JP6992534B2 - Data creation device, guidance model learning device, guidance estimation device, data creation method, guidance model learning method, guidance estimation method and program - Google Patents

Description

The present invention relates to a data creation device, a guidance model learning device, a guidance estimation device, a data creation method, a guidance model learning method, a guidance estimation method, and a program.

Appropriate guidance to people on the road can eliminate congestion, increase safety, and reduce travel time.

With the development of sensor technology, it has become possible to easily collect road information such as traffic volume. Therefore, a method of obtaining appropriate guidance by using the collected road information has been proposed. For example, a method has been proposed in which the parameters of the simulator are estimated from the collected road information, and appropriate guidance is estimated by performing trial and error with a simulator using the estimated parameters (see, for example, Non-Patent Document 1). ..

Naonori Ueda, Futoshi Naya, Hitoshi Shimizu, Tomoharu Iwata, Maya Okawa, and Hiroshi Sawada. 2015. Real-time and proactive navigation via spatio-temporal prediction. In Adjunct Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings. of the 2015 ACM International Symposium on Wearable Computers (UbiComp / ISWC'15 Adjunct). ACM, New York, NY, USA, 1559-1566. Internet <https://doi.org/10.1145/2800835.2801624>

However, estimation of simulator parameters usually requires a large amount of road information. In addition, since trial and error by a simulator is required, it may take a lot of time to obtain appropriate guidance.

The present invention has been made in view of the above points, and an object of the present invention is to estimate effective guidance using road information.

Therefore, in the data creation device according to the embodiment of the present invention, when the road structure representing the road structure and the road condition for each road structure are acquired or created, guidance is performed for each road structure. Road effect data including a guidance road structure representing the structure of the road, a guidance effect showing the effect of performing the guidance on the case where the guidance is not performed, and at least one of the road structure and the road condition. It is characterized by having a data creation means for creating the above.

Further, the guidance model learning device according to the embodiment of the present invention is a parameter of a model that outputs information on guidance when at least one of a road structure representing the road structure and the road condition for each road structure is input. It is a guidance model learning device that estimates It is characterized by having a parameter estimation means for estimating the parameter so as to minimize the error with the included induction effect.

Further, the guidance estimation device according to the embodiment of the present invention is the guidance by a model that outputs information regarding guidance when at least one of a road structure representing the road structure and the road condition for each road structure is input. It is a guidance estimation device that estimates information about, and inputs at least one of the road structure and the road condition to the model in which the parameters estimated by the parameter estimation means in the guidance model learning device are set. It is characterized by having a guidance estimation means for estimating information regarding the guidance.

Road information can be used to estimate effective guidance.

It is a figure which shows an example of the functional structure of the guidance estimation apparatus in embodiment of this invention. It is a flowchart which shows an example of the process performed by the guidance estimation apparatus in embodiment of this invention. It is a figure which shows an example of the evaluation result of this invention. It is a figure which shows an example of the hardware composition of the guidance estimation apparatus in embodiment of this invention.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the embodiment of the present invention, the guidance estimation device 10 that estimates guidance from road information will be described. The moving object to be guided is not limited to a person moving on the road (pedestrian, etc.), and may be, for example, an arbitrary moving object moving on an arbitrary graph such as a car or an automobile moving on the road. good. The graph is not limited to a road, and may be, for example, an indoor passage.

<Functional configuration of guidance estimation device 10>
First, the functional configuration of the guidance estimation device 10 according to the embodiment of the present invention will be described with reference to FIG. FIG. 1 is a diagram showing an example of the functional configuration of the guidance estimation device 10 according to the embodiment of the present invention.

As shown in FIG. 1, the guidance estimation device 10 according to the embodiment of the present invention has a data creation unit 110, a parameter estimation unit 120, and a guidance estimation unit 130. Each of these functional units is realized by a process of causing a CPU (Central Processing Unit) or the like to execute one or more programs installed in the guidance estimation device 10. It should be noted that each of these functional units may be realized by a process executed by one program, or may be realized by a process executed by a different program.

Further, the guidance estimation device 10 according to the embodiment of the present invention has a storage unit 140. The storage unit 140 can be realized by using, for example, an auxiliary storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive). The storage unit 140 may be realized by using a storage device or the like connected to the guidance estimation device 10 via a network.

