Artificial intelligence-based device, system, and method for real estate valuation and analysis
An AI-based system integrates data collection and analysis to provide reliable real estate valuation and business feasibility, addressing market volatility and complexity by generating objective business plans, enabling efficient decision-making.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- JUNGIN REAL ESTATE GROUP CO LTD
- Filing Date
- 2025-09-03
- Publication Date
- 2026-06-18
Smart Images
Figure KR2025013521_18062026_PF_FP_ABST
Abstract
Description
Artificial intelligence-based real estate valuation and analysis device, system and method
[0001] Embodiments of the present invention relate to real estate valuation and analysis, and more specifically, to an apparatus, system, and method for real estate valuation and analysis with high accuracy by utilizing data selected based on artificial intelligence and big data.
[0002] The valuation of commercial real estate varies and is complex depending on the size and location of the building, and business feasibility analysis using this also shows significant differences depending on the objectivity and accuracy of the input data.
[0003] In order to review business feasibility, it is generally necessary to review different areas of work, such as calculating the buildable area through an architectural design firm, estimating construction costs through a construction company, and calculating rent through analysis of surrounding commercial areas using data from real estate brokerage offices and platform companies.
[0004] Those who wish to conduct a business feasibility analysis find it difficult to receive the aforementioned specialized business areas as a single service, and it is also nearly impossible to coordinate directly with each expert.
[0005] In this regard, there is a problem in that it is difficult to conduct highly reliable analyses of valuation and business feasibility because they change easily due to volatility and specific characteristics resulting from market changes.
[0006] The present invention was devised to resolve the aforementioned problems and aims to provide a quantitative evaluation service for the business feasibility and valuation of real estate by providing a single integrated analysis tool.
[0007] The present invention aims to select objective and reliable data for real estate valuation based on artificial intelligence technology, and to provide an objective real estate valuation and analysis service using the selected data.
[0008] However, these tasks are exemplary and do not limit the scope of the invention.
[0009] A computing device according to an embodiment of the present invention is an electronic device comprising at least one processor and a memory in which a computer program executed by the at least one processor is stored. The at least one processor is configured to collect and preprocess big data regarding real estate, train an artificial intelligence model using the preprocessed data, and, upon receiving input data regarding a target real estate, select data necessary for valuation of the target real estate using the trained artificial intelligence model, analyze the valuation and business feasibility of the target real estate based on the selected data, and automatically generate and provide a business plan for the target real estate based on the analysis results. The at least one processor can select a comparative real estate corresponding to the target real estate, perform a correction on a value coefficient calculated using the selected data based on the valuation results of the comparative real estate based on the transaction comparison method, and perform the analysis by comparing the target real estate with the investment value.
[0010] In the above, at least one processor can calculate the valuation data of the target real estate by multiplying the asking price, time value coefficient, commercial area value coefficient, favorable factor value coefficient, and location value coefficient of the comparison real estate.
[0011] In the above, if the input data for the target real estate includes data related to each value coefficient, at least one processor may change the weight for the corresponding value coefficient and apply it when calculating the value assessment data of the target real estate.
[0012] In the above, if the transaction for applying the transaction comparison method does not satisfy a preset criterion, at least one processor may use the closest transaction, but may adjust the weights for the value coefficients for calculating the valuation data.
[0013] In the above, if the transaction time of the transaction for applying the transaction comparison method is not within a preset time, at least one processor may use the most recent transaction and adjust the weights for the value coefficients for calculating the valuation data, wherein the time value coefficient among the value coefficients is adjusted the largest and the remaining value coefficients are adjusted to be smaller than the time value coefficient.
[0014] In the above, if the input data for the target real estate includes data unrelated to the value coefficients, at least one processor may generate a user value coefficient for the data unrelated to the value coefficients among the input data, generate a weight for the user value coefficient in relation to the value coefficients, and apply it when calculating the value assessment data of the target real estate.
[0015] In the above, at least one processor can convert the asking price value factor of the comparison property calculated above into a current sale price using a time value factor.
[0016] In the above, at least one processor can sequentially correct the value coefficient of the target real estate using the commercial area value coefficient, favorable factor value coefficient, and location value coefficient of the comparison real estate calculated above.
[0017] In the above, at least one processor may further include a plurality of databases that store data necessary for the valuation of the target real estate, and an interface that maps data extracted from the plurality of databases and performs data loading and conversion.
[0018] An artificial intelligence-based real estate valuation and analysis method according to an embodiment of the present invention may include the steps of: collecting and preprocessing big data regarding real estate; training an artificial intelligence model using the preprocessed data; receiving input data regarding a target real estate; selecting data necessary for valuation of the target real estate using the trained artificial intelligence model; analyzing the valuation and business feasibility of the target real estate based on the selected data; and automatically generating and providing a business plan for the target real estate based on the analysis results. However, at this time, a comparative real estate corresponding to the target real estate may be selected, and a value coefficient calculated using the selected data may be corrected based on the valuation results of the comparative real estate based on the comparable sales method, and the analysis may be performed by comparing the investment value with the target real estate.
[0019] Other aspects, features, and advantages other than those described above will become clear from the specific details, claims, and drawings for implementing the invention below.
[0020] In addition, these general and specific aspects may be implemented using a system, method, computer program, or any combination of a system, method, or computer program.
[0021] According to an exemplary embodiment of the present invention as described above, there is an effect of being able to provide reliable valuation and analysis services for a target real estate.
[0022] According to the present invention, in particular, buyers of small and medium-sized buildings can directly perform valuations from various perspectives reflecting market conditions and real-time information, without relying on real estate brokers and consultants.
[0023] In addition, according to the present invention, efficient and objective purchasing decisions become possible through the utilization of objective data and analysis with expertise. It has the effect of quickly resolving various complex variables that must be considered in real estate transactions through web or app services, and enabling users to directly conduct business feasibility reviews.
[0024] Of course, the scope of the present invention is not limited by these effects.
[0025] FIG. 1 is a block diagram schematically illustrating an artificial intelligence-based real estate valuation and analysis system according to an exemplary embodiment of the present invention.
[0026] Figure 2 is a configuration block diagram of the computing device of Figure 1.
