WO2024209566A1 - Information processing device, information processing method, and information processing program - Google Patents

Abstract

An information processing device (100A) according to the present application comprises: an acquisition unit (133) that acquires an operation load ratio indicating a ratio between a state in which the driving load of a driver is high on a travel route of a target vehicle and a state in which the driving load is low; and an output control unit (134) that outputs the timing at which the driver should take a break by using at least the operation load ratio.

Description

Information processing device, information processing method, and information processing program

The present invention relates to an information processing device, an information processing method, and an information processing program.

In conventional car navigation systems, the general method of suggesting a break was to simply notify the driver of a message encouraging them to take a break when a set driving time (e.g., two hours) had elapsed. However, depending on the driving conditions, the timing of the suggestion could come too late, resulting in cases where the break suggestion was not appropriate.

On the other hand, a method has been proposed that uses biometric information such as drowsiness or fatigue as input and uses a learning model to recommend breaks. However, with this method, it is difficult to estimate the timing when a break is necessary when the biometric information is not changing.

JP 2021-149617 A

The present invention therefore proposes an information processing device, information processing method, and information processing program that can notify the driver of appropriate times to take a break.

The information processing device described in claim 1 includes an acquisition unit that acquires a driving load ratio that indicates the ratio between a state in which the driver's driving load is high and a state in which the driver's driving load is low on the driving route of the target vehicle, and an output control unit that uses at least the driving load ratio to output the timing when the driver should take a break.

The information processing method described in claim 13 is an information processing method executed by an information processing device, and includes an acquisition step of acquiring a driving load ratio indicating the ratio between a state in which the driver's driving load is high and a state in which the driver's driving load is low on the driving route of the target vehicle, and an output control step of outputting the timing when the driver should take a break using at least the driving load ratio.

The information processing program described in claim 14 is an information processing program executed by an information processing device, and causes the information processing device to execute an acquisition procedure for acquiring a driving load ratio indicating the ratio between a state in which the driver's driving load is high and a state in which the driver's driving load is low on the driving route of the target vehicle, and an output control procedure for outputting the timing when the driver should take a break using at least the driving load ratio.

FIG. 1 is a diagram illustrating an example of a system according to the first embodiment. FIG. 2 is a diagram illustrating an example of the configuration of a first server device according to the first embodiment. FIG. 3 is a diagram illustrating an example of the configuration of the second server device. FIG. 4 is a diagram showing a specific example of a method for estimating the WL type. FIG. 5 is a diagram showing a specific example (1) of a method for generating a prediction model. FIG. 6 is a diagram showing a specific example (2) of a method for generating a prediction model. FIG. 7 is a sequence diagram showing a procedure of processing performed between server devices included in the system according to the first embodiment. FIG. 8 is a flowchart showing the procedure of the rest timing prediction process. FIG. 9 is a diagram illustrating an example of a system according to the second embodiment. FIG. 10 is a diagram illustrating an example of the configuration of a first server device according to the second embodiment. FIG. 11 is a flowchart showing the procedure of the range specification process. FIG. 12 is a diagram showing a specific example of the range specification process. FIG. 13 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment.

[Embodiment]
Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. Note that the information processing device, information processing method, and information processing program according to the present invention are not limited to the embodiment. In addition, the same components in the following embodiments are given the same reference numerals, and duplicated descriptions will be omitted.

First Embodiment
1. System configuration
First, the configuration of a system according to the first embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of a system according to the first embodiment. Fig. 1 shows a system SyA as an example of the system according to the first embodiment. Information processing according to the first embodiment is realized in the system SyA.

As shown in FIG. 1, the system SyA includes an in-vehicle device 10, a first server device 100A, and a second server device 200. The in-vehicle device 10, the first server device 100A, and the second server device 200 are connected to each other via a network N so as to be able to communicate with each other via a wired or wireless connection.

