KR102682530B1 - Method for providing automated interior quotes based on artificial intelligence algorithms - Google Patents

Abstract

This disclosure relates to the field of providing an automatic interior quotation service, and more specifically, to a method of providing an automatic interior quotation service based on an artificial intelligence algorithm.

Description

Method of providing automatic interior quotation service based on artificial intelligence algorithm {METHOD FOR PROVIDING AUTOMATED INTERIOR QUOTES BASED ON ARTIFICIAL INTELLIGENCE ALGORITHMS}

This disclosure relates to the field of providing an automatic interior quotation service, and more specifically, to a method of providing an automatic interior quotation service based on an artificial intelligence algorithm.

Interior design refers to the planning and execution of the internal composition of spaces such as residential and commercial spaces and the arrangement of various objects. Recently, with the emergence of various tastes and the development of furniture and construction materials, the options for interior design are gradually expanding, and the number of complaints about the difficulty of making a final decision due to the diversity of choices is also increasing.

When planning and designing the interior of a space, most interior clients do not have sufficient knowledge in the field of interior design, and in this case, the client provides abstract and vague requests even when the interior is done through a separate interior design company. As this is done, there is a risk that the final result may be unexpectedly different from what was initially intended, and even experts may interpret and understand the request differently, so this risk still exists.

In addition, in the past, even if computer programs were used, most analyzes of interior design requests depended on human resources. However, in a break from this, we provide quick and reasonable proposals using an artificial neural network model learned based on verified existing interior design estimates. A way to do this is desperately needed.

Furthermore, even experts who plan interior design and calculate estimates cannot be aware of all products in a very wide range of interior design fields, and recently, based on interest in energy conservation, materials selection that takes into account the climate and environment has also been actively selected. Therefore, there is an urgent need for an automatic interior quotation service that can utilize artificial neural network algorithms to suggest more appropriate materials by considering the climatic environment of the location where the interior is to be designed, such as temperature and humidity.

Public Patent Publication No. 10-2023-0054059 (published on April 24, 2023)

This disclosure was designed to solve the above-mentioned problems, and the purpose of this disclosure is to provide a method of providing an automatic interior quotation service based on an artificial intelligence algorithm.

The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned can be clearly understood by those skilled in the art from the description below.

In one embodiment of the present disclosure, a method of providing an automatic interior quotation service based on an artificial intelligence algorithm performed by a device includes:

Providing interior quote data for a plurality of reference spaces to a data collection module;

Preprocessing each of the interior quotation data provided using a data collection module, and extracting reference spatial information data and reference construction history data from the preprocessed interior quotation data;

providing interior request data for a specific space to a data collection module;

Preprocessing the provided interior request data using a data collection module, and extracting spatial information data for a specific space and preference data for a specific space from the preprocessed interior request data;

The reference spatial information data and reference construction history data are provided to the input layer of the first artificial neural network model, and when spatial information data for a specific space is input, expected construction list data and expected construction cost data for the specific space are output. Learning the first artificial neural network model as much as possible;

Based on an environmental database storing a plurality of address data and terrain data and climate data corresponding to each of the address data, when spatial information data for a specific space is input, expected terrain data and expected climate data for the specific space are generated. Learning a second artificial neural network model to be output;

The reference spatial information data, reference construction history data, expected terrain data, and expected climate data are provided to the input layer of the third artificial neural network model, so that when spatial information data and preference data for a specific space are input, the specific space training the third artificial neural network model to output expected process difficulty data;

The expected construction list data, expected terrain data, and expected climate data are provided to the input layer of the fourth artificial neural network model, so that when spatial information data and preference data for a specific space are input, proposed construction list data for the specific space training the fourth artificial neural network model to output;

By providing the expected process difficulty data and the expected construction cost data to the proposal creation module, a first weight is obtained based on the expected process difficulty data, and the first weight is reflected in the expected construction cost data to provide a proposed construction cost. acquiring data; and

It may include the step of generating an interior proposal based on the proposed construction list data and the proposed construction cost data using a proposal generation module.

In addition, the reference spatial information data may be composed of detailed reference spatial information data including at least one of configuration data, area data, floor height data, and data on the year in which the space was created, of the target space for which the interior quotation was issued.