[0027] FIGS. 3 to 5 are drawings illustrating a method for evaluating real estate value according to an embodiment of the present invention.
[0028] FIG. 6 is a drawing illustrating the provision of analysis result data for a target real estate property customized to the user according to an embodiment of the present invention.
[0029] FIGS. 7 to 13 are drawings illustrating a method for automatically generating a business plan according to an embodiment of the present invention.
[0030] The present invention is capable of various modifications and may have various embodiments; specific embodiments are illustrated in the drawings and described in detail in the detailed description. The effects and features of the present invention, and the methods for achieving them, will become clear by referring to the embodiments described below in detail together with the drawings. However, the present invention is not limited to the embodiments disclosed below but can be implemented in various forms.
[0031] In the following embodiments, terms such as first, second, etc. are used not in a limiting sense, but for the purpose of distinguishing one component from another component.
[0032] In the following examples, singular expressions include plural expressions unless the context clearly indicates otherwise.
[0033] In the following embodiments, terms such as "include" or "have" mean that the features or components described in the specification are present, and do not preclude the possibility that one or more other features or components may be added.
[0034] In the following embodiments, when a part such as a layer, region, or component is described as being on or above another part, it includes not only cases where it is directly on top of another part, but also cases where another region, component, etc. is interposed in between.
[0035] In the drawings, the size of components may be exaggerated or reduced for convenience of explanation. For example, the size and thickness of each component shown in the drawings are depicted arbitrarily for convenience of explanation, so the present invention is not necessarily limited to what is illustrated.
[0036] Where an embodiment can be implemented differently, a specific sequence of operations may be performed differently from the order described. For example, two steps described consecutively may be performed substantially simultaneously or proceed in the reverse order of the description.
[0037] In this specification, “A and / or B” indicates the case where it is A, B, or A and B. And, “at least one of A and B indicates the case where it is A, B, or A and B.”
[0038] The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the present invention, and the present invention is defined only by the scope of the claims.
[0039] The terms used in this invention are for describing the embodiments and are not intended to limit the invention. In this invention, the singular form may include the plural form unless specifically stated otherwise in the text. The terms “comprises” and / or “comprising” used in the disclosure do not exclude the presence or addition of one or more other components in addition to the mentioned components. Throughout the disclosure, the same reference numerals refer to the same components, and “and / or” may include each of the mentioned components and all combinations of one or more. Although terms such as “first,” “second,” etc., are used to describe various components, these components are not limited by these terms. These terms are used merely to distinguish one component from another. Therefore, the first component mentioned below may be the second component within the technical scope of the invention.
[0040] The word “exemplary” is used in the present invention with the meaning of “used as an example or illustration.” Any embodiment described as “exemplary” in the present invention should not be interpreted as being preferred or having an advantage over other embodiments.
[0041] Embodiments of the present invention may be described in terms of functions or blocks performing functions. A block, which may be referred to as a “part” or “module” of the present invention, may be physically implemented by analog or digital circuits such as logic gates, integrated circuits, microprocessors, microcontrollers, memory, passive electronic components, active electronic components, optical components, hardwired circuits, etc., and may optionally be driven by firmware and software. Additionally, the term “part” as used in the disclosure refers to a hardware element such as software, FPGA, or ASIC, and the “part” may perform certain roles. However, the meaning of “part” is not limited to software or hardware. The “part” may be configured to reside in an addressable storage medium or may be configured to run one or more processors. Accordingly, as an example, a “part” may include elements such as software elements, object-oriented software elements, class elements, and task elements, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within the elements and “parts” may be combined into a smaller number of elements and “parts” or further separated into additional elements and “parts.”
[0042] Embodiments of the present invention may be implemented using at least one software program running on at least one hardware device and may perform network management functions to control elements.
[0043] Spatially relative terms such as “below,” “beneath,” “lower,” “above,” and “upper” may be used to facilitate the description of the relationship between one component and other components as illustrated in the drawings. Spatially relative terms should be understood as encompassing different orientations of components during use or operation, in addition to the orientations depicted in the drawings. For example, if a component depicted in a drawing is inverted, a component described as being “below” or “beneath” of another component may be placed “above” of that other component. Therefore, the exemplary term “below” may encompass both the lower and upper directions. Components may also be oriented in other directions, and accordingly, spatially relative terms may be interpreted according to the orientation.
[0044] Unless otherwise defined, all terms used in this invention (including technical and scientific terms) may be used in a meaning commonly understood by those skilled in the art to which this invention pertains. Furthermore, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise.
[0045] In this specification, the term "device according to the present invention" includes various devices capable of performing computational processing and providing results to a user. For example, the device according to the present invention may include a computer, a server device, and a portable terminal, or may take the form of any one of these.
[0046] Here, the computer may include, for example, a laptop, desktop, laptop, tablet PC, slate PC, smartphone, etc. equipped with a web browser.
[0047] In the above, the server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, a web server, etc.
[0048] The above portable terminal may include, for example, a wireless communication device that ensures portability and mobility, all kinds of handheld-based wireless communication devices such as smartphones, and wearable devices such as watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted devices (HMDs).
[0049] The artificial intelligence-related functions according to the present invention are operated through a processor and memory. The processor may be composed of one or more processing units. In this case, the one or more processing units may be general-purpose processors such as a CPU (Central Processing Unit), AP (Application Processor), DSP (Digital Signal Processor), graphics-dedicated processors such as a GPU (Graphic Processing Unit) or VPU (Vision Processing Unit), or artificial intelligence-dedicated processors such as an NPU (Neutral Processing Unit). In the above, the one or more processing units control the processing of input data according to predefined operation rules or artificial intelligence models stored in memory. Alternatively, if the one or more processing units are artificial intelligence-dedicated processing units, they may be designed with a hardware structure specialized for processing a specific artificial intelligence model.
[0050] Predefined behavioral rules or artificial intelligence models can be created through learning. Here, being created through learning means that a basic artificial intelligence model is trained using multiple learning data by a learning algorithm, thereby creating predefined behavioral rules or an artificial intelligence model configured to perform a desired characteristic (or objective). Such learning may be performed on the device itself where the artificial intelligence according to the present invention is executed, or it may be performed through a separate server and / or system. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the aforementioned examples.