The data creation unit 110 creates road information and data related to the guidance effect at that time (this data is referred to as “road effect data”) by simulation. The data creation unit 110 includes a road structure creation unit 111, a road condition creation unit 112, a guidance road structure creation unit 113, a guidance effect measurement unit 114, and a road effect data creation unit 115. Any traffic simulator can be used as the simulator used for the simulation.

The road structure creation unit 111 is a set of N road structures G _n .

を作成する。以降では、道路構造Ｇ_ｎの集合を「道路構造集合」と表す。

To create. Hereinafter, the set of road structures _Gn will be referred to as a “road structure set”.

The road structure _Gn is, for example, information representing the structure of the road such as the connection between the roads, the width, and the slope. The road structure _Gn may be information obtained by observing a road in the real world with a sensor or the like, or may be information generated by a simulator or the like. The road structure _Gn can be represented by a graph, for example, where a node represents a road and an edge represents a connection between roads.

The road condition creation unit 112 generates M _n simulation parameters for each road structure G _n . Then, the road condition creation unit 112 simulates using these parameters to set M _n road conditions X _nm .

を作成する。以降では、Ｍ_ｎ個の道路状況Ｘ_ｎｍの集合を「道路状況集合」と表す。

To create. Hereinafter, the set of M _n road conditions X _nm is referred to as a “road condition set”.

The road condition X _nm represents information on a moving object such as the number of people included in each road in a certain time zone, the number of people passing through a certain place, and the average moving speed of each road. For example, the number of people included in each road at each time, assuming that the road condition is X _nm .

が利用できる。ここで、ｘ_ｎｍｉｔはｎ番目の道路構造Ｇ_ｎにおけるｍ番目の道路状況Ｘ_ｎｍで時刻ｔにｉ番目の道路に含まれる人数、Ｉ_ｎはｎ番目の道路構造Ｇ_ｎの道路数、Ｔは観測の時刻数を表す。なお、時刻ｔは、シミュレーションの或る時刻から或る時刻までを或る時間幅に分割した場合における各時間幅を表すインデックスである。また、道路状況Ｘ_ｎｍとして全時刻の状況ではなく、観測の最終時刻から或る時間幅の時刻の状況を用いても良い。

Is available. Here, x _nmit is the m-th road condition in the _n -th road structure Gn, the number of people included in the i-th road at time t at X _nm , In is the number of roads in the _n -th road structure _Gn , and T is. Represents the number of observation times. The time t is an index representing each time width when the simulation is divided into a certain time width from a certain time to a certain time. Further, as the road condition X _nm , the condition of a certain time width from the last time of observation may be used instead of the condition of all time.

The guidance road structure creation unit 113 is a set of road structures G _nk when K _n guidances are made for each road structure G _n .

を作成する。

To create.

For example, when each road is closed as a guidance measure, G _nk determines the road structure when the kth road is closed, that is, the kth node (road) from _Gn and the edge corresponding to the node. It is represented by the deleted graph.

Guidance measures include, for example, closing roads, changing road widths, restricting the number of people, guiding to the next road, one-way streets, creating lanes with different speeds, increasing / decreasing the speed, adding roads, etc. can. That is, the guidance measure is not necessarily limited to guidance, and any measure that can be expressed as a road structure can be used.

The guidance effect measuring unit 114 sets the road condition x _nmT at the final time (final time of observation) created by simulating using the road structure _Gn when not guiding as the initial value, and has the same parameters as the simulation when not guiding. And the road structure G _nk in each guidance is used to measure and create the guidance effect s _nmk .

The parameters of the simulation using the road structure G _n when not guiding and the road condition x _nmT are those generated and created by the road condition creating unit 112. Further, for example, when the number of people included in each road at each time is used as the road condition X _nm , the road condition x _nmT at the final time is

である。

Is.

As the guidance effect, it is possible to use any index that you want to increase by guidance, such as the time to shorten the average time to reach the destination, the time to shorten the maximum time to reach the destination, the number of people arriving at the destination, etc. can. As the induction effect, for example, an arbitrary index that is desired to be reduced by induction, such as the degree of congestion and the number of congestion points, can be used, but in this case, the value of the index is negative (that is, -1). (Adopt the multiplied value).

The road effect data creation unit 115 is a road effect data summarizing each road structure _Gn , each road condition X _nm , and each guidance effect s _nmk .