In addition, the reference construction history data may include material estimate data identifying each of flooring, walls, doors, windows, lighting, and air conditioning equipment as construction items included in the interior estimate, and the material estimate data may include the interior It may include cost estimate data corresponding to each of the material estimate data described in the quotation, and the cost estimate data is included in each material estimate data when obtaining the expected construction cost data in the step of learning the first artificial neural network model. It can be configured to be acquired according to a separately set weight for each included material.

In addition, the spatial information data for the specific space is detailed specific spatial information data including at least one of address data, location data, configuration data, floor height data, and data on the year in which the space was formed, of the space requested by the interior request. It may be configured.

In addition, the preference data for the specific space is data that reflects the user's preference for the specific space, such as the color of the flooring of the space, the color of the walls of the space, the color and transparency of the doors and windows of the space, the illuminance of the lighting of the space, Detailed symbols including at least one of space temperature and space humidity may also be composed of data.

In addition, the expected construction list data in the step of learning the first artificial neural network model may include civil engineering identification data that identifies flooring, walls, doors, and windows.

In addition, the expected construction cost data in the step of learning the first artificial neural network model may include labor cost data and material cost data.

In addition, the address data in the step of training the second artificial neural network model may be location data based on the latitude and longitude of a specific place, and the terrain data may include the latitude, longitude, and longitude of the location indicated by the address data. It may be data about topography including altitude, and the climate data may be data about climate including average temperature, average humidity, and average amount of sunlight at the location indicated by the address data.

In addition, the expected process difficulty data in the step of training the third artificial neural network model may be configured to be obtained according to a weight separately set for each data of the detailed spatial information data.

In addition, the expected process difficulty data in the step of training the third artificial neural network model may be configured to be obtained by reflecting weights separately assigned to each detailed preference data included in the preference data.

In addition, the proposed construction list data in the step of learning the fourth artificial neural network model may include civil engineering proposal data identifying flooring, walls, doors, and windows.

In addition, the proposed construction list data in the step of learning the fourth artificial neural network model is configured to determine flooring, walls, doors, and windows included in the civil engineering proposal data according to each detailed preference data included in the preference data. It can be.

In addition, the fourth artificial neural network model may be configured to determine flooring, walls, doors, and windows included in the civil engineering proposal data based on the civil engineering identification data, expected terrain data, and expected climate data.

In the step of acquiring the proposed construction cost data, in reflecting the first weight to the expected construction cost data, the first weight dependent on the expected terrain data is added to the labor cost data included in the expected construction cost data. The proposed construction is carried out by reflecting the 1-1 weight as a lower weight, and reflecting the 1-2 weight as a lower weight of the first weight that is dependent on the material cost data included in the expected construction cost data and the expected climate data. It may be configured to obtain cost data.

In addition to this, a computer-readable recording medium recording a computer program for executing a method for implementing the present disclosure may be further provided.

According to various embodiments of the present disclosure, a method of providing an automatic interior quotation service based on an artificial intelligence algorithm can be provided.

According to various embodiments of the present disclosure, an interior request is analyzed based on topographic data and climate data obtained based on interior-related data and address data obtained from a plurality of interior quotations and included in the existing interior quotation most suitable for the request. Based on the construction list, a quick and predictable interior design service can be provided by proposing construction items that reflect the requester's preferences and providing guidance on the corresponding estimated costs.

The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned may be clearly understood by those skilled in the art from the description below.

Figure 1 is a diagram briefly illustrating a system that provides an automatic interior quotation service based on an artificial intelligence algorithm according to an embodiment of the present disclosure.
Figure 2 is a block diagram briefly showing a device that provides an automatic interior quotation service based on an artificial intelligence algorithm, according to an embodiment of the present disclosure.
Figure 3 is a flowchart for explaining a method of providing an automatic interior quotation service based on an artificial intelligence algorithm according to an embodiment of the present disclosure.

The advantages and features of the present disclosure and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various different forms. The present embodiments are merely provided to ensure that the disclosure is complete and to provide a general understanding of the technical field to which the present disclosure pertains. It is provided to fully inform those skilled in the art of the scope of the present disclosure, and the present disclosure is defined only by the scope of the claims.