The in-vehicle device 10 may be a dedicated navigation device built into or mounted on the vehicle VEn. For example, the in-vehicle device 10 may be composed of a navigation device and a recording device (drive recorder). As one example, the in-vehicle device 10 may be a composite device in which a navigation device and a recording device that are independent of each other are connected so as to be able to communicate with each other. As another example, the in-vehicle device 10 may be a single device that has a navigation function and a recording function.

The in-vehicle device 10 also includes various sensors. For example, the in-vehicle device 10 may include various sensors such as a camera, an acceleration sensor, a gyro sensor, a GPS (Global Positioning System) sensor, and an air pressure sensor. For this reason, the in-vehicle device 10 may also have a function of providing dialogue and information to assist driving based on sensor information acquired by the various sensors.

In addition, the in-vehicle device 10 can use not only the sensors installed in the device itself, but also sensor information detected by sensors installed in the vehicle VEn itself as a safe driving system.

In addition, by installing specific application software into a portable terminal device (e.g., a smartphone, tablet terminal, notebook PC, PDA, etc.) that a user uses on a daily basis, the portable terminal device can be made to operate in the same manner as the in-vehicle device 10.

In this embodiment, a user refers to a person who is directly involved with vehicle VEn (for example, the driver who drives vehicle VEn, or a passenger other than the driver). In addition, when vehicle VEn is to be uniquely displayed, an arbitrary common value is substituted for "n", and it is expressed as, for example, vehicle VE1, vehicle VE2, etc.

The first server device 100A is a central device responsible for information processing according to the first embodiment. For example, the first server device 100A calculates a driving load ratio based on the type of driving load (workload) using the driving time of a target vehicle (referred to as a "target vehicle VEx") that is the subject of a proposal among the vehicles VEn. The first server device 100A then predicts the timing at which the driver DX of the target vehicle VEx should take a break by inputting the driving load ratio into a prediction model in which the driving time that an unspecified number of drivers actually travel before taking a break is statistically modeled. The prediction result is controlled to be output from the in-vehicle device 10 of the target vehicle VEx.

Here, we will explain the workload (hereinafter abbreviated as "WL"). WL indicates the driving load, and may include both the driver's sense of burden (which can also be said to be the degree of difficulty) and the driving load set for a road section.

Types of driving load, i.e., WL types, include, for example, "BUSY," "IDEAL," and "FREE," and indicate that in road sections designated as "BUSY," the burden on the driver is above a standard (i.e., the difficulty of driving is high), in road sections designated as "FREE," the burden on the driver is below a standard (i.e., the difficulty of driving is low or not high), and in road sections designated as "IDEAL," the burden on the driver is medium (i.e., the difficulty of driving is normal or not high).

Furthermore, the degree of difficulty for the driver may be expressed numerically as the driver's sense of burden, and can be defined as follows:

For example, a severity level of "1" corresponds to a WL type of "BUSY_MAX" and is a road section where all general drivers need to be careful when driving, and it is defined that the in-vehicle device 10 should only issue a warning notification on such road sections.

The severity level of "0.80" corresponds to the WL type "BUSY+", and is a road section where more than 60% of general drivers have to be careful when driving, and it is defined that in such road sections, the in-vehicle device 10 should only issue warning notifications and caution notifications.

The severity level of "0.60" corresponds to a WL type of "BUSY," and is a road section where more than 20% of general drivers have to be careful when driving. It is defined that in such road sections, the in-vehicle device 10 should only issue warning notifications, caution notifications, and important notifications.

The severity level of "0.50" corresponds to the WL type "IDEAL", and it is defined that in the relevant road section, the in-vehicle device 10 may also speak content other than guidance-related information (warning notifications, caution notifications, important notifications).

A difficulty level of "0.25" corresponds to a WL type of "FREE," and is defined as a road section that more than 50% of general drivers would find monotonous and boring, and in which a variety of content should be spoken.

Note that the WL type is not necessarily limited to the above examples ("BUSY_MAX", "BUSY+", "BUSY", "IDEAL", and "FREE"). In the following embodiment, the WL types will be mainly described as "BUSY" and "FREE". The criteria and reference values shown above are merely examples and may be any values. For example, "BUSY" is an example of a first type indicating that the WL is high compared to the reference value. Furthermore, "FREE" is an example of a second type indicating that the WL is low compared to the reference value.