[0051] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values and performs neural network operations through operations between the results of previous layers and the multiple weights. The multiple weights possessed by the multiple neural network layers can be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model during the learning process is reduced or minimized. Artificial neural networks may include deep neural networks (DNNs), such as Convolutional Neural Networks (CNNs), Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs), Restricted Boltzmann Machines (RBMs), Deep Belief Networks (DBNs), Bidirectional Recurrent Deep Neural Networks (BRDNNs), or Deep Q-Networks, but are not limited to the examples mentioned above.
[0052] According to an exemplary embodiment of the present invention, a processor can implement artificial intelligence. Methodologies of artificial intelligence can be classified according to the learning method into supervised learning, where input data and output data are provided together as training data and the solution (output data) to the problem (input data) is determined; unsupervised learning, where only input data is provided without output data and the solution (output data) to the problem (input data) is not determined; and reinforcement learning, where a reward is given from an external environment whenever an action is taken in the current state, and learning proceeds in a direction that maximizes such reward. In addition, methodologies of artificial intelligence may be classified according to the architecture, which is the structure of the learning model. The architectures of widely used deep learning technologies can be classified into Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Transformers, and Generative Adversarial Networks (GAN).
[0053] According to an exemplary embodiment of the present invention, the processor comprises a Convolutional Neural Network (CNN) such as GoogleNet, AlexNet, VGG Network, Region with Convolutional Neural Network (R-CNN), Region Proposal Network (RPN), Recurrent Neural Network (RNN), Stacking-based Deep Neural Network (S-DNN), State-Space Dynamic Neural Network (S-SDNN), Deconvolution Network, Deep Belief Network (DBN), Restructured Boltzmann Machine (RBM), Fully Convolutional Network, Long Short-Term Memory (LSTM) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT, SP-BERT, MRC / QA, Text Analysis, Dialog System, GPT-3, GPT-4 for natural language processing, Visual Analytics, Visual Understanding, Video Synthesis for vision processing, Anomaly Detection, Prediction, Time-Series Forecasting, Optimization, Recommendation for ResNet data intelligence, Various artificial intelligence structures and algorithms, such as data creation, may be used, but are not limited thereto.
[0054] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. When describing with reference to the drawings, identical or corresponding components are given the same reference numerals, and redundant descriptions thereof will be omitted.
[0055] Meanwhile, in this specification, the term "real estate" is a concept that includes land subject to valuation and its fixtures. Here, fixtures may include buildings. Meanwhile, a building may belong to the land or be treated as an individual piece of real estate. Therefore, when the term "real estate" is used hereinafter, it may refer to land or a building depending on the user's input. Meanwhile, such real estate is not necessarily limited to residential or commercial use.
[0056] FIG. 1 is a block diagram schematically illustrating an artificial intelligence-based real estate valuation and analysis system (1) according to an exemplary embodiment of the present invention. FIG. 2 is a block diagram of the configuration of a computing device (20) of FIG. 1.
[0057] The value of real estate, including small and medium-sized buildings, can vary significantly depending on factors such as location, structure, position, and use. However, the value of real estate calculated through appraisal fails to reflect rapid market changes and is therefore not utilized as its actual value. Accordingly, this invention aims to present a model capable of automatic real-time valuation of a target property by analyzing big data related to real estate valuation factors, such as commercial areas, public data, real estate policies, and development plans, in order to enable valuations that reflect market changes.
[0058] However, when simply utilizing big data that can be collected online, such as from real estate platforms, or offline, such as from markets, inaccurate information such as fake news or fictitious figures is included, errors are inevitable in the accurate valuation of the target property and in the business feasibility analysis results based on such valuation. These errors ultimately reduce the accuracy of the real estate valuation and can further affect its reliability. Accordingly, the present invention aims to improve the accuracy and reliability of the valuation by selecting data from various big data related to real estate valuation and enabling the valuation of the target property to be performed based on the selected data. Meanwhile, the above-mentioned data selection may be performed individually, for example, depending on the time of the valuation request or the target property.
[0059] As illustrated in FIG. 1, an artificial intelligence-based real estate valuation and analysis system (1) according to one embodiment of the present invention may include a terminal (10) and a computing device (20). In this case, the artificial intelligence-based real estate valuation and analysis system (1) may be configured to further include an external device (30) depending on the embodiment.
[0060] The terminal (10) can access the artificial intelligence-based real estate valuation and analysis platform provided by the computing device (20) and request valuation and analysis of the target real estate.
[0061] The terminal (10) may be in the form of a fixed terminal such as a TV or PC, or a mobile terminal such as a smartphone, tablet PC, or laptop. Alternatively, the terminal (10) may be in the form of a wearable device capable of communicating with the aforementioned terminal type. Alternatively, the terminal (10) may be a terminal dedicated to the artificial intelligence-based real estate valuation and analysis platform according to the present invention.
[0062] The terminal (10) may include, be embedded in, or be connected to various input / output devices to output a user interface provided through an artificial intelligence-based real estate valuation and analysis platform or to input data through said user interface.
[0063] The computing device (20) may provide the aforementioned artificial intelligence-based real estate valuation and analysis platform and, when the terminal (10) connects, provide a user interface created to receive various data, such as target real estate.
[0064] For convenience, the AI-based real estate valuation and analysis platform in the present invention is exemplified as being provided in the form of a web service, but the present invention is not limited thereto. For example, the AI-based real estate valuation and analysis platform may be provided in the form of a web application.
[0065] When the computing device (20) receives data input regarding the target real estate from the terminal (10), it can generate AI-based real estate valuation and analysis data for the target real estate based on the input and provide it to the terminal (10). At this time, the AI-based valuation and analysis data provided may be provided as result data in the form of a business plan as described later.
[0066] Depending on the embodiment, the computing device (20) may be called by various names such as computer, server, controller, control unit, etc.
[0067] In FIG. 1, the external device (30) may be a database (DB) that provides real estate data collected by the computing device (20) for artificial intelligence-based real estate value assessment and analysis. However, the present invention is not limited thereto. For example, the external device (30) may represent multiple DB servers rather than a single DB server, and in this case, such DB servers may include DB servers provided by public institutions.