The terminology used herein is for the purpose of describing embodiments and is not intended to limit the disclosure. As used herein, singular forms also include plural forms, unless specifically stated otherwise in the context. As used in the specification, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other elements in addition to the mentioned elements.

Like reference numerals refer to like elements throughout the specification, and “and/or” includes each and every combination of one or more of the referenced elements. Although “first”, “second”, etc. are used to describe various components, these components are of course not limited by these terms. These terms are merely used to distinguish one component from another. Therefore, it goes without saying that the first component mentioned below may also be the second component within the technical spirit of the present disclosure.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art to which this disclosure pertains. Additionally, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless clearly specifically defined.

Spatially relative terms such as “below”, “beneath”, “lower”, “above”, “upper”, etc. are used as a single term as shown in the drawing. It can be used to easily describe the correlation between a component and other components. Spatially relative terms should be understood as terms that include different directions of components during use or operation in addition to the directions shown in the drawings.

For example, if a component shown in a drawing is flipped over, a component described as "below" or "beneath" another component will be placed "above" the other component. You can. Accordingly, the illustrative term “down” may include both downward and upward directions. Components can also be oriented in other directions, so spatially relative terms can be interpreted according to orientation.

In describing the present disclosure, “manager” may mean a person who creates an interior proposal using a service provided by a server. Additionally, “user” may refer to a person who submits an interior design request using a service provided by a server and receives an interior design proposal generated accordingly.

Below, a method of providing an automatic interior quotation service based on an artificial intelligence algorithm will be described in detail with reference to the drawings.

Figure 1 is a diagram briefly illustrating a system that provides an automatic interior quotation service based on an artificial intelligence algorithm, according to an embodiment of the present disclosure.

As shown in FIG. 1, the system 1000 for implementing a method of providing an automatic interior quotation service based on an artificial intelligence algorithm includes a device 100, a terminal device 200 used by the first user, and a database ( 300).

Here, Figure 1 shows a case where the device 100 is implemented as a desktop, and shows a case where the terminal device 200 used by the first user is implemented as a smart phone, but is not limited to this. no.

The device 100 and the terminal device 200 used by the first user may be implemented as various types of electronic devices (e.g., laptop, desktop, laptop, tablet PC, slate PC device, server device, etc.). It can also be implemented as a device group in which more than one type of device is connected.

For example, device 100 may be implemented as a group of devices in which one or more types of devices are connected. For example, the device 100 may be implemented as a device that manages an application that provides an automatic interior quotation service based on an artificial intelligence algorithm, a cloud server that stores data related to the application, etc.

In Figure 1, it is assumed that there is only one user (i.e., the first user) who receives a consultation service based on an artificial intelligence algorithm, but the situation is not limited to this. The number of users can be implemented with various values.

The device 100 included in the system 1000, the terminal device 200 used by the first user, and the database 300 (i.e., the cloud server including the database 300) communicate through the network W. It can be done.

Here, the network W may include a wired network and a wireless network. For example, the network may include various networks such as a local area network (LAN), a metropolitan area network (MAN), and a wide area network (WAN).

Additionally, the network W may include the known World Wide Web (WWW). However, the network (W) according to an embodiment of the present disclosure is not limited to the networks listed above, and may include at least some of a known wireless data network, a known telephone network, and a known wired and wireless television network.

The device 100 may provide an application that provides an automatic interior quotation service based on an artificial intelligence algorithm to one or more users. The application can provide a service that receives an interior design request form from a user and provides the user with an interior design proposal automatically generated by an artificial neural network learned from data included in multiple interior design estimates.

Specifically, the device 100 extracts reference spatial information data and reference construction history data from a plurality of interior quotations, based on the extracted data, a plurality of address data, terrain data and climate data corresponding to the address data. Thus, spatial information data and preference data for a specific space can be extracted from the interior design request, and an automatically generated interior proposal can be provided by learning and using a plurality of artificial neural network models.

How the device 100 performs the various operations described above will be described in detail with reference to FIGS. 2 and 3.

The database 300 (i.e., a cloud server including the database 300) may refer to a database in which various text/image data used by the device 100 to learn an AI model are constructed. The database 300 may be implemented as a component of the device 100, but is not limited thereto and may be implemented as a separate cloud server.