Next, road sections will be explained. For example, a road section means a section between characteristic points of a road, and is called a link. Characteristic points of a road are intersections, corners, dead ends, etc., and are called nodes. In other words, a link means a road section that is set based on a specific rule. In other words, a link means a unit that divides a recorded section of a movement history based on a specific rule.

Following the above example, in the following embodiment, a road section is represented as a link, and a connection point between links is represented as a node. For example, the first server device 100A has a map information storage unit 121 (FIG. 2), which includes road data that represents a road network as a combination of nodes and links, facility data, and object information around the road. The object information includes information on obstacles that exist temporarily, as well as features such as signs such as road signs, road markings such as stop lines, road dividing lines such as center lines, and structures along the road. Obstacles refer to factors that impede the passage of pedestrians and bicycles, such as puddles, sunken parts of the road, fallen objects, and drains (including parts blocked by nets). The object information may include highly accurate point cloud information of objects to be used for vehicle position estimation, etc. In addition, in the map information storage unit 121, links may be identified by link IDs.

Returning to FIG. 1, the second server device 200 generates a prediction model that statistically models the driving time that an unspecified number of drivers actually travel before taking a break, and provides the generated prediction model to the first server device 100A.

Note that the management operator may be the same or different between the first server device 100A and the second server device 200. Furthermore, each of the first server device 100A and the second server device 200 corresponds to an example of an information processing device according to the first embodiment, but the first server device 100A and the second server device 200 may be integrated into a single server device. When the first server device 100A and the second server device 200 are implemented as a single server device, this single server device corresponds to the information processing device according to the first embodiment.

<2. Functional configuration>
From here on, configuration examples of the first server device 100A and the second server device 200 will be described.

[First server device 100A]
Fig. 2 is a diagram showing an example of the configuration of the first server device 100A according to the first embodiment. As shown in Fig. 2, the first server device 100A includes a communication unit 110, a storage unit 120A, and a control unit 130A.

[Communication unit 110]
The communication unit 110 is realized by, for example, a network interface card (NIC) etc. The communication unit 110 is connected to the network N by wire or wirelessly, and transmits and receives information between the second server device 200 and the in-vehicle device 10, for example.

[Memory unit 120A]
The storage unit 120A is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120A may store, for example, data and programs related to the information processing according to the embodiment. According to the example of FIG. 2, the storage unit 120A may include a map information storage unit 121, a WL type estimation result storage unit 122, and a ratio information storage unit 123.

[Map information storage unit 121]
The map information storage unit 121 stores map data used for estimating the WL type. The map data includes road data in which a road network is represented by a combination of nodes and links. The links are managed by link IDs, and may be associated with the WL type and the link length.

[WL type estimation result storage unit 122]
The WL type estimation result storage unit 122 stores the WL type estimated for each link included in the travel route (constituting the travel route).

[Ratio information storage unit 123]
The ratio information storage unit 123 stores a driving load ratio indicating the ratio between a high driving load state and a low driving load state.

[Control unit 130A]
The control unit 130A is realized by executing various programs (e.g., the information processing program according to the embodiment) stored in a storage device inside the first server device 100A using a RAM as a working area by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), etc. Also, the control unit 130A is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 2, the control unit 130A has an estimation unit 131, a calculation unit 132, an operating load ratio acquisition unit 133, an output control unit 134, and a search unit 135, and realizes or executes the functions and actions of the information processing described below. Note that the internal configuration of the control unit 130A is not limited to the configuration shown in FIG. 2, and may be other configurations as long as they perform the information processing described below. Also, the connection relationships between the processing units of the control unit 130A are not limited to the connection relationships shown in FIG. 2, and may be other connection relationships.

