KR102252599B1 - Apparatus for Land Appraisal Service and Land Appraisal Method, and Computer Readable Recording Medium - Google Patents

Abstract

The present invention relates to a land appraisal service device, a driving method of the device, and a computer readable recording medium which can provide users with a reasonable price based on objective data. According to an embodiment of the present invention, the land appraisal service device comprises: a storage unit which matches an image analysis result for random real estate across the country with real estate data related to the random real estate to store the same as a land appraisal result; and a control unit, when a user requests an estimated price for real estate in a designated area, providing the estimated price of the designated area based on the image analysis result of the designated area obtained upon request and the (pre)stored land appraisal result.

Description

Apparatus for Land Appraisal Service and Land Appraisal Method, and Computer Readable Recording Medium}

The present invention relates to a land appraisal service device, a method of driving the device, and a computer-readable recording medium, and in more detail, by using spatial images and artificial intelligence, the price of land is calculated and predicted in a rational manner compared to the conventional one. , Land appraisal that predicts the present value and future value of land by using spatial images and artificial intelligence technology without constructing real estate-related analysis data required in other existing analysis processes, and predicts the price in a non-face-to-face manner without visiting the site intuitively. It relates to an evaluation service device, a driving method of the device, and a computer-readable recording medium.

Looking at the number of recent land transactions in Korea, in 2017, about 1,300 transactions of 5 billion won or more in Seoul/Gyeonggi area, and 190,000 or less of 5 billion won are being actively carried out. However, the existing land value evaluation method does not reflect the rational value of the land by relying on the method of evaluating the value according to the recently traded price, and various development information and spatial information that can reflect the land value may be obtained. The reality is that it is difficult and difficult to understand. In particular, there is a problem that the future value of the land is determined by some real estate companies due to rumors of unfounded development plans.

In this respect, in recent years, the necessity of a system to reflect the rational value of land is urgently required.

Korean Patent Publication No. 10-2009-0103087 (2009.10.01) Korean Patent Publication No. 10-2002-0004710 (2002.01.16) Korean Patent Application Publication No. 10-2010-0021849 (2010.02.26) Korean Registered Patent Publication No. 10-1755182 (2017.06.30)

The embodiment of the present invention uses spatial images and artificial intelligence to reasonably calculate and predict the price of land compared to the existing ones, and spatial images and artificial intelligence technology without the construction of real estate-related analysis data required in other existing analysis processes. Its purpose is to provide a land appraisal service device that predicts the present value and future value of land by utilizing the system, and predicts the price intuitively without visiting the site in person, a driving method of the device, and a computer-readable recording medium. .

The land appraisal service device according to an embodiment of the present invention includes a storage unit that matches the video analysis result of an arbitrary real estate with real estate data related to the arbitrary real estate and stores it as a land appraisal result, and a real estate in a designated area by the user And a control unit configured to provide an estimated price of the designated area based on a result of analyzing the image of the designated area acquired at the time of the request and a result of the stored land appraisal of the designated area when requesting the estimated price for the designated area.

The control unit may generate a market price prediction model to which the stored land appraisal result is applied and use it when calculating the estimated price.

The control unit analyzes the image by acquiring more than the standard number of samples for random real estate nationwide, and learns and verifies the analysis result of the image and the real estate data by applying deep learning technology of artificial intelligence (AI). And completing the test to generate the market price prediction model.

The storage unit may store, as the real estate data, at least one of land usage status, administrative affiliation, cadastral map, surrounding traffic, and market price related to the arbitrary real estate.

The controller may use a satellite image or a drone image captured by a drone vehicle as an image for the arbitrary real estate.

In addition, the driving method of the land appraisal service device according to an embodiment of the present invention comprises the steps of: a storage unit matching the video analysis result for an arbitrary real estate with real estate data related to the arbitrary real estate and storing it as a land appraisal result, And when the user requests the estimated price for real estate in the designated area, providing the estimated price of the designated area based on the video analysis result of the designated area acquired at the time of the request and the stored land appraisal result. Includes steps.

The driving method may further include generating a market price prediction model to which the stored land appraisal result is applied and using it when calculating the estimated price.

