KR20180040841A - Method for Fingerprinting Positioning Based on the Reliability of the Measurement Reference Position and Apparatus therefor - Google Patents

Abstract

The present invention relates to a method for positioning a fingerprint according to reliability of a reference position measuring method and a device therefor, which set a weight for each measuring method of a reference position through a machine learning method, and measure a position of a terminal device by applying the set weight, thereby reducing an error of positioning according to the reference position measuring method and increasing accuracy of position measurement. The method for positioning a fingerprint based on positioning reliability of a reference position comprises the following steps of: collecting first wireless propagation environment information for a plurality of reference positions by a positioning server, and constructing a positioning DB; setting the weight for each reference position in consideration of positioning reliability of the reference position; receiving second wireless propagation environment information from a positioning target terminal device; applying the weight for each measuring method, and calculating a positioning similarity between the second wireless propagation environment information and the first wireless propagation environment information set for each of the plurality of reference positions; and estimating a position of the positioning target terminal device based on the calculated positioning similarity.

Description

FIELD OF THE INVENTION [0001] The present invention relates to a fingerprint positioning method according to positioning reliability of a reference position,

[0001] The present invention relates to a fingerprint positioning method according to the reliability of a reference position measuring method and an apparatus therefor, and more particularly, to a fingerprint positioning method using a plurality of reference position radio wave environment information stored in a positioning database (DB) When the current position is calculated based on the similarity of the radio propagation environment information, the weight is set differently in consideration of the reliability according to the method of measuring the reference position at each of the plurality of reference positions, And more particularly, to a fingerprint positioning method and a device therefor that enable more accurate position measurement by calculating similarity by applying differently set weights.

The contents described in this section merely provide background information on the present embodiment and do not constitute the prior art.

As the mobile communication network develops and the specifications of the mobile communication network evolve, the mobile communication terminal has become a necessity of the modern person beyond the scope of the conventional simple communication apparatus or information providing apparatus, and is evolving into a total entertainment apparatus.

In addition, in recent years, the use of a smart phone, which combines functions of a communication terminal and a function of a PDA (Personal Digital Assistant), has been popularized. This smart phone is an intelligent terminal that adds computer support functions such as internet communication and information search to a mobile phone. It has a large capacity memory and a high performance CPU (Central Processing Unit) compared to conventional communication terminals, / An operating system (OS) for supporting data communication and PC (personal computer) interworking.

As one of application technologies using such a smart phone, various location-based services (for example, navigation for vehicles, maps, directions, indoor shop guidance, etc.), which provide convenience to users, have been introduced and attracted much attention.

An important part of location-based services lies in the degree to which the user's location can be measured.

In the meantime, the above-mentioned position measurement method includes a Cell-ID, a triangulation, a fingerprint technique, and the like. Among these fingerprint techniques, a plurality of positions are arbitrarily selected in advance in a service area, (Received Signal Strength Indication) (RSSI).

Although this fingerprint technique shows high accuracy in location tracking compared to the Cell-ID technique, the positioning accuracy of the fingerprint positioning technique is greatly influenced by the reliability of the location of the acquisition point recorded in the positioning database, That is, it is a reality that different positional errors are inherent depending on whether the position is measured by GPS or manually.

Accordingly, a method for minimizing an error according to a measurement method and a method for measuring a position of the terminal by minimizing an error when there is a positioning request in the terminal using the method Research is needed.

U.S. Patent No. 8,692,667 (entitled METHOD AND APPARATUS FOR DISTRIBUTED LEARNING OF PARAMETERS OF A FINGERPRINT PREDICTION MAP MODEL, Apr. 4, 2014)

In order to satisfy the above-mentioned requirement, the present invention is characterized in that the weighted values are set differently in consideration of different reliability for each position measurement method of the reference position, the positioning similarity degree reflecting the reliability of the reference position is calculated, And a fingerprint positioning method and apparatus according to reliability of a reference position measurement method for estimating a position of a target terminal apparatus.

In addition, a method and an apparatus for setting a weight value for each position measurement method through a machine learning method are provided.

However, the object of the present invention is not limited to the above-mentioned objects, and other objects not mentioned can be clearly understood from the following description.

