Automatic recommendation system for rental composition and space utilization concepts

Abstract

The present invention relates to an information processing system using a computer, and more specifically, to an automatic recommendation system for lease configuration and space utilization concepts that supports a user's investment decision-making by collecting and analyzing real estate-related data to evaluate the commercial value of a specific property and automatically recommending lease configurations and space utilization plans optimized thereto.

Description

Technology Field

[0001] The present invention relates to an information processing system using a computer, and more specifically, to an automatic recommendation system for lease configuration and space utilization concepts that supports a user's investment decision-making by collecting and analyzing real estate-related data to evaluate the commercial value of a specific property and automatically recommending lease configurations and space utilization plans optimized thereto. Background Technology

[0002] Recently, as the importance of data-driven decision-making in the real estate investment and development sector has increased, various information provision systems are being utilized.

[0003] Conventional real estate information systems had limitations in that they were limited to providing fragmentary data, such as basic physical information like the location, area, and price of a specific property, or lists of surrounding transportation and amenities. These systems merely listed fragmented information to users and failed to organically synthesize this data to quantitatively evaluate the commercial potential or business value of the location. Consequently, users had to judge investment value based on scattered data and rely on their subjective experience or intuition, which carried the potential for errors in judgment.

[0004] Furthermore, while general business feasibility analysis software provides a function to calculate the expected rate of return when users directly input projected sales, rent, and investment costs, it had a problem in that it completely failed to consider the specific locational characteristics of the property under analysis or the surrounding commercial environment. In other words, even though actual profitability can vary significantly depending on the potential of the location and the characteristics of surrounding customers, the software failed to organically integrate these external environmental variables into the analysis model.

[0005] In conclusion, conventional technologies had clear limitations in providing comprehensive and objective answers regarding specific business plans optimized for the unique characteristics of a particular property—specifically, how to combine different business types and utilize space to maximize profits—because physical real estate information and business feasibility analysis functions were disconnected. The problem to be solved

[0006] The present invention was devised to solve the problems of the prior art described above, and its main purpose is to provide a system and method that automatically recommend the optimal lease configuration and space utilization concept for a specific property by organically combining and analyzing physical information of real estate, external commercial environment data, and characteristics of potential customers.

[0007] Another objective of the present invention is to enhance the reliability of investment decision-making by minimizing the user's subjective judgment and providing data-based objective analysis results.

[0008] Another objective of the present invention is to support users in constructing a stable and efficient optimal investment portfolio by going beyond simply evaluating the suitability of a single industry and comprehensively evaluating the 'risk-adjusted profitability' for various scenarios combining multiple industries.

[0009] A system according to one embodiment of the present invention for solving the above-mentioned problem is characterized by sequentially performing a first analysis step (process 1) for evaluating the fundamental commercial value of the location of the property itself, a second analysis step (process 2) for analyzing the lifestyle of potential customers through the residential environment surrounding the property and evaluating the suitability with the industry based thereon, a third analysis step (process 3) for determining the overall suitability of a specific single industry by synthesizing the results of the first and second analysis steps, and a fourth analysis step (process 4) for recommending an optimal investment plan by evaluating risk-adjusted profitability for a scenario combining the determined multiple industries.

[0010] The problems of the present invention are not limited to those mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below. means of solving the problem

[0012] In an automatic recommendation system for lease configuration and space utilization concepts according to an embodiment of the present invention for solving the above problem,

[0013] User terminal unit; and

[0014] It is connected to communicate with the above user terminal unit, and

[0015] An information receiving module configured to receive basic information of the property to be analyzed from the above-mentioned user terminal unit;

[0016] An external data collection module configured to collect commercial area data and residential environment data surrounding the above-mentioned property from external sources;

[0017] One or more processors configured to perform: a first analysis evaluating the commercial potential of the location of the property itself based on the collected commercial area data; a second analysis evaluating the degree of compatibility between a specific business type and the profile of potential customers surrounding the property based on the collected residential environment data; and a third analysis determining the overall suitability of the specific business type by synthesizing the results of the first analysis and the second analysis; and

[0018] A server unit including a result providing module configured to transmit and display the above analysis results to the user terminal unit; and

[0019] The above server unit is,

[0020] It further includes a commercial area potential analysis module configured to evaluate the commercial potential based on judgment criteria including a visibility coefficient indicating the degree to which the above-mentioned property is exposed to potential customers, an accessibility score indicating the ease with which the above-mentioned potential customers can reach the above-mentioned property, a number of pedestrians indicating the size of the potential market passing around the above-mentioned property, a competition density evaluating the market saturation around the above-mentioned property, and a mutual growth density evaluating market opportunities around the above-mentioned property.

[0021] The above commercial area potential analysis module is,

[0022] The unique physical value of the above property is calculated by combining the above visibility coefficient and the above accessibility score;

[0023] The above physical value is reflected in the above pedestrian traffic, and if the above pedestrian traffic exceeds a preset threshold value, the growth rate of the result is adjusted to become gradual;

[0024] It is characterized by being configured to calculate a commercial area structure index representing a structural advantage of opportunity relative to competition, based on the ratio of dividing the above-mentioned mutual growth density by the above-mentioned competition density.

[0025] The above server unit is,

[0026] It further includes a residential environment and demographic analysis module configured to evaluate the degree of compatibility based on judgment criteria including residential building types representing the physical form of residential buildings distributed around the aforementioned property, the dominant residential form which is the residential building type with the highest proportion within the said area, resident statistics including the average age and number of people per household in the said area, and industry-lifestyle compatibility representing the degree of alignment between the target customer base of the said specific industry and the lifestyle profile of the said area.

[0027] The above residential environment and demographic analysis module is,

[0028] Collect building information surrounding the above-mentioned property, classify it by the above-mentioned residential building types, and calculate the size of each type;

[0029] Based on the above classification results and resident statistics, the lifestyle profile of the area is determined as one of 'youth / single-person household-centered', 'middle-aged / family unit-centered', or 'office worker-centered living area';

[0030] It is characterized by being configured to calculate the degree of compatibility by evaluating the correlation between the target customer characteristics of the aforementioned specific industry and the aforementioned determined lifestyle profile, and

[0031] The above server unit is,

[0032] It may further include an industry suitability determination module configured to determine the overall suitability of the specific industry by applying the degree of suitability evaluated in the second analysis as a weight, based on the commercial potential evaluated in the first analysis. Effects of the invention

[0034] According to the present invention, through a multi-layered analysis process involving the physical value of the location, the opportunity structure of the commercial area, the lifestyle of potential customers, the financial characteristics of the industry, and portfolio risk management, the analysis of real estate business feasibility, which relied on the subjective experience of users, is transformed into a data-based, objective, and systematic analysis, thereby significantly reducing the possibility of errors in investment decision-making.

[0035] By utilizing the 'Commercial Area Structure Index,' which evaluates the structural advantage of mutual growth density relative to competition density, and the 'Residential Environment Suitability Index,' which infers the lifestyle patterns of potential customers based on housing types, it is possible to quantitatively identify 'hidden niche markets' or 'potential opportunity sectors' that conventional systems failed to discover.

[0036] By creatively applying portfolio theory from financial engineering to the problem of real estate lease composition, it is possible to identify the most stable and efficient optimal combination of sectors—that is, the highest expected net return per unit of risk—rather than simply the scenario with the highest total expected return. This significantly contributes to protecting investors' assets and securing long-term return stability.

