KR102449143B1 - Bigdata-based residential model recommendation system for users and a method for recommending a residential model using the same - Google Patents

Abstract

The present invention relates to a big data-based user-customized housing model recommendation system and a housing model recommendation method using the same.
According to a preferred embodiment of the present invention, it is made in the big data-based housing model management server 100, and is network-connected to the big data-based BIM database 200 and the user terminal 300 including housing model information to provide a customized housing for the user. A method for recommending a model, comprising the steps of: a) receiving user information including information directly related to at least one residence; b) generating building trend information based on a preset building trend deriving method; c) generating user lifestyle information by matching the received user information with the building trend information; d) receiving housing model information matching the user lifestyle information from the big data-based BIM database 200 and generating user-customized housing model information; and e) transmitting the user-customized housing model information to the user terminal 300; a big data-based user-customized housing model recommendation method is provided, including a.

Description

{Bigdata-based residential model recommendation system for users and a method for recommending a residential model using the same}

The present invention is a big data-based user-customized housing model recommendation system and a housing model recommendation method using the same. Specifically, by matching architectural trends and BIM data derived from user information and big data to users of various ages, tendencies, and types of residence. It relates to a big data-based user-customized housing model recommendation system that can automatically recommend a housing model including an optimized residential environment, and a housing model recommendation method using the same.

With the development of building technology, various buildings are being built. In particular, instead of providing a uniform housing model to users, such as an apartment building, a housing model of a suitable form is provided to the user so that construction can be done based on the type of housing model recommended by the user in the process of new construction or reconstruction. services are provided.

However, the process of recommending a residential model to the user is very complicated. From the process of collecting user information, the process of understanding the user's lifestyle through an interview with the expert who is well aware of the architectural trend, to the user's customized housing according to the lifestyle and architectural trend The process of recommending a model takes a lot of time and reflects the opinions of experts, so differentiated results are derived according to the abilities of experts. Therefore, there are many unreasonable points in terms of economic feasibility, such as the concentration of recommendation requests to specific experts, which causes cost increases.

In particular, it was often difficult to obtain satisfactory results compared to the cost invested in the research process that required various manpower and capital, such as market research, floor plan research, and post-residence evaluation.

As an example of the prior art for improving this irrationality and recommending a housing model to a user, there is a "situation-aware energy-saving residential design platform system" of Korean Patent Registration No. 10-1958567.

The prior art provides an energy-saving, user-customized space design function through the application of a context-aware-based library module, and calculates the energy consumption of a residential space based on context awareness through an IT device to design an energy-saving residential design. There are advantages to being able to

However, the prior art recommends a housing model to the user according to the energy consumption of the residential space, and only according to the user's selection input without considering other matters such as the user's tendency, the number of household members, the surrounding environment, and the architectural trend as a whole. There is a problem in that users can be judged only from the perspective of energy consumption based on household composition and household energy consumption and a housing model can be recommended.

In addition, even when attempting to reconstruct in the area where the user resides, the above-mentioned complicated process in recommending an appropriate housing model must be passed as it is, and there is a difficulty in proposing an optimal housing model while minimizing the user's concerns.

The present invention is to solve the problems of the prior art, and by matching architectural trends and BIM data derived from user information and big data, a residential model including a residential environment optimized for users of various ages, tendencies, and types of residence. The purpose of this study is to provide a big data-based user-customized housing model recommendation system that enables automatic recommendations and a housing model recommendation method using the same.

According to a preferred embodiment of the present invention for solving the above problems, it is made in a big data-based residential model management server, and it is connected to a big data-based BIM database and a user terminal including housing model information to provide a customized housing model to the user. A method of recommending a user, comprising the steps of: a) receiving user information including information directly related to at least one residence; b) generating building trend information based on a preset building trend deriving method; c) generating user lifestyle information by matching the received user information with the building trend information; d) receiving housing model information matching the user lifestyle information from the big data-based BIM database and generating user-customized housing model information; and e) transmitting the user-customized housing model information to a user terminal; a big data-based user-customized housing model recommendation method is provided, including a.

According to another preferred embodiment of the present invention, the big data-based residential model management server is network-connected to a GIS database including building-related information and location information, and the user-customized residential model information in step d) is the GIS database. It is characterized in that it includes at least one or more location information received from.

According to another preferred embodiment of the present invention, the location information is characterized in that it is selected based on the user lifestyle information.

According to another preferred embodiment of the present invention, the preset construction trend deriving method extracts the characters included in the document according to the text extraction technique, and reflects the weights according to the extraction location to the extracted characters to derive the architectural trend. It is characterized by doing so.

