JP6249442B2 - Program for estimating moving vehicle on which user is on board, portable terminal and method - Google Patents

Description

  The present invention relates to a technique for estimating a movement state of a mobile terminal that communicates with a base station.

  In recent years, there is a technique for causing a user to visually recognize a targeting advertisement corresponding to a position of an advertising system. Conventionally, there is a technique for extracting users located in a direction in which a display surface of digital signage on a street can be visually recognized (see, for example, Patent Document 1). According to this technology, GPS (Global Positioning System) positioning results mounted on each user terminal are collected, and the moving direction of each user is detected. Digital signage can display content that matches the attributes of the user with the extracted user as the viewing target.

  In addition, there is a technique for collecting movement histories from a first visited place to a next visited place by a user and allowing a user staying at the first visited place to visually recognize an advertisement of a store having a high possibility of the next visited place (for example, Patent Document 2) reference). According to this technology, for each user terminal, past positions based on GPS positioning can be collected as a transition table, and a store having a high possibility of visiting next can be statistically searched.

  Furthermore, there is a technique for displaying an advertisement of a store near the bus on a display installed in the bus (see, for example, Patent Document 3). According to this technology, the position and the advertisement information are stored in advance in association with each other, and the advertisement information corresponding to the current position is reproduced on the display according to the positioning result of the GPS mounted on the bus, and used as a digital signage. Make it work.

  Furthermore, there is a technique for identifying the passenger's use application based on boarding section information acquired from passengers of public transportation and distributing advertisement information suitable for the use (see, for example, Patent Document 4). Specifically, the boarding classification is determined by reading a non-contact IC tag into a predetermined card reader when boarding, and advertisement information corresponding to the classification is searched.

  Furthermore, there is a technique for estimating the position of a user on a bus or train by periodically measuring the position and speed of each station or bus stop of transportation by the GPS method or the network positioning method (for example, patents). Reference 5).

JP 2010-146212 A JP 2008-310620 A JP 2003-241698 A JP 2012-088871 A JP 2011-0661615 A

  According to the technologies described in Patent Documents 1, 2, and 5 described above, the portable terminal possessed by the user needs to be periodically measured by GPS. Increasing the frequency of GPS positioning is inconvenient in terms of power consumption in mobile terminals, and decreasing the frequency coarsens the positioning position granularity and reduces the effectiveness of position-linked targeting advertising. . Moreover, according to the technique described in Patent Document 3, an advertisement is merely displayed according to the position of the bus. Furthermore, according to the technique described in Patent Document 4, in order to recognize whether or not the user is in public transportation, a predetermined action is performed on the user such as holding the non-contact ID tag over a predetermined card reader. Will be required.

  On the other hand, can the inventors of the present invention estimate the moving vehicle on which the user is boarding only by observing the base station identifier with the mobile terminal without using GPS positioning? I thought. Thereby, the advertisement information corresponding to the moving vehicle can be reproduced on the user's portable terminal.

  Therefore, according to the present invention, it is an object to provide a program, a portable terminal, and a method that can estimate a moving vehicle on which a user is boarding without starting GPS positioning.

According to the present invention, using a portable terminal capable of communicating with a base station, a program that causes a computer to function to estimate a moving vehicle on which a user is boarded,
Model storage means for storing time series of observed base station identifiers as model transitions for each moving vehicle;
Radio wave monitoring means for acquiring a time series of base station identifiers observed for a predetermined number or period,
A computer is caused to function as a moving vehicle estimation means for estimating that the user is on a moving vehicle based on a model transition most similar to the time series of the current base station identifier acquired by the radio wave monitoring means. To do.

According to another embodiment of the program of the present invention,
The model transition is a Left-to-Right (LR) type hidden Markov model,
A plurality of states S set according to the observation ratio of one or more base station identifiers;
It consists of the transition probability A from the previous state S to the subsequent state S,
The moving vehicle estimation means
Based on the time series y ₁ ⁿ of the current base station identifier acquired by the radio wave monitoring means, a plurality of state transitions x that can occur from the initial state to the final state are derived in the model transition,
For each moving vehicle M _i , the total probability P (y ₁ ⁿ | M _i ) of the probability that each state transition x occurs is calculated based on the time series y ₁ ⁿ of the current base station identifier,
It is also preferable to cause the computer to function so as to estimate a moving vehicle based on the total probability P that is equal to or higher than a predetermined value and has the highest probability Pmax = P (y ₁ ⁿ | M _i ).