[0037] By providing a dynamic simulation environment where users can change industry combinations and areas in real time and immediately verify changes in investment results, it supports an interactive decision-making process that goes beyond passive information reception to actively explore optimal solutions, thereby maximizing user satisfaction and analytical efficiency.

[0038] The effects according to the present invention are not limited to those exemplified above, and a wider variety of effects are included within the present invention. Brief explanation of the drawing

[0040] Figure 1 illustrates an overall relationship diagram according to the present invention. Figure 2 illustrates a flowchart between all components according to the present invention. Figure 3 illustrates a flowchart of the commercial area potential analysis process according to the present invention. Figure 4 illustrates a flowchart of a residential environment-based suitability analysis process according to the present invention. Figure 5 illustrates a flowchart of the industry suitability determination process according to the present invention. Figure 6 illustrates a flowchart of a scenario profitability evaluation process according to the present invention. Specific details for implementing the invention

[0041] Hereinafter, various embodiments are described in more detail with reference to the attached drawings. The embodiments described in this specification may be modified in various ways. Specific embodiments may be depicted in the drawings and described in detail in the detailed description. However, specific embodiments disclosed in the attached drawings are intended only to facilitate understanding of various embodiments. Accordingly, the technical concept is not limited by specific embodiments disclosed in the attached drawings, and it should be understood that it includes all equivalents or substitutions that fall within the spirit and scope of the invention.

[0042] Terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but these components are not limited by the aforementioned terms. The aforementioned terms are used solely for the purpose of distinguishing one component from another.

[0043] Functions related to artificial intelligence according to the present disclosure are operated through a processor and memory. The processor may be composed of one or more processors. In this case, the one or more processors may be general-purpose processors such as CPUs, APs, and DSPs (Digital Signal Processors), graphics-dedicated processors such as GPUs and VPUs (Vision Processing Units), or artificial intelligence-dedicated processors such as NPUs. The one or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in memory. Alternatively, if the one or more processors are artificial intelligence-dedicated processors, the artificial intelligence-dedicated processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0044] The predefined rules of operation or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that a basic artificial intelligence model is trained using a number of training data by a learning algorithm, thereby creating predefined rules of operation or artificial intelligence models configured to perform desired characteristics (or objectives). Such learning may be performed on the device itself where the artificial intelligence according to the present disclosure 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 examples described above.

[0045] An artificial intelligence model can be composed of multiple neural network layers. Each of the multiple neural network layers has multiple nodes and weight values, and performs neural network operations through calculations 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, multiple weights can be updated so that the loss value or cost value obtained by the artificial intelligence model during the learning process is reduced or minimized. Additionally, to minimize the loss value or cost value, multiple weights can be updated in a direction that minimizes the gradient associated with the loss value or cost value. 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.

[0046] A network is a network that serves as a transmission path for web pages; it may be a closed network such as a LAN (Local Area Network) or WAN (Wide Area Network), but it is desirable for it to be an open network such as the Internet. The Internet refers to a global open computer network structure that provides the TCP / IP protocol and various services existing at its upper layers, namely HTTP (HyperText Transfer Protocol), Telnet, FTP (File Transfer Protocol), DNS (Domain Name System), SMTP (Simple Mail Transfer Protocol), SNMP (Simple Network Management Protocol), NFS (Network File Service), and NIS (Network Information Service).

[0047] Terminals can be implemented in various forms. For example, the terminals described in this specification may include mobile terminals such as smartphones, tablet PCs, PDAs, portable multimedia players, and MP3 players, as well as fixed terminals such as smart TVs and desktop computers.

[0048] In this specification, terms such as “comprising” or “having” are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. When a component is described as being “connected” or “connected” to another component, it should be understood that it may be directly connected to or connected to that other component, or that there may be other components in between. On the other hand, when a component is described as being “directly connected” or “directly connected” to another component, it should be understood that there are no other components in between.

[0049] Meanwhile, a "module" or "part" for a component as used in this specification performs at least one function or operation. Furthermore, a "module" or "part" may perform a function or operation by hardware, software, or a combination of hardware and software. Additionally, a plurality of "modules" or a plurality of "parts," excluding a "module" or "part" that must be performed on specific hardware or on at least one processor, may be integrated into at least one module. A singular expression includes a plural expression unless the context clearly indicates otherwise.

[0050] In addition, power, power transmission, and control therefor for the following assembly configurations and embodiments, including "by control," follow conventional technology including terminals, applications, hardware control modules, etc., so they are omitted to avoid redundancy.

[0051] In addition, the operation embodiments and configurations described in a general manner without being explained in detail below follow the prior art and are omitted in order to focus on describing the purpose of the present invention and the resulting effects.

[0052] Furthermore, in describing the present invention, if it is determined that a detailed description of related known functions or configurations may unnecessarily obscure the essence of the invention, such detailed description is abbreviated or omitted.

[0053] The system for implementing the present invention is largely composed of a user terminal unit (100) that performs the role of a user interface, a server unit (200) that processes major operations and analysis, and a database unit (400) that permanently stores and manages all data. The server unit (200) is equipped with a plurality of software modules subdivided by function to perform the major analysis process of the present invention and operates organically.

[0054] The above user terminal unit (100) is a physical hardware device directly operated by a user accessing the system of the present invention, and includes a personal computer, a smartphone, a tablet, etc. The above user terminal unit (100) provides a user interface for communicating with a server unit (200) through a web browser or a dedicated application, and the user inputs basic information such as the address of a property to be analyzed through the user interface, configures a business combination scenario, and visually checks the analysis results provided by the system. In addition, the analysis request information entered by the user is transmitted to the server unit (200) through an encrypted communication protocol, and conversely, the final analysis results are received from the server unit (200) and displayed on the screen.

[0055] The server unit (200) is a central processing system that executes all analysis and computation processes of the present invention and may be composed of one or more physical server computers. The server unit (200) is the entity that carries all software modules described below and controls their operation. When it receives a request from the user terminal unit (100), it drives the embedded modules sequentially or in parallel to perform tasks such as data processing, analysis, and evaluation. In addition, it controls the data flow between each module, manages data input and output with the database unit (400), and exchanges data with an external API server through an external data collection module (220).

[0056] The information receiving module (210) included in the server unit (200) performs the role of a gateway for the server unit (200), receives and standardizes the initial analysis request from the user terminal unit (100). The information receiving module (210) verifies the validity of the received data and performs the role of, for example, converting address text into latitude and longitude coordinates or standardizing the input area unit into square meters, and receives analysis request data from the user terminal unit (100) and transmits the standardized data to subsequent analysis modules.

[0057] The external data collection module (220) is a module that collects external environmental data required for system analysis in real time or periodically. The external data collection module (220) automatically collects information such as floating population, surrounding business information, public transportation information, and building information based on specific coordinates by linking with predefined external information sources, such as the government public data portal, private map service API, and telecommunications company commercial area analysis API. The module transmits parameters such as location coordinates required for analysis to an external API server and receives data in JSON or XML format as a result. The received data is either directly transmitted to another module for real-time analysis or stored in a database unit (400) for reuse.