According to another preferred embodiment of the present invention, in step b), b1) the big data-based residential model management server and the network connectable web page, document file, or text included in the social network document are extracted according to the text extraction technique. extracting; b2) reflecting a weight according to the extraction position to the extracted characters; and b3) generating building trend information based on the letters to which the weight is reflected.

According to another preferred embodiment of the present invention, the user lifestyle information includes at least one housing module information composed of a plurality of modules, and the housing module information is the building trend information or user information in a preset housing module matrix. It is characterized in that at least one piece of information is matched and formed.

According to another preferred embodiment of the present invention, a user information management module that receives user information including information directly related to at least one or more dwellings, and a building trend generating building trend information based on a preset building trend deriving method An information management module, a lifestyle information management module for generating user lifestyle information by matching the user information and architectural trend information, and a user-customized housing model information generated based on the lifestyle information and delivered to a user terminal Big data-based residential model management server including a residential model information management module; a big data-based BIM database that is network-connected to the big data-based residential model management server and transmits residential model information matching the user lifestyle information to the big data-based residential model management server; and a user-customized housing model that is network-connected to the big data-based residential model management server, transmits user information to the big data-based residential model management server, and is generated based on the user information from the big data-based residential model management server A user terminal configured to receive information is provided.

According to another preferred embodiment of the present invention, it is connected to the network with the big data-based housing model management server, and provides at least one or more location information included in the user-customized housing model information to the big data-based housing model management server. It is characterized in that it further comprises a; GIS database is configured.

The present invention has the advantage of being able to easily provide an architectural trend suitable for the user without the user going through an interview with an architectural designer and/or a related expert or a complicated selection process.

In particular, the present invention has the advantage of allowing the user to construct a new residential model at an optimal location or to select a residential model most suitable for the user from among existing buildings.

In addition, the present invention has the advantage of being able to recommend to the user an optimized residential model suitable for the surrounding environment and the user's lifestyle, even when a reconstruction is attempted in the area where the user resides.

1 is a schematic diagram of the configuration of a big data-based user-customized residential model recommendation system according to an embodiment of the present invention.
2 is a schematic diagram of the configuration of a big data-based residential model management server according to an embodiment of the present invention.
3 is a schematic diagram of the configuration of a big data-based user-customized residential model recommendation system according to another embodiment of the present invention.
4 and 5 are flowcharts of a method for recommending a user-customized residential model based on big data according to an embodiment of the present invention.
6 is an exemplary diagram illustrating that a housing model recommended to a user is displayed on a user terminal by the big data-based user-customized housing model recommendation method according to an embodiment of the present invention.
7 is an exemplary diagram of user information input through a user terminal according to an embodiment of the present invention.
8 is a conceptual diagram related to generation of building trend information according to an embodiment of the present invention.
9 is an exemplary diagram of user lifestyle information according to an embodiment of the present invention.
10 is an exemplary diagram of user-customized housing model information according to an embodiment of the present invention.
11 is a conceptual diagram for explaining that location information is included in user-customized housing model information according to an embodiment of the present invention.
12 is an exemplary diagram of location information among user-customized housing model information according to an embodiment of the present invention.
13 and 14 are conceptual views for explaining a housing module according to an embodiment of the present invention.
15 is an exemplary view of a residential module according to an embodiment of the present invention.
16 and 17 are conceptual diagrams related to generation of residential module information according to another embodiment of the present invention.
18 is an exemplary diagram in which housing module information is mapped on a map according to another embodiment of the present invention.
19 is a flowchart for exemplarily explaining the big data-based user-customized housing model recommendation method according to the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, in the description of the present invention, in the case of obscuring or obscuring the technical idea of the present invention due to the detailed description of the known configuration, the description of the above known configuration will be omitted.

1 is a schematic diagram of a big data-based user-customized residential model recommendation system according to an embodiment of the present invention, FIG. 2 is a configuration schematic diagram of a big data-based residential model management server according to an embodiment of the present invention, and FIG. 3 is this It is a schematic diagram of the configuration of a big data-based user-customized residential model recommendation system according to another embodiment of the present invention.

As shown in FIG. 1 , the big data-based user-customized housing model recommendation system 10 according to an embodiment of the present invention is a big data-based housing model management server 100 that recommends an optimal housing model suitable for a user. ), including a big data-based BIM database 200 and a user terminal 300 connected to the network with the big data-based residential model management server 100 to provide BIM data to the big data-based residential model management server 100 is done by

For example, as shown in FIG. 2 , the big data-based residential model management server 100 includes a user information management module 120 that receives user information including at least one or more directly related information about a dwelling, and a preset A building trend information management module 140 for generating building trend information based on a method of deriving a building trend, and a lifestyle information management module 160 for generating user lifestyle information by matching the user information with the building trend information; and a housing model information management module 180 for generating user-customized housing model information based on the lifestyle information and transmitting it to the user terminal 300 .

