KR20220112334A - Location estimation apparatus and method using heat map of received signal strength, and recording medium on which a program for performing the same - Google Patents

Abstract

A location estimation device is provided. The location estimation device receives a radio signal transmitted from a relay device, collects reference information indicating a location where a repeater is installed and the received strength of a wireless signal, generates image information to indicate a level of the received strength of the reference information, creates a location estimation model to estimate location information of receiving a radio signal from the image information, and estimates the location information from the image information based on the location estimation model.

Description

Apparatus and method for estimating location using a heat map of received signal strength, and a recording medium on which a program for performing the same is recorded

The present invention relates to a location estimating apparatus and method using a heat map of received signal strength, and more particularly, to a location estimating apparatus and method for estimating a location using a heat map indicating received signal strength.

The conventional Wi-Fi received signal strength index (RSSI: Received Signal Strength Indication) location measurement technique using the effective to identify the location of the user indoors. The location measurement technique based on Wi-Fi RSSI estimates the signal strength of access points (APs) in the receiver and identifies the user's indoor location.

Such Wi-Fi RSSI-based location measurement technique estimates a user's location using raw RSSI signals obtained from APs. However, raw RSSI signals are easily deformed or interfered with in indoor channel conditions. Signal interference in indoor channel conditions is a major factor in reducing the positioning performance of Wi-Fi RSSI-based positioning techniques.

Accordingly, there is a need for a method for reducing the influence of deformation and interference and for performing more accurate position measurement in indoor channel conditions.

The technical problem to be solved by the present invention is to provide an apparatus and method for estimating a position for generating an image from the strength of a signal transmitted from a repeater, and estimating a position using the generated image.

One aspect of the present invention, a receiving unit for receiving a radio signal transmitted from a relay device prepared in advance; a reception strength collecting unit that collects reference information indicating a location where the relay device is installed and reception strength of the radio signal; an image generating unit generating image information to indicate the level of the reception intensity in the reference information; a learning unit for generating a location estimation model by learning the image information to estimate location information on which the radio signal is received from the image information; a location estimator for estimating location information from the image information based on the location estimation model; and an output unit for outputting the location information.

In addition, the learning unit may include: a first learning module that extracts a feature vector by analyzing the image information, and generates a first location estimation model by learning the image information to estimate first feature information matching the feature vector; and estimating second characteristic information according to the first characteristic information, and learning the first characteristic information to estimate position information matching the second characteristic information to generate a second position estimation model, and a second learning module configured to generate the second position estimation model to estimate the second characteristic information from the first characteristic information, based on the second characteristic information.

The position estimation unit may be configured to estimate first characteristic information from the image information based on the first position estimation model, and based on the second position estimation model, to obtain the second characteristic information from the first characteristic information. , the second feature information may be estimated in consideration of previously estimated second feature information, and the location information may be estimated from the second feature information based on the second location estimation model.

In addition, the image generating unit generates image information so that reception strengths of a plurality of wireless signals received from a plurality of repeaters installed at different locations appear, respectively, and is preset with respect to the level of reception strength of the wireless signals Based on the plurality of level ranges, reception strengths satisfying different level ranges may be represented in different shapes.

Another aspect of the present invention provides a method for estimating a position in a position estimating apparatus using a heat map of received signal strength, the method comprising: receiving a radio signal transmitted from a repeater provided in advance by a receiver; collecting, by a reception strength collecting unit, reference information indicating a location where the repeater is installed, and reception strength of the radio signal; generating, by an image generator, image information to indicate the level of the reception intensity in the reference information; generating a location estimation model by learning the image information so that a learning unit estimates location information on which the radio signal is received from the image information; estimating, by a location estimation unit, location information from the image information based on the location estimation model; and outputting the location information by an output unit.

In addition, the step of generating a location estimation model by learning the image information may include extracting a feature vector by analyzing the image information by a first learning module, and estimating first feature information matching the feature vector. generating a first position estimation model by learning ; and a second learning module estimating second characteristic information according to the first characteristic information, and learning the first characteristic information to estimate position information matching the second characteristic information to generate a second position estimation model. , generating the second position estimation model to estimate the second characteristic information from the first characteristic information based on the previously estimated second characteristic information.

The estimating of the location information from the image information may include estimating first feature information from the image information based on the first location estimation model, and estimating the first feature information based on the second location estimation model. Estimating the second characteristic information from information, estimating the second characteristic information in consideration of previously estimated second characteristic information, and based on the second position estimation model, the location information from the second characteristic information can be estimated.