In the step of generating the market price prediction model, the image is analyzed by acquiring a reference number or more samples for random real estate nationwide, and the analysis result of the image and the real estate data are applied to deep learning technology of artificial intelligence (AI). Training, verification, and testing may be completed to generate the price prediction model.

In the storing of the real estate, at least one of land use status, administrative affiliation, cadastral map, surrounding traffic, and market price related to the arbitrary real estate may be stored as the real estate data.

As the image for the arbitrary real estate, a satellite image or a drone image captured by a drone vehicle may be used.

On the other hand, the computer-readable recording medium according to an embodiment of the present invention is a computer-readable recording medium that stores a program for executing the land appraisal method, the land appraisal method, a designated number of images for an arbitrary real estate Analyzing the analysis result of the image and real estate data related to the arbitrary real estate by applying deep learning technology of artificial intelligence (AI) to complete learning, verification, and testing to generate a market price prediction model, and specified by the user When an estimated price for real estate in a region is requested, a step of calculating the estimated price of the designated region is performed by applying the result of analyzing the image of the designated region acquired at the time of the request to the generated market price prediction model.

According to an embodiment of the present invention, it is possible to reasonably present a market price based on objective data to users by solving problems such as determining the future value of a specific land by some real estate agents due to rumors of existing groundless development plans, etc. I will be able to.

In addition, by using artificial intelligence and spatial images in land appraisal and evaluation according to an embodiment of the present invention, the present value and future value of the land can be predicted, and the price can be predicted in a non-face-to-face manner without a site visit.

1 is a diagram showing a land appraisal system according to an embodiment of the present invention;
2 is a diagram for explaining a land appraisal process using spatial images;
3 is a block diagram illustrating a detailed structure of the land appraisal service device of FIG. 1;
4 is a flowchart showing a driving process of the land appraisal service device of FIG. 1 according to an embodiment of the present invention, and
5 is a flowchart showing a land appraisal method according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

1 is a diagram showing a land appraisal system according to an embodiment of the present invention, and FIG. 2 is a view for explaining a land appraisal process using a spatial image.

As shown in Fig. 1, the land appraisal system 90 according to an embodiment of the present invention includes a user terminal device 100, a communication network 110, a land appraisal (service) device 120, and a third-party device ( 130).

Here, "including some or all" means that some components such as the third-party device 130 are omitted so that the land appraisal system 90 is configured, or a component constituting the land appraisal service device 120 It means that some or all of the communication network 110 is integrated into a network device (eg, a wireless switching device, etc.) or a third-party device 130 to be configured, and to help a sufficient understanding of the invention. Explain that it is all inclusive.

The user terminal device 100 includes terminal devices of users who access the service provided by the land appraisal service device 120 and use the service. The user terminal device 100 includes various image display devices such as smartphones held by users. For example, the user terminal device 100 may include a desktop computer, a laptop computer, a tablet PC, a smart phone, a smart TV, and further, a wearable device such as a domestic company S's Gall* Gear. The peripheral device may further include an artificial intelligence speaker or the like. The user terminal device 100 accesses the service of the land appraisal service device 120 and provides address information for a specific area requested by the user (eg, providing address information for parcels), so that the land for that area is easily You can check the estimated price for real estate such as buildings or buildings. For example, the user terminal device 100 may input address information of a place where you want to check the estimated price of real estate in a search window, such as a search portal service. Just by entering the address information like this, you can simply check the estimated price for the real estate in the area. Since a user accesses the land appraisal service device 120 through the user terminal device 100 and checks the estimated price at a desired place, there may be various methods, so in the embodiment of the present invention, it is specifically limited to any one form. I won't.

The communication network 110 includes all wired and wireless communication networks. For example, as the communication network 110, a wired or wireless Internet network may be used or interlocked. Here, the wired network includes an Internet network such as a cable network or a public telephone network (PSTN), and the wireless communication network includes CDMA, WCDMA, GSM, Evolved Packet Core (EPC), Long Term Evolution (LTE), and Wibro networks. It is meant to include. Of course, the communication network 110 according to the embodiment of the present invention is not limited thereto, and may be used as an access network for a next-generation mobile communication system, for example, a cloud computing network or a 5G network under a cloud computing environment. For example, if the communication network 110 is a wired communication network, the access point within the communication network 110 can be connected to the switching center of the telephone station, but in the case of a wireless communication network, data is accessed by accessing SGSN or GGSN (Gateway GPRS Support Node) operated by a communication company. It can process or process data by accessing various repeaters such as BTS (Base Transceiver Station), NodeB, and e-NodeB.