In order to store and manage the user information, architectural trend information, user lifestyle information, and housing model information, the big data-based housing model management server 100 includes a user information DB 130 , a construction trend information DB 150 and a residence It may further include a model information DB (170). At this time, the user lifestyle information is closely linked with user information and may be stored in the user information DB 130 , and user-customized housing model information among the housing model information is also generated and then stored in the user information DB 130 . It is desirable to store it together with user information.

In the present invention, the 'user' is preferably a 'resident' living in a specific area or a 'prospective resident' who wishes to reside in a specific area. It can also be understood as a person who lives in an existing building or wants to build a new residential model.

The user may be a representative, manager, planner, etc. of a corporation or public sector in addition to individuals such as the above-mentioned residents. can also be used.

The user information management module 120 manages the user information input by the user, and the input user information may be stored in the user information DB 130 through the user's consent.

The user information may include personal information such as name and age, and preferably, a unique personal number based on unique information of the user terminal 300 may be automatically assigned. The user information may further include not only information directly related to housing, such as housing type (individual-communal), number of rooms, desired area, number of occupants, etc., but also various types of additional information necessary for personality or residence (refer to FIG. 7).

The building trend information management module 140 generates building trend information based on a preset building trend deriving method, and stores the generated building trend information in the building trend information DB 150 .

The architectural trend information is not reflected in the user's opinion or inclination to recommend the user's housing model, but is provided to the user by confirming the trend of the residential market, or the intention of some users may be reflected according to the user's selection. A detailed description of the generation of architectural trend information will be described later.

The lifestyle information management module 160 generates user lifestyle information by matching user information with the generated architectural trend information, and stores it in the user information DB 130 .

The housing model information management module 180 receives BIM data about a housing model matching the user lifestyle information from the big data-based BIM database 200 to generate user-customized housing model information, and the created user Customized housing model information may be stored in the user information DB 130 .

Although the housing model information DB 170 may store user-customized housing model information, it is more preferable to group, classify, and store housing model information matching each building trend information and/or lifestyle information.

The housing model information management module 180 and the housing model information DB 170 store and manage information on grouping and classification of housing models according to architectural trends, and are generated according to the matching of the building trend information and user information. Residential model information that can be matched with user lifestyle information is classified in advance, and a detailed description will be given later.

For example, the user-customized housing model information generated by the housing model information management module 180 includes user information and housing model information, and may further include location information of a building for realizing the housing model information. The user-customized housing model information may further include any one of architectural trend information and lifestyle information, but since the housing model information is generated based on matching of architectural trend information and/or lifestyle information and user information, It is possible to recommend suitable housing model information to the user only with the user information, the housing model information, and the location information.

In addition, the big data-based residential model management server 100 is further provided with an operation module (not shown) in charge of overall server operation and a communication module (not shown) for network connection.

The big data-based BIM database (BIM DB, 200) is network-connected with the big data-based residential model management server (100).

The big data-based BIM database 200 is a variety of data used through a computer technology-based architectural design method that is Building Information Modeling, that is, three-dimensional building geometry data and building materials, construction methods, and maintenance. It is configured to store BIM data corresponding to housing model information including information such as space, room, use, and furniture as well as method.

The big data-based residential model management server 100 pre-groups and classifies various BIM data stored in the big data-based BIM database 200 into residential model information according to each lifestyle information, and each grouped The information may be stored in the lifestyle information DB and/or the residential model information DB.

The big data-based residential model management server 100 generates user lifestyle information according to the generated architectural trend information based on a preset architectural trend derivation method when user information is input, and the user lifestyle information The big data-based BIM database 200 requests housing model information selected by matching based on the big data, and the big data-based BIM database 200 provides housing model information that matches the user lifestyle information based on the big data. It is transmitted to the residential model management server 100 .

The building corresponding to the housing model information may be a pre-built existing building, or may be a housing model of a building that the user intends to construct or reconstruct. In other words, when the user selects an existing building according to the user-customized housing model recommended to the user, as well as when the user tries to (re)construction at the same or similar location in the area where the user resides, architectural trends and user's life It is possible to recommend a residential model optimized for the style to the user.

The user terminal 300 is network-connected with the big data-based residential model management server 100, and transmits user information to the big data-based residential model management server 100, and the big data-based residential model management server ( 100) is configured to receive the user-customized housing model information generated based on the user information.