[0068] The computing device (20) can collect real estate data by communicating with an external device (30) on a regular or irregular basis. At this time, the computing device (20) may selectively select data to collect based on whether the artificial intelligence model has been updated, the time of the previous update, etc., and proceed with the collection process.
[0069] In FIG. 1, for convenience, only one terminal (10) is shown, but there may be multiple terminals. If requests for real estate value assessment and analysis for the same target real estate are received from multiple terminals within a predefined time range, the computing device (20) may form a temporary group of the multiple terminals based on the target real estate and process them together. At this time, the processing of the target real estate may be performed differently from other cases, for example, by considering it as a real estate of high interest to the user, and by performing the process for calculating coefficients for real estate value assessment, and deriving real estate value assessment and analysis results, which will be described later.
[0070] Meanwhile, when multiple terminals are connected to the AI-based real estate valuation and analysis platform, the computing device (20) may provide different results for requests from registered terminals and unregistered terminals, and from terminals using paid services and terminals using free services. In this case, different results may refer, for example, to differences in the accuracy or reliability of result data, or differences in the amount of result data. Additionally, the computing device (20) may not include registered terminals and unregistered terminals, or / and terminals using paid services and terminals using free services, among the multiple terminals in the same group. This may be the case even if terminals under different conditions make requests for valuation and analysis of the same target real estate.
[0071] If requests for real estate valuation and analysis for the same target real estate are received from multiple terminals within a predefined time range, the computing device (20) generates standard valuation and analysis result data for the said real estate, and in addition, even if requests for valuation and analysis for the same target real estate are made, if the needs or items of interest determined from the input data of each terminal are different, individual valuation and analysis result data in which weights for the corresponding needs or items of interest are reflected in the standard valuation may be provided together.
[0072] Meanwhile, the term "same target real estate" in the above description may refer to land or a building. Alternatively, the real estate may be grouped and processed as the same target real estate even if the form or type of the real estate is different, such as when one of the multiple terminals requests land at the same address and another terminal requests a building at the same address.
[0073] Referring to FIG. 2, a computing device (20) according to an embodiment of the present invention may include a receiver (210), a preprocessor (220), a processor (230), a memory (240), etc. In this case, depending on the embodiment, the receiver (210), the preprocessor (220), and the memory (240) may all be included and referred to as a processor. Alternatively, depending on the embodiment, the remaining components excluding the memory (240) in the configuration of FIG. 2 may all be included and referred to as a processor.
[0074] The receiving unit (210) can exchange data with the outside by providing a wired or wireless communication environment. Here, the outside may include a terminal (10), an external device (30), etc.
[0075] The receiving unit (210) can receive input data regarding the target real estate from the terminal (10). At this time, the input data may include at least one of information regarding the target real estate, information regarding a request for valuation and analysis of the target real estate, and information regarding a part of the target real estate of interest.
[0076] The receiving unit (210) can receive (collect) training data for learning an artificial intelligence model for real estate value assessment and analysis from an external device (30).
[0077] The preprocessing unit (220) can preprocess the training data received (collected) through the receiving unit (210).
[0078] The processor (230) can perform a valuation and analysis process for real estate based on the data preprocessed in the preprocessing unit (220).
[0079] The memory (240) can store data such as models, programs, etc., for real estate valuation and analysis, including artificial intelligence learning models.
[0080] The memory (2400) can temporarily store data received (collected) from the outside through the receiving unit (210), data processed by the processor (230), etc.
[0081] FIGS. 3 to 5 are drawings illustrating a method for evaluating real estate value according to an embodiment of the present invention.
[0082] FIG. 3 is a block diagram of a real estate valuation module (30), FIG. 4 is a diagram illustrating the operation of the valuation engine (330) of FIG. 3, and FIG. 5 is a flowchart illustrating a real estate valuation method.
[0083] Meanwhile, the real estate valuation module (30) of FIG. 3 may be included, for example, within the processor (230) of the computing device (20) of FIG. 2, or separately from the processor (230) of the computing device (20).
[0084] First, referring to FIG. 3, the real estate valuation module (30) may be configured to include a database (310), an interface (320), a valuation engine (330), a data generation unit (340), etc.
[0085] The database (310) may include various data (big data) related to real estate valuation. Such data may include, for example, officially assessed land prices, actual transaction prices, online sales prices, and highest and lowest sales prices. Such data may include, for example, commercial area analysis data (small business owners / NICE). Such data may include, for example, urban renewal project data (residential land / transportation / industrial complex). Such data may include, for example, individual location information (building register / land and forest register).
[0086] The interface (320) may include a data mapping unit that receives and maps data from a database (310), a data loader for efficient data loading for a valuation engine (330), and a data conversion unit that converts the data into a data format for a valuation engine (330).
[0087] The valuation engine (330) may include an algorithm that performs valuation operations on a target real estate by including a plurality of modules. These modules may include at least two of a comparison case selection module, a time value analysis module, a commercial area value analysis module, a favorable factor value analysis module, a location value analysis module, an investment indicator analysis module, a selection module, etc. Some of the plurality of modules may be used only partially or all of them depending on the real estate selected by the selection module or the real estate being valued.
[0088] The output value of each of the above modules may be named as a value coefficient. That is, at least two modules or each module included in the valuation engine (330) may receive corresponding data stored in the database (310), analyze it, and derive a value coefficient suitable for the target real estate, and the value coefficient derived in this way may be provided or recommended in the form of valuation result data of the target real estate.
[0089] The data generation unit (340) can generate and output result data for real estate valued through the valuation engine (330). The output may be performed directly to the terminal (10).
[0090] FIG. 4 discloses the specific operation process of the valuation engine (330) of FIG. 3.
[0091] Referring to FIGS. 3 and 4, the valuation engine (330) can receive information about the target real estate from the processor (230). Here, the information about the target real estate may include, for example, at least one of address data, industry data, etc. of the target real estate.
[0092] The valuation engine (330) searches for comparative cases based on input information regarding the target real estate. The selection module included in the valuation engine (330) can search for comparative cases based on the input information. Meanwhile, the selection module can search for comparative cases by further referring to data such as the officially assessed land price, actual transaction price, online sale price, and highest and lowest sale prices from the database (310) of FIG. 3. The selection module selects comparative cases based on the input information and data mentioned above, and can calculate and output the sale price of the comparative real estate corresponding to the selected comparative case as a value coefficient.