The communication network 110 may include an access point. Here, the access point includes a small base station such as a femto or pico base station that is frequently installed in a building. Here, the femto or pico base station is classified according to how many user terminal devices 100 and the like can be accessed according to the classification of the small base station. Of course, the access point may include a short-range communication module for performing short-range communication such as ZigBee and Wi-Fi, such as the user terminal device 100. The access point may use TCP/IP or Real-Time Streaming Protocol (RTSP) for wireless communication. Here, short-range communication may be performed in various standards such as Bluetooth, Zigbee, infrared, radio frequency (RF) such as ultra high frequency (UHF) and very high frequency (VHF), and ultra wideband communication (UWB) in addition to Wi-Fi. Accordingly, the access point extracts the location of the data packet, designates the best communication path for the extracted location, and transmits the data packet to the next device, for example, the land appraisal service device 120 along the designated communication path. The access point can share several lines in a general network environment, and includes, for example, a router, a repeater, and a repeater.

The land appraisal service device 120 according to an embodiment of the present invention builds a land appraisal model using artificial intelligence and spatial images, and through this, the user terminal device 100 calculates the estimated price of real estate for a specific area. Can be presented. First, the land appraisal service device 120 constructs an algorithm model capable of predicting the market price for real estate of land or buildings according to an embodiment of the present invention. To this end, an embodiment of the present invention performs a deep learning operation using an artificial intelligence program. For example, the land appraisal service device 120 acquires sample data or training samples for real estate in a certain area across the country, and, for example, as sample data, an image (or image) such as parcels for real estate in a certain area. It acquires and analyzes it, and objective data related to the real estate, for example, land use status, real estate data related to administrative (for example, city, county, district, etc.) affiliation, surrounding traffic information, topographic information, past market prices, etc. Based on this, deep learning operations of artificial intelligence are performed to conduct learning, verification, and testing. Of course, in this process, learning through deep learning increases the accuracy of prediction as the amount of data increases, so it is possible to acquire and process at least 10 million sample data nationwide. Of course, in the case of providing services by restricting land valuation to the metropolitan area of Korea, it does not need to be nationwide. In an embodiment of the present invention, it is preferable to use a number of sample data that can satisfy prediction accuracy. In addition, the image analysis result of the sample data and data related to real estate may be matched and stored. This can be summarized as shown in <Table 1> briefly. <Table 1> shows the attribute information of the training sample.

Parcel video
(Including RGB) Land use status City/Gun/Gu Affiliation Surrounding traffic quote Input Layer Output Layer

Of course, the land appraisal model according to an embodiment of the present invention does not generate a model in the land appraisal service device 120, but a separate program developer such as a third-party device 130 generates and provides a model. The appraisal service device 120 may be capable of constructing a corresponding model. Therefore, in the embodiment of the present invention, there will be no particular limitation on where such a prediction model is generated. However, for convenience of explanation, it will be described as being generated by the land appraisal service device 120.

For example, the land appraisal service device 120 is an aerial photograph provided by the National Geographic Information Institute in order to implement a market price prediction technology for each land lot using artificial intelligence technology, and a series provided by the Korea Land Information Corporation (LX). Using cadastral maps, for example, you can create training samples for each lot by overlapping them. This is the training data that the training sample is used for learning in an artificial intelligence program, and it becomes the sample data. In other words, when acquiring a sample, an image of a part corresponding to a specific lot number of the continuous cadastral map can be acquired and used in the aerial photograph. For example, let's assume that an aerial photograph of Gwangjin-gu in Seoul is obtained as map data. Accordingly, on the map data, each lot of land can be classified based on the continuous cadastral map, and it is possible to perform image analysis by extracting a part of the map data corresponding to the corresponding lot. In order to obtain sample data according to an embodiment of the present invention, it may be understood to the extent that a photographed image and cadastral information of a specific area can be used. The land appraisal service device 120 may store data by reflecting cadastral information on the map data.