According to another aspect of the present invention, there is provided a method of positioning a fingerprint according to reliability of a reference position measuring method, wherein a positioning server collects first radio propagation environment information for a plurality of reference positions, Setting a weight for each measurement method of the reference position, receiving second wireless propagation environment information from the positioning target terminal device, receiving second wireless wave propagation environment information from the second wireless wireless environment information by applying a weight for each measurement method, Calculating the positioning similarity between the radio wave environment information and the first radio wave propagation environment information, and estimating the position of the positioning target terminal based on the calculated positioning similarity.

의 수식을 통해 상기 가중치를 산출하고,

는 상기 가중치,

은 상기 전파환경 수집 단말장치의 실제 위치,

는 측정 위치를 의미할 수 있으며, 상기 기준위치 측정 방법 별 가중치를 산출하는 단계는 기울기 하강 알고리즘(Gradient Descent Algorithm)을 통해 상기 가중치를 산출할 수 있다.The step of setting the weights may include collecting learning data including radio propagation environment information collected at a plurality of actual positions and the plurality of actual positions and an estimated position estimated based on the radio wave environment information, Calculating a weight for each of the reference position measuring methods by performing a machine learning so that an error between the measured position and the estimated position is minimized based on the collected learning data, The step

≪ / RTI >< RTI ID = 0.0 >

The weight,

The actual location of the propagation environment collection terminal device,

May be a measurement position, and calculating the weight for each reference position measurement method may calculate the weight through a gradient descent algorithm (Gradient Descent Algorithm).

의 수식을 통해 측위 유사도를 추정하며,

는 상기 가중치,

는 상기 기준위치,

는 상기 측위 유사도,

는 상기 기준위치에서 사용되는 무선전파발생 장치의 비율,

는 기준위치에서 특정 무선전파발생장치에 대해 상기 단말장치에서 스캔한 신호세기 값과 기 저장된 신호세기 값의 차이 값,

는 상기 단말장치에서 스캔한 특정 무선전파발생장치의 신호세기 값을 의미하고, 상기 단말장치의 위치를 추정하는 단계는

의 수식을 통해 추정할 수 있다.In addition, the step of setting the weights may further set the weights according to the geographical characteristics in consideration of the geographical characteristic of the reference location, and the step of calculating the positioning similarity may further comprise:

, The positional similarity is estimated through the equation of

The weight,

The reference position,

The positioning similarity,

The ratio of the radio wave generator used at the reference position,

A difference value between a signal intensity value scanned by the terminal device and a previously stored signal intensity value for a specific radio wave propagating device at a reference position,

Means a signal intensity value of a specific radio wave generator scanned by the terminal, and estimating the position of the terminal

Can be estimated by the following equation.

Meanwhile, the fingerprint positioning method according to the reliability of the reference position measuring method can be provided as a computer-readable recording medium having recorded thereon a program for executing the same, and a computer program stored in a computer-readable recording medium, Can be provided.

According to another aspect of the present invention, there is provided a positioning server including a communication module for transmitting / receiving data to / from a terminal device, a radio wave propagation environment information for each location, a storage module for storing weights for each reference location measurement method, And sets a weight for each measurement method of the reference position and receives second wireless wave environment information from the positioning target terminal device through the communication module, Calculating a position similarity degree between the second radio wave propagation environment information and the first radio wave propagation environment information set for each of the plurality of reference positions by applying the weights to the measurement target station and based on the calculated positioning similarity degree, And may include a control module for estimating the power consumption.

At this time, the control module collects the learning data including the radio propagation environment information collected at the plurality of actual positions and the plurality of actual positions and the estimated position estimated based on the radio wave propagation environment information, The weight of each reference position measurement method can be calculated by performing the machine learning so that the error between the actual position and the estimated position is minimized.

According to the present invention, the weight of each measurement method of the reference position is set through the machine learning method, and the position of the terminal is measured by applying the set weight, thereby reducing the error of positioning according to the reference position measurement method, Accuracy can be increased.

In addition, various effects other than the above-described effects can be directly or implicitly disclosed in the detailed description according to the embodiment of the present invention to be described later.