[0058] The above commercial area potential analysis module (280) is a module that performs Process 1 of the present invention and evaluates the fundamental commercial potential of a specific location itself to calculate a commercial area potential index (CPI). The above commercial area potential analysis module (280) quantifies the intrinsic value of the location by synthesizing the visibility, accessibility, pedestrian traffic, and density of competitive and mutually beneficial business sectors of the property, and receives physical characteristic information of the property from the information receiving module (210) and commercial area data from the external data collection module (220), respectively. The finally calculated CPI value is transmitted to the business sector suitability determination module (290).

[0059] The above residential environment and demographic analysis module (300) is a module that performs process 2 of the present invention, analyzes the residential environment around the property to derive a lifestyle profile of potential customers, and evaluates the degree of compatibility with a specific industry based on this to calculate a residential environment suitability index (RESI). The above residential environment and demographic analysis module (300) analyzes the distribution of residential building types to determine the dominant residential form of the region, evaluates the degree of compatibility between the lifestyle inferred therefrom and the target customer base of the industry to be analyzed, and receives residential building and demographic data from an external data collection module (220). The calculated RESI value is transmitted to the industry suitability determination module (290) and used as correction data to increase the analysis accuracy of the module.

[0060] The above-mentioned industry suitability determination module (290) is a module that performs process 3 of the present invention and calculates an industry suitability score (ISS) by making a final determination of how comprehensively a specific single industry is suitable for the location. The above-mentioned industry suitability determination module (290) calculates a final score by comprehensively considering the value of the location (CPI), compatibility with customers (RESI), basic profitability of the industry, and specific competitive risk, and receives the CPI from the commercial area potential analysis module (280) and the RESI from the residential environment and demographic analysis module (300). In addition, it retrieves data such as average sales by industry and market rent prices from the database unit (400) and transmits the calculated ISS value to the scenario profitability evaluation module (310) or the result provision module (270).

[0061] The above-mentioned scenario generation module (250) is a module that automatically generates an optimal lease configuration scenario to be recommended to the user by the system based on the analysis results. The above-mentioned scenario generation module (250) combines the industries that obtained the highest scores among the multiple industry-specific ISS scores received from the industry-specific suitability determination module (290) into 2 to 3 recommended scenarios according to predefined rules, and transmits the recommended scenario information generated by receiving the industry-specific ISS score list from the industry-specific suitability determination module (290) to the result provision module (270).

[0062] The simulation module (260) is a module that controls a real-time simulation environment in which a user can directly change the industry combination and area and predict investment results. When a scenario change event occurs in the user terminal unit (100), the simulation module (260) immediately detects it, transmits the changed scenario information to the scenario profitability evaluation module (310), and requests recalculation. The module receives modified scenario configuration data from the user terminal unit (100) and transmits it to the scenario profitability evaluation module (310), and receives the recalculated SPI value from the module to update the screen of the user terminal unit (100) in real time through the result provision module (270).

[0063] The above-mentioned risk analysis module (320) is a specialized module that professionally calculates the financial stability, i.e., the integrated risk, of a specific scenario. Based on modern portfolio theory, the above-mentioned risk analysis module (320) calculates the integrated risk of the entire scenario by comprehensively considering the unique sales volatility and investment weight of each industry included in the scenario, receives scenario configuration information from the scenario profitability evaluation module (310), and retrieves sales volatility data for each industry from the database unit (400). The calculated integrated risk value is returned to the scenario profitability evaluation module (310).

[0064] The above-mentioned scenario profitability evaluation module (310) is a module that performs process 4 of the present invention and evaluates the final investment attractiveness of a specific investment scenario to calculate the Scenario Profitability Index (SPI). The above-mentioned scenario profitability evaluation module (310) quantifies the value of the expected net profit per unit risk by combining the total expected profit of the scenario, the total initial investment cost, and the integrated risk received from the risk analysis module (320), and receives the ISS score of each industry from the industry suitability determination module (290) and scenario configuration information from the simulation module (260). In addition, it exchanges integrated risk data with the risk analysis module (320) and transmits the final calculated SPI value to the result provision module (270).

[0065] The result providing module (270) is a module that processes and visualizes complex numerical data generated from all analysis modules into a form (report, chart, grade, etc.) that is easy for the user to understand, and finally provides it. The result providing module (270) converts various indices into scores and grades, generates comparison charts by scenario, and combines final text-based recommendation opinions to generate a single completed report data. The module receives the final output from each analysis module and transmits the processed report data to the user terminal unit (100).

[0066] The above database unit (400) is a data storage system that permanently stores and manages all structured and unstructured data necessary for the operation of the system of the present invention, and may be configured by combining relational databases, NoSQL databases, etc. The above database unit (400) processes data storage and retrieval requests from each module of the server unit (200), maintains data integrity, and performs tasks such as indexing for efficient searching. The above database unit (400) exchanges data with each module of the server unit (200) through SQL queries or other database protocols, and the stored data includes user account information, property listing information, commercial area data collected from the outside, statistical data by industry, and logs of past analysis results.

[0067] Hereinafter, for each analysis process of the present invention, the definition and purpose of the judgment criteria, the logical processing procedure, the method of acquiring data, the method of utilizing the results, the specific processing procedure, the method of ensuring reliability, the comparison with prior art, the objectivity of the judgment rules, the effect of adoption, and the definition of terms will be explained in detail.

[0068] The commercial area potential analysis process according to the present invention aims to objectively evaluate the fundamental commercial value of the location itself where the subject property is situated. To this end, key physical and environmental factors that influence the likelihood of success of a location, regardless of the industry, are defined as judgment criteria. These criteria include a visibility coefficient, which is a physical indicator representing how easily a property is exposed to potential customers; an accessibility score, which is an indicator representing how easily potential customers can reach the property; a number of pedestrians, which represents the absolute size of the potential market passing around the property; a competition density, which evaluates the degree of market saturation, or "red ocean"; and a mutual growth density, which evaluates the potential for market opportunities, or "blue ocean" possibilities.

[0069] The aforementioned judgment criteria are not merely listed but are processed according to an organic logical procedure to produce a single integrated index. This logical procedure includes, firstly, a step of calculating the inherent physical value of the property by synthesizing the visibility coefficient and accessibility score; this corresponds to the fundamental strength of the real estate itself, independent of the external environment. Secondly, it includes a step of considering market size by reflecting the number of pedestrians in the physical potential, while adjusting the growth rate of the result to be moderate so that the influence is not excessively reflected when the number of pedestrians exceeds a certain level. This serves as a technical basis reflecting the reality that a location with 10,000 pedestrians cannot be simply evaluated as being 10 times better than one with 1,000. Thirdly, to evaluate the qualitative structure of the commercial district, a ratio-based 'Commercial District Structure Index' is calculated by dividing the density of coexistence by the density of competition. This is intended to assess the 'structural advantage of opportunity relative to competition,' going beyond the mere presence or absence of competitors; this ratio-based approach enables the objective comparison of potential regardless of the absolute size of the commercial district. In the fourth step, the intermediate values ​​calculated in the first, second, and third steps are combined to finally calculate the Commercial Area Potential Index (CPI), a single indicator representing the potential of the location.