In addition, the land appraisal service apparatus 120 may convert an RGB spectral value (or pixel value) from the image of the acquired sample data into a spatial graphic as shown in FIG. 2. Here, the pixel value of the pixel may include various values. Typically, pixels are expressed in 256 gradations for each color. In other words, even in the case of the same color (eg R), the color can be expressed in 256 steps. In addition, the color of the pixel may be expressed or have a wavelength value related to a wavelength or information related to a wavelength band. Normally, color expression is based on CIE-1931.

The land appraisal service apparatus 120 according to an embodiment of the present invention stores a spatially graphic value as shown in FIG. 2 in a memory rather than substantially visualizing it as shown in FIG. 2. That is, each acquired sample data can be analyzed to store RGB pixel values or brightness values (or luminance values). Since the result of the analysis is used through image analysis, it is simply referred to as “analysis result” in the exemplary embodiment of the present invention. In other words, in the embodiment of the present invention, since various analysis results for pixels of an image can be used, it is intended to be expressed as an analysis result of an image or an analysis result of a pixel.

As shown in FIG. 2, when spatial figures are converted, the same pixel units and values are extracted into the same range figure, and then vectorized. Here, "to vectorize" means a method of formulating and recording various lines and points included in an image. For example, a bitmap contrasts with the memory of the image as it appears as a collection of points. In other words, since bitmaps are stored as dots, the capacity is much smaller, but if the picture is reduced or enlarged, the image quality may change severely due to the need to increase or compress the dots. However, even if the size of the image is changed, the resolution does not change. In addition, image information (e.g., RGB band) superimposed on the parcel, land use status, parcel property information including city, county and district affiliation, surrounding traffic information including roads and subways, and terrain information including flatland and slopes, etc. It consists of attribute information. This was covered in <Table 1> above. The output layer is set to the price of the lot of the training sample. In order to extract statistical correlation through learning, training samples are constructed and deep learning techniques are applied to train, validate, and test the training samples. As a result, the model of the price prediction algorithm for each land lot is finally completed. Meanwhile, in order to merge values of the same pixel when recognizing an image, a first pixel and a pixel value adjacent to the remaining pixels may be compared. This can be used, for example, to clarify the boundaries of parcels based on cadastral information.

Meanwhile, the land appraisal service apparatus 120 according to an embodiment of the present invention may analyze an image based on a cloud on a web/mobile. Images are acquired or serviced satellite images or drone images are uploaded (periodically). Satellite images or drone images may be provided by a third-party device 130 as seen in FIG. 1. In addition, the land appraisal service device 120 may estimate an appropriate spatial resolution that can be analyzed when extracting the RGB value of an image based on artificial intelligence (AI). In addition, the spatial resolution is found and analyzed to find the reflection value of the image, that is, the brightness value, and analysis data is created. It is possible to analyze in real time the regression model of the brightness value of the image, the RGB value, that is, the pixel value, and the announced land price of real estate. As mentioned above, since image analysis can be performed in various ways, it will not be specifically limited to any one form in the exemplary embodiment of the present invention.

In addition, the land appraisal service device 120 may use a platform technology that conveniently analyzes on the web/mobile. When applying for satellite image service, land appraisal results using RGB band information and other information from Landsat satellite images can be provided. Landsat means sending an image of the surface captured by a camera from a resource exploration satellite launched by NASA to the ground. When applying for a drone video service, it is possible to provide a more accurate and specific appraisal result by providing land appraisal results using RGB band information and other information of drone video. When applying for a drone video service, a drone video shooting service can also be provided by contacting a drone shooting company in real time. In the case of using drone video, it may be possible to process fees through the relay business between the photographer and the user.

In summary, the land appraisal service device 120 according to an embodiment of the present invention applies deep learning technology of artificial intelligence using at least 10 million samples of sample data nationwide by using spatial images related to artificial intelligence and real estate. The solution is trained, verified, and tested to generate a predictive model. Of course, it can be seen that this improves the accuracy of the prediction model. Therefore, if the user wants to know the estimated price for a specific lot of land, for example, real estate in a specific area desired by the user based on this prediction model, the land appraisal service device 120 applies the image analysis result of the corresponding lot to the prediction model. Thus, if there is a value of a matching location, a market price that matches the location can be presented, but in the case of a region not included in the sample data, it can be considered that a predicted price is presented. For example, if there are 10,000 lots related to real estate in Gwangjin-gu, only 500 training samples may be used. Therefore, it is an advantage of artificial intelligence to be able to calculate the estimated price for other parcels in Gwangjin-gu even through the prediction model based on the corresponding 500 pieces. In other words, artificial intelligence differs in that it can perform predictions, unlike existing rule-based methods. Therefore, the existing rule-based method does not produce a result if it is not in the rule, but the deep learning method of artificial intelligence can calculate the prediction result. To this end, if there is a place that is analyzed as a pixel value of a spatial image under the same conditions in an adjacent area other than Gwangjin-gu, it is possible to determine whether it is acceptable to calculate the market price of the corresponding area, and to provide a response to the user's request based on this. In other words, in response to the user's request, the estimated price for the property, such as land, can be presented.