[0093] The time value analysis module within the valuation engine (330) can receive information on self-fluctuation rate / inflation rate from the database (310) of FIG. 3 and calculate and output a time value coefficient.
[0094] The commercial area value analysis module, favorable factor value analysis module, and location value analysis module within the valuation engine (330) can each receive input information regarding the target real estate and receive related data from the database (310) of Fig. 3 to calculate and output value coefficients.
[0095] For example, the commercial value analysis module can receive information regarding commercial area change indicators, market size, floating population, industry suitability, industry sales growth rate, number of competing stores, vacancy rate, transaction turnover rate, investment / operation return rate, etc. from the database (310) of FIG. 3 and calculate and output a commercial value coefficient.
[0096] For example, the favorable value analysis module can receive information regarding the project promotion stage, land development information, transportation network development information, industrial complex development information, etc. from the database (310) of FIG. 3 and calculate and output a favorable value coefficient.
[0097] For example, the location value analysis module can receive information regarding street conditions, access conditions, environmental conditions, plot conditions, administrative conditions, building register, land and forest register, etc. from the database (310) of FIG. 3 and calculate and output a location value coefficient.
[0098] The investment indicator analysis module included in the valuation engine (330) can receive each of the aforementioned value coefficients, analyze the investment indicators for the target real estate, and generate analysis result data. Based on the analysis result data generated in this way, the valuation engine (330) can generate and provide a valuation recommendation opinion for the target real estate.
[0099] The investment indicator analysis module may analyze investment indicators for the target real estate using all input value coefficients, or it may select only some of the above value coefficients and analyze investment indicators using only the selected value coefficients.
[0100] Conversely, the investment indicator analysis module may determine and select the necessary value coefficient based on input information regarding the target real estate, and request the calculation and provision of the value coefficient only from the module(s) corresponding to the selected value coefficient. In relation to the above selection, the valuation engine (330) may determine and select the necessary value coefficient by referring to information regarding a comparative real estate selected as a comparative case for the target real estate through the selection module.
[0101] FIG. 5 is illustrated to explain the operation of a valuation engine (330) according to an embodiment of the present invention, but the present invention is not limited thereto.
[0102] Referring to FIG. 5, the valuation engine (330) can select a comparison property based on input information about the target property and obtain a sale price for the selected comparison property (S110).
[0103] The valuation engine (330) can convert the sale price of the comparison real estate obtained in the above S110 operation to a local time point (S120).
[0104] The valuation engine (330) can first correct the value coefficient by reflecting commercial area analysis data (S130).
[0105] The valuation engine (330) can make a second correction to the value coefficient by reflecting development favorable data (S140).
[0106] The valuation engine (330) can adjust the value coefficient three times by reflecting individual location data (S150).
[0107] The valuation engine (330) can obtain comparison data by comparing the investment value of the target real estate and the comparison real estate based on the corrected value coefficient (S160).
[0108] The valuation engine (330) can provide a recommendation service including the sale price and sale opinion for the target real estate by synthesizing the valuation results (S170).
[0109] In the above-described FIG. 5, only one or two of the operations S130 to S150 may be performed. The operations S130 to S150 may be performed in parallel with each other. The order of the operations S130 to S150 may be different from that shown.
[0110] As described in FIGS. 3 to 5 above, the valuation engine (330) can calculate and recommend a sale price for the final target real estate by correcting the value coefficient, and the following mathematical formula 1 can be used.
[0111]
[0112] In the above mathematical formula 1, V represents the final sale price (recommended) of the subject property, Vc represents the asking price of the comparison property, Xt represents the calculated time value coefficient, Xr represents the calculated commercial value coefficient, Xi represents the calculated favorable factor value coefficient, and Xb represents the calculated location value coefficient. For example, based on the above mathematical formula 1, if the asking price (Vc) of the comparison property is 35 billion won, the calculated time value coefficient (Xt) is 1.00962, the calculated commercial value coefficient (Xr) is 1.00, the calculated favorable factor value coefficient (Xi) is 1.035, and the calculated location value coefficient (Xb) is 0.9913, the final sale price (recommended) (V) of the subject property can be derived as 36.2 billion won.
[0113] A computing device (20) according to an embodiment of the present invention is an electronic device comprising at least one processor and a memory in which a computer program executed by the at least one processor is stored. The at least one processor is configured to collect and preprocess big data regarding real estate, learn an artificial intelligence model using the preprocessed data, and when input data regarding a target real estate is received, select data necessary for valuation of the target real estate using the learned artificial intelligence model, analyze the valuation and business feasibility of the target real estate based on the selected data, and automatically generate and provide a business plan for the target real estate based on the analysis results. The at least one processor can select a comparative real estate corresponding to the target real estate, perform a correction on the value coefficient calculated using the selected data based on the valuation results of the comparative real estate based on the transaction comparison method, and perform the analysis by comparing the target real estate with the investment value.
[0114] In the above, at least one processor can calculate the valuation data of the target real estate by multiplying the asking price, time value coefficient, commercial area value coefficient, favorable factor value coefficient, and location value coefficient of the comparison real estate.
[0115] In the above, if the input data for the target real estate includes data related to each value coefficient, at least one processor may change the weight for the corresponding value coefficient and apply it when calculating the value assessment data of the target real estate.
[0116] In the above, if the transaction for applying the transaction comparison method does not satisfy a preset criterion, at least one processor may use the closest transaction, but may adjust the weights for the value coefficients for calculating the valuation data.
[0117] In the above, if the transaction time of the transaction for applying the transaction comparison method is not within a preset time, at least one processor may use the most recent transaction and adjust the weights for the value coefficients for calculating the valuation data, wherein the time value coefficient among the value coefficients is adjusted the largest and the remaining value coefficients are adjusted to be smaller than the time value coefficient.
[0118] In the above, if the input data for the target real estate includes data unrelated to the value coefficients, at least one processor may generate a user value coefficient for the data unrelated to the value coefficients among the input data, generate a weight for the user value coefficient in relation to the value coefficients, and apply it when calculating the value assessment data of the target real estate.