を作成する。ここで、

To create. here,

はｎ番目の道路構造Ｇ_ｎにおけるｍ番目の道路状況Ｘ_ｎｍでの誘導効果ｓ_ｎｍｋをまとめたベクトルである。道路状況Ｘ_ｎｍとして、誘導をする直前の時刻のみの道路状況を用いても良いし、誘導をする直前の時刻から或る一定時間の道路状況を用いても良い。

Is a vector summarizing the guidance effect s _nmk at the mth road condition X _nm in the _nth road structure Gn. As the road condition X _nm , the road condition only at the time immediately before the guidance may be used, or the road condition for a certain period of time from the time immediately before the guidance may be used.

Hereinafter, the information including the road structure _Gn and the road condition X _nm is also referred to as “road information”. Therefore, it can be said that the road guidance data is data that summarizes the road information and each guidance effect s _nmk .

However, the road information may be information including either the road structure _Gn or the road condition X _nm .

The road effect data created by the road effect data creating unit 115 is stored in the storage unit 140. This road effect data is learning data used for parameter estimation of the guidance model described later.

It should be noted that the data creation unit 110 does not necessarily have to create at least one of each road structure _Gn and each road condition X _nm , and for example, data obtained by observing the real world with a sensor or the like is input from the outside. May be. That is, the road structure creating unit 111 may acquire each road structure _Gn input from the outside. Similarly, the road condition creation unit 112 may acquire the road condition X _nm input from the outside.

The parameter estimation unit 120 estimates the parameters of the guidance model using the road effect data stored in the storage unit 140. The guidance model is a model that estimates and outputs guidance (or information corresponding to guidance) by inputting road information.

The parameter estimation unit 120 estimates the parameters of the guidance model so that more appropriate guidance (more effective guidance) can be estimated when the road information is given. As the guidance model, a graph convolutional neural network can be used. However, the model is not limited to this, and any model such as a neural network, a support vector machine, or a Gaussian process can be used as a guidance model as long as it is a model that can estimate and output guidance when road information is given. be able to.

In the case of a graph convolutional neural network, for example, a neural network layer as shown in Equation 1 below can be used.

ここで、

here,

はｌ層目のノードｉにおける隠れ層のベクトルであり、０層目の隠れ層は道路状況、すなわち、

Is the vector of the hidden layer in the node i of the lth layer, and the hidden layer of the 0th layer is the road condition, that is,

であるとする。

Suppose that

In this case, a linear transformation matrix

が推定すべきパラメータである。

Is the parameter to be estimated.

Assuming the guidance of road closure, the size of the final hidden layer (that is, the hidden layer of the Lth layer) is set to 1 because the index i indicating each road and the index k indicating each guidance correspond to each other. Last hidden layer value

を出力とすることができる。なお、簡単のため、最終隠れ層の値を「ｚ_ｎｍｉ」とも表すものとする。

Can be output. For the sake of simplicity, the value of the final hidden layer is also expressed as "z _nmi ".

On the other hand, depending on the guidance measures, the index i indicating each road and the index k indicating each guidance may not correspond to each other. In this case, it can be dealt with by constructing the graph so that the node of the graph representing the road structure _Gn corresponds to the index indicating each guidance.

In many road effect data, the objective function is one in which the value becomes high when it is output so as to correlate with the induction effect s _nmk , and the value becomes low when it is not, and the value of the objective function is made as small as possible. Estimate the parameters as follows. For example, y _nmi is obtained by adding the inducing effect s _nmi by the softmax function and normalizing it so that it becomes 1 (sum total is 1). Since the index i indicating each road and the index k indicating each guidance correspond to each other, the index k is replaced with the index i.

Here, the higher the value of the induction effect s _nmi (similarly normalized y _nmi ), the higher the effect of induction (that is, for example, the average time to reach the destination is short, to the destination. The number of arrivals is large, the degree of congestion is low, the number of crowded areas is small, etc.). Then, as shown in Equation 2 below, the cross entropy of y _nmi and the softmax function for the value z _nmi of the final hidden layer can be used as the objective function in all road effect data.

なお、交差エントロピー以外にも、例えば、二乗誤差等の他の誤差を用いても良い。

In addition to the cross entropy, other errors such as a square error may be used.

The parameters estimated by the parameter estimation unit 120 are stored in the storage unit 140.