The user terminal 300 transmits and receives information through a network with an input unit for inputting user information, a display unit for displaying related information including user-customized housing model information, and the big data-based housing model management server 100 . It is made including a communication unit that enables it.

For example, the user information may be guided to include trend period selection information when user information is input through the user terminal 300 . The trend period selection information has the advantage of providing a housing model suitable for the trend of the time (period) desired by the user by broadening the selection so that the user can select a trend that is popular at a specific time. By allowing the user to select the trend of a specific period by user selection, the architectural style of the user's desired period can be actively reflected. In this case, the building trend information may be generated based on a document created within a trend period range included in the trend period selection information.

For example, the user terminal 300 may include a user biometric recognition module (not shown) directly or indirectly, and based on the user's biometric information recognized by the user biometric module, at least some information related to the user. may be configured to be automatically entered.

For example, the user terminal 300 may recognize biometric information such as a user's heart rate, biorhythm, and sleep time through a camera and/or sensor provided therein, and may include a smart watch that is worn or possessed separately. It may be configured to receive biometric information recognized through the device using a wireless network such as Bluetooth, ZigBee, or NFC.

The user's health status or age can be identified through the biometric information, and when user information is input through the user terminal 300, such biometric information is automatically converted to the user information as user information by the big data-based residential model management server 100 ) can be transferred.

The delivery of biometric information as the user information can help to recommend a housing model suitable for the user even if the user does not input it by himself/herself.

For example, if the user's health condition is recognized as not good regardless of age, the residence may be recommended as a location or area (eg, near a large hospital) to improve the user's health condition, and even in the residential model, the user A housing model designed in a form that can help improve the health status of people can be recommended.

As shown in FIG. 3 , the big data-based user-customized housing model recommendation system 10 according to a preferred embodiment of the present invention is network-connected with the big data-based housing model management server 100 and the big data-based housing It further includes a GIS database 400 configured to provide at least one or more location information included in the user-customized housing model information to the model management server 100 .

The GIS database (GIS DB, 400) may include building-related information and location information.

As an example, the location information may be information and location information related to a building in which the corresponding housing model is implemented, and as another example, it may be location information of a building target for building the corresponding residential model, and information such as building area and land price. It may include more.

The location information may be, for example, information of an area classified based on user group information grouped according to user information, such as a target area for young households, a target area for newlywed households, and a target area for elderly households, and latitude and longitude It is configured to provide information displayed on a map in terms of coordinates.

The residential model information management module 180 of the big data-based residential model management server 100 collects information about a building that can be matched with the user-customized residential model information from the GIS database 400, information about a building location, etc. To this end, location information according to each housing model information (and/or architectural trend information, lifestyle information) may be grouped, classified, and stored in the housing model information DB 170 for this purpose.

For example, an area where a large hospital is located, an area that is less affected by fine dust, an area where public transportation is convenient, an area where school districts and academies are developed, an area where large houses are located, a studio village, an area with a lot of good reviews for the living room view, etc. Location information can be grouped and classified according to housing model information, architectural trend information, lifestyle information, and the like.

That is, the big data-based residential model management server 100 according to a preferred embodiment of the present invention groups and classifies each of the building trend information, lifestyle information, housing model information, and location information into a plurality of groups and forms a matrix. The groups can be arranged, and based on the user information input by the user terminal 300, by matching each group, it is possible to easily create user-customized housing model information and recommend it to the user.

4 and 5 are flowcharts of a big data-based user-customized housing model recommendation method according to an embodiment of the present invention, and FIG. 6 is a big data-based user-customized housing model recommendation method according to an embodiment of the present invention. An exemplary view showing that the recommended housing model is displayed on the user terminal 300, FIG. 7 is an exemplary view of user information input through the user terminal 300 according to an embodiment of the present invention, and FIG. 8 is an exemplary view of the present invention. A conceptual diagram of generation of architectural trend information according to an embodiment, FIG. 9 is an exemplary view of user lifestyle information according to an embodiment of the present invention, and FIG. 10 is an example of user-customized housing model information according to an embodiment of the present invention 11 is a conceptual diagram for explaining that location information is included in user-customized housing model information according to an embodiment of the present invention, and FIG. 12 is a view of location information among user-customized housing model information according to an embodiment of the present invention. It is also an example.

The big data-based user-customized housing model recommendation method according to a preferred embodiment of the present invention is made in the big data-based housing model management server 100 and includes a big data-based BIM database 200 and a user terminal 300 including housing model information. ) and a method to recommend a customized housing model to the user through network connection.