1 is a diagram showing the configuration of a fingerprint positioning system according to an embodiment of the present invention.
2 is a block diagram showing a configuration of a positioning server according to the present invention.
3 is a flowchart illustrating a method of setting and storing a weight according to an embodiment of the present invention.
4 is a flowchart illustrating a positioning method according to an embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS For a more complete understanding of the nature and advantages of the present invention, reference should be made to the following detailed description taken in conjunction with the accompanying drawings, in which:

In the following description and the accompanying drawings, detailed description of well-known functions or constructions that may obscure the subject matter of the present invention will be omitted. It should be noted that the same constituent elements are denoted by the same reference numerals as possible throughout the drawings.

The terms and words used in the following description and drawings are not to be construed in an ordinary sense or a dictionary, and the inventor can properly define his or her invention as a concept of a term to be described in the best way It should be construed as meaning and concept consistent with the technical idea of the present invention. Therefore, the embodiments described in the present specification and the configurations shown in the drawings are merely the most preferred embodiments of the present invention, and not all of the technical ideas of the present invention are described. Therefore, It is to be understood that equivalents and modifications are possible.

In addition, embodiments within the scope of the present invention include computer-readable media having computer-executable instructions or data structures stored on computer-readable media. Such computer-readable media can be any available media that is accessible by a general purpose or special purpose computer system. By way of example, and not limitation, such computer-readable media can comprise RAM, ROM, EPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or in the form of computer- But is not limited to, a physical storage medium such as any other medium that can be used to store or communicate certain program code means of the general purpose or special purpose computer system, .

A fingerprint positioning method according to the reliability of the reference position measuring method according to an embodiment of the present invention will now be described in detail with reference to the drawings.

1 is a diagram showing a configuration of a system for performing fingerprint positioning according to the reliability of a reference position measuring method according to an embodiment of the present invention.

1, the fingerprint positioning system according to the present embodiment may include a terminal device 200 and a positioning server 300. The terminal device 200 and the positioning server 300 may communicate with each other through a communication network 100, Data can be transmitted / received through the network.

Each component will now be schematically described with reference to FIG.

First, the communication network 100 transmits data for transmitting and receiving data between the terminal device 200 and the positioning server 300. The communication network 100 may include Ethernet, xDSL (ADSL, VDSL), HFC (WLAN), Wi-Fi, WiBro, WiMAX, etc., can be used, such as a wired communication method such as a hybrid fiber coaxial cable, a fiber to the curb (FTTC), and a fiber to the home (WIMAX), High Speed Downlink Packet Access (HSDPA), Long Term Evolution (LTE), and Long Term Evolution Advanced (LTE-A). In addition to the above communication methods, Lt; RTI ID = 0.0 > a < / RTI >

The terminal apparatus 200 refers to a user apparatus capable of transmitting and receiving various data to and from the positioning server 300 through the communication network 100 according to a user's operation.

The terminal device 200 can perform voice or data communication through the communication network 100 and includes a memory for storing programs and protocols for data transmission and reception and a microprocessor for executing and controlling various programs, And the like. In addition, the terminal device 200 of the present invention can be implemented in various forms. For example, the terminal device 200 described in the present specification may be a mobile terminal such as a smart phone, a tablet PC, a PDA (personal digital assistant), a portable multimedia player (PMP) Of course, a fixed terminal such as a Smart TV, a laptop computer, a desktop computer, or the like may be used, and any apparatus capable of transmitting and receiving data according to the present invention may be applied to embodiments of the present invention As shown in FIG.

Meanwhile, the terminal device 200 according to the present invention can collect the radio propagation environment information around the terminal device 200 and transmit it to the positioning server 300.

At this time, the terminal device 200 can serve as a learning data collection device that transmits learning data for setting weights to the positioning server 300, and sets a positioning DB for radio propagation environment information at each reference position And may also serve as a radio wave propagation environment collecting device for requesting positioning by the positioning server 300 and transmitting the location information of the terminal 200 to the positioning target terminal 200 that receives the position of the current terminal 200 from the positioning server 300 It can also play a role.

When the terminal device 200 serves as the radio wave environment collecting terminal device 200, the radio wave propagation environment information collected at the actual position and the actual position of the area where the terminal device 200 is located is transmitted to the positioning server 300 When the terminal device 200 serves as the learning data collection terminal device 200, the terminal device 200 further includes an estimated location estimated based on the collected radio wave environment information, and transmits the estimated location to the positioning server 300.