The guidance model is not only a model that uses two pieces of information of the road structure _Gn and the road condition X _nm , but also a model that uses information of either the road structure _Gn or the road condition X _nm , for example. Is also good.

The guidance estimation unit 130 estimates the guidance by using the guidance model in which the parameters stored in the storage unit 140 are set and the road information. That is, for example, the guidance estimation unit 130 obtains an output z _nmi by inputting the road structure G _n and the road condition X _nm included in the road information into the guidance model in which the parameters are set. Of the outputs z _nmi , the induction corresponding to the output z _nmi having the highest value is the optimum induction (that is, the induction expected to have a high effect (induction effect)). Further, for example, when it is desired to rank a plurality of leads, the output values may be sorted in descending order.

Moreover, you may combine a plurality of inductions. For example, after obtaining the optimum guidance by the guidance model, the road structure is modified according to this guidance, and the next guidance is obtained again by the guidance model using the modified road structure. This makes it possible to obtain a combination of a plurality of leads.

When the parameters of the guidance model are estimated using the information of either the road structure _Gn or the road condition X _nm , either the road structure _Gn or the road condition X _nm included in the road information is used. The guidance may be obtained as an output by inputting it into the guidance model in which the parameters are set.

The guidance estimated by the guidance estimation unit 130 is output to a predetermined output destination. The predetermined output destination may be a display device such as a display, a storage unit 140, an external recording medium, or the like, or another device or the like connected via a network. ..

In the example shown in FIG. 1, a case where one device (guidance estimation device 10) has a data creation unit 110, a parameter estimation unit 120, and a guidance estimation unit 130 has been described, but the present invention is not limited to this. .. The data creation unit 110, the parameter estimation unit 120, and the guidance estimation unit 130 may be distributed to a plurality of devices. For example, even if the embodiment of the present invention is realized by, for example, a data creation device having a data creation unit 110, a guidance model learning device having a parameter estimation unit 120, and a guidance estimation device having a guidance estimation unit 130. good.

<Process executed by the guidance estimation device 10>
Next, the flow of processing executed by the guidance estimation device 10 according to the embodiment of the present invention will be described with reference to FIG. FIG. 2 is a flowchart showing an example of a process executed by the guidance estimation device 10 according to the embodiment of the present invention.

Step S101: The data creation unit 110 creates road effect data. That is, the data creation unit 110 creates or acquires each road structure _Gn by the road structure creation unit 111, creates or acquires each road condition X _nm by the road condition creation unit 112, and each of the guide road structure creation unit 113. The road structure G _nk is created, and each induction effect s _nmk is created by the induction effect measuring unit 114. Then, the data creation unit 110 creates the road effect data by the road effect data creation unit 115, and stores the created road effect data in the storage unit 140.

Step S102: Next, the parameter estimation unit 120 estimates the parameters of the guidance model using the road effect data stored in the storage unit 140. That is, the parameter estimation unit 120 estimates the parameters that minimize the error between the output of the guidance model using the road information included in the road effect data and the guidance effect included in the road effect data. Then, the parameter estimation unit 120 stores the estimated parameters in the storage unit 140.

Step S103: Next, the guidance estimation unit 130 estimates the guidance using the guidance model in which the parameters stored in the storage unit 140 are set and the road information.

That is, for example, the guidance estimation unit 130 obtains an output by inputting the road structure G _* and the road condition X _* included in the road information into the guidance model in which the parameters are set. Alternatively, when the parameters of the guidance model are estimated using either the road structure G _* or the road condition X _* , the guidance estimation unit 130 uses either the road structure G _* or the road condition X _* included in the road information. An output is obtained by inputting one of them into the guidance model in which the relevant parameter is set. Then, the guidance estimation unit 130 sets, for example, the guidance corresponding to the output of the highest output value as the optimum guidance.

As described above, the guidance estimation device 10 according to the embodiment of the present invention creates road information and data (road effect data) relating to the guidance effect at that time by simulation. Then, the guidance estimation device 10 in the embodiment of the present invention estimates the parameters of the guidance model using the road effect data. As a result, in the guidance estimation device 10 according to the embodiment of the present invention, the optimum guidance (that is, effective guidance) can be estimated at high speed by inputting the road information into the guidance model in which this parameter is set. become able to.