[0119] In the above, at least one processor can convert the asking price value factor of the comparison property calculated above into a current sale price using a time value factor.
[0120] In the above, at least one processor can sequentially correct the value coefficient of the target real estate using the commercial area value coefficient, favorable factor value coefficient, and location value coefficient of the comparison real estate calculated above.
[0121] In the above, at least one processor may further include a plurality of databases that store data necessary for the valuation of the target real estate, and an interface that maps data extracted from the plurality of databases and performs data loading and conversion.
[0122] An artificial intelligence-based real estate valuation and analysis method according to an embodiment of the present invention may include the steps of: collecting and preprocessing big data regarding real estate; training an artificial intelligence model using the preprocessed data; receiving input data regarding a target real estate; selecting data necessary for valuation of the target real estate using the trained artificial intelligence model; analyzing the valuation and business feasibility of the target real estate based on the selected data; and automatically generating and providing a business plan for the target real estate based on the analysis results. However, at this time, a comparative real estate corresponding to the target real estate may be selected, and a value coefficient calculated using the selected data may be corrected based on the valuation results of the comparative real estate based on the comparable sales method, and the analysis may be performed by comparing the investment value with the target real estate.
[0123] The data selection and processing technology in the aforementioned processor (230) is described as follows.
[0124] The processor (230) can manage the update cycle to maintain the latest status of each data type. This update cycle is automatically determined and updates are performed, but if an error occurs, it is desirable to send a notification message requesting manual update processing to an administrator terminal (not shown).
[0125] In the processor (230), the Net Operating Income (NOI) value is determined as an outlier, and the method and numerical range criteria can be calculated and displayed based on, for example, NOI = rent / exclusive area (pyeong) of a rental case in the current system. At this time, data stored in an external device is crawled and calculated as NOI and displayed, and based on the data stored in the external device, the user can select an appropriate NOI by individual judgment and utilize it by excluding false listings or inaccurate calculation values with errors.
[0126] The algorithm for deriving the calculated value can filter data by region, floor, size, year, and amount within a 5km radius of the request site from an external device, and calculate and display NOI in ascending order, for example. It can also automatically input appropriate data from the automatically calculated values into the plan to be described later.
[0127] In addition to the aforementioned data, building shops stored in memory (240) (only values directly verified with property data are registered) may be displayed together with or individually with the aforementioned data.
[0128] Furthermore, the NOC within the building shop is calculated based on the formula NOC = Rent / Exclusive Area (pyeong), but weights can be assigned based on region, floor, building age, and condition to automatically calculate the appropriate rent range for the property.
[0129] It may be desirable for the processor (230) to reflect the degree of change in the market in real time.
[0130] For example, the processor (230) can collect and synchronize public data APIs or real estate platform data in real time.
[0131] Meanwhile, the processor (230) uses an algorithm to detect market changes, and to do this, it can crawl data from various external devices and use figures such as the status of permits and completions, vacancy rates, and rental price indices as supporting data.
[0132] The processor (230) can provide a notification message when there is a sudden change in transaction volume by analyzing the number of actual transactions within a radius of 2 km, for example, by analyzing the number of actual transactions within a periodic period (monthly, quarterly, semi-annually, annually, etc.) based on the lot number being analyzed for business feasibility through a process of analyzing actual transaction data used when searching for items for sale.
[0133] The processor (230) can also provide analysis result data for the target property customized to the user, as illustrated in FIG. 6 (a) and (b).
[0134] The processor (230) can calculate the rate of return by utilizing, for example, expected rent, construction costs, management costs, etc., and to do this, it can directly input the values or, if there are values automatically calculated according to a formula, calculate the rate of return and future asset value, etc. as shown below and provide them in a customized manner.
[0135] The real estate purchase amount can be entered directly, and the total project cost can be calculated based on the unit price per pyeong designated by experts registered on the platform in advance, such as land costs, construction costs, and financing costs, and the sum of these can be reflected as the total project cost. The loan amount can be entered as the loan (debt) amount for the real estate purchase and value-up process. The lease deposit and annual income can be reflected as amounts derived from the appropriate NOC calculation value * developable area based on the analysis of surrounding rental and sales cases. The rate of return can be calculated as “annual income / (total project cost - lease deposit)”, and the future asset value can be calculated from the expected annual income / expected rental yield.
[0136] The processor (230) can also provide visual information analysis and prediction services using image data.
[0137] The processor (230) can analyze the building's exterior condition and reflect its value (Visual Condition Assessment), for example, by analyzing the building's exterior image using an artificial intelligence model (e.g., CNN-based) to quantify the building's condition (e.g., age, degree of damage, etc.) and reflect it in the value assessment.
[0138] To this end, the processor (230) can analyze a photo of a real estate (building) uploaded by a terminal (user) (10) and evaluate the appearance condition into a score within a preset score range (e.g., 0 to 100).
[0139] And the processor (230) can adjust the valuation based on the building condition score (e.g., depreciation applied to old buildings, premium applied to newly built buildings).
[0140] Additionally, the processor (230) can further convert features extracted from image data (e.g., exterior materials, window condition, presence of parking facilities, etc.) into text data and reflect them in the value assessment.
[0141] The processor (230) can, for example, analyze the exterior wall cracks, paint condition, and window cleanliness condition in a photo of an officetel in Gangnam-gu, Seoul uploaded by a terminal (user) (10) using an artificial intelligence model to assess the degree of deterioration as 20%, and based on this, apply a 5% depreciation factor to the real estate value of the building.
[0142] The processor (230) can also perform environmental contextual analysis, and can analyze image data of the surrounding environment of the building (e.g., roads, green spaces, commercial facilities, etc.) to refer to location analysis and value assessment.
[0143] To this end, the processor (230) can quantify road width, traffic accessibility, green space ratio, surrounding building density, etc., using an artificial intelligence (e.g., CNN-based) model that analyzes satellite photos and street view images, and can apply additional weights to real estate value based on the results analyzed by the artificial intelligence model (e.g., applying a premium if road accessibility is good, deducting points if green space is lacking).
[0144] The processor (230) can also generate future development simulations and renderings. When a terminal (user) (10) inputs a specific development plan, it can automatically generate an expected rendering of the development after it is completed and provide a visual simulation.