According to another embodiment of the program of the present invention,
The model transition is a Markov model,
A state S in which the observed base station identifier is set;
It consists of the transition probability A from the previous state S to the subsequent state S,
The moving vehicle estimation means
Based on the time series y ₁ ⁿ of the current base station identifier acquired by the radio wave monitoring means, the usage probability P (y ₁ ⁿ | M _i ) obtained by multiplying the transition probability A between states in the model transition is calculated. And
It is also preferable to cause the computer to function so as to estimate a moving vehicle based on the highest probability Pmax = P (y ₁ ⁿ | M _i ), where the use probability P is equal to or greater than a predetermined value.

According to another embodiment of the program of the present invention,
The model transition and base station identifier time series are represented by a set of base station identifier and radio wave information,
The radio wave monitoring means obtains radio wave information of each observed base station identifier,
The moving vehicle estimation means preferably causes the computer to function so as to estimate the moving vehicle by using the set of the observed base station identifier and radio wave information.

According to another embodiment of the program of the present invention,
Radio wave information
Base station identifier of adjacent base station RSCP (Received Signal Code Power)
Ec / No (ratio of connected station RSCP to total received power)
RSS (Received Signal Strength)
C / I (interference wave ratio)
Ec / Io (adjacent base station transmission level vs. current base station transmission level)
RSRP (reference signal received power)
RSRQ (reference signal reception quality)
SNR (signal to noise ratio)
Of these, it is also preferable to make the computer function to include at least one.

According to another embodiment of the program of the present invention,
Advertising information storage means for storing advertising information for each moving vehicle;
It is also preferable to further cause the computer to function as application means for reproducing the advertisement information searched for the advertisement information storage means on the display of the terminal based on the moving vehicle estimated by the moving vehicle estimation means.

According to another embodiment of the program of the present invention,
The application means is communicable with the server storing the advertisement information for each moving vehicle, and uses the identifier of the moving vehicle estimated by the moving vehicle estimation means as a query and sends an advertisement information acquisition request to the server via the network. It is also preferable to make the computer function to transmit, receive advertisement information from the server, and temporarily store it in the advertisement information storage means.

According to the present invention, a mobile terminal capable of communicating with a base station and estimating a moving vehicle on which a user is boarded,
Model storage means for storing time series of observed base station identifiers as model transitions for each moving vehicle;
Radio wave monitoring means for acquiring a time series of base station identifiers observed for a predetermined number or period,
It has a moving vehicle estimation means for estimating that the user is on a moving vehicle based on the model transition most similar to the time series of the current base station identifier acquired by the radio wave monitoring means.

According to the present invention, using a device capable of communicating with a base station, a method for estimating a moving vehicle on which a user is boarding,
For each moving vehicle, it has a model storage unit that stores a time series of observed base station identifiers as model transitions,
A first step of obtaining a time series of observed base station identifiers for a predetermined number or period;
A second step of estimating that the user is on a moving vehicle based on a model transition that is most similar to the time series of the current base station identifier acquired by the radio wave monitoring means.

  According to the program, the portable terminal, and the method of the present invention, it is possible to estimate the moving vehicle on which the user is boarding without starting the GPS positioning. The mobile terminal of the present invention can reproduce the advertisement information corresponding to the moving vehicle without consuming special power only by observing the base station identifier.

It is a schematic map showing the position of a route and a road, and a base station. It is a functional block diagram of the portable terminal in this invention. It is explanatory drawing showing the hidden Markov model memorize | stored in the model memory | storage part. It is explanatory drawing showing the base station identifier actually observed with the portable terminal. It is explanatory drawing showing the several state transition x corresponding to a hidden Markov model. It is explanatory drawing showing the Markov model memorize | stored in the model memory | storage part.

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

  FIG. 1 is a schematic map showing routes and positions of roads and base stations.

  According to FIG. 1, a number of routes and roads are represented on the map, and a number of base stations 1 for a wireless communication network are also represented. In addition to walking, the user can board and move on a vehicle 3 such as a train, a bus, or an automobile. Here, according to the present invention, when a user gets on a vehicle and moves, the user can estimate which vehicle the portable terminal possessed by the user is on. The mobile terminal can estimate the moving vehicle from the change in the base station identifier that can be observed while traveling on the vehicle. If the moving vehicle can be estimated, the advertisement information corresponding to the moving vehicle can be reproduced on the mobile terminal and made visible to the user. Moreover, the estimation result of a moving vehicle has a use application also in various applications.