<Evaluation Example of the Present Invention>
Here, an evaluation example of the present invention will be described. In order to evaluate the present invention, the following experiments were conducted. That is, first, 700 road structures were created based on the roads around Japanese railway stations. In each road structure, a total of 100,000 people, including pedestrians heading to the station from some random places around the station and pedestrians heading to some random places from the station, were simulated for 30 minutes. Using the end time of this 30-minute simulation as the start time, a simulation was additionally performed for an additional 30 minutes in the case of guiding to close each road.

The induction effect is the average time to reach the destination multiplied by -1 in the simulation for all 1 hour. The parameters of the guidance model were estimated using the road effect data including one road condition and the guidance effect in each of the 700 road structures as learning data. As the road condition, the number of people included in each road at 1 hour immediately before the guidance was used.

Then, the road effect data of 70 road structures different from the training data was used as verification data, and the road effect data of 70 road structures different from the learning data and the verification data were used as test data. As the guidance model, a graph convolutional neural network with 3 hidden layers and 10 hidden layers was used, and the initial values were changed and learned 5 times, and the one with the lowest cross entropy in the verification data was adopted. On the other hand, as a comparison method with the present invention, "random" for randomly selecting a road to be closed, "maximum number of people" for selecting the road with the largest number of people, and "the road leading to the road with the largest number of people" are selected. We used "before the maximum number of people" and "after the maximum number of people" to select the road connecting from the road with the largest number of people.

For each of the present invention and each comparison method, the difference between the average arrival time without induction and the average arrival time with induction is shown in FIG. 3 using test data. In FIG. 3, a negative value indicates that the average arrival time was shorter when the induction was performed than when the induction was not performed.

As shown in FIG. 3, it can be seen that when the guidance estimated by the present invention was performed, the arrival time per person was shortened by 21.9 seconds as compared with the case where the guidance was not performed. On the other hand, as shown in FIG. 3, in the comparison method, the arrival time is longer when the guidance is performed than when the guidance is not performed.

<Hardware configuration of guidance estimation device 10>
Finally, the hardware configuration of the guidance estimation device 10 according to the embodiment of the present invention will be described with reference to FIG. FIG. 4 is a diagram showing an example of the hardware configuration of the guidance estimation device 10 according to the embodiment of the present invention.

The guidance estimation device 10 shown in FIG. 4 includes an input device 201, a display device 202, an external I / F 203, a RAM (Random Access Memory) 204, a ROM (Read Only Memory) 205, a CPU 206, and a communication I /. It has an F207 and an auxiliary storage device 208. Each of these hardware is connected so as to be communicable via the bus B.

The input device 201 is, for example, a keyboard, a mouse, a touch panel, or the like, and is used for a user to input various operations. The display device 202 is, for example, a display or the like, and displays the processing result of the guidance estimation device 10. The guidance estimation device 10 does not have to have at least one of the input device 201 and the display device 202.

The external I / F 203 is an interface with an external device. The external device includes a recording medium 203a and the like. The guidance estimation device 10 can read or write the recording medium 203a or the like via the external I / F 203. A program or the like that realizes each function of the guidance estimation device 10 may be recorded on the recording medium 203a.

The recording medium 203a includes, for example, a flexible disk, a CD (Compact Disc), a DVD (Digital Versatile Disk), an SD memory card (Secure Digital memory card), a USB (Universal Serial Bus) memory card, and the like.

The RAM 204 is a volatile semiconductor memory that temporarily holds programs and data. The ROM 205 is a non-volatile semiconductor memory that can hold programs and data even when the power is turned off. The ROM 205 stores, for example, OS (Operating System) settings, network settings, and the like.

The CPU 206 is an arithmetic unit that reads programs and data from the ROM 205, the auxiliary storage device 208, and the like onto the RAM 204 and executes processing.

The communication I / F 207 is an interface for connecting the guidance estimation device 10 to the communication network. The program that realizes each function of the guidance estimation device 10 may be acquired (downloaded) from a predetermined server device or the like via the communication I / F 207.

The auxiliary storage device 208 is, for example, an HDD, an SSD, or the like, and is a non-volatile storage device that stores programs and data. The programs and data stored in the auxiliary storage device 208 include, for example, an OS, an application program that realizes various functions on the OS, a program that realizes each function of the guidance estimation device 10, and the like.

The guidance estimation device 10 according to the embodiment of the present invention can realize the above-mentioned various processes by having the hardware configuration shown in FIG.