The method for recommending a user-customized housing model includes the steps of: a) receiving user information including information directly related to at least one dwelling; b) generating building trend information based on a preset building trend deriving method; c) generating user lifestyle information by matching the received user information with the building trend information; d) receiving housing model information matching the user lifestyle information from the big data-based BIM database 200 and generating user-customized housing model information; and e) transmitting the user-customized housing model information to the user terminal 300 .

In step a), the user information can be input through the user terminal 300, and as shown in FIG. 7, the user information input through the user terminal 300 is the big data-based residential model through the network. It is transmitted to the management server (100). The input information is a housing type, number of rooms, desired area, number of occupants, age group, personality, requests, etc. In addition to the examples, the user's health information and desired surrounding environment information may be further included.

For example, the user information includes user group information formed by grouping and classifying users into a plurality of groups, and the building trend information may be formed based on the user group information.

The user group information is classified into various forms such as age (eg, 40s, 60s, etc.), family composition (eg, newlyweds, three-generation families, families including teenagers), tastes (eg, reading, watching art performances, etc.) can be configured.

By grouping the information about each user included in the user information into user group information, it is faster even when matching the architectural trend extracted in step b) and/or the lifestyle, housing model, etc. of steps d) and e) Matching can be done.

In step b), for example, the preset construction trend deriving method may be to extract characters included in a document according to a text extraction technique.

The text extraction technique may be understood as a known text mining technique, and is to extract characters included in a document and group and classify them according to the number of corresponding characters.

The text mining is mapped through analysis using technologies such as wordcloud and word2vec.

The word2vec is a text mining tool for collecting and quantifying key keywords on a document, and generates vector values for words by vectorizing key keywords in three or more dimensions. For example, when all keywords are vectorized, since keywords having similar vector values have similar meanings, it is possible to visualize key keywords and similar words so that various meanings can be inferred.

The wordcloud is a kind of visualization tool that intuitively shows the key keywords collected by text mining. By making it possible to grasp at a glance, it is used to derive architectural trends through big data analysis of the present invention using a vast amount of information.

Since the word2vec and wordcloud are known technologies in the text mining field and can be understood through various monhuns, further detailed description of text mining will be omitted.

The above document may be a document on a page provided to individuals and companies on social network services (SNS) such as Facebook, Instagram, and blogs operated on portal sites, and may include newspaper articles, news, research reports, papers, patents, etc. It can be a document.

As shown in FIG. 8, the building trend information management module 140 collects various documents included in thesis, patent, article, report, SNS, etc., and uses wordcloud and word2vec to collect keywords from the documents derive By extracting big data in these various fields by text extraction technique, it becomes possible to derive architectural trends.

Building trend information can be generated by sequentially organizing the derived architectural trends by high index based on the number of citations, and various types of architectural trend information can be generated by era, region, and user.

At this time, it may be configured to derive an architectural trend by reflecting a weight according to the extraction location to the extracted text.

As a preferred example, the weight may be assigned according to a distance between a key keyword corresponding to a search word and a corresponding character (keyword). In this case, the closer the distance to the core keyword is, the higher the weight is, and the farther the distance from the core keyword is, the lower the weight is.

For example, if the key keyword is youth or urban living housing, the keyword in the document that is close to the key keyword youth and/or urban living housing is rent or customized rental housing, the keyword has a higher weight (e.g., 2.0), and when convenience store, walking, etc. are extracted as keywords with a relatively long distance, the weight of keywords such as convenience store and walking is given relatively low (eg, 0.5).

By reflecting these weights and deriving the building trend information, it is possible to more accurately identify and provide the current building trend in the written document.

In this case, the key keyword may be derived from the results of a survey collected from two or more users, and characters (keywords ) can also be derived from

Table 1 is an example of key keywords according to user group information classified into young people, newlyweds, and the elderly.

key keywords number youth honeymoon old man One Youth - Urban Living Housing Newlyweds - Hobby Room Old Man - Silver Town 2 Youth - Station area Newlyweds - near the station Elderly - Living alone - Community 3 Share house-toilet Newlyweds - Dressing Room Residential - wheelchair 4 Share House-Game-Room Newlyweds - gym Silver Interior - Handrail 5 College Student - Cinema Room Newlyweds - Lifecycle Elderly - Toilet - Non-slip 6 College Student - Music Room Newlyweds - IKEA Silver interior-sliding door 7 Share house - Roommates - Number of people Newlyweds-Happiness-Housing old man - balcony - flowers 8 college student - trace Newlyweds-Baby-Room old man - tea room 9 Share House - Hobby Room Newlyweds - Kids Room old man - threshold - remove 10 One-room-portable storage Newlyweds - self-development Elderly - Housing - Caregiver

As another embodiment, the weight may be understood as an expected value according to the degree of reliability of a document to be extracted as a keyword. In other words, since the reliability and accuracy of each document are not the same in a one-to-one relationship, it helps to decide which part of the text extracted from each document to be recognized as an architectural trend by placing more weight on it.