[Estimation unit 131]
The estimation unit 131 estimates the WL type for each link included in a predetermined driving route. For example, the estimation unit 131 estimates the WL type for each link included in the driving route of the target vehicle VEx. The driving route of the target vehicle VEx may be a driving route that has been traveled by continuous driving from the start of driving of the target vehicle VEx to the current time, or may be a planned driving route that the driver DX plans to drive the target vehicle VEx. Note that the start of driving here means the start of driving from a state of a long-term stay with a specific purpose (for example, stopping at a home or a rest area) excluding a temporary stop on the road (for example, stopping at a traffic light), and can also be rephrased as engine start. For example, the estimation unit 131 can distinguish between a temporary stop on the road and a long-term stay with a specific purpose based on the stopping time. In addition, the planned driving route may be, for example, a route that is a search result that is searched to satisfy a search condition based on information (for example, a destination) input to the in-vehicle device 10, or a route that is directly input by the user as a route to be driven from now on. Alternatively, the planned driving route may be a route to a destination predicted based on the driver DX's usual driving history.

The estimation unit 131 also estimates the WL type for each link included in the driving route indicated by the driving records of an unspecified number of vehicles VEn, which are driving records based on continuous driving from engine start (start of driving) to engine stop (end of driving).

In the following, driving from engine start (start of driving) to engine stop (end of driving) may be referred to as "one trip." Continuous driving refers to driving without a break. For this reason, for example, the driving route indicated by the driving record of continuous driving from engine start to engine stop means the driving route for one trip that does not include a break, and does not include temporary stops on the road (for example, stopping at traffic lights).

Here, the estimation unit 131 can, for example, detect engine stoppage for a break (e.g., engine stoppage for 10 to 20 minutes) based on data representing the behavior of the vehicle VEn, and extract the driving from engine start to engine stoppage for a break as one trip.

As another example, the estimation unit 131 may extract the driving from the engine start (start of driving) to the rest point where the driver of the vehicle VEn took a rest as one trip. For example, the estimation unit 131 generates stay point information indicating the stay points of the vehicle VEn, stay time information indicating the stay time at the stay points, and traveling direction change information indicating the change in the traveling direction of the vehicle VEn between three consecutive stay points on the driving route of the vehicle VEn, based on the driving history of the vehicle VEn. Then, the estimation unit 131 may estimate the rest point where the driver of the vehicle VEn took a rest, based on the stay point information, stay time information, and traveling direction change information. As an example, the estimation unit 131 may determine whether the stay time at the stay point is within a predetermined time range (e.g., 10 minutes to 20 minutes), and estimate the stay point where the stay time is determined to be within the predetermined time range as the rest point. Furthermore, the estimation unit 131 may estimate, as a rest point, a stay point that is determined to be moving away from the departure point of the vehicle VEn based on the angular relationship established between the first stay point where the vehicle VEn first arrives, the second stay point where the vehicle VEn next arrives, and the tertiary stay point where the vehicle VEn last arrives.

The estimation unit 131 also stores the WL type estimation result in the WL type estimation result storage unit 122.

Here, a method for estimating the WL type will be described with reference to FIG. 4. FIG. 4 is a diagram showing a specific example of the method for estimating the WL type. FIG. 4 shows a scene in which the WL type is estimated for an arbitrary driving route RT. The arbitrary driving route RT may be an actual driving route traveled by continuous driving from the start of driving of the target vehicle VEx to the present time, or may be a planned driving route that the driver DX plans to travel in the target vehicle VEx. In addition, the arbitrary driving route RT may be a driving route for one trip, not including rest periods, by a certain vehicle VEn selected from an unspecified number of vehicles VEn. In other words, the method for estimating the WL type of the links included in the driving route is the same regardless of the driving route.

For example, if the driving route RT is the actual driving route traveled by continuous driving from the start of the target vehicle VEx's driving to the present time, the position PT1 is the point where the target vehicle VEx's driving started, and the position PT2 is the current position of the target vehicle VEx.