[0070] The data for the above judgment criteria is obtained through an external data collection module and a database unit. The visibility coefficient (V) is entered by a system administrator or user checking the location of the property on a map and selecting one of the predefined types, for example, 'main road corner (2.0)', 'main road (1.5)', 'side road corner (1.2)', 'side road (1.0)', 'basement / 2nd floor or higher (0.7)', and for example, if it is a corner location, V=2.0 is obtained. The accessibility score (A) is linked with the Ministry of Land, Infrastructure and Transport Bus Information System or the subway public data API to automatically count the number of bus stops and subway station exits within a radius of 100 meters based on the property coordinates, and for example, if there are 2 bus stops and 1 subway exit, A=3 is obtained. The number of people in the area (P_f) is obtained by acquiring average pedestrian traffic data for specific days and times through the commercial area analysis API of an affiliated private telecommunications company; for example, P_f=1500 is obtained based on 1,500 people per hour at 2 PM on weekdays. The competition and coexistence density (C_d, C_s) is obtained by utilizing the place search API of an external map service to automatically count the number of businesses by industry category within a radius of 200 meters; for example, the total number of potential competitors such as restaurants, cafes, and bars is obtained as C_d=35, and the total number of potential coexistence businesses such as bookstores, movie theaters, and offices is obtained as C_s=10.

[0071] The Commercial Area Potential Index (CPI) finally calculated through the above process is used as an objective comparison indicator that allows users to compare the location values ​​of various properties under consideration using the same standard, and is also directly transmitted as foundational data reflecting the fundamental value of the location in subsequent process 3 to improve the accuracy of industry matching analysis.

[0072] The processing procedure of this process can be described using a specific scenario, for example, where a user requests an analysis of 'Property A (located in Seongbuk-gu, situated on a main road corner)', as follows. In the first step, the information acquisition stage, the system acquires data with V=2.0, A=3, P_f=1500, C_d=35, and C_s=10 as described above. In the second step, the physical potential calculation stage, the system combines V=2.0 and A=3 to calculate a first median value that reflects the excellent physical conditions of Property A. In the third step, the market activity correction stage, the system calculates a second median value with the growth rate corrected to stably reflect the high floating population of P_f=1500. In the fourth step, the commercial district structure index calculation stage, the system compares C_s=10 and C_d=35 to calculate a third median value that reflects the structural characteristics of a commercial district where competition is somewhat fierce but there is also potential for mutual growth. In the fifth step, the final index derivation stage, the system organically combines the first, second, and third intermediate values ​​calculated above to derive the final CPI of 'Property A' as a quantitative value such as '75.8 points'.

[0073] To ensure the reliability of the logic of this process, if specific data cannot be obtained due to a failure in external API integration, the system includes an exception handling step that requests the user to manually enter the value or automatically supplements it with alternative statistical data, such as the average value of the relevant administrative district. Additionally, to prevent calculation errors where the denominator becomes zero in the case of a new commercial district with a competition density of zero, the system includes a step of adding a default value of 1 to all density calculations. To guarantee the timeliness of the data, the external data collection module also includes a step of automatically updating commercial district data according to a set cycle and specifying the last update date of the data to the user.

[0074] The present invention is compared with the prior art as follows. In a scenario analyzing the above-mentioned 'Property A', the prior art simple information provision system provides the user with five pieces of individual information simply listed as 'corner location, 3 nearby bus stops, pedestrian traffic of 1,500 people / hour, 35 nearby competitors, and 10 nearby partner companies'. In this case, the user must make a subjective judgment based on this scattered information, such as "competition is fierce, but it seems okay because there is a lot of pedestrian traffic," and the basis for this judgment is ambiguous and the possibility of error is high. However, the present invention organically integrates the above information to provide a single, objective judgment result of a commercial area potential index of 75.8 points (B+ grade). In particular, by quantitatively reflecting the fact that the competition density is 3.5 times higher than the coexistence density in the 'commercial area structure index', the system automatically interprets and clearly presents to the user that "the advantage of high pedestrian traffic is partially offset by the disadvantage of overheated competition."

[0075] The judgment rules defined in this process systematically decompose the success factors of real estate investment and reconstruct them into logical relationships that can be processed by a computer. In particular, defining competitive density and mutual growth density as a single 'ratio' rather than independent variables to form a 'Commercial District Structure Index' is an inevitable configuration for evaluating the potential of a commercial district. While simply subtracting the number of competing business types leads to distortion depending on the absolute size of the commercial district, using a ratio allows for the objective evaluation of the structural advantage of opportunity relative to competition, regardless of the district's scale; this is an inevitable logical conclusion for assessing the qualitative essence of a commercial district.

[0076] By adopting the components and judgment rules of this process, judgments based on users' subjective experience or intuition are excluded, and consistent, objective location evaluation results based on data are provided, thereby significantly reducing the possibility of errors in investment decisions. Furthermore, through the 'Commercial Area Structure Index,' it is possible to quantitatively discover locations that appear highly competitive but actually possess high potential due to numerous hidden factors for mutual growth. Additionally, by enabling the comparison of multiple properties located in different regions using the same CPI metric, it supports users in efficiently selecting the properties with the highest potential within a limited timeframe.

[0077] As used in this specification, the 'Commercial Potential Index (CPI)' refers to a normalized score ranging from 0 to 100 points representing the overall commercial potential of a specific location, calculated through Process 1 of the present invention. The system may assign grades to the CPI score according to pre-set intervals; for example, a score of 90 or higher is defined as 'Grade A (Top-tier location highly suitable for investment)', a score of 70 or higher but less than 90 as 'Grade B (Excellent location suitable for investment)', a score of 50 or higher but less than 70 as 'Grade C (Average location requiring careful review)', and a score of less than 50 as 'Grade D (Location likely to be unsuitable for investment)', thereby providing the user with intuitive judgment criteria. Here, terms such as 'highly suitable' or 'high' are clearly interpreted based on the defined grade or score intervals.

[0078] The residential environment-based suitability analysis process according to the present invention aims to define potential customer profiles in depth around the property subject to analysis. This step goes beyond the quantitative concept of simply "a large population" and answers the qualitative question, "What kind of lifestyle patterns do people with?" To this end, objective resident statistics—such as the type of residential building (the physical form of residential buildings distributed around the property), the dominant housing type occupying the highest proportion within a specific area, the average age of the area, and the number of people per household—are defined as judgment criteria for most objectively inferring the lifestyle of potential customers. Additionally, an industry-lifestyle fit is defined, which indicates the degree of alignment between the primary target customer base of a specific industry and the derived lifestyle profile of the area.

[0079] This process consists of a logical procedure that infers the lifestyle of potential customers from residential environment data and matches it with an industry. The logical procedure includes, in the first step, a step of classifying building information obtained through the building register and map information API by residential type and calculating the total number of households or gross floor area of ​​each type to create a database; in the second step, a step of determining the dominant residential form of the region based on the database and supplementing it with resident statistical data to categorize the region's lifestyle profile into categories such as 'youth / single-person household-centered,' 'middle-aged / family unit-centered,' and 'office living area centered on office workers'; in the third step, a step of evaluating the correlation between the target customer characteristics of a specific industry to be analyzed and the regional lifestyle profile determined in the second step; and in the fourth step, a step of quantifying the results of the suitability evaluation to finally calculate the Residential Environment Suitability Index (RESI), which is a single indicator representing the suitability between a specific industry and the corresponding residential environment.