In addition, the generating of the image information so that the level of the reception strength appears, generating the image information so that the reception strength of a plurality of wireless signals received from a plurality of repeaters installed in different positions respectively appears, the wireless signal Based on a plurality of level ranges set in advance for the level of the reception strength of , reception strengths satisfying different level ranges may be represented in different shapes.

Another aspect of the present invention may be a computer-readable recording medium in which a computer program is recorded for performing a location estimation method.

According to one aspect of the present invention described above, by providing an apparatus and method for estimating a location using a heat map of a received signal intensity, an image is generated from the intensity of a signal transmitted from a repeater, and a location is estimated using the generated image. can do.

1 is a schematic diagram of a location estimation system including a location estimation apparatus according to an embodiment of the present invention.
2 is a control block diagram of a location estimation apparatus according to an embodiment of the present invention.
3 is a block diagram illustrating a process of generating a location estimation model in the learning unit of FIG. 2 .
4 is a block diagram illustrating a process of estimating location information by the location estimator of FIG. 2 .
5 is a schematic diagram illustrating an embodiment of image information generated by the image generator of FIG. 2 .
6 is a schematic diagram illustrating an embodiment of a location estimation model generated by the learning unit of FIG. 2 .
7 is a flowchart of a location estimation method according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0013] Reference is made to the accompanying drawings, which show by way of illustration specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the present invention. It should be understood that the various embodiments of the present invention are different but need not be mutually exclusive. For example, certain shapes, structures, and characteristics described herein with respect to one embodiment may be implemented in other embodiments without departing from the spirit and scope of the invention. In addition, it should be understood that the location or arrangement of individual components within each disclosed embodiment may be changed without departing from the spirit and scope of the present invention. Accordingly, the detailed description set forth below is not intended to be taken in a limiting sense, and the scope of the present invention, if properly described, is limited only by the appended claims, along with all scope equivalents to those claimed. Like reference numerals in the drawings refer to the same or similar functions throughout the various aspects.

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

1 is a schematic diagram of a location estimation system including a location estimation apparatus according to an embodiment of the present invention.

The position estimating system 1 may be provided to estimate the position of the position estimating apparatus 100 according to signals transmitted from the plurality of repeaters 200 .

To this end, the relay device 200 may transmit a wireless signal, where the wireless signal may mean a wireless signal such as Wi-Fi (Wireless Fidelity) or Bluetooth.

Accordingly, the relay device 200 may refer to a device provided to transmit wireless signals such as a beacon, a Wi-Fi transmitter, an access point (AP) device, and a wireless router.

In this regard, the relay device 200 may set reference information indicating the location where the relay device 200 is installed in advance, and accordingly, the relay device 200 transmits the reference information through a wireless signal to the location estimation device ( 100) can be forwarded.

On the other hand, the location estimating apparatus 100 may receive a radio signal transmitted from the repeater 200, in this case, the location estimating apparatus 100 is a plurality of transmitted from a plurality of repeaters 200 installed in different locations. Each of the radio signals can be received.

Also, the location estimator 100 may receive reference information from the relay device 200 , and in this case, the location estimation device 100 receives a plurality of pieces of reference information from a plurality of relay devices 200 installed at different locations. Each can be delivered.

As such, the location estimating apparatus 100 may be provided in the shape of a mobile terminal or the like, or the location estimating apparatus 100 may be provided to be embedded in a terminal such as a smart phone.

Accordingly, the location estimation apparatus 100 may generate image information according to the reference information and the reception strength of the radio signal.

Here, the reference information may be set to indicate a location where the relay device 200 is installed.

The reception strength may mean the strength of a radio signal received by the location estimation apparatus 100, and such reception strength may be expressed using a Received Signal Strength Indication (RSSI).

In this case, the received signal strength index can be understood as a technique prepared to measure and indicate the strength of a signal received from the terminal.

Also, the image information may be generated to indicate the level of reception intensity in the reference information, and in this case, the image information may be generated to indicate different reception strengths in different shapes.

As such, the image information may be generated using a heat map technique in which arbitrary information is expressed in various colors of a heat distribution shape, and in this case, the image information may represent colors of different reception intensities differently.

Accordingly, the location estimating apparatus 100 may estimate location information using the image information, and in this case, the location information may be generated to indicate a location at which the radio signal transmitted from the relay apparatus 200 is received.

Here, the location information may mean coordinates based on the plurality of relay devices 200 , in other words, the location information may be provided to indicate a relative location with respect to the reference information.