For example, papers and policy-related documents have already been verified by a large number of people, so the highest weight (eg, 2) can be reflected. can reflect In addition, in the case of a newspaper article, it can be adjusted so that a low weight is reflected in the case of a promotional article.

For example, if there is a document containing the text 'North European style' 5 times in the thesis, and the text 'Eastern European style' is included 10 times on Facebook, the weight given to the thesis is 2, the weight given to the SNS document is If the weight of 0.5 is reflected respectively, 'North European style' can be recognized as an architectural trend even though there are twice as many 'Eastern European style' texts as 'North European style' texts.

The architectural trend in which such a weight is not reflected, and the architectural trend in which only the frequency is considered and the architectural trend in which the weight is reflected can be confirmed through the example of derivation of the architectural trend shown in FIG. 9 .

The weight may be given based on the user's situation (eg, age, family composition, etc.) in addition to the distance from the key keyword and the reliability and accuracy of the document.

For example, if the user is a newlywed, a higher weight may be given to the SNS document because the document on SNS, which is frequently used by young people of newlyweds, is more consistent with the architectural trend in many cases, and the user is an elderly family member. In the case of , more weight may be given to the thesis.

As another embodiment, it may be set to generate architectural trend information by simultaneously reflecting a weight according to the distance between the extracted character (keyword) and the key keyword and a weight according to the reliability of the document.

The reflection of the weight according to the user has an advantage that it is possible to provide a more suitable architectural trend to the user even if the user inputs simple situational information in recommending a customized residential model according to the user.

In the user-customized housing model recommendation method according to an example of the present invention for reflecting the weight, step b), as shown in FIG. 5, b1) network connection with the big data-based housing model management server 100 Steps of extracting characters included in possible web pages, document files or social network documents according to a text extraction technique; b2) reflecting a weight according to the extraction location to the extracted characters; b3) extracting the characters with the weight reflected It may consist of a step of generating architectural trend information based on the basis.

The building trend information to which the weight is reflected may also be sequentially arranged in the order of high for each index to which the weight is reflected. In this case, the user may directly select a desired architectural trend from among the architectural trend information displayed through the user terminal 300 , and a user-customized architectural trend may be automatically selected.

In step c), the lifestyle information management module 160 of the big data-based residential model management server 100 generates user lifestyle information by matching the received user information with the architectural trend information, and the user life The style information may be understood as architectural trend information suitable for the user.

As described above, the generation of the user lifestyle information may be performed by a user's selection or automatically.

In step d), the residential model management module 180 of the big data-based residential model management server 100 receives the residential model information matching the user lifestyle information from the big data-based BIM database 200 and receives the user Create customized housing model information.

As shown in FIG. 10 , the housing model information may be detailed information about the interior space of a residential facility, such as an entrance hall, a kitchen, a living room, and a bathroom, and may be displayed in the form of a plan view, a perspective view, or the like. The residential model information may further include information about devices or facilities for external spaces of residential facilities, space utilization (eg, sensors, CCTVs, vegetable gardens), and the like.

As an example, the big data-based residential model management server 100 is network-connected to the GIS database 400 including building-related information and location information, and the user-customized housing model information in step d) is the GIS database 400 ) includes at least one or more location information received from

For example, the location information may be understood as information for realizing a recommended housing model, and the location information may be selected based on the user-customized housing model information.

In this case, as shown in FIG. 11 , the big data-based residential model management server 100 according to the present invention may match the user lifestyle information, the residential model information, and the location information together, and the location information is It may be generated based on user lifestyle information.

For example, when the user is a young man, he prefers to live near a university or library, so the location information preferably includes housing model information applicable to a university and/or a library nearby. Therefore, the user-customized housing model information is an area in which housing model information matched with the user lifestyle information can be realized or is being realized, and includes location information corresponding to the area near the university and/or library. .

For example, if the user is a newlywed, it is preferable to live near facilities such as companies with 100 or more people, government offices, daycare centers, kindergartens, etc., so it is preferable to match location information near the facilities.

For example, when the user is an elderly person, he prefers to live near facilities such as mid- to large-sized hospitals, public health centers, senior centers, and welfare centers, so it is preferable to match location information near the facilities.