[0080] The data for the above judgment criteria is obtained by the residential data analysis module. The type and size of residential buildings are linked with the Government 24 Building Register data API to obtain the building uses and total number of households within a 500-meter radius of the property; for example, within the radius, 1,500 apartment households, 450 multi-family / studio villa households, and 800 officetel households are obtained. Resident statistics are obtained through the Statistics Korea Population and Housing Census microdata API to acquire data on the population distribution by age group and the average number of people per household for the relevant administrative district; for example, the proportion of the population in their 20s in the relevant administrative district is obtained as 45%, and the average number of household members is 1.8.

[0081] The Residential Environment Suitability Index (RESI) finally calculated through the above process is not used independently, but is organically linked with subsequent processes to improve the analysis accuracy of the entire system. That is, the RESI is passed to Process 3 and used as a key correction value to determine how deeply the relevant business type fits the commercial area, which enables 'people'-centered qualitative analysis beyond simple financial analysis.

[0082] The processing procedure of this process can be described using a specific scenario, for example, where a user requests an analysis for opening a 'study cafe' at 'Property B (near a university)' as follows. In the first step, the data identification and classification stage, the system collects information on residential buildings surrounding Property B and classifies them into 850 units of multi-family / studio villas, 300 units of officetels, and 150 units of small apartments. In the second step, the dominant housing type determination stage, since the proportion of multi-family / studio villas exceeds a threshold (e.g., 60%), the area is determined to be a 'region centered on young adults / single-person households'. In the third step, the lifestyle profile matching stage, based on the above determination result, the system determines that the area strongly matches a lifestyle profile characterized by 'academic / job preparation', 'preference for studying in cafes', and 'emphasis on personal space'. In the fourth step, the compatibility evaluation stage, the 'study cafe', the business type under analysis, is evaluated as having a very high degree of compatibility with all characteristics of the aforementioned profile. In the fifth step, the final index calculation step, based on the above high conformity evaluation result, the RESI for 'Study Cafe' is calculated as a high value such as '88.5 points', and this result is passed to process 3.

[0083] To ensure the reliability of the logic in this process, the system includes an exception handling step in which, when a specific housing type does not hold a clear dominance and is distributed in a complex manner, it determines the area as a 'mixed living zone' and generates a profile by weighting and averaging lifestyle characteristics according to the proportion of each housing type. Additionally, if a significant discrepancy is found between the number of households in the building register and the household count data from Statistics Korea, the system includes a step to prioritize the more recent data or display a warning message to the user to encourage a manual review.

[0084] The present invention is compared with the prior art as follows. In a scenario analyzing the opening of a 'study cafe' at 'Property C' located between an apartment complex and a university, the simple demographic analysis of the prior art merely concludes that the population in their 20s and 40s is similarly large among the total population surrounding Property C. Based solely on this information, it is very ambiguous to judge the potential for success of the study cafe, and users may reach a confusing conclusion. However, Process 2 of the present invention analyzes the residential type to identify that the location is closer to the 'daily movement patterns of apartment residents.' Therefore, it determines that the influence of the 'middle-aged / family unit' profile is greater and calculates a relatively low RESI score for the 'study cafe,' such as '45.2 points.' This has the effect of clearly warning against the risk of incorrect decision-making by analyzing the influence of the actual living area rather than the simple sum of population numbers.

[0085] This process systematically implements the fundamental marketing principle that "the success of a specific industry is closely linked to the lifestyle patterns of the local residents." In particular, going beyond merely listing demographics, the logical connection step that infers the abstract concept of potential customers' "lifestyles" from objective and unchanging physical data regarding "housing types" is a key component of this invention; this is an essential analytical procedure for evaluating the fundamental alignment between the industry and the customers.

[0086] By adopting the components and judgment rules of this process, it goes beyond simple demographic analysis to predict the lifestyle patterns and consumption trends of potential customers, thereby dramatically improving the accuracy and persuasiveness of business recommendations. Furthermore, it significantly reduces the risk of investment failure by preventing "mismatch" errors—where a business is selected despite a favorable commercial location that does not align with the characteristics of the actual residents. Additionally, the lifestyle profiles derived by the system can serve as supporting data for establishing specific strategies regarding which customers to target and what marketing measures to implement upon future business opening.

[0087] As used in this specification, the 'Residential Environment Suitability Index (RESI)' refers to a normalized score ranging from 0 to 100, calculated through Process 2 of the present invention, indicating how well a specific industry aligns with the residential environment and lifestyle profile of the area. 'Dominant Housing Type' refers to a case where the proportion of households occupied by a single housing type within a specific analysis radius exceeds a pre-set threshold (e.g., 60%). 'RESI Grade' intuitively expresses the degree of suitability based on the RESI score; for example, a score of 85 or higher is defined as 'Grade A (Lifestyle very strongly aligns),' a score of 70 or higher but less than 85 as 'Grade B (Considerably aligns),' a score of 50 or higher but less than 70 as 'Grade C (Lack of distinct association),' and a score of less than 50 as 'Grade D (Lifestyle not aligns),' and is used as a standard for applying weights in the following process.

[0088] The process for determining industry suitability according to the present invention aims to make a final determination of how economically and strategically a specific single industry is suitable for a given location by synthesizing the potential of the location and the characteristics of the customers analyzed in the preceding steps. This is a step that answers the question, "Is it really reasonable to run 'this industry' on this good land, targeting these people?" and defines, as criteria for judgment, the Commercial Area Potential Index (CPI) calculated in Process 1, the Residential Environment Suitability Index (RESI) calculated in Process 2, a basic profitability indicator that compares the average revenue generation ability of the industry with the burden of fixed costs, and a specific competitive risk that evaluates the difficulty of securing market share.

[0089] This process consists of a logical procedure that organically integrates the results of preceding processes and adds new judgment criteria to derive a final score. The aforementioned logical procedure includes, in the first step, a step of receiving CPI from Process 1 and RESI from Process 2 as input and utilizing them as basic data for analysis; this is a key technical component that ensures the analysis of the present invention is not fragmentary but inherits both macroscopic environmental and microscopic customer analysis. In the second step, a 'basic profitability indicator' is calculated by comparing the average sales revenue by industry with the average rent of the region; this systematically implements the principle of break-even point analysis, which is the most fundamental aspect of all business analysis, and thus possesses technical necessity. In the third step, a 'specific competitive risk' is calculated to adjust the aforementioned 'basic profitability indicator,' but the adjustment is made so that the negative impact on the profitability indicator increases non-linearly as the number of competitors increases; this has a technical basis for systematically reflecting the law of diminishing marginal returns due to market saturation. In the fourth step, the RESI derived in Process 2 is applied as a weight to the above-mentioned adjusted profitability indicators. This serves to lower the final score for industries that appear financially sound but do not align with actual customer lifestyle patterns, and conversely, raise it in the opposite case. In the fifth step, all the above analysis results are comprehensively reflected in the CPI, which is the fundamental value of the location, to finally calculate the Industry Suitability Score (ISS), which represents the overall attractiveness of the industry.

[0090] The data for the above judgment criteria is obtained by directly receiving CPI and RESI internally from preceding processes, while basic profitability-related data and specific competitive risk are obtained through the system's database unit and external map service APIs. Average sales by industry are utilized from the system's industry database unit, which is built based on statistics from the National Tax Service, and average regional rent is obtained by linking with rental trend survey data from the Korea Real Estate Institute. Specific competitive risk is obtained by automatically counting the number of businesses in the same category as the analyzed industry within a radius of 200 meters through an external map service API.