On the other hand, when the terminal device 200 serves as the positioning target terminal device 200, the terminal device 200 transmits the radio wave environment information around the terminal device 200 to the positioning server 300 together with the positioning request, 300, < / RTI >

Finally, the positioning server 300 constructs a positioning DB using the first radio propagation environment information collected at a plurality of reference positions, and transmits the second radio wave (radio wave) received from the positioning DB and the positioning target terminal device 200 And estimates the position of the positioning target terminal device 200 based on the environment information.

In particular, the positioning server 200 according to the present invention sets a weight for each measurement method for a plurality of reference positions, applies second weight for each measurement method, and generates second radio propagation environment information set for a plurality of reference positions, Estimates the positional similarity of the positioning target terminal device 200 based on the calculated positioning similarity, and transmits the positional information estimated by the positioning target terminal device 200.

Here, the weight of each of the plurality of reference positions is set. The method of measuring the reference position is a method of measuring the radii of radii of the reference positions. The positioning DB constructor may manually set the radii, Or may measure the position of the peripheral base station by measuring the position of the peripheral base station to the reference position or may measure the position of the reference point such as the position of the surrounding AP (Access Point) To a method for realizing the same.

At this time, an error between the estimated position and the actual position may occur according to the measurement method. In this case, the weight is assigned differently according to the reliability of the measurement method, and the given weight is applied, By estimating the position, the error according to the measurement method can be reduced.

In particular, when weights are set for each measurement method, machine learning is performed so that the error between the actual position and the estimated position is minimized.

This is because it is practically impossible to determine the combination with the highest positioning accuracy as the measurement method of the reference position and the weight value are varied. In order to set the weight according to the optimum reference position measurement method through the machine learning using the specific algorithm do.

Meanwhile, the weights can be set not only by the measurement method but also by the measurement method and the geographical characteristic, taking into consideration the geographical characteristic of the reference location.

Here, the geographical characteristic of the reference position may mean a characteristic of a place where a reference position is located, for example, whether the reference position is located in the center of the city, in a residential area, or in a suburban area.

A specific method of setting the weight value will be described later.

2 is a block diagram for explaining the configuration of the positioning server 300 according to the present invention.

2, the positioning server 300 may include a communication module 310, a storage module 330, and a control module 350.

The communication module 310 is for transmitting and receiving data to and from the terminal device 200 through the communication network 100. The communication module 310 collects first radio propagation environment information for a plurality of reference positions to construct a positioning DB, And can receive the second radio propagation environment information and the positioning request from the device 200. [

Further, it is possible to receive learning data for setting a weight for each measurement method of the reference position.

The storage module 330 may include a positioning DB 331. The positioning DB 331 stores a fingerprint map generated by collecting first radio propagation environment information for a plurality of reference positions.

In addition, the storage module 330 may store a weight for each optimum reference position measurement method set through machine learning. At this time, the weight may be set in consideration of reliability having a deviation according to the reference position measurement method. A method of setting a weight for this will be described later.

The control module 350 is an apparatus for controlling the entire operation process of the positioning server 300 according to the present invention and may include a positioning module 351 and a learning module 353. [

The positioning module 351 is configured to calculate the position of the terminal device 200 when receiving the positioning request from the terminal device 200 and the learning module 353 calculates the position in the positioning module 351 And calculating the optimal weight for each combination of the measurement method or the geographic characteristic of the reference position.

The specific operation of the control module 350 of the positioning server 300 including the positioning module 351 and the learning module 353 will be described with reference to FIGS. 3 to 4. FIG.

3 is a flowchart illustrating a process of measuring the position of the positioning target terminal device 200 performed by the positioning module 351 of the positioning server 300. FIG 4 is a flowchart of a process of measuring the position of the learning module 353 ) Or a process of calculating an optimal weight according to geographical characteristics.

3 may be performed in advance by the learning module 353 or the control module 350 of the positioning server 300 and may be performed in advance by the positioning server 300. For example, The positioning module 351 of FIG.

Referring to FIG. 3, the positioning server 300 collects first radio propagation environment information for a plurality of reference positions and establishes a positioning DB for each reference position (S101) A weight is set (S103).