  FIG. 2 is a functional configuration diagram of the mobile terminal according to the present invention.

  The mobile terminal 2 is, for example, a mobile phone, a smartphone, or a tablet terminal, and is carried by the user. The portable terminal 2 can communicate with the base station 1 via a wireless communication network. According to the present invention, the mobile terminal 2 only needs to be able to observe the base station identifiers of one or more base stations 1 at the current position at all times without connecting to a specific base station. Of course, the portable terminal 2 can observe not only the base station identifier of the connection destination but also the base station identifiers of the neighboring base stations. The base station 1 is not limited to a base station of a cellular phone network, and may be a WiMAX base station, a wireless LAN access point, or a femtocell base station.

  According to FIG. 2, the mobile terminal 2 includes a wireless communication interface 201, a display 202, a data transmission / reception unit 211, and an application unit 212. These functions are generally installed in existing smartphones and the like. The mobile terminal 2 of the present invention further includes a model storage unit 22, a radio wave monitoring unit 23, and a moving vehicle estimation unit 24. These functional components are realized by executing a program that causes a computer mounted on the mobile terminal to function. Also, the processing steps of these functional components can be understood as a moving vehicle estimation method of the apparatus.

[Model storage unit 22]
The model storage unit 22 stores time series y of observed base station identifiers as model transitions for each moving vehicle i. Each moving vehicle is a train, a bus, an automobile, or the like, and is stored by a route or a system. <Hidden Markov Model> will be described as a model, and finally <Markov Model> will be described as another embodiment.

<Hidden Markov Model>
FIG. 3 is an explanatory diagram illustrating a hidden Markov model stored in the model storage unit.

  The Hidden Markov Model is a probabilistic model that assumes that the system is a Markov process with unknown parameters and estimates the unknown parameters from observable information. In general, it is applied to speech recognition and morphological analysis (natural language processing), and is suitable for pattern extraction of a signal sequence that can be continuously expanded and contracted. As particularly targeted by the present invention, for example, a base station identifier string that can be observed while traveling on a route is considered as a “continuous and expandable signal string” and can be applied to pattern extraction of moving vehicles. .

  The general hidden Markov model has no final state in the Markov chain. On the other hand, the hidden Markov model of the present invention preferably uses an LR (Left-to-Right) type in which an “initial state” and a “final state” can be set. In the case of a route or road targeted by the present invention, since it only moves forward in one direction, the LR type can be applied. This is a model generally used in speech recognition.

The model M is set for each moving vehicle i to be estimated.
M _i (i = 1, 2,..., L and L are the maximum number of moving means)
When the model transition is a hidden Markov model, it is composed of the following state S and transition probability A.
State S: Set according to the observation ratio of one or more base station identifiers Transition probability A: Probability of transition from the previous state S to the subsequent state S According to the hidden Markov model, there is an overlap between the output probability distributions. For this reason, the state of the transition destination is not uniquely determined from the base station identifier sequence as in the Markov model.

Here, a hidden Markov model M ₁ in the mobile vehicle 1 (i = 1) is assumed to be configured as follows.
Number of states = 3 (S1, S2, S3)
Number of base station identifiers = 2 (10, 12)
(State S1) Observation probability b ₁ (10) = 0.8 of the base station 10
Observation probability b ₁ (12) = 0.2 of base station 12
(State S2) Observation probability b ₂ (10) = 0.6 of base station 10
Observation probability b ₂ (12) = 0.4 of base station 12
(State S3) Observation probability b ₃ (10) = 0.2 of base station 10
Observation probability b ₃ (12) = 0.8 of base station 12
(Transition probability of S1-> S1) A ₁₁ = 0.50
(S1-> S2 transition _{probabilities)} A 12 = 0.45
(Transition probability of S1-> S3) A ₁₃ = 0.05
(Transition probability of S2-> S2) A ₂₂ = 0.30
(S2-> S3 transition _{probabilities)} A 23 = 0.70
This hidden Markov model M _i is constructed from a time series of base station identifiers that can be actually observed by placing a test device for each moving vehicle i.