Figure 2 is a block diagram briefly illustrating the configuration of a server that provides an automatic interior quotation service based on an artificial intelligence algorithm according to an embodiment of the present disclosure.

As shown in FIG. 2 , device 100 may include memory 110, communication module 120, display 130, and processor 150.

However, the configuration shown in FIG. 2 is an illustrative diagram for implementing embodiments of the present disclosure, and appropriate hardware and software configurations that are obvious to those skilled in the art may be additionally included in the device 100.

The memory 110 may store one or more instructions for the processor 150 to perform various operations. The memory 110 can store data supporting various functions of the device 100, a program for the operation of the processor 150, and can store input/output data.

The memory 110 may store interior design estimates, interior design requests, address data, terrain data, and climate data. The memory 110 may store one or more parameters for performing learning/inference operations for various AI models (eg, a first AI model, a second AI model, and an entire AI model). As described above, the memory 110 can store voice/data data built in the database 300 of FIG. 1.

The memory 110 is a flash memory type, hard disk type, solid state disk type, SDD type (Silicon Disk Drive type), and multimedia card micro type. ), card type memory (e.g. SD or XD memory, etc.), RAM (random access memory), SRAM (static random access memory), ROM (read-only memory), EEPROM (electrically erasable programmable read) -only memory), PROM (programmable read-only memory), magnetic memory, magnetic disk, and optical disk may include at least one type of storage medium.

The communication module 120 may include one or more components including a circuit that enables communication with an external device (eg, a terminal device used by a user, etc.). For example, the communication module 120 may include at least one of a broadcast reception module, a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

The display 130 displays (outputs) information processed by the device 100. For example, the display 130 displays information on the execution screen of an application running on the device 100 (e.g., an application/website that provides an automatic interior quotation service based on an artificial intelligence algorithm), or such execution screen. A UI (User Interface) based on information (for example, a UI that allows the manager to input text for detailed items of the interior quotation and images that describe the detailed items, etc.), GUI (Graphic User Interface) information can be displayed. there is.

The input module 140 refers to a component for applying various input data and/or input interactions (eg, touch, swipe, etc.) to the device 100.

The processor 150 may provide a method of providing an automatic interior quotation service based on an artificial intelligence algorithm by executing one or more instructions stored in the memory 110. That is, the processor 150 can control overall operations and functions using each component of the device 100.

Specifically, the processor 150 has a memory that stores data for an algorithm for controlling the operation of components in the device 100 or a program that reproduces the algorithm, and performs the above-described operations using the data stored in the memory. It can be implemented with at least one processor. At this time, the memory and processor may each be implemented as separate chips. Alternatively, the memory and processor may be implemented as a single chip.

In addition, the processor 150 may control any one or a combination of the components described above in order to implement various embodiments according to the present disclosure described in FIG. 3 below on the device 100.

Figure 3 is a flowchart for explaining a method of providing an automatic interior quotation service based on an artificial intelligence algorithm according to an embodiment of the present disclosure.

The device may include a data collection module, a first artificial neural network model, a second artificial neural network model, a third artificial neural network model, a fourth artificial neural network model, and a proposal generation module.

The device may allow the data collection module to receive interior quote data for a plurality of reference spaces (S310).

For example, the data collection module can receive various interior design estimates issued for various spaces and places, and secure and provide meaningful data from them. Various spaces and places include general houses, apartments, officetels, office spaces, restaurants, etc. It may be a cafe, a sales showroom, etc., and meaningful data may include data on the physical structure and environment of each space and place itself, as well as data on flooring, walls, doors, windows, etc. for the interior of each space and place. there is.

In other words, the data collection module can scan various interior design quotations and identify and provide information such as text and images included in the quotations as data, and various information can also be input into the module by a separate manager. Data resulting from interior design estimates collected through the data collection module can be stored and managed as a separate database.

The device may preprocess each interior quotation data provided using a data collection module and extract reference spatial information data and reference construction history data from the preprocessed interior quotation data (S320).