[0145] To this end, the processor (230) can render the building exterior and surrounding environment after development based on, for example, Stable Diffusion and GAN (Generative Adversarial Network), and the terminal (user) (10) can input the building size, type of exterior material, color, etc. to generate a 3D simulation and an expected bird's-eye view through an artificial intelligence model, and can also provide visual data integrated with existing building data by linking with SketchUp or Rhino, etc.
[0146] The processor (230) can, for example, generate a 12-story commercial building rendering on a given plot through an artificial intelligence model according to a development plan based on plot conditions (e.g., floor area ratio, building coverage ratio, etc.) entered by the terminal (user) (10), and the result is provided as a 3D rendering, and can also analyze the estimated rent and construction costs.
[0147] The processor (230) can also provide an image-based property matching service, which can recommend building and property data with similar appearances based on building photos uploaded by the terminal (user) (10).
[0148] To this end, the processor (230) can apply a CNN-based image feature extraction model (ResNet, EfficientNet, etc.) to the image search engine, automatically search and recommend properties in the database that have a similar architectural style, age, and exterior condition to the uploaded building photo, and can provide the expected value and business feasibility analysis results of each building together with the recommendation results.
[0149] The processor (230) can recommend, for example, 10 properties with a style and age similar to the building uploaded as an image (photo) by the terminal (user) (10), and can also provide the rental yield and estimated maintenance costs for each property.
[0150] In addition, the processor (230) may provide an image-based visual trend prediction service, which can predict changes in building condition and market price fluctuations over time by utilizing photos of the building's exterior and past image data.
[0151] To this end, the processor (230) can use an LSTM + CNN combined model that learns state changes along the time axis by collecting past satellite and building photo data, and can predict future expected market prices and when maintenance is needed by combining the rate of change in building state with market data.
[0152] The processor (230) may, for example, analyze satellite images to analyze the rate of reduction in green space and the rate of improvement in the road network for a specific area, and based on this, predict the expected rate of increase in the sale price of the area.
[0153] Next, in the present invention, after performing a value assessment and analysis on a target real estate property, the result data can be returned to a terminal (10). At this time, the returned result data can be named a business plan, and in the present invention, when a target real estate property is selected and a value assessment and analysis is requested at the terminal (10), a business plan can be automatically generated and provided to the terminal (10).
[0154] The processor (230) can perform the following actions in relation to the automatic creation of a business plan.
[0155] The processor (230) can check public data (up-to-date information) by searching for information (e.g., parcels) about the target real estate, as illustrated in FIGS. 7 and 8.
[0156] In relation to the above information search, the processor (230) may search by lot number and building name, select a land by clicking directly on a map, and select multiple land parcels with multiple lot numbers.
[0157] The processor (230) can also check public data regarding the land, buildings, commercial areas, locations, etc. of the selected plot, and it is desirable to set the public data to be automatically updated on a regular or irregular basis so that the latest information is always obtained and provided.
[0158] The processor (230) can store an image of a real estate property as shown in FIG. 9.
[0159] The terminal (10) can directly upload a photo corresponding to the address on the platform provided by the processor (230) or save a desired image through the street view capture function.
[0160] The processor (230) can store rental / sale cases as illustrated in FIG. 10 so that comparison cases can be selected later.
[0161] The processor (230) can check a list of real estate listings around the corresponding lot number (e.g., a desired radius can be set), and when providing the list, it can filter the list so that only objective listings are displayed by automatically calculating the NOC value and deleting fictitious data that exceeds the standard NOC value of the area (pre-reflected by area). In this case, it is also possible for the user to make a direct selection.
[0162] The processor (230) can store location information as illustrated in FIG. 11. For example, the processor (230) can automatically display and provide location information such as subways, buses, supermarkets, apartments, schools, public institutions, etc., around the address (e.g., a desired radius can be set). This information can be displayed and provided so that the user can select the information they want.
[0163] The processor (230) can automatically generate a business plan as shown in FIGS. 12 and 13 through the above-mentioned operation. At this time, the processor (230) can automatically calculate the building coverage ratio, floor area ratio, building area, above-ground / underground total floor area, possible number of floors, etc. of a building to be newly constructed according to the selected plot (e.g., multiple plots can be selected).
[0164] In addition, the processor (230) can calculate and provide information on the expected rental yield by automatically reflecting appropriate rent and management fees, etc., in the selected rental / sale case.
[0165] And the processor (230) can analyze and provide the construction period, business costs, etc. by reflecting the opinions of experts (registered in advance on the platform and located closest to the target property) and market conditions.
[0166] In addition, the processor (230) can provide a service that allows the user to easily calculate the rental yield and future asset value (appropriate sale price) after final development.
[0167] At least one of the user interfaces (610, 620, 700, 800, 900, 1000, 1100, 1200, 1300) disclosed in FIGS. 6 to 13 described above may be provided to a terminal (10) on a platform.
[0168] As described above, an apparatus, method, and system for providing valuation and analysis services for a target real estate have been disclosed, but the present invention is not limited thereto.
[0169] The present invention has been described with reference to the embodiments illustrated in the drawings, but this is merely illustrative, and those skilled in the art will understand that various modifications and equivalent alternative embodiments are possible therefrom. Accordingly, the true technical scope of protection of the present invention should be determined by the technical spirit of the appended claims.