[Radio wave monitoring unit 23]
FIG. 4 is an explanatory diagram showing base station identifiers actually observed by the mobile terminal.

The radio wave monitoring unit 23 acquires a time series of observed base station identifiers for a predetermined number or a predetermined period. According to FIG. 4, it is assumed that the base station identifier is periodically observed, for example, in the following time series by the mobile terminal 2 possessed by the user.
y ₁ ⁴ = (10, 10, 12, 12)
The observed base station identifier time series y is output to the moving vehicle estimation unit 24.

Note that the radio wave monitoring unit 23 may further acquire radio wave information from the wireless communication interface 201. The radio wave information may include at least one of the following radio qualities, for example.
Base station identifier of adjacent base station RSCP (Received Signal Code Power)
Ec / No (ratio of connected station RSCP to total received power)
RSS (Received Signal Strength)
C / I (interference wave ratio)
Ec / Io (adjacent base station transmission level vs. current base station transmission level)
RSRP (reference signal received power)
RSRQ (reference signal reception quality)
SNR (signal to noise ratio)

In this case, both the model of the model storage unit 22 and the time series y of the base station identifier of the radio wave monitoring unit 23 need to be expressed by a set of base station identifier and radio wave information. The time series y _i may be expressed as, for example, a multidimensional vector including a base station identifier and radio wave information. The radio wave intensity is preferably quantized.

[Moving vehicle estimation unit 24]
The moving vehicle estimation unit 24 estimates that the user is on a moving vehicle based on the model transition that is most similar to the time series of the current base station identifier acquired by the radio wave monitoring unit 23. The moving vehicle estimation unit 24 executes the following three steps.

(Step 1) Based on the time series y ₁ ⁿ of the current base station identifier acquired by the radio wave monitoring unit 24, a plurality of state transitions x that can occur from the initial state to the final state are derived in the model transition.

  FIG. 5 is an explanatory diagram showing a plurality of state transitions x corresponding to the hidden Markov model.

Here, there are the following three cases where the possible state transition x is [initial S1] [final S3].
Observation base station identifier 10 10 12 12
State transition 1: x ₁ = [initial S1]->S1->S2-> [final S3]
State transition 2: x ₂ = [initial S1]->S2->S2-> [final S3]
State transition 3: x ₃ = [initial S1]->S1->S1-> [final S3]

(Step 2) For each moving vehicle M _i , based on the time series y ₁ ⁿ of the current base station identifier, a total probability P (y ₁ ⁿ | M _i ) of the probability that each state transition x occurs is calculated.

Specifically, the probability P (y ₁ | M ₁ ) of obtaining y ₁ ⁴ for the model M ₁ is calculated as follows.
P (y ₁ | M ₁ ) = ΣP (y ₁ | x _i , M ₁ )
= ΣP (y ₁ | x _i ) P (x _i | M ₁ )

[In case of state transition 1]: x ₁ = [initial S1]->S1->S2-> [final S3]
P (x ₁ | M ₁ ) = a ₁₁ × a ₁₂ × a ₂₃
= 0.5 x 0.45 x 0.7 = 0.1575
P (y ₁ | x ₁ ) = b ₁ (10) × b ₁ (10) × b ₂ (12) × b ₃ (12)
= 0.8 x 0.8 x 0.4 x 0.8 = 0.2048
P (y ₁ | x ₁ , M ₁ ) = 0.1575 × 0.2048
= 0.0322560

[In the case of state transition 2]: x ₂ = [initial S1]->S2->S2-> [final S3]
P (x ₂ | M ₁ ) = a ₁₂ × a ₂₂ × a ₂₃
= 0.45 x 0.3 x 0.7 = 0.0945
P (y ₁ | x ₂ ) = b ₁ (10) × b ₂ (10) × b ₂ (12) × b ₃ (12)
= 0.8 x 0.6 x 0.4 x 0.8 = 0.1536
P (y ₁ | x ₂ , M ₁ ) = 0.0945 × 0.1536
= 0.0145152

[In case of state transition 3]: x ₃ = [initial S1]->S1->S1-> [final S3]
P (x ₃ | M ₁ ) = a ₁₁ × a ₁₁ × a ₁₃ =
= 0.5 x 0.5 x 0.05 = 0.0125
P (y ₁ | x ₃ ) = b ₁ (10) × b ₁ (10) × b ₁ (12) × b ₃ (12)
= 0.8 x 0.8 x 0.2 x 0.8 = 0.1024
P (y ₁ | x ₃ , M ₁ ) = 0.0125 × 0.1024
= 0.0012800