As such, the location estimation system 1 may be provided so that the location estimation device 100 receives radio signals transmitted from a plurality of repeaters 200 to estimate location information, and as such, the location estimation system 1 ) may have an effect of more accurately estimating location information in an indoor space in which a plurality of relay devices 200 are installed.

Hereinafter, a location estimation apparatus according to an embodiment of the present invention will be described in detail.

2 is a control block diagram of a location estimation apparatus according to an embodiment of the present invention.

The position estimating apparatus 100 may include a receiving unit 110 , a receiving strength collecting unit 120 , an image generating unit 130 , a learning unit 140 , a position estimating unit 150 , and an output unit 160 . .

In addition, the location estimation apparatus 100 may be implemented by more components than the components shown in FIG. 2 , and may be implemented by fewer components. Alternatively, in the position estimating apparatus 100 , at least two components provided in the position estimating apparatus 100 may be integrated into one component, and one component may perform a complex function. Hereinafter, the above-described components will be described in detail.

The receiver 110 may receive a wireless signal transmitted from the relay device 200 prepared in advance, and in this case, the receiver 110 may receive a plurality of wireless signals transmitted from the plurality of relay devices 200, respectively. have.

Also, the receiver 110 may receive reference information from the relay device 200 , and the receiver 110 may receive respective pieces of reference information from a plurality of relay devices 200 .

The reception strength collection unit 120 may collect reference information indicating a location where the relay device 200 is installed and reception strength of a wireless signal.

In this case, the reception strength collecting unit 120 may collect the reception strength to match the reference information, and the reception strength collection unit 120 may collect the reception strength according to a preset time interval.

The image generator 130 may generate image information to indicate the level of the reception intensity in the reference information.

In this regard, the image generating unit 130 may generate image information such that reception strengths of a plurality of wireless signals received from a plurality of relay devices 200 installed at different locations are respectively indicated.

In this case, the image generator 130 may represent the reception strengths satisfying the different level ranges in different shapes based on a plurality of level ranges preset with respect to the level of the reception strength of the radio signal.

For example, the image generator 130 may set the level range at intervals of 20 when the reception intensity level is 0 to 100, and in this case, the image generator 130 determines that the reception intensity level is Image information may be generated so that colors of the first wireless signal represented by 10 and the second wireless signal having a reception intensity level of 50 are different.

At this time, the image generating unit 130 indicates the color according to the first radio signal at the position according to the first reference information of the relay device 200 that has transmitted the first radio signal, and the color according to the second radio signal is the second color according to the second radio signal. It may be indicated at a location according to the second reference information of the relay device 200 that has transmitted the radio signal.

In an embodiment, the image generating unit 130 may generate image information according to the strength of a wireless signal by using a plotly library of MATLAB software.

The learning unit 140 may generate a position estimation model by learning the image information to estimate the position information that receives the radio signal from the image information.

To this end, the learning unit 140 may generate a location estimation model using an artificial intelligence (AI) technique such as machine learning.

Here, machine learning can be understood as a technique for generating a learning model to classify a plurality of information into one or more groups based on a plurality of information, and classifying arbitrary information based on the generated learning model, and Similarly, machine learning may refer to supervised learning that creates a learning model to classify arbitrary information according to a plurality of pieces of information classified by an administrator.

To this end, the learning unit 140 may include a first learning module for generating a first position estimation model and a second learning module for generating a second position estimation model.

The first learning module may analyze the image information to extract a feature vector, and the first learning module may learn the image information to estimate the first feature information matching the feature vector to generate a first location estimation model. .

In this regard, the first learning module may generate the first location estimation model using a Convolution Neural Network (CNN), which is an artificial intelligence technique prepared to extract a feature vector from an image.

Specifically, the first location estimation model may be generated to include an input layer that receives image information, and the first location estimation model includes a convolution layer that extracts a feature vector from the input information. may be generated to include, and the first position estimation model may be generated to include a pooling layer that reduces the size of the feature vector.

Accordingly, the first learning module may receive image information and perform learning to extract a feature vector, and the first learning module may perform learning to reduce the size of the extracted feature vector.

Meanwhile, the first location estimation model may be generated to further include a fully connected layer (FC) that is provided to estimate the first feature information matching the information reduced by the pooling layer.

Accordingly, the first learning module may perform learning to estimate the first feature information matching the reduced feature vector.