The third-party device 130 may be a server of a company that generates and provides a prediction model according to an embodiment of the present invention, or may be a server or a computer of a company that develops and provides a program required in the embodiment of the present invention. In addition, it may be a server or computer of a company that provides aerial photographs or drone images to reflect the changing real estate situation in a specific area in real time or periodically. In addition, the sub-party device 130 may include a server of a government agency or a related institution, such as the National Geographic Information Institute.

3 is a block diagram illustrating a detailed structure of the land appraisal service device of FIG. 1.

As shown in FIG. 3, the land appraisal service device 120 according to an embodiment of the present invention includes a communication interface unit 300, a control unit 310, a land appraisal processing unit 320, and a storage unit 330. Includes some or all.

Here, "including some or all" means that some components such as the storage unit 330 are omitted so that the land appraisal service device 120 is configured, or some components such as the land appraisal processing unit 320 are It refers to something that can be integrated and configured with other components such as the control unit 310, and will be described as including all in order to help a sufficient understanding of the invention.

The communication interface unit 300 may communicate with the user terminal device 100 or the third-party device 130 via the communication network 110 of FIG. 1. In the process of performing communication, the communication interface unit 300 may perform operations such as modulation/demodulation, muxing/demuxing, encoding/decoding, and scaling of resolution conversion, which are well known to those skilled in the art. It should be omitted.

The communication interface unit 300 may receive aerial photographs or drone images related thereto from the third-party device 130 so as to acquire at least 10 million training samples nationwide, and transmit them to the control unit 310. Alternatively, the continuous cadastral map data provided by the LX may be received and transmitted to the control unit 310. Of course, this provides relevant data to be used to generate a prediction model according to an embodiment of the present invention.

On the other hand, the communication interface unit 300 may perform an operation for providing a service according to an embodiment of the present invention to the user terminal device 100 after a prediction model using artificial intelligence and spatial images is generated. When there is a service request from the user terminal device 100, a service screen may be transmitted under the control of the controller 310.

In addition, when the user terminal device 100 provides address information of a specific region through the provided service screen, the communication interface unit 300 controls the information, etc., when it is desired to know the estimated price for real estate such as land. It is transmitted to 310, and as a result of a response according to the user's request, information of an estimated price based on the corresponding address information may be provided to the user terminal device 100.

The control unit 310 is in charge of overall control operations of the communication interface unit 300, the land appraisal evaluation processing unit 320, and the storage unit 330 of FIG. 3. Representatively, the control unit 310 performs an operation for generating a prediction model for land appraisal evaluation according to an embodiment of the present invention in connection with the land appraisal evaluation processing unit 320, and based on the performed prediction model, the user terminal device When (100) requests an estimated price for a specific area (eg, lot according to a lot), the estimated price may be provided as a result of a response to the request.

In addition, in the process of generating the prediction model, the control unit 310 temporarily stores aerial photographs or drone images of a specific area provided from the third-party device 130 in the storage unit 330 and then transfers the data to the land appraisal processing unit 320. It can be provided, and the data that has been analyzed by the land appraisal processing unit 320 may be systematically classified and stored in the DB 120a of FIG. 1, so that the communication interface unit 300 may be controlled.

The land appraisal processing unit 320 performs an operation for appraising and evaluating land by using artificial intelligence and spatial images according to an embodiment of the present invention. Of course, in the process of objection, the land appraisal processing unit 320 can generate a prediction model using artificial intelligence, and of course, even if the prediction model is not generated by itself, it can receive and install an initial model and perform subsequent operations. have. In other words, if the initial model is to analyze 10 million parcels nationwide, the land appraisal processing unit 320 continuously learns and uploads the image analysis results related to the newly provided parcels. By gradually accumulating and using data such as 50 million pieces, it is possible to increase the accuracy of the estimated price.