As another example, if the travel route RT is a travel route for one trip by a single vehicle VEn that does not include a rest stop, position PT1 is the point where the engine of vehicle VEn is started, and position PT2 is the stop point of vehicle VEn.

Here, in the example of FIG. 4(a), the estimation unit 131 compares the traveling route RT with map data in which a WL type is associated with each link, and links each link included in the traveling route RT with a link ID (link_id). FIG. 4(a) shows an example in which the estimation unit 131 divides the traveling route RT into five links by linking link ID "100", link ID "101", link ID "102", link ID "103", link ID "104", and link ID "105" to the traveling route RT.

In addition, in FIG. 4(a), node ND01 is shown as information on the connection point where the link identified by link ID "100" (link 100) and the link identified by link ID "101" (link 101) are connected.

In addition, node ND12 is shown as information on the connection point where the link identified by link ID "101" (link 101) and the link identified by link ID "102" (link 102) are connected.

In addition, node ND23 is shown as information on the connection point where the link identified by link ID "102" (link 102) and the link identified by link ID "103" (link 103) are connected.

In addition, node ND34 is shown as information on the connection point where the link identified by link ID "103" (link 103) and the link identified by link ID "104" (link 104) are connected.

In addition, node ND45 is shown as information on the connection point where the link identified by link ID "104" (link 104) and the link identified by link ID "105" (link 105) are connected.

The estimation unit 131 may also refer to map data and calculate the distance (len) of each link. FIG. 4(a) shows an example in which the estimation unit 131 calculates the distance "100" of link 100, the distance "200" of link 101, the distance "300" of link 102, the distance "100" of link 103, the distance "500" of link 104, and the distance "200" of link 105.

FIG. 4(b) shows an example in which the estimation unit 131 refers to map data in which a WL type is associated with each link, and estimates the WL type of link 100 as "FREE", the WL type of link 101 as "FREE", the WL type of link 102 as "FREE", the WL type of link 103 as "BUSY", the WL type of link 104 as "FREE", and the WL type of link 105 as "BUSY".

In the following, links whose WL type is estimated to be "BUSY" may be referred to as "BUSY sections", links whose WL type is estimated to be "FREE" may be referred to as "FREE sections", and links whose WL type is estimated to be "IDEAL" may be referred to as "IDEAL sections".

In FIG. 4, an example is shown in which the estimation unit 131 estimates the WL type of a link by comparing the map data in which a WL type is associated with each link with the links included in the travel route RT. However, the estimation unit 131 may estimate the WL type of each link based on the link type (link_kind) of the link included in the travel route R or the road type (road_kind) of the travel route RT. The link type here refers to classification information such as a main road, connecting road, etc., for example. The road type refers to classification information such as an expressway, national road, narrow street, etc.

[Calculation unit 132]
Returning to FIG. 2, the calculation unit 132 calculates a first cumulative time, which is the cumulative time that the target vehicle VEx has traveled on links that are included in the travel route of the target vehicle VEx and that are estimated to have a WL type of "BUSY" (first type indicating that the WL is high compared to a reference value). The calculation unit 132 also calculates a second cumulative time, which is the cumulative time that the target vehicle VEx has traveled on links that are included in the travel route of the target vehicle VEx and that are estimated to have a WL type of "FREE" (second type indicating that the WL is low compared to a reference value). This point will be described using the example of FIG. 4(b).

In explaining the processing of the calculation unit 132, the travel route RT is assumed to be the actual travel route traveled by continuous driving from the start of the target vehicle VEx to the present time. In this example, the target vehicle VEx starts traveling from position PT1, and is currently traveling at position PT2 by being continuously driven without a break. In this case, the calculation unit 132 calculates the first cumulative time by accumulating the travel time required for traveling on each link (specifically, link 100, link 101, link 102, link 104) for which the WL type is estimated to be "BUSY". In addition, the calculation unit 132 calculates the second cumulative time by accumulating the travel time required for traveling on each link (specifically, link 103, link 105) for which the WL type is estimated to be "FREE". For example, the calculation unit 132 can calculate the travel time based on the travel history of the target vehicle VEx acquired from the in-vehicle device 10 and sensor information.