For example, the data collection module can analyze the provided interior quotation data, extract the sub-data and vectors contained therein, classify and label them, and classify and label the sub-data and vectors extracted from the interior quotation data according to predefined rules. By combining them, reference spatial information data and reference construction history data can be extracted. Reference space information may be data about the target space for which an interior quotation was issued, and reference construction history data may be data on the classification of various items that were estimated to be constructed in the target space for which an interior quotation was issued and the materials or products included in each item. It may be data about

For example, the reference spatial information data may be composed of detailed reference spatial information data including at least one of configuration data, area data, floor height data, and data on the year in which the space was formed of the target space for which the interior quotation was issued. .

For example, the reference construction history data may include material estimate data identifying each of flooring, walls, doors, windows, lighting, and air conditioning equipment as construction items included in the interior estimate, and the material estimate data It may include cost estimate data corresponding to each of the material estimate data described in the interior estimate, and the cost estimate data may be used for each material estimate in obtaining the expected construction cost data in the step of learning the first artificial neural network model. It can be configured to be acquired according to a separately set weight for each material included in the data.

The device may allow the data collection module to receive interior request data for a specific space (S330).

For example, the data collection module can receive a request for the interior of a specific space, secure meaningful data from it, and the specific space can be general houses, apartments, officetels, office spaces, restaurants, cafes, and sales showrooms. etc., and meaningful data may include data on the physical structure and environment of each space and place itself, and data on flooring, walls, doors, windows, etc. for the interior of each space and place.

That is, the data collection module can scan various interior design requests and identify and provide information such as text and images included in the quotation as data, and various information can also be input into the module by a separate user. Data resulting from interior design requests collected through the data collection module can be stored and managed as a separate database.

The device may preprocess the interior request data provided using a data collection module, and extract spatial information data for a specific space and preference data for a specific space from the preprocessed interior request data (S340).

For example, the data collection module can analyze the provided interior request data, extract the sub-data and vectors contained therein, classify and label them, and classify and label the sub-data and vectors extracted from the interior request data according to predefined rules. By combining them, spatial information data for a specific space and preference data for a specific space can be extracted. Spatial information data for a specific space may be data about the target space for which the interior design request is intended, and preference data for a specific space may include the interior concept, design direction, and desired interior design desired by the user who wrote the interior design request when the interior is completed. It may be abstract information about the atmosphere of the space, and includes all items that make up the perception of space, such as the main color or color expressed by the combination of various materials that make up the space, the illuminance and brightness of the space, humidity, and scent. It could be data about something.

For example, the spatial information data for the specific space is detailed specific spatial information including at least one of address data, location data, configuration data, floor height data, and data on the year the space was formed, of the space requested by the interior request. It may be composed of data.

For example, the preference data for the specific space is data that reflects the user's preference for the specific space, such as the color of the flooring of the space, the color of the walls of the space, the color and transparency of the doors and windows of the space, and the lighting of the space. Detailed symbols including at least one of illuminance, space temperature, and space humidity may also be composed of data.

The device provides the reference spatial information data and reference construction history data to the input layer of the first artificial neural network model, and when spatial information data for a specific space is input, expected construction list data and expected construction cost data for the specific space. The first artificial neural network model can be trained so that is output (S350).

For example, the first artificial neural network module is a supervised learning method that learns to optimize problem solving by inputting a teacher signal (correct answer), and an unsupervised learning method that does not require a teacher signal. It can be learned in a way that includes, and can be learned using machine learning technology.

The first artificial neural network module uses the reference spatial information data and reference construction history data provided and extracted from the interior quotation to determine whether the interior for the space was performed based on the spatial information data for a specific space provided and extracted from the interior request. In this case, data on necessary construction items and elements included in each item can be output, and estimated construction cost data can be output by combining cost data paired with each of the elements.

In other words, by submitting an interior design request, the user can receive an automatically generated interior proposal by inputting various data included in the interior design request into an artificial neural network. By using a separate artificial neural network module, the user can receive an interior design proposal that is predicted when preference is reflected. Information about the contents of the interior can also be provided.

For example, the expected construction list data in the step of training the first artificial neural network model may include civil engineering identification data that identifies flooring, walls, doors, and windows. In other words, the expected construction list data includes data on the construction of each floor, wall, door, and window, and may include which specific elements can be selected when each element is constructed and the corresponding expected cost.