Above all, the land appraisal processing unit 320 performs a deep learning operation of artificial intelligence, in contrast to not being able to produce a result when there is no matching policy like the existing rule-based operation method. Even if there is no data that matches exactly, the result can be calculated based on the data of the neighboring region, or the result can be calculated based on the data of other regions under similar conditions. However, when calculating the results by referring to data from other regions, it may be desirable to belong to an adjacent region or the same city or district. In this way, the land appraisal processing unit 320 may predict the result through self-learning and present the result calculated to the user, for example, using data of an autonomous district under similar conditions among 25 autonomous districts in Seoul.

In addition, the land appraisal processing unit 320 can calculate the estimated price for the land requested by the user by reflecting it when a new environmental variable, such as development information of an adjacent area, is input based on the structured data. It can also be said that the advantage of artificial intelligence deep learning. For example, if there is a favorable development in the adjacent area under the same conditions (eg, the analysis results of spatial images are the same), if the market price has risen, the price can be predicted based on this and presented to the user.

Above all, when the land appraisal processing unit 320 according to an embodiment of the present invention requests an estimated price for the land, etc. of the place requested by the user, the image is secured based on the address information of the corresponding region, and then As a result of the analysis, it is possible to find, for example, parcels with similar conditions, based on, for example, pixel values, etc., and present a market price based on this. For example, a request was made for an estimated price of a forest, but it is not desirable to search for data on the land and calculate the estimated price. Accordingly, it is preferable that the land appraisal processing unit 320 presents the estimated price based on the analysis result of the spatial image.

Furthermore, when a user requests an estimated price for a specific area, the land appraisal processing unit 320 according to an embodiment of the present invention does not use only the image for a specific lot in the area, but an analysis result of the image within the specified range. Can be used together. Through this, it will be possible to calculate a more accurate predicted price by further analyzing the surrounding traffic and applying it to the predictive model. It can be seen that the accuracy of the results increases as more data are used.

The storage unit 330 may store various types of information or data processed under the control of the controller 310. Here, since the terms of information and data are used interchangeably in practice, there will be no particular limitation on their meaning. For example, when looking at video data in image data, binary 16 bits and 32 bits related to pixels are referred to as pixel data, but information related to compression, that is, encoding, is generally referred to as information. Except for these, since they are used interchangeably, the meaning of such terms will not be particularly limited.

The storage unit 330 may also store attribute information as shown in Table 1 in the form of a lookup table (LUT). Accordingly, when the control unit 310 searches through RGB data for a specific lot requested by the user, the storage unit 330 may output data such as price information matched thereto. For example, when a user provides address information on a lot of a specific area, the control unit 310 can obtain an image based on the address information, and the acquired image is obtained from the land appraisal processing unit 320. Can be analyzed. Accordingly, when the analysis result is provided to the control unit 310 again, the storage unit 330 may output a market price matching the analysis result.

On the other hand, as another embodiment of the present invention, the control unit 310 may include a CPU and a memory, and may be formed into a single chip. The CPU includes a control circuit, an operation unit (ALU), an instruction analysis unit, and a registry, and the memory may include RAM. The control circuit performs the control operation, the operation unit operates the operation of binary bit information, and the instruction analysis unit converts high-level language into machine language and machine language into high-level language, including interpreters and compilers. In addition, the registry can be involved in software data storage. According to the above configuration, for example, by copying the program stored in the land appraisal processing unit 320 at the beginning of the operation of the land appraisal evaluation service device 120 of Fig. 1, loading it into memory, that is, RAM, and executing it. You can quickly increase the processing speed of data operations.

In addition to the above, the communication interface unit 300, the control unit 310, the land appraisal processing unit 320, and the storage unit 330 of FIG. 3 can perform various operations. I want to replace it with the contents.

4 is a flowchart illustrating a driving process of the land appraisal service apparatus of FIG. 1 according to an embodiment of the present invention.