The calculation unit 132 also calculates the operating load ratio, which is the ratio between the first cumulative time and the second cumulative time, and transmits it to the operating load ratio acquisition unit 133.

The calculation unit 132 may calculate a cumulative distance instead of a cumulative time. Similarly, using the example of FIG. 4(b), the calculation unit 132 may calculate a first cumulative distance by accumulating the distances of each link whose WL type is estimated to be "BUSY" (specifically, links 100, 101, 102, and 104). The calculation unit 132 may calculate a second cumulative distance by accumulating the distances of each link whose WL type is estimated to be "FREE" (specifically, links 103 and 105). In this example, the calculation unit 132 calculates a driving load ratio, which is the ratio between the first cumulative distance and the second cumulative distance, and transmits it to the driving load ratio acquisition unit 133.

[Operating load ratio acquisition unit 133]
The driving load ratio acquisition unit 133 acquires a driving load ratio indicating the ratio between a state in which the driving load of the driver DX is high and a state in which the driving load is low on the driving route of the target vehicle VEx.

Specifically, the driving load ratio acquisition unit 133 acquires a driving load ratio indicating the ratio between the first accumulated time calculated by the calculation unit 132 (information indicating a state in which the driving load is high) and the second accumulated time calculated by the calculation unit 132 (information indicating a state in which the driving load is low).

As another example, the driving load ratio acquisition unit 133 acquires a driving load ratio indicating the ratio between the first cumulative distance calculated by the calculation unit 132 (information indicating a state in which the driving load is high) and the second cumulative distance calculated by the calculation unit 132 (information indicating a state in which the driving load is low). The driving load ratio is stored in the ratio information storage unit 123.

The driving load ratio acquisition unit 133 may also perform a process of calculating a predicted driving time of the target vehicle VEx based on the driving load ratio and the prediction model generated by the second server device 200. Specifically, the driving load ratio acquisition unit 133 predicts the time for which the target vehicle VEx will be continuously driven (the time for which the driver DX will drive continuously without a break) based on the driving load ratio and the prediction model. The method of generating the prediction model will be described later.

[Output control unit 134]
The output control unit 134 predicts the timing when the driver DX should take a rest based on the predicted driving time calculated by the driving load ratio acquisition unit 133. Specifically, the output control unit 134 predicts the timing when the driver DX should take a rest based on the difference between the driving time of the target vehicle VEx and the predicted driving time. For example, the output control unit 134 predicts the timing when the driver DX should take a rest based on the difference between the predicted driving time and the driving time calculated for the actual driving route traveled by continuous driving from the start of driving of the target vehicle VEx to the present time as the driving time of the target vehicle VEx.

The timing when driver DX should take a break may be expressed in terms of time, such as "Driver DX should take a break at x:00" or in terms of distance, such as "Driver DX should take a break after traveling △ meters."

[Search Unit 135]
The search unit 135 searches for a rest spot that the target vehicle VEx can reach by the time it is time to take a rest. For example, the search unit 135 searches for a rest spot within a range of a predicted driving distance, which is a distance that the target vehicle VEx is predicted to travel until the time it is time to take a rest. The search unit 135 may also calculate a predicted arrival time, which is a time when the target vehicle VEx is predicted to arrive at the rest spot. In this case, the output control unit 134 controls output so that proposal information including information indicating the contents of the rest spot and a predicted arrival time at the rest spot is output from the in-vehicle device 10 as proposal information proposing the rest spot.

As another example, since the planned driving route of the target vehicle VEx is known in advance, when a rest timing is predicted for this planned driving route, the search unit 135 may estimate a point on the planned driving route that the target vehicle VEx may reach at the time when the driver DX takes a rest, and search for a rest spot in the area corresponding to the estimated point. Note that the planned driving route referred to here may be a guided route searched based on input information by the driver DX (e.g., a destination input before departure). Furthermore, the time when the driver DX takes a rest may be predicted based on a prediction result that predicts the timing when the driver DX should take a rest. Furthermore, when a request operation by the driver DX (e.g., a request for a rest spot) is accepted, the search unit 135 may perform a search process for a rest spot using such a guided route, and output the search result to the output control unit 134.