After that, the positioning module 351 of the positioning server 300 receives the positioning request from the positioning target terminal device 200 and the second radio propagation environment information indicating the radio propagation environment information around the positioning target terminal device 200 (S105).

The positioning server 300 receiving the positioning request calculates a positioning similarity degree between the second radio wave environment information and the first radio wave environment information set for a plurality of reference positions by applying a predetermined weight to each measurement method ), And the equation for calculating the positioning similarity may be as follows.

는 상기 측정 방법 별 가중치,

는 상기 기준위치,

는 상기 측위 유사도,

는 상기 기준위치에서 사용되는 무선전파발생 장치의 비율,

는 기준위치에서 특정 무선전파발생장치에 대해 상기 측위 대상 단말장치(200)에서 스캔한 신호세기 값과 측위 DB(331)에 기 저장된 신호세기 값의 차이 값,

는 상기 단말장치에서 스캔한 특정 무선전파발생장치의 신호세기 값을 의미한다.here,

The weight of each measurement method,

The reference position,

The positioning similarity,

The ratio of the radio wave generator used at the reference position,

A difference value between the signal intensity value scanned by the positioning target terminal device 200 and the signal intensity value stored in the positioning DB 331 for a specific radio wave propagating device at the reference position,

Means a signal intensity value of a specific radio wave generator scanned by the terminal.

The similarity of the positional similarity becomes higher as the similarity between the radio wave propagation environment information collected at each reference position or an arbitrary collection point and the radio wave propagation environment information collected by the positioning target terminal device 200 in Equation (1) And calculates the positional similarity by summing these values.

에 따라 측위 유사도는 정규화된다.When a score for each radio wave generating device is collected for each position, the ratio of the radio wave generating device used at that location

, The positioning similarity is normalized.

In addition, the similarity score is determined according to the difference of the signal strengths of the respective radio wave generators, and the smaller the difference is, the greater the similarity is.

) 에 따라 다른 유사도를 가지게 되며,

값이 커질수록, 동일한 신호세기의 차이에 대해 큰 유사도 값을 가진다.In other words, when the measured position is measured by two different measurement methods for one radio wave generator, even if the same signal intensity is different, the weight

), And thus,

The larger the value, the larger the similarity value to the difference in the signal strength.

에 의해 신호 세기의 차이가 유사도로 변환되고,

에 의해 동일한 신호세기 차이더라도 측위 대상 단말장치(200)에서 수신한 신호세기가 클수록 더 높은 유사도 점수를 준다.In other words,

The difference of the signal intensity is converted into the degree of similarity,

The higher the signal strength received by the positioning target terminal device 200, the higher the similarity score is given.

When the positioning similarity degree is calculated through the above equation, the position of the positioning target terminal device 200 is estimated based on the calculated positioning similarity degree, and the equation for estimating the position may be as follows.

는 측위 대상 단말장치(200)의 위치를 의미한다.Here, Z is a sum of the positional similarities calculated at all of the collecting points or the reference positions,

Quot; refers to the position of the positioning target terminal device 200.

If the position of the positioning target terminal device 200 is estimated through the above equation (S109), the estimated position is transmitted to the positioning target terminal device 200 (S111).

On the other hand, when measuring the position of the positioning target terminal device 200, the learning module 353 can set the weight for each reference position measurement method used for reducing the error through machine learning.

Referring to FIG. 4, the learning module 353 sets a weight for each reference position measurement method through machine learning. The wireless propagation environment information collected from the plurality of actual positions and the plurality of actual positions, (S201). The learning data including the estimated position is acquired based on the estimated position.

At this time, the plurality of measured positions may be a reference position or an arbitrary collection point.

In addition, the estimated position estimated based on the radio wave propagation environment information may be calculated through the above-mentioned [Equation 1] to [Equation 2] and included in the learning data.

Then, based on the collected learning data, a weight can be calculated for each reference position measurement method by performing machine learning so that an error between the actual position and the estimated position is minimized (S203). The objective function for calculating the weight is Can be defined as the following equation (3).