The present invention is not limited to the above-described embodiment disclosed specifically, and various modifications and modifications can be made without departing from the scope of claims.

10 Guidance estimation device 110 Data creation unit 111 Road structure creation unit 112 Road condition creation unit 113 Guidance road structure creation unit 114 Guidance effect measurement unit 115 Road effect data creation unit 120 Parameter estimation unit 130 Guidance estimation unit 140 Storage unit

Claims (9)

When the first road structure representing the road structure is acquired or created, each of the first road structure and the plurality of simulation parameters corresponding to the first road structure for each of the first road structures. By performing the first traffic simulation using and, the road condition creating means for creating the road condition at each simulation time for each of the first road structure and the simulation parameter , and
For each of the first road structures, the second road structure when a predetermined guidance measure is applied to the first road structure, and the first traffic simulation using the first road structure. Using the road condition at the final simulation time when the road condition was obtained and the same simulation parameter as the simulation parameter used in the first traffic simulation when the road condition was obtained, the road condition was set as an initial value. By performing each of the second traffic simulations, the guidance effect creation means for creating the guidance effect showing the effect of the guidance measure and the guidance effect creation means.
A data creation means for creating road effect data including the guidance effect and at least one of the first road structure and the road condition.
A data creation device characterized by having. It is a guidance model learning device that estimates the parameters of a model that outputs information on guidance measures when at least one of the road structure representing the road structure and the road condition for each road structure is input.
The error between the information regarding the guidance measure output by inputting the road effect data created by the data creation device according to claim 1 into the model as learning data and the guidance effect included in the road effect data is minimized. A parameter estimation means that estimates the parameters so as to be
A guidance model learning device characterized by having. The parameter estimation means is
The guidance model learning according to claim 2, wherein the parameter is estimated so as to minimize the error between the information regarding the guidance measure and the value obtained by normalizing the guidance effect using a predetermined function. Device. It is a guidance estimation device that estimates information on the guidance measure by a model that outputs information on the guidance measure when at least one of the road structure representing the road structure and the road condition for each road structure is input.
Information on the guidance measure is estimated by inputting at least one of the road structure and the road condition to the model in which the parameters estimated by the guidance model learning device according to claim 2 or 3 are set. Guidance estimation means,
A guidance estimation device characterized by having. When the first road structure representing the road structure is acquired or created, each of the first road structure and the plurality of simulation parameters corresponding to the first road structure for each of the first road structures. By performing the first traffic simulation using and, the road condition creation procedure for creating the road condition at each simulation time for each of the first road structure and the simulation parameter , and
For each of the first road structures, the second road structure when a predetermined guidance measure is applied to the first road structure, and the first traffic simulation using the first road structure. Using the road condition at the final simulation time when the road condition was obtained and the same simulation parameter as the simulation parameter used in the first traffic simulation when the road condition was obtained, the road condition was set as an initial value. By performing the second traffic simulations, the guidance effect creation procedure for creating the guidance effect showing the effect of the guidance measure and the guidance effect creation procedure.
A data creation procedure for creating road effect data including the guidance effect and at least one of the first road structure and the road condition.
A data creation method characterized by a computer performing. When at least one of the road structure representing the road structure and the road condition for each road structure is input, a computer that estimates the parameters of the model that outputs information on the guidance measures is used.
The error between the information regarding the guidance measure output by inputting the road effect data created by the data creation method according to claim 5 into the model as learning data and the guidance effect included in the road effect data is minimized. Parameter estimation procedure for estimating the above parameters,
A guided model learning method characterized by performing. The parameter estimation procedure is
The guidance model learning according to claim 6, wherein the parameter is estimated so as to minimize the error between the information regarding the guidance measure and the value obtained by normalizing the guidance effect using a predetermined function. Method. When at least one of the road structure representing the road structure and the road condition for each road structure is input, the computer that estimates the information about the guidance measure by the model that outputs the information about the guidance measure is used.
Information on the guidance measure is estimated by inputting at least one of the road structure and the road condition to the model in which the parameters estimated by the guidance model learning method according to claim 6 or 7 are set. Guidance estimation procedure,
A guided estimation method characterized by performing. A program for making a computer function as the data creation device according to claim 1, the guidance model learning device according to claim 2 or 3, or the guidance estimation device according to claim 4.

Images