For example, the output control unit 134 outputs suggestion information that suggests rest spots along with the planned driving route, which is the guidance route. With such advance suggestions, the driver DX can decide on rest spots in advance, for example, at the time of setting the route before departure, and can therefore make an appropriate driving plan before departure.

Furthermore, according to the above example, the search unit 135 may also perform general route guidance processing, specifically, route search to a destination using search conditions. The search conditions and destination are input to the in-vehicle device 10 by the user.

[Second Server Device]
3 is a diagram showing an example of the configuration of the second server device 200. As shown in FIG. 3, the second server device 200 includes a communication unit 210, a storage unit 220, and a control unit 230.

[Communication unit 210]
The communication unit 210 is realized by, for example, a NIC etc. The communication unit 210 is connected to the network N by wire or wirelessly, and transmits and receives information between the first server device 100A and the in-vehicle device 10, for example.

[Memory unit 220]
The storage unit 220 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 220 may store, for example, data and programs related to the information processing according to the embodiment. In addition, according to the example of FIG. 3, the storage unit 220 may include a WL type estimation result storage unit 221 and a prediction model storage unit 222.

[Control unit 230]
The control unit 230 is realized by a CPU, an MPU, or the like executing various programs (e.g., the information processing program according to the embodiment) stored in a storage device inside the second server device 200 using a RAM as a working area. The control unit 230 is also realized by an integrated circuit such as an ASIC or an FPGA.

As shown in FIG. 3, the control unit 230 has a WL type acquisition unit 231, a prediction model generation unit 232, and a transmission unit 233, and realizes or executes the functions and actions of the information processing described below. Note that the internal configuration of the control unit 230 is not limited to the configuration shown in FIG. 3, and may be other configurations as long as they perform the information processing described below. Also, the connection relationships between the processing units of the control unit 230 are not limited to the connection relationships shown in FIG. 3, and may be other connection relationships.

[WL type acquisition unit 231]
The WL type acquisition unit 231 acquires the WL type estimated by the estimation unit 131. Specifically, the WL type acquisition unit 231 acquires information on the WL type estimated for each link included in a travel route for one trip, which is indicated by the travel records of an unspecified number of vehicles VEn and does not include rest periods. The acquired WL type is stored in the WL type estimation result storage unit 221.

[Prediction model generation unit 232]
The prediction model generation unit 232 generates a prediction model that predicts the driving time by continuous driving based on the WL type estimated for each link included in the driving route of one trip, which is indicated by the driving history of an unspecified number of vehicles VEn, and does not include rest breaks.

Specifically, the prediction model generation unit 232 calculates a model ratio, which is the ratio of links whose WL type is estimated to be "BUSY" (first type indicating that the WL is high compared to a reference value) to links whose WL type is estimated to be "FREE" (second type indicating that the WL is low compared to a reference value) among the links included in the driving route of one trip that does not include a break. The driving route of one trip that does not include a break that is treated here may be common between vehicles VEn, or may be different between vehicles VEn.

The prediction model generation unit 232 also calculates, for each model ratio, the average driving time, which is the average time that the vehicle VEn is continuously driven. Then, the prediction model generation unit 232 generates a prediction model based on the model ratio and the average driving time.

For example, the prediction model generation unit 232 generates a prediction model based on a three-dimensional graph that shows the relationship between the model ratio and the average driving time in three dimensions.

Here, a method for generating a predictive model will be described with reference to Figures 5 and 6. Figure 5 is a diagram showing a specific example (1) of a method for generating a predictive model. Figure 6 is a diagram showing a specific example (2) of a method for generating a predictive model.