[0091] The Industry Suitability Score (ISS) finally calculated through the above process is used to recommend the most suitable industry ranking by comparing the ISS scores of various candidate industries when a user is considering which industry would be best for a specific property, and is also used as basic data for the final scenario analysis of combining multiple industries in process 4.

[0092] The processing procedure of this process can be described using a specific scenario, for example, the case where the final decision is made to open a 'study cafe' at 'Property B (near a university)', as follows. In the first step, the base data acquisition stage, the system receives CPI = 78.0 points from Process 1 and RESI = 88.5 points from Process 2. In the second step, the financial feasibility review stage, a positive basic profitability indicator is calculated by comparing the monthly average sales per m² of the 'study cafe' (35,000 won) with the rent in the area (25,000 won). In the third step, the competitive environment adjustment stage, the above basic profitability indicator is slightly lowered by reflecting the 'specific competitive risk' where there are three businesses of the same type in the vicinity. In the fourth step, the qualitative fit weighting application stage, the RESI score (88.5 points, Grade A) is applied with a high weight to the above-adjusted profitability indicator to adjust the score upward again. In the fifth step, the final score calculation stage, all the above analysis results are combined based on the fundamental value of the location, CPI (78.0 points), to calculate the final ISS of the 'study cafe' as a very high value, such as '85.2 points (Grade A)'.

[0093] To ensure the reliability of the logic of this process, for new industries where average sales information is not available in the database, the system includes an exception handling step that applies data from the most similar industry category or requests the user to directly input the expected sales and specifies that the value is an estimate. Additionally, if there are no specific competitors, rules may be added to treat the competitive risk as 0 so that there is no penalty during the correction process, or to grant a small bonus point by considering the 'first-mover advantage'.

[0094] The present invention is compared with the prior art as follows. In a scenario analyzing the entry of a 'laundry shop' into a property near Gangnam Station, which has a very high CPI due to high pedestrian traffic, the simple profitability analysis of the prior art may conclude that profitability is low by comparing the high rent of Gangnam Station with the average sales of the 'laundry shop'; however, it fails to consider the specific characteristic that there is high demand for laundry from single-person households due to the large number of officetels in the surrounding area. However, Process 3 of the present invention strongly reflects the RESI calculated in Process 2 (which indicates a high degree of alignment between the 'Gangnam Station office worker / single-person household' profile and the 'laundry shop') as a weight, even if the CPI is high. Furthermore, by taking into account the fact that there are few competing laundries in the vicinity, it derives that a very high ISS can be achieved in that specific location even if the average profitability of the industry is low. This has a significant effect in systematically discovering opportunities in 'niche markets' that the prior art misses.

[0095] For an industry to succeed in a specific location, the land must be good (CPI), it must be compatible with the people living there (RESI), it must be profitable (profitability), and it must be able to win in competition (competitive risk). This process has a logical structure that adopts all four of these major elements of success as judgment criteria and organically integrates them to convert them into a single score. In particular, the configuration that inherits and uses CPI and RESI, which are the results of the preceding process, as the main input values ​​for analysis is an inevitable design to prevent discontinuity between each analysis stage and to increase the depth of analysis of the entire system.

[0096] By adopting the components and judgment rules of this process, it provides comprehensive analysis results that consider all four major factors—location, customers, finance, and competition—thereby preventing users from relying on biased information and supporting them in making balanced decisions. Furthermore, even for industries where conventional technology might deem them unsuitable based solely on financial figures, this invention has the effect of discovering and recommending the hidden potential of the industry based on a high degree of alignment with location and customer profiles. Additionally, it has the effect of significantly reducing the user's time and effort by automatically processing complex analysis processes that would otherwise take several days for an expert to perform within just a few minutes.

[0097] The 'Industry Fit Score (ISS)' used in this specification refers to a normalized score between 0 and 100, calculated through Process 3 of the present invention, indicating how comprehensively a specific single industry fits a given location environment and customer profile. The 'ISS Grade' intuitively expresses the degree of fit based on the ISS score and is defined, for example, as 'Grade A (optimal industry candidate for the location)' for a score of 85 or higher, 'Grade B (very promising industry candidate)' for a score of 70 or higher but less than 85, 'Grade C (possibility of success but need to review risk factors)' for a score of 50 or higher but less than 70, and 'Grade D (highly likely unsuitable for the location)' for a score of less than 50, and is used as a criterion for determining priority when configuring the final scenario.

[0098] The scenario profitability evaluation process according to the present invention is a final decision support stage of the system and aims to comprehensively evaluate how economically attractive and stable a combination of multiple industries (investment scenarios) configured by the user is as a single investment plan. This is a stage that answers the ultimate question, "When investing by combining these industries with this area, what is the plan that is ultimately most advantageous to me?" and defines the Industry Suitability Score (ISS) of each individual industry calculated in Process 3 as a judgment criterion, the allocated area which is the size of the physical space allocated by the user to each industry within the scenario, the total initial investment cost which is the sum of all initial costs required to execute the scenario, and the integrated risk which indicates the financial stability of the entire investment plan.

[0099] This process creatively applies the 'Modern Portfolio Theory' of financial engineering to the problem of real estate lease composition, consisting of a logical procedure to identify the plan with the best 'risk-adjusted return,' rather than simply a plan with high returns. The above logical procedure includes: a first step in which a user virtually divides the space to be analyzed through the system interface, places specific business sectors in each section, and inputs information on the expected initial investment costs of the business sectors to construct one or more scenarios; a second step in which, for each business sector included in the constructed scenario, the expected return for each business sector is calculated based on the ISS calculated in Process 3 and the allocated area, and the expected returns are all summed up to calculate the 'total expected return' of the entire scenario; a third step in which the 'integrated risk' of the entire scenario is calculated by comprehensively considering the unique sales volatility of each business sector and the allocated area through the risk analysis module of the system, while reflecting the portfolio effect where risk is diversified when combining business sectors of different characteristics; and a fourth step in which the 'net return' obtained by subtracting the 'total initial investment costs' from the 'total expected return' calculated above is divided by the 'integrated risk' to calculate the final scenario profitability index (SPI) representing the value of the expected net return per unit risk.

[0100] The data for the above judgment criteria is obtained by directly receiving the output of Process 3 internally within the system, directly inputting the allocated area and initial investment costs through the simulation interface, and utilizing the standard deviation value of the past monthly average sales for each industry category that is pre-stored in the system's industry database unit.

[0101] The Scenario Profitability Index (SPI) ultimately calculated through the above process serves as the system's final output. It is used to compare the SPI scores of various scenarios configured by the user and recommend the scenario with the highest score as the 'optimal investment plan.' Additionally, if the user changes the industry composition or area of ​​a scenario, the system recalculates and displays the SPI in real-time, thereby supporting the user in dynamically exploring the optimal combination.

[0102] The processing procedure of this process can be described using a specific scenario, for example, where a user compares two investment plans (Plan A: Cafe-only entry, Plan B: Cafe + Stationery store combined entry) for the same 100m² space as follows. In the first step, the information acquisition stage, the system recognizes the industry composition and area information of each plan and obtains the relevant ISS and sales volatility (σ) values ​​from the database. In the second step, the total expected return calculation stage, the total expected return for each plan is calculated. In the third step, the integrated risk calculation stage, the risk analysis module calculates the integrated risk for each plan; however, in the case of Plan B, the integrated risk is calculated to be relatively low because a portfolio effect occurs by combining a highly volatile cafe with a stable stationery store. In the fourth step, the final index calculation stage, the SPI for each plan is calculated. In the fifth step, the result presentation stage, the system presents the results to the user along with the reason for recommendation, stating, "Although Plan B has a slightly lower total expected return, its investment efficiency (SPI) considering risk is significantly superior to Plan A, making it a more stable and reasonable investment plan."