Claims
1. At least one processor; and An electronic device comprising a memory in which a computer program executed by at least one processor is stored, The above-mentioned at least one processor is, It is configured to collect and preprocess big data regarding real estate, train an artificial intelligence model using the preprocessed data, and upon receiving input data regarding a target real estate, select data necessary for the valuation of the target real estate using the trained artificial intelligence model, analyze the valuation and business feasibility of the target real estate based on the selected data, and automatically generate and provide a business plan for the target real estate based on the analysis results. The above-mentioned at least one processor is, Select a comparable property corresponding to the above-mentioned target property, perform a correction on the value coefficient previously calculated using the above-mentioned selected data based on the valuation results of the above-mentioned comparable property according to the sales comparison method, and perform the above-mentioned analysis by comparing the investment value with the above-mentioned target property. The above-mentioned at least one processor is, When requests for real estate valuation and analysis for the same target property are received from multiple terminals within a predefined time range, The above plurality of terminals form a temporary group based on the target real estate, and Generate standard valuation and analysis result data for the above-mentioned subject real estate, If the needs or items of interest determined from the input data of each terminal belonging to the above temporary group are different, individual value assessment and analysis result data reflecting the weights for the corresponding needs or items of interest in the above standard value assessment are provided together, and The above-mentioned same real estate indicates a case where at least one of the land or the building matches, and Among the plurality of terminals mentioned above, only the terminal that has been pre-registered to the electronic device or has subscribed to a paid service belongs to the temporary group, and The above-mentioned at least one processor is, Check the list of real estate listings based on input data for the above-mentioned target real estate, automatically calculate the NOC value, filter out false real estate listings that exceed the standard NOC value of the corresponding area based on the input data for the above-mentioned target real estate, and provide the list of real estate listings for selection. The above-mentioned at least one processor is, Provides real estate exterior condition analysis and value reflection data based on image data including at least one of a building, the surrounding environment of the building, a satellite photo of the building, and a street view image of the building among the input data for the above-mentioned target real estate, wherein Based on the above image data, the image of the target property is analyzed to evaluate and quantify the exterior condition into a score within a preset range, and The above quantified evaluation score is adjusted according to the real estate condition score, and Features extracted from the above image data are converted into text data and reflected in the above evaluation, and Provides an image-based market price fluctuation prediction service based on the above image data, Predicting changes in building condition and market price fluctuations over time based on the exterior images and historical image data of the aforementioned real estate, and predicting future expected market prices and the timing of maintenance requirements by combining the rate of change in building condition and market data, Electronic device.
2. In Paragraph 1, The above-mentioned at least one processor is, Calculating the valuation data of the above-mentioned target real estate by multiplying the asking price, time value coefficient, commercial area value coefficient, favorable factor value coefficient, and location value coefficient of the above-mentioned comparative real estate, Electronic device.
3. In Paragraph 2, The above-mentioned at least one processor is, If the input data for the above-mentioned subject property includes data related to each of the above-mentioned value coefficients, the weights for the corresponding value coefficients are changed and applied when calculating the valuation data of the above-mentioned subject property. Electronic device.
4. In Paragraph 2, The above-mentioned at least one processor is, If the transaction for applying the above transaction comparison method does not satisfy the pre-set criteria, the closest transaction is used, but the weights for the value coefficients for calculating the above valuation data are adjusted. Electronic device.
5. In Paragraph 2, The above-mentioned at least one processor is, If the transaction time of the transaction for the application of the above comparable sales method is not within a pre-set time, the most recent transaction shall be used, but the weights for the value coefficients for calculating the above valuation data shall be adjusted, Correcting the time value coefficient most significantly among the above value coefficients, and correcting the remaining value coefficients to be smaller than the above time value coefficient, Electronic device.
6. In Paragraph 2, The above-mentioned at least one processor is, If the input data for the above-mentioned subject property includes data unrelated to the above-mentioned value coefficients, a user value coefficient is generated for the data unrelated to the above-mentioned value coefficients among the input data, and a weight is generated for the user value coefficient in relation to the above-mentioned value coefficients and applied when calculating the value assessment data of the above-mentioned subject property. Electronic device.
7. In Paragraph 2, The above-mentioned at least one processor is, Converting the asking price value coefficient of the comparison property calculated above into a current sale price using a time value coefficient, Electronic device.
8. In Paragraph 2, The above-mentioned at least one processor is, Sequentially adjusting the value coefficients of the subject property using the commercial area value coefficient, favorable factor value coefficient, and location value coefficient of the comparative property calculated above, Electronic device.
9. In Paragraph 3, The above-mentioned at least one processor is, A plurality of databases storing data necessary for the valuation of the aforementioned subject real estate, and Further including an interface for mapping data extracted from the aforementioned plurality of databases and for data loading and conversion, Electronic device.
10. Performed by a computer, A step of collecting and preprocessing big data on real estate; A step of training an artificial intelligence model using preprocessed data; Step of receiving input data for the target property; A step of selecting data necessary for the valuation of the target real estate using the above-mentioned trained artificial intelligence model; A step of analyzing the valuation and business feasibility of the target real estate based on the selected data above; and The method includes the step of automatically generating and providing a business plan for the target real estate based on the above analysis results, Select a comparable property corresponding to the above-mentioned target property, perform a correction on the value coefficient previously calculated using the above-mentioned selected data based on the valuation results of the above-mentioned comparable property according to the sales comparison method, and perform the above-mentioned analysis by comparing the investment value with the above-mentioned target property. When requests for real estate valuation and analysis regarding the same target property are received from multiple terminals within a predefined time range, the multiple terminals are formed into a temporary group based on the target property, and standard valuation and analysis result data for the target property are generated; however, if the needs or items of interest determined from the input data of each terminal belonging to the temporary group are different, individual valuation and analysis result data in which weights for the corresponding needs or items of interest are reflected in the standard valuation are provided together. The above-mentioned same real estate indicates a case where at least one of the land or the building matches, and Among the plurality of terminals mentioned above, only the terminal that has been pre-registered to the electronic device or has subscribed to a paid service belongs to the temporary group, and Check the list of real estate listings based on input data for the above-mentioned target real estate, automatically calculate the NOC value, filter out false real estate listings that exceed the standard NOC value of the corresponding area based on the input data for the above-mentioned target real estate, and provide the list of real estate listings for selection. Data for analyzing the exterior condition of a property and reflecting its value is provided based on image data including at least one of a building, the surrounding environment of the building, a satellite photograph of the building, and a street view image of the building among the input data for the above-mentioned target property, wherein the image of the target property is analyzed based on the image data to evaluate and quantify the exterior condition into a score within a preset range, the quantified evaluation score is adjusted according to the property condition score, and features extracted from the image data are converted into text data and reflected in the evaluation. Provides an image-based market price fluctuation prediction service based on the above image data, Predicting changes in building condition and market price fluctuations over time based on the exterior images and historical image data of the aforementioned real estate, and predicting future expected market prices and the timing of maintenance requirements by combining the rate of change in building condition and market data, Artificial intelligence-based real estate valuation and analysis method.