For example, the expected construction cost data in the step of training the first artificial neural network model may include labor cost data and material cost data. In other words, the expected construction cost data may include data about the cost of the material itself and data about the labor cost that must be spent while performing construction. Each of the above data may be output separately or may be hidden.

Based on an environmental database storing a plurality of address data and terrain data and climate data corresponding to each of the address data, the device provides expected terrain data and expected climate for the specific space when spatial information data for a specific space is input. A second artificial neural network model can be trained so that data is output (S360).

For example, the second artificial neural network module utilizes random address data and corresponding terrain data and climate data to provide corresponding terrain data and climate data when random spatial information data is provided, or predicted terrain data and climate data. Climate data can be provided.

In other words, as the second artificial neural network module is used, related terrain data and climate data can be provided only with the spatial information data provided from the interior request, and the provided terrain data and climate data are used to select materials for the interior and determine construction items. , can be used to determine construction methods and calculate construction-related costs.

For example, the address data in the step of training the second artificial neural network model may be location data based on the latitude and longitude of a specific place, and the terrain data may be the latitude and longitude of the location indicated by the address data. , and may be data about the terrain including altitude, and the climate data may be data about the climate including the average temperature, average humidity, and average amount of sunlight at the location indicated by the address data.

The device provides the reference spatial information data, reference construction history data, expected terrain data, and expected climate data to the input layer of the third artificial neural network model, and when spatial information data and preference data for a specific space are input, the specific The third artificial neural network model can be trained so that expected process difficulty data for space is output (S370).

For example, the expected process difficulty data in the step of training the third artificial neural network model may be configured to be acquired according to a weight separately set for each data of the detailed spatial information data. For example, the address data, location data, configuration data, floor height data, and data on the year the space was formed may each have separate weights preset for the space included in the detailed spatial information data. For example, if the floor height of a space is too low, the overall process difficulty may increase due to an increase in work difficulty, so relatively high weight is given compared to other factors, and an interior design is requested for a space with a floor height that is too low. The expected process difficulty can be evaluated as significantly high.

For example, the expected process difficulty data in the step of training the third artificial neural network model may be configured to be obtained by reflecting weights separately assigned to each detailed preference data included in the preference data.

The device provides the expected construction list data, expected terrain data, and expected climate data to the input layer of the fourth artificial neural network model, and proposes construction for the specific space when spatial information data and preference data for a specific space are input. The fourth artificial neural network model can be trained to output list data (S380).

For example, the proposed construction list data in the step of training the fourth artificial neural network model may include civil engineering proposal data identifying flooring, walls, doors, and windows. In addition, the proposed construction list data in the step of learning the fourth artificial neural network model is configured to determine flooring, walls, doors, and windows included in the civil engineering proposal data according to each detailed preference data included in the preference data. It can be. For example, if the items included in the detailed preference map specify the material of the flooring, the data regarding the flooring included in the proposed construction list data may indicate the material of the flooring specified by the interior request. Additionally, the fourth artificial neural network model may be configured to determine flooring, walls, doors, and windows included in the civil engineering proposal data based on the civil engineering identification data, expected terrain data, and expected climate data.

The device may allow the proposal generation module to receive the expected process difficulty data and the expected construction cost data, obtain a first weight based on the expected process difficulty data, and apply the first weight to the expected construction cost data. By reflecting this, proposed construction cost data can be obtained (S390).

For example, in the step of acquiring the proposed construction cost data, in reflecting the first weight to the expected construction cost data, the first weight is dependent on the labor cost data included in the expected construction cost data and the expected terrain data. The 1-1 weight is reflected as a lower weight of the weight, and the 1-2 weight is reflected as a lower weight of the first weight that is dependent on the expected climate data in the material cost data included in the expected construction cost data. It may be configured to obtain proposed construction cost data.

The device may use the proposal generation module to generate an interior proposal based on the proposed construction list data and the proposed construction cost data (S310). In other words, after submitting an interior design request, the user can be provided with an interior design proposal automatically generated by the device.

Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium that stores instructions executable by a computer. Instructions may be stored in the form of program code and, when executed by a processor, may create program modules to perform operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

Computer-readable recording media include all types of recording media storing instructions that can be decoded by a computer. For example, there may be Read Only Memory (ROM), Random Access Memory (RAM), magnetic tape, magnetic disk, flash memory, optical data storage device, etc.