In an embodiment, the first location estimation model may be generated in the shape of 'Input-Conv2D-Max Pooling-Conv2D-Max Pooling-Dense', where Input means an input layer, and Conv2D is a convolution layer Meaning, Max Pooling means a pooling layer, and Dense means a fully connected layer.

The second learning module may generate the second location estimation model by estimating the second feature information according to the first feature information and learning the first feature information to estimate location information matching the second feature information.

In this case, the second learning module may generate a second position estimation model to estimate the second characteristic information from the first characteristic information based on the previously estimated second characteristic information.

In this regard, in the process of generating output information according to arbitrary input information, the second learning module stores previously output information to affect information to be output next, which is an artificial intelligence technique called Long-Short (LSTM). Term Memory) may be used to generate a second location estimation model.

Specifically, the second position estimation model may be generated to include an LSTM layer for estimating the second characteristic information by receiving the first characteristic information generated in the first learning module, and the second position estimation model is It may be generated to include a fully connected layer (FC) for estimating location information matching the second characteristic information, and the second location estimation model is generated to include an output layer for outputting location information can be

Accordingly, the second learning module may receive the first feature information and learn to estimate the second feature information, and the second learning module learns to estimate and output location information matching the second feature information. can be done

In an embodiment, the second location estimation model may be generated in the form of 'LSTM-Dense-Output', where LSTM means an LSTM layer, Dense means a fully connected layer, and Output means an output layer. it means.

In this regard, the location estimation model may be understood as a connection between the first location estimation model and the second location estimation model, and accordingly, the location estimation model includes the first characteristic information estimated by the first location estimation model and the second location It may be provided to be input to the estimation model.

In an embodiment, the location estimation model may be provided in the form of 'Input-Conv2D-Max Pooling-Conv2D-Max Pooling-Dense-LSTM-Dense-Output'.

In this regard, the position estimation model may determine the performance by using a plurality of image information used to generate the position estimation model, and through this, the learning unit 140 determines the position estimation model whose performance exceeds a certain threshold. can create

The location estimator 150 may estimate location information from image information based on the location estimation model.

In this case, the location estimator 150 may estimate the first characteristic information from the image information based on the first location estimation model.

Also, the position estimator 150 may estimate the second characteristic information from the first characteristic information based on the second position estimation model, and in this case, the position estimator 150 determines the previously estimated second characteristic information. The second characteristic information may be estimated in consideration of .

Accordingly, the location estimator 150 may estimate location information from the second characteristic information based on the second location estimation model.

In an embodiment, the location estimation model may be provided in the form of 'Input-Conv2D-Max Pooling-Conv2D-Max Pooling-Dense-LSTM-Dense-Output'. In this case, the location estimation unit 150 may image information may be input through .

Accordingly, the position estimator 150 may estimate the second characteristic information from the first characteristic information through the LSTM, and the position estimator 150 estimates position information matching the second characteristic information through Dense. can

In this case, the position estimator 150 may output the estimated position information through Output.

The output unit 160 may output location information. In this case, the output unit 160 may be provided as a display device such as a monitor, and in this case, the output unit 160 may output the estimated position information in the form of an image.

In this case, the output unit 160 may output location information on a pre-prepared image. In this case, the pre-prepared image may be provided such that reference information is fixed to any one point on the image.

3 is a block diagram illustrating a process of generating a location estimation model in the learning unit of FIG. 2 .

Referring to FIG. 3 , the receiver 110 may receive a wireless signal transmitted from the relay device 200 prepared in advance, and the receiver 110 may receive reference information from the relay device 200 . .

Accordingly, the reception strength collecting unit 120 may collect the reference information indicating the location where the relay device 200 is installed and the reception strength of the radio signal.

The image generator 130 may generate image information to indicate the level of the reception intensity in the reference information.

In this regard, the image generating unit 130 may generate image information such that reception strengths of a plurality of wireless signals received from a plurality of relay devices 200 installed at different locations are respectively indicated.

Accordingly, the learning unit 140 may generate a position estimation model by learning the image information to estimate the position information on which the radio signal is received from the image information.

To this end, the learning unit 140 may include a first learning module generating a first position estimation model and a second learning module generating a second position estimation model.

The first learning module may analyze the image information to extract a feature vector, and the first learning module may learn the image information to estimate the first feature information matching the feature vector to generate a first location estimation model. .

The second learning module may generate the second location estimation model by estimating the second feature information according to the first feature information and learning the first feature information to estimate location information matching the second feature information.