For convenience of explanation, referring to FIG. 4 together with FIG. 1, the land appraisal service device 120 of FIG. 1 according to an embodiment of the present invention is The data is matched and stored as a result of land appraisal evaluation (S500). Of course, it is possible to create a prediction model using deep learning of artificial intelligence and store the generated prediction model's memory or registry as mentioned above.

In addition, when a user requests an estimated price for real estate in a designated area, the land appraisal service device 120 is based on the image analysis result of the designated area acquired at the time of request and the stored land appraisal result. Provides an estimated price of (S510).

As described above, the land appraisal service device 120 obtains an image of the address information and applies the analysis result of the image to the predicted model when, for example, the user provides address information for the lot number of the land for which the predicted price is desired. Calculate the price.

In addition to the above contents, the land appraisal service apparatus 120 of FIG. 1 can perform various operations, and other details have been sufficiently described above, and thus the contents will be substituted.

5 is a flowchart showing a land appraisal method according to an embodiment of the present invention.

For convenience of explanation, referring to FIG. 5 together with FIG. 1, the land appraisal service apparatus 120 of FIG. 1 according to an embodiment of the present invention extracts RGB values of satellite images and drone images, and based on the extracted values ( For example, neighboring pixels in the same or similar wavelength band are merged (S500).

For example, as a result of analyzing an image, it can be considered that an area having similar characteristics of pixels is regarded as one area or processed. Of course, cadastral information using cadastral maps, etc. may be used in the process of objection.

In addition, the land appraisal service device 120 recognizes and vectorizes the outside of the merged pixel (S510). In this process, the land appraisal service device 120 may store, for example, a wavelength value as an attribute. Here, vectorization means recognizing it as a figure, unlike a bitmap. For example, figure recognition can also be recognized through the pixel coordinate value of the boundary.

Subsequently, the land appraisal service device 120 stores attribute information such as a wavelength value as a spatial information file (S520). As mentioned above, various data may be stored in the spatial information file. Representatively, data such as analysis results of images on specific parcels at a national level, surrounding traffic, and land use status may be included.

In addition, the land appraisal service device 120 extracts X and Y based on the address of the published land price data and performs statistical training with the published land price data on the values of the extracted X and Y pixels (S530).

Subsequently, the land appraisal service device 120 extracts a real estate price pattern of a specific wavelength band (S540). Here, the wavelength band may be understood to the extent that the wavelength value of the pixel is used as an analysis or search parameter. In other words, as a value obtained from a pixel through image analysis, a value related to various parameters such as a color value, a brightness value, and a wavelength value can be obtained, and thus at least one of these values can be used.

The land appraisal service device 120 may extract an estimated price of a specific area requested by the user based on the extracted real estate price pattern (S550).

In addition to the above, the land appraisal service apparatus 120 of FIG. 5 according to an embodiment of the present invention can perform various operations, and other details have been sufficiently described above, and thus the contents will be substituted.

On the other hand, even if all the constituent elements constituting an embodiment of the present invention are described as being combined into one or operating in combination, the present invention is not necessarily limited to this embodiment. That is, within the scope of the object of the present invention, all the constituent elements may be selectively combined and operated in one or more. In addition, although all the components may be implemented as one independent hardware, a program module that performs some or all functions combined in one or a plurality of hardware by selectively combining some or all of the components. It may be implemented as a computer program having Codes and code segments constituting the computer program may be easily inferred by those skilled in the art. Such a computer program is stored in a non-transitory computer readable media that can be read by a computer and is read and executed by a computer, thereby implementing an embodiment of the present invention.

Here, the non-transitory readable recording medium is not a medium that stores data for a short moment, such as a register, cache, memory, etc., but a medium that stores data semi-permanently and can be read by a device. . Specifically, the above-described programs may be provided by being stored in a non-transitory readable recording medium such as a CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM, or the like.

In the above, preferred embodiments of the present invention have been illustrated and described, but the present invention is not limited to the specific embodiments described above, and is generally used in the technical field to which the present invention pertains without departing from the gist of the present invention claimed in the claims. Of course, various modifications may be made by those skilled in the art, and these modifications should not be understood individually from the technical idea or perspective of the present invention.

