and selected based on the relationship between the candidate image selected by the user and the image showing the construction content that each contractor can perform. In particular, when the same image as the image selected by the user as the candidate image is used as the image showing the work that the contractor can actually perform, the selection of the construction contractor becomes more reliable.

[0039] In this embodiment, the learning model included in the artificial intelligence unit 14 can input a candidate image selected by the user and output the specifications of the property shown in the selected candidate image. As a result, in an example of function execution, the artificial intelligence unit 14 inputs a candidate image showing an image of a property selected and input by the user, and generates and outputs the specifications of the property shown in the candidate image based on a prompt generated by the AI ​​control unit 13.

[0040] Property specifications are information about a property that is required when constructing a building on land, such as the property's layout, the building's orientation relative to the land, construction details, etc. This information about property specifications allows you to understand what type of work will be required when constructing a building, as well as the shape and area of ​​the land required to build a building with those specifications.

[0041] In another example of function execution, the artificial intelligence unit 14 receives information related to the specifications of a property as input, generates and outputs property proposal information based on a prompt generated by the AI ​​control unit 13. The property proposal information is simulation information in the case where the property shown in the selected candidate image is actually provided, and is a compilation of actual land for sale close to the property, contractors who can construct properties similar to the property, estimates of the various costs of the land for sale and construction, etc. By referring to the proposal information generated by the artificial intelligence unit 14, the user can understand how much it would cost and where the property he or she wants can actually be purchased.

[0042] The generation of the property proposal information can be performed by a learning model possessed by the artificial intelligence unit 14, and can also be optimized by referring to information in the land information database DB2 and / or the contractor information database DB3 using RAG (Retrieval Augmented Generation). That is, in a proposal of a property that matches a candidate image selected by the user, a command is input in a prompt to the artificial intelligence unit 14 to refer to the land information database DB2 so that the land can be selected from those registered in the land information database DB2. This allows a proposal to be made so that the user can understand what kind of cost and contractor can obtain a property that matches the user's desire, assuming that the land is actually available, rather than fictitious land or land that is not for sale. Similarly, in a prompt to the artificial intelligence unit 14, a command is input to refer to the contractor information database DB3 so that the contractor information is based on information registered in the contractor information database DB3. This allows more realistic estimates and construction details to be clarified, and the period required for construction can be foreseen by referring to a schedule as contractor information.

[0043] The communication processing unit 15 is a processing unit that enables data transmission and reception processing according to a predetermined protocol with the user terminal 20 via a network NW such as the Internet. The communication processing unit 15 receives requests for proposals and the like from the user terminal 20, and transmits information related to property proposals generated by the artificial intelligence unit 14 to the user terminal 20.

[0044] By using this communication processing unit 15, the server device 10 presents a plurality of candidate images showing an image of the property to the user via the user terminal 20.

[0045] Furthermore, the communication processing unit 15 enables the server device 10 to accept the following information from the user terminal 20: That is, in one example, the communication processing unit 15 accepts, from the user terminal 20, a user's selection from a plurality of candidate images showing the property.

[0046] In another example, the communication processing unit 15 accepts registration of an image showing the content of the work that the contractor can perform from a contractor terminal used by the contractor, etc., from the user terminal 20. The image showing the content of the work that the contractor can perform may be registered in, for example, the contractor information database DB3.

[0047] In another example, the communication processing unit 15 accepts an additional request from the user for a property from the user terminal 20. The additional request for a property is, for example, a request for additional construction for the property shown in the candidate image selected by the user, such as a request for special construction. There are cases where the user's detailed wishes cannot be fully reflected by the selection of the candidate image alone, and in such cases, it is convenient if the additional request can be added separately from the selection of the candidate image. The additional request may be provided, for example, separately from the selection of the candidate image, and may be provided to the user as an item that can be selected at will. The item that can be selected at will may be guided in text format or in image format. In addition, the user may be able to input other additional requirements such as location, building or land area, and budget. These additional requests form part of the prompts generated by the AI ​​control unit 13 for the artificial intelligence unit 14, thereby making it possible to request the server device 10 to generate and output property specifications that take into account the additional requests.

[0048] Processing flow As shown in Fig. 2, first, the server device 10 refers to the image database DB1 and transmits a plurality of candidate images to the user terminal 20, requesting the selection of a desired property (step S101). In response to this, the user selects a candidate image that represents a property that matches his / her desires (step S102). Note that the user may be able to input additional requests for the property together with the selection of the candidate image.

[0049] The AI ​​control unit 13 inputs the candidate image selected by the user to the artificial intelligence unit 14 and causes it to output the specifications of the property appearing in the candidate image (step S103). The AI ​​control unit 13 causes the artificial intelligence unit 14 to refer to the land information database DB2 and the contractor information database DB3 (steps S104, S105) and select a piece of land for sale that matches the image of the property represented by the candidate image, and also to output specific construction details and cost estimates according to the specifications of the property, as well as information on contractors who can carry out the construction (step S106). The output information is transmitted to the user terminal 20 as property proposal information (step S107).

[0050] As described above, according to the property proposal system 1 of the present invention, even a vague image of a property desired by a user can be made concrete, and practical property proposals can be made.