Finally, it looks like this:
P (y ₁ | M ₁ ) = ΣP (y ₁ | x _i , M ₁ )
= P (y ₁ | x ₁ , M ₁ ) + P (y ₁ | x ₂ , M ₁ ) + P (y ₁ | x ₃ , M ₁ )
= 0.0322560 + 0.0145152 + 0.0012800
= 0.0480512
In this manner, P (y ₁ | M _i ) is calculated for all models M _i .

(Step 3) A moving vehicle based on the highest probability Pmax = P (y ₁ ⁿ | M _i ) having a sum total probability P equal to or greater than a predetermined value is estimated. When the total probability P is less than a predetermined value, it is estimated that it does not correspond to any moving vehicle.

  Finally, the moving vehicle estimation unit 24 outputs the estimated moving vehicle identifier to the application unit 212.

[Advertising Information Storage Unit 213]
The advertisement information storage unit 213 stores advertisement information for each moving vehicle. For example, advertisement information for trains and advertisement information for buses are accumulated in advance.

[Application unit 212]
Based on the moving vehicle estimated by the moving vehicle estimation unit 24, the application unit 212 reproduces the advertisement information searched for the advertisement information storage unit 213 on the display of the terminal. For example, the advertisement information may be an electronic coupon for each moving vehicle. It may be provided only to users using a train or bus.

  In addition, the application unit 212 may be communicable with a server that stores advertisement information for each moving vehicle. Then, the application unit 212 uses the identifier of the moving vehicle estimated by the moving vehicle estimation unit 24 as a query, transmits an advertisement information acquisition request to the server via the network, receives the advertisement information from the server, and stores the advertisement information. The data is temporarily stored in the unit 213.

<Markov model>
FIG. 6 is an explanatory diagram illustrating a Markov model stored in the model storage unit.

The Markov model is a probability model in which the appearance probability of a predetermined symbol at a later time depends on the appearance of a previous symbol. When the model transition is a Markov model, it is composed of the following state S and transition probability A.
State S: Set observed base station identifier Transition probability A: Probability of transition from previous state S to subsequent state S

Each moving vehicle has a model M of transition probability of base station identifier. For example, when the observed base station identifier transits from 10->12-> 14 (or 10->11->12-> 14) while the moving vehicle on which the user has boarded moves, the following is performed: Construct a transition probability model.
Transition probability P (12 | 10) = 0.9 to 10-> 12
Transition probability P (11 | 10) = 0.1 to 10-> 11
11-> 12 transition probability P (12 | 11) = 0.5
Transition probability P (14 | 12) = 1.0 to 12-> 14

Assume that the time series of base station identifiers observed by the radio wave monitoring unit 23 is as follows.
y ₁ ³ = (10, 12, 14)
In this case, the use probability P (y ₁ ⁿ | M _i ) obtained by multiplying the transition probability A between states in the model transition is calculated as follows.
Usage probability P (M _i | y ₁ ⁿ ) = P (12 | 10) × P (14 | 12)
= 0.9 x 1.0
= 0.9
Utilization probabilities P are calculated for all models, and a moving vehicle is estimated based on the highest probability Pmax = P (y ₁ ⁿ | M _i ) that is greater than or equal to a predetermined value. On the contrary, when the maximum value of the use probability P is less than the predetermined value, it is estimated that the vehicle is not in any moving vehicle.

  As described above in detail, according to the program, the portable terminal, and the method of the present invention, it is possible to estimate the moving vehicle on which the user is boarding without starting the GPS positioning. The mobile terminal of the present invention can reproduce the advertisement information corresponding to the moving vehicle without consuming special power only by observing the base station identifier.

  Various changes, modifications, and omissions of the above-described various embodiments of the present invention can be easily made by those skilled in the art. The above description is merely an example, and is not intended to be restrictive. The invention is limited only as defined in the following claims and the equivalents thereto.