[0103] To ensure the reliability of the logic in this process, for industries lacking sales volatility data, an exception handling step is included to apply the average volatility value of the same major category and notify the user that this value is an estimate. Additionally, if the total sum of areas configured by the user exceeds the total property area or if a combination of industries not permitted by law is configured, the system includes a step to display an error message in real-time to guide the configuration of the correct scenario.

[0104] The present invention is compared with the prior art as follows. In a scenario comparing 'Plan A' and 'Plan B', the prior art simple profit aggregation system simply aggregates the expected profits of each industry for comparison; therefore, it is highly likely to incorrectly recommend 'Plan A' as the better investment option due to its higher total expected profit, and it has an obvious limitation in that it fails to consider 'risk,' which is one of the most important factors in investment. However, Process 4 of the present invention creatively integrates financial portfolio theory, a heterogeneous technical field, into real estate lease composition to introduce a new dimension of 'risk' into the analysis. Through this, it provides a qualitatively different judgment criterion called 'risk-adjusted profitability,' which considers not only immediate profits but also long-term stability, and consequently has a significant effect in inducing wiser and more rational investment decisions.

[0105] When managing multiple investment targets, it is a fundamental principle of modern investment theory to consider not only the profitability of individual assets but also the risk diversification effects resulting from their interactions. This process applies these portfolio optimization principles to solving real estate lease partnership problems, representing an essential logical framework for protecting user assets and maximizing long-term returns. Simply summing the returns of each sector constitutes an incomplete analysis; evaluating 'risk-adjusted return' by considering 'integrated risk' is an essential step for true optimization.

[0106] By adopting the components and judgment rules of this process, it enables investors to implement 'risk management,' which previously relied on intuition or experience, into a quantitative and systematic process, thereby supporting even non-experts in constructing stable investment portfolios. Furthermore, it allows for the discovery of optimal combinations that maximize the value of the entire portfolio by offsetting risk when combined with other sectors, even if a single sector lacks appeal on its own. Additionally, by enabling users to directly observe changes in the SPI while switching sectors and areas in real time, it provides an interactive experience that goes beyond passive recommendations to actively seeking the optimal solution.

[0107] The 'Scenario Profitability Index (SPI)' used in this specification refers to a relative index representing the value of expected net profit per unit risk of a specific industry combination scenario, calculated through Process 4 of the present invention, and is intended primarily to compare relative superiority between scenarios rather than absolute scores. The 'optimal investment plan' refers to the scenario having the highest SPI value among multiple scenarios presented by the user for comparison, where 'optimal' refers not to the highest absolute profit, but to a reasonable plan that exhibits the highest profit efficiency relative to the risk to be accepted.

[0108] Hereinafter, an example illustrating how the components and processes of the present invention interact organically to produce specific results is described in detail. This example assumes a scenario in which a potential investor, 'Kim OO', seeks to find the most suitable and profitable lease configuration for a corner commercial space (total area 120m²) located at 123-45, Seongsan-dong, Mapo-gu, Seoul.

[0109] First, user 'Kim OO' inputs the address, area, and location type of the property to be analyzed through a dedicated application installed on their user terminal unit (100) and requests the start of analysis. The request is transmitted to the server unit (200) in the form of a specific data packet, and the data packet is composed of attributes including a request identifier, a user identifier, and detailed information of the property to be analyzed. In particular, the detailed information is composed of an address in text form, floor number information, a total area in square meters, and a predefined visibility type code. The information receiving module (210) that receives the packet converts the address into latitude and longitude coordinates and standardizes the visibility type into an internal system code, processing it into a form that subsequent modules can use immediately.

[0110] Next, the external data collection module (220) calls various external APIs based on the standardized coordinates to collect the following data and stores it in the database unit (400).

[0111]

[0112] Subsequently, the server unit (200) performs two analysis processes in parallel. The commercial area potential analysis module (280) performs process 1 based on the collected data to calculate the commercial area potential index (CPI) as '88.2 points'. At the same time, the residential environment and demographic analysis module (300) analyzes the housing type and average age to determine the lifestyle profile of the area as a 'living area centered on trend-sensitive youth / single-person households', and based on this, calculates the residential environment suitability index (RESI) for various candidate business sectors considered by the system.

[0113]

[0114] Next, the industry suitability determination module (290) performs process 3. It calculates the final industry suitability score (ISS) by combining the previously calculated CPI, the RESI of each industry, and the industry-specific financial data and specific competitive risk stored in the database unit (400). The result provision module (270) processes the result and presents it to the user terminal unit (100) in the following visualized form.

[0115]

[0116] Next, the user views the above recommendation results and envisions two specific investment scenarios, namely 'Scenario A: Standalone entry of a casual dining pub (120m²)' and 'Scenario B: Combined entry of a casual dining pub (80m²) + design bakery (40m²)', and inputs them into an interface controlled by the simulation module (260). At this time, the user terminal unit (100) transmits a specific data packet to the server unit (200), and the packet includes a session identifier that identifies the current analysis session and an array attribute containing multiple scenario information. Each scenario information has a unique identifier such as 'A' or 'B' and includes one or more industry unit information constituting the scenario. Each industry unit information is configured to include a predefined industry identifier such as 'PUB_CASUAL_01', an allocated area (m²) such as '120', and information on an expected initial investment cost (won) such as '120000000'.

[0117] Finally, the scenario profitability evaluation module (310) performs process 4. Based on the packet information, it calculates the total expected profit for each scenario and calls the risk analysis module (320) to calculate the integrated risk level. The risk analysis module (320) calculates the risk level by querying sales volatility data for each industry from the database unit (400). Finally, the result provision module (270) synthesizes all these results and presents the following final comparison report to the user terminal unit (100).

[0118]

[0119] Thus, by implementing abstract concepts into concrete data packets, tables, and step-by-step processing procedures, the present invention enables those skilled in the art to clearly understand the technical concept and effects and to easily construct the system.