[0051] In this embodiment, more detailed requests may be incorporated as one of the user's additional requests or as a separate additional request as conditions on the user's side and reflected in the property proposal. For example, when the user selects a candidate image, the user may input a budget, construction time, or construction period as conditions. In this case, for example, the AI ​​control unit 13 may incorporate an instruction to generate a result reflecting the conditions in a prompt to the artificial intelligence unit 14, and such an instruction may be a request to generate a result based on learned data, or a request to generate a result by referring to the contractor information database DB3. In addition, the property proposal information generated by the artificial intelligence unit 14 may be narrowed down based on the user's budget and construction time. In addition, the server device 10 may transmit a request for the user's desired budget and construction time to the contractor terminal of a contractor capable of construction included in the property proposal information, and transmit a response to the request received from the contractor terminal to the user terminal 20.

[0052] The server device 10 may also be provided with a discrimination processing unit that discriminates contractors capable of carrying out construction work in accordance with the specification information based on the property specification information generated by the artificial intelligence unit 14, by referring to the contractor information database DB3. In this case, the discrimination processing unit may discriminate contractors capable of carrying out construction work based on not only the specification information but also conditions such as a budget, construction time, or construction period separately received from a user. For example, the budget is determined based on the unit price set by the contractor, and the construction time or construction period is determined from the contractor's schedule information. [Explanation of symbols]

[0053] 1. Property proposal system 10. Server device 11 Display control unit 12 Memory control unit 13 AI control section 14 Artificial Intelligence Department 15 Communication processing section DB1 Image information database DB2 Vendor Information Database DB3 Land Information Database 20 User terminal

Claims

1. A property proposal system, a contractor information storage means for storing a relationship between a contractor, information indicating the type of work that the contractor can perform, and information serving as a basis for calculating the cost of each work; The processor: A first reception step of receiving registration of a predetermined image showing the content of the work that the contractor can perform from a contractor terminal used by the contractor; A presentation step of presenting a plurality of candidate images representing an image of the constructed property to a user; a second receiving step of receiving a user's selection from the plurality of candidate images; A first instruction step of instructing the first artificial intelligence to extract construction details of the property in the selected candidate image; A second instruction step of instructing the second artificial intelligence to select a contractor capable of constructing the property in the selected candidate image; an estimation step of referring to the contractor information storage means and outputting an estimate of the cost when a contractor capable of constructing the property in the selected candidate image performs construction according to the construction content; The first artificial intelligence has a first learning model that receives the candidate image as an input and outputs the construction content of the property shown in the candidate image, The second artificial intelligence is a learning model that performs machine learning on the contractor and the predetermined image received in the first reception step, and has a second learning model that uses the candidate image as an input and outputs a contractor who can perform construction of the property shown in the candidate image based on the relationship between the candidate image and the predetermined image. Property proposal system.

2. A land selection step is further carried out, which refers to a land information storage means which stores information on land that is up for sale based on the selected candidate image, and selects a piece of land for sale that corresponds to the selected candidate image; The estimation step further includes outputting an estimate including the cost of the selected land for sale. The property recommendation system according to claim 1 .

3. A property proposal method, comprising: a contractor information storage means for storing a relationship between a contractor, information indicating the type of work that the contractor can perform, and information serving as a basis for calculating the cost of each work; By computer, A first reception step of receiving registration of a predetermined image showing the content of the work that the contractor can perform from a contractor terminal used by the contractor; A presentation step of presenting a plurality of candidate images representing an image of the constructed property to a user; a second receiving step of receiving a user's selection from the plurality of candidate images; A first instruction step of instructing the first artificial intelligence to extract construction details of the property in the selected candidate image; A second instruction step of instructing the second artificial intelligence to select a contractor capable of constructing the property in the selected candidate image; an estimation step of referring to the contractor information storage means and outputting an estimate of the cost when a contractor capable of constructing the property in the selected candidate image performs construction according to the construction content; The first artificial intelligence has a first learning model that receives the candidate image as an input and outputs the construction content of the property shown in the candidate image, The second artificial intelligence is a learning model that performs machine learning on the contractor and the predetermined image received in the first reception step, and has a second learning model that uses the candidate image as an input and outputs a contractor who can perform construction of the property shown in the candidate image based on the relationship between the candidate image and the predetermined image. Property proposal method.

4. A property proposal program, comprising: a contractor information storage means for storing a relationship between a contractor, information indicating the type of work that the contractor can perform, and information serving as a basis for calculating the cost of each work; For computers, A first reception step of receiving registration of a predetermined image showing the content of the work that the contractor can perform from a contractor terminal used by the contractor; A presentation step of presenting a plurality of candidate images representing an image of the constructed property to a user; a second receiving step of receiving a user's selection from the plurality of candidate images; A first instruction step of instructing the first artificial intelligence to extract construction details of the property in the selected candidate image; A second instruction step of instructing the second artificial intelligence to select a contractor capable of constructing the property in the selected candidate image; an estimation step of referring to the contractor information storage means and outputting an estimate of the cost when a contractor capable of construction of the property in the selected candidate image performs construction according to the construction content; The first artificial intelligence has a first learning model that receives the candidate image as an input and outputs the construction content of the property shown in the candidate image, The second artificial intelligence is a learning model that performs machine learning on the contractor and the predetermined image received in the first reception step, and has a second learning model that uses the candidate image as an input and outputs a contractor who can perform construction of the property shown in the candidate image based on the relationship between the candidate image and the predetermined image. Property proposal program.

Images