As described above, the disclosed embodiments have been described with reference to the attached drawings. A person skilled in the art to which this disclosure pertains will understand that the present disclosure may be practiced in forms different from the disclosed embodiments without changing the technical idea or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be construed as limiting.

Claims (1)

A method of providing an automatic interior quotation service based on an artificial intelligence algorithm performed by a device,
Providing interior quote data for a plurality of reference spaces to a data collection module;
Preprocessing each of the interior quotation data provided using a data collection module, and extracting reference spatial information data and reference construction history data from the preprocessed interior quotation data;
providing interior request data for a specific space to a data collection module;
Preprocessing the provided interior request data using a data collection module, and extracting spatial information data for a specific space and preference data for a specific space from the preprocessed interior request data;
The reference spatial information data and reference construction history data are provided to the input layer of the first artificial neural network model, and when spatial information data for a specific space is input, expected construction list data and expected construction cost data for the specific space are output. Learning the first artificial neural network model as much as possible;
Based on an environmental database storing a plurality of address data and terrain data and climate data corresponding to each of the address data, when spatial information data for a specific space is input, expected terrain data and expected climate data for the specific space are generated. Learning a second artificial neural network model to be output;
The reference spatial information data, reference construction history data, expected terrain data, and expected climate data are provided to the input layer of the third artificial neural network model, so that when spatial information data and preference data for a specific space are input, the specific space training the third artificial neural network model to output expected process difficulty data;
The expected construction list data, expected terrain data, and expected climate data are provided to the input layer of the fourth artificial neural network model, and when spatial information data and preference data for a specific space are input, proposed construction list data for the specific space training the fourth artificial neural network model to output;
By providing the expected process difficulty data and the expected construction cost data to the proposal creation module, a first weight is obtained based on the expected process difficulty data, and the first weight is reflected in the expected construction cost data to provide a proposed construction cost. acquiring data; and
Comprising: generating an interior proposal based on the proposed construction list data and the proposed construction cost data using a proposal generation module;
The reference spatial information data consists of detailed reference spatial information data including at least one of configuration data, area data, floor height data, and data on the year in which the space was formed, of the target space for which the interior quotation was issued,
The reference construction history data includes material estimate data identifying each of the flooring, walls, doors, windows, lighting, and air conditioning equipment as construction items included in the interior estimate, and the material estimate data includes the above described in the interior estimate. It includes cost estimate data corresponding to each material estimate data, and the cost estimate data is separately for each material included in each material estimate data when acquiring the expected construction cost data in the step of learning the first artificial neural network model. It is configured to be obtained according to the set weight,
The spatial information data for the specific space consists of detailed specific spatial information data including at least one of address data, location data, configuration data, floor height data, and data on the year in which the space was formed, of the space requested by the interior request. ,
The preference data for the specific space is data that reflects the user's preference for the specific space, such as the color of the flooring of the space, the color of the walls of the space, the color and transparency of the doors and windows of the space, the illuminance of the lighting of the space, and the color of the space's walls. Detailed symbols including at least one of temperature and space humidity are also composed of data,
The expected construction list data in the step of learning the first artificial neural network model includes civil engineering identification data identifying flooring, walls, doors, and windows,
The expected construction cost data in the step of learning the first artificial neural network model includes labor cost data and material cost data,
The address data in the step of learning the second artificial neural network model is location data based on the latitude and longitude of a specific place, and the terrain data includes the latitude, longitude, and altitude of the location indicated by the address data. It is data about topography, and the climate data is data about climate including average temperature, average humidity, and average amount of sunlight at the location indicated by the address data,
The expected process difficulty data in the step of training the third artificial neural network model is configured to be acquired according to a weight separately set for each data of the detailed spatial information data,
The expected process difficulty data in the step of learning the third artificial neural network model is configured to be obtained by reflecting weights separately assigned to each detailed preference data included in the preference data,
A method of providing an automatic interior quotation service, characterized in that the proposed construction list data in the step of learning the fourth artificial neural network model includes civil engineering proposal data identifying flooring, walls, doors, and windows.