는 실측 위치이고,

은 측정위치이며, 상기 실측 위치와 측정위치의 차가 최소화되는 지점을 구하면, 본 발명에 따라, 측위 정확도를 높이기 위한 가중치인

를 산출할 수 있다.here,

Is a measured position,

If a point at which the difference between the measured position and the measured position is minimized is determined, the weighting value for increasing the positioning accuracy

Can be calculated.

를 산출하기 위해서는 상기 목적함수를 기울기 하강 알고리즘(Gradient Descent Algorithm)에 대입시킨다.More specifically, the weight

, The objective function is substituted into the gradient descent algorithm (Gradient Descent Algorithm).

The gradient descent algorithm is a method in which when the solution of the minimum value can not be directly obtained due to the complexity of the objective function, the derivative is obtained at each point and the parameter is continuously updated in a direction giving a smaller function value.

The slope descending algorithm will be described in detail as follows.

Equation (4) is an example obtained by substituting the objective function of Equation (3) into the gradient descent algorithm, and the initial weights are collectively set to 40 regardless of the measurement method.

Then, an algorithm is performed to obtain an optimum weight that minimizes an error between the actual position and the estimated position.

를 최소화하기 위하여, 목적함수의 도함수에 따라, 가중치를 업데이트 하면서, 목적함수의 값을 줄여 나가가고, 측정 방법 별 함수 값의 차이가

내로 수렴하게 되면, 기계학습을 종료하고, 그 때의

값을 각 측정 방법 별 가중치로 설정한다.That is, the objective function of Equation (3)

In order to minimize the value of the objective function, the value of the objective function is reduced while updating the weight according to the derivative of the objective function,

, The machine learning is terminated, and at that time

Set the value to the weight for each measurement method.

이내인지를 판단하여(S205), 상기 오차값 이내가 아니면, S203단계로 돌아가, 측정 방법 별 가중치를 기계 학습 방법을 계속하여 산출하고, 상기 오차값 이내로 들어오면 기준위치 측정 방법 별로 산출된 가중치를 저장한다(S207).In other words, when the difference between the actual position and the estimated position is a predetermined error value

(S205). If it is not within the error value, the process returns to step S203, and the weight for each measurement method is continuously calculated by the machine learning method. If the error is within the error value, (S207).

의 도함수인

을 계산해야 할 필요성이 있는데,

은 다음과 같을 수 있다.In order to perform the slope descending algorithm of Equation (4), an objective function

The derivative of

There is a need to calculate,

Can be as follows.

와

는 아래의 [수학식 6]과 같다.At this time, the expression

Wow

Is expressed by Equation (6) below.

On the other hand, when calculating the weight for each reference position measuring method, the learning module 353 may set the weight by considering not only the reference position measuring method but also the geographical characteristic of the reference position.

That is, by setting the weights considering the reference position measurement method and the geographical characteristic, the positioning error caused by the geographical characteristic can be reduced, and the positioning accuracy can be improved.

The weights set in consideration of the reference position measurement method and the geographical characteristics are stored in the storage module 330. The DB form of the weights stored in the storage module 330 may be as shown in Table 1 below.

Downtown Residential Rural Manual 53.98 120.83 127.80 In building 12.67 17.78 17.76 GPS 39.68 11.35 9.85 WiFi 39.57 40.19 40.22

As described above, the present specification contains details of a number of specific implementations, but they should not be construed as being limitations on the scope of any invention or claimability, but rather on the particular embodiment of a particular invention But should be understood as an explanation of the features.

In addition, although the operations are depicted in the drawings in a particular order, it should be understood that such operations must be performed in that particular order or sequential order shown to obtain the desired results, or that all illustrated operations should be performed. In certain cases, multitasking and parallel processing may be advantageous. Also, the separation of the various system components of the above-described embodiments should not be understood as requiring such separation in all embodiments, and the described program components and systems will generally be integrated together into a single software product or packaged into multiple software products It should be understood.

The description sets forth the best modes of the present invention and provides examples for the purpose of illustrating the invention and enabling a person skilled in the art to make and use the invention. The written description is not intended to limit the invention to the specific terminology presented. Thus, while the present invention has been described in detail with reference to the above examples, those skilled in the art will recognize that modifications, changes, and modifications can be made thereto without departing from the scope of the present invention.

Therefore, the scope of the present invention should not be limited by the described embodiments but should be defined by the claims.