In this case, the second learning module may generate a second position estimation model to estimate the second characteristic information from the first characteristic information based on the previously estimated second characteristic information.

In this regard, the position estimation model may determine the performance by using a plurality of image information used to generate the position estimation model, and through this, the learning unit 140 determines the position estimation model whose performance exceeds a certain threshold. can create

4 is a block diagram illustrating a process of estimating location information by the location estimator of FIG. 2 .

Referring to FIG. 4 , the receiver 110 may receive a wireless signal transmitted from the relay device 200 prepared in advance, and the receiver 110 may receive reference information from the relay device 200 . .

Accordingly, the reception strength collecting unit 120 may collect reference information indicating the location where the relay device 200 is installed and the reception strength of the radio signal.

The image generator 130 may generate image information to indicate the level of the reception intensity in the reference information.

In this regard, the image generating unit 130 may generate image information such that reception strengths of a plurality of wireless signals received from a plurality of relay devices 200 installed at different locations are respectively indicated.

Accordingly, the location estimator 150 may estimate location information from the image information based on the location estimation model.

In this case, the location estimator 150 may estimate the first characteristic information from the image information based on the first location estimation model.

Also, the position estimator 150 may estimate the second characteristic information from the first characteristic information based on the second position estimation model, and in this case, the position estimator 150 determines the previously estimated second characteristic information. The second characteristic information may be estimated in consideration of .

Accordingly, the location estimator 150 may estimate location information from the second characteristic information based on the second location estimation model.

5 is a schematic diagram illustrating an embodiment of image information generated by the image generator of FIG. 2 .

Referring to FIG. 5 , it can be seen that the reception strength of the wireless signal appearing at four positions can be confirmed, and it can be understood that the vertical bar shown on the rightmost side is a bar indicating a color matching the reception strength.

In this regard, the image generating unit 130 may generate image information such that reception strengths of a plurality of wireless signals received from a plurality of relay devices 200 installed at different locations are respectively indicated.

In this case, the image generator 130 may represent the reception strengths satisfying the different level ranges in different shapes based on a plurality of level ranges preset with respect to the level of the reception strength of the radio signal.

6 is a schematic diagram illustrating an embodiment of a location estimation model generated by the learning unit of FIG. 2 .

Referring to FIG. 6 , an embodiment of the location estimation model generated by the learning unit 140 may be confirmed, and such location estimation model may be understood as a Hybrid Deep Learning Model.

As described above, the location estimation model may be provided in the shape of 'Input-Conv2D-Max Pooling-Conv2D-Max Pooling-Dense-LSTM-Dense-Output', and the location estimation model includes the first location estimation model and the second location estimation model. It can be understood that the model is connected.

Accordingly, the first position estimation model may be generated in the shape of 'Input-Conv2D-Max Pooling-Conv2D-Max Pooling-Dense', where Input means an input layer, Conv2D means a convolution layer, , Max Pooling means a pooling layer, and Dense means a fully connected layer.

In addition, the second location estimation model may be generated in the shape of 'LSTM-Dense-Output', where LSTM means an LSTM layer, Dense means a fully connected layer, and Output means an output layer.

7 is a flowchart of a location estimation method according to an embodiment of the present invention.

Since the location estimation method according to an embodiment of the present invention proceeds on substantially the same configuration as that of the location estimation apparatus 100 shown in FIG. 1 , the same reference numerals refer to the same components as the location estimation apparatus 100 of FIG. , and repeated descriptions will be omitted.

The position estimation method includes the steps of receiving a wireless signal (600), collecting the reception strength of the wireless signal (610), generating image information to indicate the level of reception strength (620), learning the image information to position It may include generating an estimation model ( 630 ), estimating location information from image information ( 640 ), and outputting location information ( 650 ).

The step 600 of receiving the wireless signal may be a step in which the receiver 110 receives a wireless signal transmitted from a pre-prepared relay device.

The step 610 of collecting the reception strength of the wireless signal may be a step in which the reception strength collection unit 120 collects reference information indicating the location where the relay device 200 is installed and the reception strength of the wireless signal.

The operation 620 of generating the image information to indicate the level of the reception intensity may be an operation in which the image generator 130 generates the image information to indicate the level of the reception strength in the reference information.

The step 630 of generating a location estimation model by learning the image information may be a step of generating a location estimation model by learning the image information so that the learning unit 140 estimates location information that receives a wireless signal from the image information. .

The step 640 of estimating the location information from the image information may be a step in which the location estimator 150 estimates location information from the image information based on the location estimation model.