1, 10, 11, 12, 14 Base station 2 Mobile terminal 201 Wireless communication interface 202 Display 211 Data transmission / reception unit 212 Application unit 213 Advertising information storage unit 22 Model storage unit 23 Radio wave monitoring unit 24 Moving vehicle estimation unit 3 Moving vehicle

Claims (9)

A program that causes a computer to function so as to estimate a moving vehicle on which a user is boarded, using a mobile terminal that can communicate with a base station,
Model storage means for storing a time series of observed base station identifiers as model transitions for each moving vehicle;
Radio wave monitoring means for acquiring a time series of base station identifiers observed for a predetermined number or period,
A computer is caused to function as a moving vehicle estimation unit that estimates that the user is on a moving vehicle based on a model transition most similar to the time series of the current base station identifier acquired by the radio wave monitoring unit. Program. The model transition is a Left-to-Right (LR) type hidden Markov model,
A plurality of states S set according to the observation ratio of one or more base station identifiers;
It consists of the transition probability A from the previous state S to the subsequent state S,
The moving vehicle estimation means includes
Based on the time series y ₁ ⁿ of the current base station identifier acquired by the radio wave monitoring means, a plurality of state transitions x that can occur from the initial state to the final state are derived in the model transition,
For each moving vehicle M _i , the total probability P (y ₁ ⁿ | M _i ) of the probability that each state transition x occurs is calculated based on the time series y ₁ ⁿ of the current base station identifier,
The computer is made to function so as to estimate a moving vehicle based on the highest probability Pmax = P (y ₁ ⁿ | M _i ), wherein the total probability P is equal to or greater than a predetermined value. The program described in. The model transition is a Markov model,
A state S in which the observed base station identifier is set;
It consists of the transition probability A from the previous state S to the subsequent state S,
The moving vehicle estimation means includes
Based on the time series y ₁ ⁿ of the current base station identifier acquired by the radio wave monitoring means, the use probability P (y ₁ ⁿ | M _i ) obtained by multiplying the transition probability A between states in the model transition. To calculate
The computer is caused to function so as to estimate a moving vehicle based on the highest probability Pmax = P (y ₁ ⁿ | M _i ), wherein the use probability P is equal to or higher than a predetermined value. The program described. The model transition and the time series of the base station identifier are represented by a set of base station identifier and radio wave information,
The radio wave monitoring means acquires radio wave information of each observed base station identifier,
The said moving vehicle estimation means makes a computer function so that a user may estimate a moving vehicle using the set of the observed base station identifier and radio wave information, The any one of Claim 1 to 3 characterized by the above-mentioned. The program described in. The radio wave information is
Base station identifier of adjacent base station RSCP (Received Signal Code Power)
Ec / No (ratio of connected station RSCP to total received power)
RSS (Received Signal Strength)
C / I (interference wave ratio)
Ec / Io (adjacent base station transmission level vs. current base station transmission level)
RSRP (reference signal received power)
RSRQ (reference signal reception quality)
SNR (signal to noise ratio)
The program according to claim 4, wherein the computer is caused to function so as to include at least one of the programs. Advertising information storage means for storing advertising information for each moving vehicle;
The computer is further caused to function as application means for reproducing the advertisement information searched for the advertisement information storage means on the display of the terminal based on the moving vehicle estimated by the moving vehicle estimation means. 6. The program according to any one of items 1 to 5. The application means is communicable with the server storing the advertisement information for each moving vehicle, and uses the identifier of the moving vehicle estimated by the moving vehicle estimation means as a query to the server via the network. The program according to claim 6, wherein the computer functions to transmit an acquisition request, receive advertisement information from the server, and temporarily store the advertisement information in the advertisement information storage unit. A mobile terminal capable of communicating with a base station and estimating a moving vehicle on which a user is boarded,
Model storage means for storing a time series of observed base station identifiers as model transitions for each moving vehicle;
Radio wave monitoring means for acquiring a time series of base station identifiers observed for a predetermined number or period,
Mobile vehicle estimation means for estimating that the user is on a moving vehicle based on the model transition most similar to the time series of the current base station identifier acquired by the radio wave monitoring means Mobile device. A method for estimating a moving vehicle on which a user is boarded using a device capable of communicating with a base station,
Each mobile vehicle has a model storage unit that stores a time series of observed base station identifiers as model transitions,
A first step of obtaining a time series of observed base station identifiers for a predetermined number or period;
A second step of estimating that the user is on a moving vehicle based on a model transition that is most similar to a time series of current base station identifiers acquired by the radio wave monitoring means. Device moving vehicle estimation method.

Images