The present invention relates to a fingerprint positioning method according to the reliability of a reference position measuring method and an apparatus therefor, and more particularly, to a fingerprint positioning method and apparatus for establishing a plurality of reference positions (DB) The present invention relates to a fingerprint positioning method and apparatus for setting a weight differently according to a method of measuring a reference position in a terminal and applying a weight that is set differently when a terminal requests a positioning.

According to the present invention, the weight of each measurement method of the reference position is set through the machine learning method, and the position of the terminal is measured by applying the set weight, thereby reducing the error of positioning according to the reference position measurement method, Accuracy can be increased.

Therefore, the present invention can contribute to the development of the fingerprint industry through the above-described fingerprint positioning method, and it is possible to be industrially applicable because it is possible to carry out marketing or business as well as being practically possible.

100: communication network 200: terminal device 300: positioning server
310: Communication server module of the positioning server 330: Storage module of the positioning server
331: Positioning of positioning server DB 350: Controlling module of positioning server
351: Positioning module of positioning server 353: Learning module of positioning server

Claims (10)

The positioning server collecting first radio propagation environment information for a plurality of reference positions and constructing a positioning DB;
Setting a weight for each reference position in consideration of positioning reliability of the reference position;
Receiving second radio propagation environment information from the positioning target terminal device;
Calculating a positioning similarity degree between the second radio propagation environment information and the first radio wave propagation environment information set for each of the plurality of reference positions by applying a weight for each measurement method; And
Estimating a position of the positioning target terminal based on the calculated positioning similarity;
And the reliability of the reference location positioning. 2. The method of claim 1, wherein setting the weights comprises:
Wherein the weights are set differently according to the method of measuring the reference position, the geographical characteristic information, or a combination thereof. 2. The method of claim 1, wherein setting the weights comprises:
Collecting learning data including a plurality of actual positions and radio propagation environment information collected at the plurality of actual positions and an estimated position estimated based on the radio wave propagation environment information; And
Calculating a weight for each reference position measurement method by performing a machine learning operation so that an error between an actual position and an estimated position is minimized based on the collected learning data;
And a fingerprint positioning method according to the reliability of the reference position positioning 4. The method of claim 3, wherein calculating the weights by the reference position measuring method comprises:

≪ / RTI >< RTI ID = 0.0 >

The weight,

The actual location of the propagation environment collection terminal device,

Is a measurement position. The method according to claim 1, 4. The method of claim 3, wherein calculating the weights by the reference position measuring method comprises:
Wherein the weights are calculated through a gradient descent algorithm (Gradient Descent Algorithm). The method of claim 1, wherein the calculating the positioning similarity comprises:

, The positional similarity is estimated through the equation of

The weight,

The reference position,

The positioning similarity,

The ratio of the radio wave generator used at the reference position,

A difference value between a signal intensity value scanned by the terminal device and a previously stored signal intensity value for a specific radio wave propagating device at a reference position,

Means a signal intensity value of a specific radio wave generator scanned by the terminal,
The step of estimating the position of the terminal apparatus

Wherein the estimating method is based on the formula of the reference position measuring method. A computer-readable recording medium on which a program for executing the method according to any one of claims 1 to 6 is recorded. A computer program stored in a computer-readable medium embodied thereon for carrying out the method recited in any one of claims 1 to 6. A communication module for transmitting and receiving data to and from the terminal device;
A storage module for storing wireless environment information by location and a weight for each reference position measurement method; And
Acquiring first radio propagation environment information from a plurality of reference positions, setting a positioning DB, setting a weight for each measurement method of the reference position, and transmitting second radio wave propagation environment information from the positioning target terminal device through the communication module And calculating a position similarity degree between the second radio propagation environment information and the first radio propagation environment information set for each of the plurality of reference positions by applying the weights of the measurement relays to the positioning target terminal based on the calculated positioning similarity, A control module for estimating a position of the device;
. 10. The apparatus of claim 9, wherein the control module
Collecting learning data including a plurality of actual positions and radio propagation environment information collected at the plurality of actual positions and an estimated position estimated based on the radio wave propagation environment information, and based on the collected learning data, And estimates a weight for each of the reference position measuring methods by performing a machine learning so that an error between the estimated position and the estimated position is minimized.

Images