The location information may further include information on existing buildings or information necessary to construct a corresponding housing model.

For example, the user-customized housing model information may further include construction cost information, and additional information such as land price per pyeong of the corresponding location and estimated construction cost according to a construction trend may be included.

As shown in FIG. 12 , the location information may include map information of a corresponding location, and location information on two or more recommended areas may be included.

Such additional information may be collected through the big data-based BIM database 200 and the GIS database 400, and information may be collected from each database in advance and grouped and classified by type.

In step e), the big data-based housing model management server transmits the user-customized housing model information generated in step d) to the user terminal 300 over the network.

As shown in FIG. 6 , the user can check the recommended user-tailored housing model information through the display unit (not shown) provided in the user terminal 300, and optionally more detailed configuration or location information of the housing model, etc. You can check the contents.

The user-customized housing model information may include a plurality of pieces of recommendation information, and may be displayed on the user terminal 300 to be sequentially listed from the housing model most suitable for the user.

19 is a flowchart for exemplarily explaining a process for executing construction according to the big data-based user-customized housing model recommendation method according to the present invention.

As shown in FIG. 19 , by input of user information, each user may be classified as an individual in the form of a single dwelling or a worker in the development and construction industry (or corporation, etc.) in the form of a joint dwelling.

For example, if the user is an individual, the user's lifestyle is analyzed according to the user's lifestyle type (hobbies, personality, income, number of people accommodated, etc.) collected by the input user information, and a pre-set residential model for each user type Accordingly, a user-customized housing model is recommended using BIM data that includes building technology such as furniture, equipment, and other technologies. The residential model recommended to the user may reflect architectural trend information derived based on a preset construction trend derivation method from housing market big data such as research data, SNS, newspaper articles, papers, and patents, and the user type is the user group. It can be understood as information (eg, young/newly/old). When the lifestyle is analyzed, type plane matching is performed with a housing module, which will be described later, and the BIM data may be provided in a form matching the housing module according to the lifestyle of each user. A detailed description of the housing module will be described later.

The user-customized residential model information provides location information using GIS data such as building ledger, geographic information, environmental data, and urban infrastructure, so that a suitable building site can be selected for the user, and the user can select the recommended building site for the user. Residential buildings can be built according to customized housing models.

As another example, if the user is engaged in the development or construction industry, the user's lifestyle type is not an important factor, so the market demand can be predicted according to the architectural trend information derived based on the method and type-plane matching with the residential module is performed using the information related to the characteristics of the development space collected by the input user information. The matching of the residential module and the BIM data and the location information according to the characteristics of the development space is similar to the case where the user is an individual, and the user can build a communal residential building according to the user-customized residential model on the recommended building site. can

13 and 14 are conceptual views for explaining a housing module according to an embodiment of the present invention, FIG. 15 is an exemplary view of a housing module according to an embodiment of the present invention, and FIGS. 16 and 17 are another view of the present invention A conceptual diagram of generation of housing module information according to an embodiment, FIG. 18 is an exemplary diagram in which housing module information is mapped on a map according to another embodiment of the present invention.

The user lifestyle information according to another embodiment of the present invention comprises at least one housing module information composed of a plurality of modules, and the housing module information is one of the building trend information or user information in a preset housing module matrix. At least one piece of information is matched and formed (selected).

For example, as shown in FIG. 13 , the housing module matrix is formed by combining each category of user type, housing type, residence type, area (number of rooms) and lifestyle, regardless of input user information. It is to create a plurality of residential modules through a combination of a plurality of modules in advance.

When the housing model information according to an example of the present invention is generated through a combination of modules, it is easy to dismantle and reinstall the building during the construction process, and it is easy to add and remove the module, and it is possible to reduce the construction period by more than 50% compared to the traditional method. On the other hand, since the main constituent materials can be produced in a factory, high quality is possible.

In particular, the user-customized housing model information according to the present invention is configured to match each user's age, inclination, composition of people, and architectural trends in a comprehensive manner, so it is preferable to provide housing models of various structures. Therefore, when the housing model according to the present invention is configured in a modular type, it is possible to provide an optimal housing model to each user by variability.

For example, it is possible to provide a modular housing model that can be varied, such as installation of a height-adjustable bathtub, free adjustment of the door width, and a wall that can be installed at the entrance to facilitate access between the bathroom and the bedroom.

In addition, even when matching with BIM data, it is composed of a modular type, so that each module can easily design and arrange a space independently. As shown in FIG. 18, the classification ( clustering) is possible, so that each housing model (housing model group) can be easily displayed as location information on the map, and the user can grasp the residential status of the area at a glance.