[0120] Although preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above. Various modifications are possible by those skilled in the art without departing from the essence of the invention as claimed in the claims, and such modifications should not be understood individually from the technical spirit or perspective of the present invention. Explanation of the symbols

[0121] User terminal unit (100) Server unit (200) Information receiving module (210) External data collection module (220) Commercial area analysis module (230) Profitability prediction module (240) Scenario generation module (250) Simulation module (260) Result providing module (270) Commercial area potential analysis module (280) Industry suitability determination module (290) Demographic analysis module (300) Scenario profitability evaluation module (310) Risk analysis module (320) Housing data analysis module (330) Database unit (400)

Claims

Claim 1 An automatic recommendation system for lease configuration and space utilization concepts, comprising: a user terminal unit; and a server unit connected to communicate with the user terminal unit; wherein the server unit comprises: an information receiving module configured to receive basic information of a property to be analyzed from the user terminal unit; an external data collection module configured to collect commercial area data and residential environment data surrounding the property from an external information source; a database unit for storing data; and one or more processors configured to perform a first analysis evaluating the commercial potential of the location itself of the property based on the collected commercial area data, a second analysis evaluating the degree of compatibility between a specific business type and a potential customer profile around the property based on the collected residential environment data, and a third analysis determining the overall suitability of the specific business type by synthesizing the results of the first analysis and the second analysis. and a result providing module configured to transmit and display the analysis results to the user terminal unit; the server unit further includes a commercial area potential analysis module configured to evaluate the commercial potential based on judgment criteria including a visibility coefficient indicating the degree to which the property is exposed to potential customers, an accessibility score indicating the ease with which potential customers can reach the property, a number of pedestrians indicating the size of the potential market passing around the property, a competition density evaluating the market saturation around the property, and a mutual growth density evaluating market opportunities around the property; the commercial area potential analysis module is configured to calculate the unique physical value of the property by combining the visibility coefficient and the accessibility score, reflect the number of pedestrians in the physical value, and correct so that the growth rate of the result value becomes moderate when the number of pedestrians exceeds a preset threshold value, and calculate a commercial area structure index indicating the structural advantage of opportunity relative to competition based on the ratio of dividing the mutual growth density by the competition density; and the server unitThe system further includes a residential environment and demographic analysis module configured to evaluate the degree of compatibility based on judgment criteria including residential building types representing the physical form of residential buildings distributed around the aforementioned property, the dominant residential form which is the residential building type with the highest proportion within the region, resident statistics including the average age and number of people per household in the region, and industry-lifestyle compatibility representing the degree of alignment between the target customer base of the aforementioned specific industry and the lifestyle profile of the region. The residential environment and demographic analysis module collects building information around the aforementioned property, classifies it by residential building type, and calculates the scale of each type. Based on the classification results and resident statistics, it determines the lifestyle profile of the region as one of 'youth / single-person household-centered', 'middle-aged / family unit-centered', or 'office worker-centered office living area'. It is configured to calculate the degree of compatibility by evaluating the correlation between the target customer characteristics of the aforementioned specific industry and the determined lifestyle profile. The server unit determines the overall suitability of the aforementioned specific industry by applying the degree of compatibility evaluated in the second analysis as a weight based on the commercial potential evaluated in the first analysis, and the Industry Suitability Score (ISS) It further includes an industry suitability determination module configured to calculate, and the server unit comprises a scenario generation module that combines industries that have obtained the highest scores among the multiple industry-specific industry suitability scores (ISS) received from the industry suitability determination module into 2 to 3 recommended scenarios according to predefined rules; and detects when a scenario change event occurs at a user terminal unit, receives modified scenario configuration data, transmits the modified scenario configuration information to a scenario profitability evaluation module, and requests recalculation.A simulation module configured to receive a scenario profitability index (SPI) recalculated from the scenario profitability evaluation module and update the screen of the user terminal unit in real time through the result provision module; and a risk analysis module configured to receive scenario configuration information from the simulation module, query sales volatility data for each industry from the database unit, calculate the integrated risk of the entire scenario by comprehensively considering the unique sales volatility and investment weight of each industry included in the scenario based on modern portfolio theory, and return the calculated integrated risk value to the scenario profitability evaluation module. The automatic recommendation system for lease configuration and space utilization concepts further comprises: a scenario profitability evaluation module configured to receive the industry suitability score (ISS) of each industry from the industry suitability determination module and receive scenario configuration information from the simulation module, calculate the total expected profit and total initial investment cost of the scenario, and calculate the scenario profitability index (SPI) representing the value of the expected net profit per unit risk by dividing the net profit (obtained by subtracting the total initial investment cost from the total expected profit) by the integrated risk level and transmit it to the result providing module; wherein the result providing module is configured to compare the scenario profitability index (SPI) of a plurality of scenarios and recommend the scenario having the highest SPI value as an investment plan, and to recalculate and provide the scenario profitability index (SPI) in real time according to changes in the industry configuration or area of ​​the scenario by the user. Claim 2 The automatic recommendation system for lease configuration and space utilization concepts according to claim 1, wherein the system is configured to request the user to manually input the value or to automatically supplement it with alternative statistical data, such as the average value of the relevant administrative district, when specific data cannot be obtained due to a failure in external application programming interface (API) integration; wherein the system is configured to perform calculations by adding a default value of 1 to all density calculations to prevent calculation errors in which the denominator becomes 0 in the case of a new commercial district with a competition density of 0; wherein the external data collection module is configured to automatically update commercial district data according to a set cycle to ensure data freshness and to specify the final update date of the data to the user; and wherein the visibility coefficient is configured to be obtained by the system administrator or user confirming the location of the property on a map and selecting and inputting one of the predefined types: 'main road corner (2.0)', 'main road (1.5)', 'side road corner (1.2)', 'side road (1.0)', and 'basement / 2nd floor or higher (0.7)'. Claim 3 In Paragraph 2, the accessibility score is characterized by being configured to be obtained by automatically counting the number of bus stops and subway station exits within a radius of 100 meters based on the property coordinates in conjunction with the Ministry of Land, Infrastructure and Transport Bus Information System or the Subway Public Data API; the floating population is characterized by being configured to be obtained by acquiring average floating population data for specific days and times through the commercial area analysis API of an affiliated private telecommunications company; the competition density and the mutual growth density are characterized by being configured to be obtained by automatically counting the number of businesses by industry category within a radius of 200 meters using the place search API of an external map service; the commercial area potential index is a normalized score between 0 and 100 points calculated through a commercial area potential analysis process; and the system is configured to assign a grade to the commercial area potential index score according to a pre-set range, with 90 points or more being 'Grade A', 70 points or more but less than 90 points being 'Grade B', 50 points or more but less than 70 points being 'Grade C', and less than 50 points being 'Grade D'. It is characterized by defining terms such as 'very suitable' or 'high' and configuring them to be interpreted based on the grade or score range defined above; the residential environment and demographic analysis module is characterized by classifying building information obtained through the building register and map information API by residential type, calculating the total number of households or gross floor area of ​​each type and creating a database, determining the dominant residential form of the region based on the database, and categorizing the region's lifestyle profile by supplementing this with resident statistical data; the dominant residential form refers to a case where the ratio of the number of households occupied by a single residential type within a specific analysis radius exceeds a pre-set threshold, and the threshold is 60%; and the industry suitability determination module isAn automatic recommendation system for lease configuration and space utilization concepts, characterized by being configured to calculate a basic profitability indicator by comparing the average monthly sales per square meter of the target business type with the rent of the area based on the Commercial Area Potential Index (CPI) received from the commercial area potential analysis process and the Residential Environment Suitability Index (RESI) received from Process 2, downwardly adjust the basic profitability indicator by reflecting a specific competitive risk where the same business type exists nearby, upwardly adjust the corrected profitability indicator by applying the grade of the Residential Environment Suitability Index (RESI) as a weight, and calculate the Business Type Suitability Score (ISS) by synthesizing the analysis results based on the Commercial Area Potential Index (CPI), which is the fundamental value of the location; and the result providing module is characterized by being configured to process and visualize numerical data calculated from all analysis modules into at least one of a report, a chart, and a grade, convert various indices into scores and grades, generate comparison charts by scenario, generate report data by combining text-based recommendation opinions, and then transmit it to the user terminal unit. Claim 4 delete Claim 5 delete Claim 6 delete

Images