The step 650 of outputting the location information may be a step of outputting the location information by the output unit 160 .

Such a position estimation method may be implemented as an application or implemented in the form of program instructions that may be executed through various computer components and recorded in a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc. alone or in combination.

The program instructions recorded on the computer-readable recording medium are specially designed and configured for the present invention, and may be known and available to those skilled in the art of computer software.

Examples of the computer-readable recording medium include a hard disk, a magnetic medium such as a floppy disk and a magnetic tape, an optical recording medium such as a CD-ROM and DVD, and a magneto-optical medium such as a floppy disk. media), and hardware devices specially configured to store and execute program instructions such as ROM, RAM, flash memory, and the like.

Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform processing according to the present invention, and vice versa.

Although the above has been described with reference to the embodiments, it will be understood by those skilled in the art that various modifications and changes can be made to the present invention without departing from the spirit and scope of the present invention as set forth in the following claims. will be able

1: Position estimation system
100: location estimation device
200: relay device

Claims (9)

a receiving unit for receiving a radio signal transmitted from a pre-prepared repeater;
a reception strength collecting unit that collects reference information indicating a location where the relay device is installed and reception strength of the radio signal;
an image generating unit generating image information to indicate the level of the reception intensity in the reference information;
a learning unit for generating a location estimation model by learning the image information to estimate location information on which the radio signal is received from the image information;
a location estimator for estimating location information from the image information based on the location estimation model; and
and an output unit for outputting the location information.
According to claim 1, wherein the learning unit,
a first learning module that extracts a feature vector by analyzing the image information and generates a first location estimation model by learning the image information to estimate first feature information matching the feature vector; and
A second position estimation model is generated by estimating second characteristic information according to the first characteristic information, and learning the first characteristic information to estimate position information matching the second characteristic information, A second learning module configured to generate the second position estimation model to estimate the second characteristic information from the first characteristic information, based on the second characteristic information.
The method of claim 2, wherein the position estimating unit,
estimating first characteristic information from the image information based on the first position estimation model;
based on the second location estimation model, estimating the second characteristic information from the first characteristic information, and estimating the second characteristic information in consideration of the previously estimated second characteristic information;
and estimating the location information from the second characteristic information based on the second location estimation model.
According to claim 1, wherein the image generating unit,
Image information is generated so that reception strengths of a plurality of wireless signals received from a plurality of repeaters installed at different locations appear respectively, and based on a plurality of level ranges preset for the reception strength levels of the wireless signals , a position estimating apparatus representing reception strengths satisfying different level ranges in different shapes.
A method for estimating a position in a position estimating apparatus using a heat map of received signal strength, the method comprising:
receiving, by a receiving unit, a radio signal transmitted from a relay device prepared in advance;
collecting, by a reception strength collecting unit, reference information indicating a location where the repeater is installed, and reception strength of the radio signal;
generating, by an image generating unit, image information to indicate the level of the reception intensity in the reference information;
generating a location estimation model by learning the image information so that a learning unit estimates location information on which the radio signal is received from the image information;
estimating, by a location estimation unit, location information from the image information based on the location estimation model; and
Including; outputting the location information by an output unit, location estimation method.
According to claim 5, wherein the step of generating a location estimation model by learning the image information,
generating, by a first learning module, a first location estimation model by analyzing the image information to extract a feature vector, and learning the image information to estimate first feature information matching the feature vector; and
A second learning module generates a second position estimation model by learning the first characteristic information to estimate the second characteristic information according to the first characteristic information, and to estimate position information matching the second characteristic information, generating the second position estimation model to estimate the second characteristic information from the first characteristic information based on the previously estimated second characteristic information;
The method of claim 6, wherein the estimating of location information from the image information comprises:
estimating first characteristic information from the image information based on the first position estimation model;
based on the second location estimation model, estimating the second characteristic information from the first characteristic information, and estimating the second characteristic information in consideration of the previously estimated second characteristic information;
and estimating the location information from the second characteristic information based on the second location estimation model.
The method of claim 5, wherein the generating of the image information to indicate the level of the reception strength comprises:
Image information is generated so that reception strengths of a plurality of wireless signals received from a plurality of repeaters installed at different locations appear respectively, and based on a plurality of level ranges preset for the reception strength levels of the wireless signals , a method for estimating a position, representing reception strengths satisfying different level ranges in different shapes.
A computer-readable recording medium having a computer program recorded thereon for performing the method for estimating a position according to any one of claims 5 to 8.

Images