Each of the housing models may be pre-classified according to the user's type.

14 is an example of housing model classification when the user group is young, and the types of housing modules according to each housing type are shown. At this time, each residential module may be displayed in the form of AM-B or AM-B-C, where A is the number of modules, and B and C are the types (or arrangement method) of each module.

For example, as shown in FIG. 14 , the housing module for single-person residence of young people is 2M-1, which is a combination of two modules, and 3M-1, 3M-2-1, 3M-, which is a combination of three modules. 2-2, 4M-1, etc. may be provided.

Each module can consist of a bedroom, a living room, a kitchen, a multipurpose room, a wardrobe, a toilet (bathroom), a warehouse, and an alpha room, and a doorway can be further added with a combination of modules.

As an example, as shown in FIGS. 16 and 17 , when building trend information is generated from the big data-based residential model management server 100, based on the generated building trend information, building trend information and/or a user Residential modules corresponding to the information may be selected, and housing module information regarding the selected residential modules may be generated in the big data-based housing model management server 100 .

As shown in FIG. 15 , the housing module information is matched with BIM data to configure user-customized housing model information. Since a housing module matching user information and/or architectural trend information is selected from each of the housing modules provided in the housing module matrix, information that matches the BIM data to the housing module suitable for the user is the user customized housing model information. is provided to As described above, the user can realize by selecting desired housing model information from the user-customized housing model information provided by two or more.

In the above, the present invention has been described in detail with reference to specific embodiments, but since the embodiments are merely examples for easy understanding of the present invention, substitutions, additions and modifications are made within the scope not departing from the technical spirit of the present invention. Embodiments will also fall within the protection scope of the present invention defined by the following claims.

10: Residential model recommendation system
100: Big data-based residential model management server
200: Big data-based BIM database
300: user terminal 400: GIS database

Claims (8)

It is made in the big data-based housing model management server 100, and it is connected to the big data-based BIM database 200 and the user terminal 300 including housing model information and is connected to a network to recommend a method of recommending a customized housing model to the user,
a) receiving user information including information directly related to at least one residence;
b) generating building trend information based on a preset building trend deriving method;
c) generating user lifestyle information by matching the received user information with the building trend information;
d) receiving housing model information matching the user lifestyle information from the big data-based BIM database 200 and generating user-customized housing model information; and
e) transmitting the user-customized housing model information to the user terminal 300; Big data-based user-customized housing model recommendation method comprising a.
In claim 1,
The big data-based residential model management server 100 is network-connected to the GIS database 400 including building-related information and location information,
The user-customized housing model information of step d) is a big data-based user-customized housing model recommendation method, characterized in that it includes at least one or more location information received from the GIS database (400).
In claim 2,
The location information is a big data-based user-customized housing model recommendation method, characterized in that it is selected based on the user lifestyle information.
In claim 1,
The preset construction trend deriving method is,
A method for recommending a user-customized residential model based on big data, characterized in that the characters included in the document are extracted according to the text extraction technique, but the weights according to the extraction location are reflected in the extracted characters to derive the architectural trend.
In claim 1,
Step b) is,
b1) extracting the characters included in the web page, document file or social network document capable of network connection with the big data-based residential model management server 100 according to a text extraction technique;
b2) reflecting a weight according to the extraction position to the extracted characters;
b3) generating architectural trend information based on the letters to which the weight is reflected;
In claim 1,
The user lifestyle information includes at least one residential module information composed of a plurality of modules,
The housing module information is a big data-based user-customized housing model recommendation method, characterized in that the information is formed by matching at least one of the building trend information and the user information to a preset housing module matrix.
A user information management module that receives user information including information directly related to at least one or more dwellings, a building trend information management module that generates building trend information based on a preset building trend derivation method, and the user information and the building trend A lifestyle information management module for generating user lifestyle information by matching information, and a housing model information management module for generating user-customized housing model information based on the lifestyle information and delivering it to the user terminal 300 Big data-based residential model management server 100;
A big data-based BIM database 200 that is network-connected with the big data-based residential model management server 100 and delivers residential model information matching the user lifestyle information to the big data-based residential model management server 100 ; and
It is connected to the network with the big data-based residential model management server 100, and transmits user information to the big data-based residential model management server 100, and receives the user information from the big data-based residential model management server 100. User terminal 300 configured to receive the user-customized housing model information generated on the basis of; Big data-based user-customized housing model recommendation system comprising a.
In claim 7,
A GIS database ( 400); Big data-based user-customized housing model recommendation system, characterized in that it further comprises.

Images