100: user terminal device 110: communication network
120: land appraisal service device 130: third party device
300: communication interface unit 310: control unit
320: land appraisal and processing unit 330: storage unit

Claims (11)

A storage unit for matching the video analysis result of the arbitrary real estate with real estate data related to the arbitrary real estate and storing it as a land appraisal result; And
When a user requests an estimated price for real estate in a designated area, a control unit for providing an estimated price of the designated area based on the result of analyzing the image of the designated area acquired at the time of the request and the result of the stored land appraisal evaluation; But,
The control unit,
An image related to an arbitrary real estate is acquired as sample data, and a space is plotted based on the pixel value obtained by analyzing the acquired image, and when the space is plotted, the same pixel unit value is extracted as a figure in the same range and vectorized. , Generating the image analysis result by formulating and recording lines and points for the vectorization,
The control unit,
Land appraisal service device for finding parcels with similar conditions based on pixel values as a result of image analysis of the designated area according to the user's request, from the stored land appraisal results, and providing an estimated price based on the found parcels . The method of claim 1,
The control unit generates a market price prediction model in which the stored land appraisal results are reflected and is used when calculating the estimated price. The method of claim 2,
The control unit analyzes the image by acquiring sample images of more than a standard number of random real estates nationwide, and learns the analysis result of the image and the real estate data by applying deep learning technology of artificial intelligence (AI), Land appraisal service device for generating the market price prediction model by completing verification and testing. The method of claim 1,
The storage unit, as the real estate data, the land appraisal service device for storing at least one of the land use status, administrative affiliation, cadastral map, surrounding traffic, and market price related to the arbitrary real estate as the real estate data. The method of claim 1,
The control unit is a land appraisal service device using a satellite image or a drone image captured by a drone vehicle as an image for the arbitrary real estate. Matching, by a storage unit, a result of analyzing an image of an arbitrary real estate with real estate data related to the arbitrary real estate and storing it as a result of land appraisal; And
When a user requests an estimated price for real estate in a designated area, providing an estimated price of the designated area based on the video analysis result of the designated area acquired at the time of the request and the stored land appraisal result Including ;,
The control unit acquires an image related to an arbitrary real estate as sample data, analyzes the acquired image to form a space based on a pixel value obtained, and when plotting the space, the same pixel unit value is converted into a figure in the same range. Extracting and vectorizing, and generating the image analysis result by formulating and recording lines and points for the vectorization; And
The control unit, at the request of the user, finds parcels with similar conditions based on pixel values as a result of image analysis of the designated area from the stored land appraisal results, and provides an estimated price based on the found parcels. ; To
Driving method of the land appraisal service device further comprising. The method of claim 6,
Generating a market price prediction model reflecting the stored land appraisal result and using it when calculating the estimated price; and driving method of the land appraisal service device further comprising. The method of claim 7,
Generating the price prediction model,
Analyzing the image by acquiring more than the standard number of sample images for random real estate nationwide, and completing learning, verification, and testing by applying deep learning technology of artificial intelligence (AI) to the analysis result of the image and the real estate data. A method of driving a land appraisal service device that generates a market price prediction model. The method of claim 6,
The storing step,
A method of driving a land appraisal service device for storing at least one data of land use status, administrative affiliation, cadastral map, surrounding traffic and market price related to the arbitrary real estate as the real estate data. The method of claim 6,
A method of driving a land appraisal service device using a satellite image or a drone image captured by a drone vehicle as an image for the arbitrary real estate. As a computer-readable recording medium storing a program for executing the land appraisal method,
The above land appraisal method is:
Analyzes a specified number of images for random real estate, and completes learning, verification and testing of the analysis result of the images and real estate data related to the random real estate by applying deep learning technology of artificial intelligence (AI) to create a market price prediction model. Generating; And
When a user requests an estimated price for real estate in a designated area, calculating the estimated price of the designated area by applying the result of analyzing the image of the designated area acquired at the time of the request to the generated market price prediction model; ,
An image related to an arbitrary real estate is acquired as sample data, and a space is plotted based on the pixel value obtained by analyzing the acquired image, and when the space is plotted, the same pixel unit value is extracted as a figure in the same range and vectorized. And generating the image analysis result by formulating and recording lines and points for the vectorization; And
At the request of the user, finding parcels with similar conditions based on pixel values as a result of image analysis of the designated area from the stored land appraisal results, and providing an estimated price based on the found parcels;
Computer-readable recording medium for further execution.

Images