According to the example of FIG. 5, the prediction model generation unit 232 tallies, for each model ratio, the time that the vehicle VEn corresponding to that model ratio was continuously driven. The model ratio may be the ratio between the distance of a link whose WL type is estimated to be "BUSY" and the distance of a link whose WL type is estimated to be "FREE" among the links included in a driving route for one trip that does not include rest breaks. On the other hand, the model ratio may be the ratio between the cumulative time that the vehicle VEn traveled on links whose WL type is estimated to be "BUSY" and the cumulative time that the vehicle VEn traveled on links whose WL type is estimated to be "FREE" among the links included in a driving route for one trip that does not include rest breaks.

As an example, let us assume that a model ratio, which is the ratio between busy and free sections, of "100:0" is calculated based on the result of estimating the WL type for one trip of the driving route of vehicle VE11. Let us also assume that a model ratio, which is the ratio between busy and free sections, of "100:0" is calculated based on the result of estimating the WL type for one trip of the driving route of vehicle VE12. In this example, as shown in FIG. 5(a), the prediction model generation unit 232 counts the driving time required to travel the driving route for one trip for each vehicle VEn, such as vehicle VE11 and vehicle VE12, which have a common model ratio of "100:0". For example, the prediction model generation unit 232 can calculate the driving time based on the driving history of vehicle VEn acquired from the in-vehicle device 10 and sensor information.

FIG. 5(a) shows an example in which the prediction model generation unit 232 calculates "TM11" as the driving time required for vehicle VE11 to travel the driving route for one trip, and calculates "TM12" as the driving time required for vehicle VE12 to travel the driving route for one trip.

In this state, the prediction model generation unit 232 aggregates the driving time "TM11", the driving time "TM12", etc., and calculates the average driving time AV1, which is the average of the aggregated driving times.

As another example, let us say that a model ratio, which is the ratio between busy and free sections, of "90:10" is calculated based on the result of estimating the WL type for one trip of the driving route of vehicle VE21. Also, let us say that a model ratio, which is the ratio between busy and free sections, of "90:10" is calculated based on the result of estimating the WL type for one trip of the driving route of vehicle VE22. In this example, the prediction model generation unit 232 tallies the driving time required to travel the driving route for one trip for each vehicle VEn, such as vehicle VE21 and vehicle VE22, which have a common model ratio of "90:10", as shown in FIG. 5(b).

Figure 5(b) shows an example in which the prediction model generation unit 232 calculates "TM21" as the driving time required for vehicle VE21 to travel the driving route for one trip, and calculates "TM22" as the driving time required for vehicle VE22 to travel the driving route for one trip.

In this state, the prediction model generation unit 232 aggregates the driving time "TM21", the driving time "TM22", etc., and calculates the average driving time AV2, which is the average of the aggregated driving times.

As yet another example, let us assume that a model ratio, which is the ratio between busy and free sections, of "80:20" is calculated based on the result of estimating the WL type for one trip of the driving route of vehicle VE31. Also, let us assume that a model ratio, which is the ratio between busy and free sections, of "80:20" is calculated based on the result of estimating the WL type for one trip of the driving route of vehicle VE32. In this example, the prediction model generation unit 232 tallies up the driving time required to travel the driving route for one trip for each vehicle VEn, such as vehicle VE31 and vehicle VE32, which have a common model ratio of "80:20", as shown in FIG. 5(c).

FIG. 5(c) shows an example in which the prediction model generation unit 232 calculates "TM31" as the travel time required for vehicle VE31 to travel the travel route for one trip, and calculates "TM32" as the travel time required for vehicle VE32 to travel the travel route for one trip.

In this state, the prediction model generation unit 232 aggregates the driving time "TM31", the driving time "TM32", etc., and calculates the average driving time AV3, which is the average of the aggregated driving times.

In the examples of Figures 5(a), 5(b), and 5(c), the driving time required to travel the driving route for one trip can be rephrased as the time during which the vehicle VEn was driven continuously (continuous driving time).

In FIG. 5, the "continuous driving time" and "average driving time" are listed for each "model ratio" and the Re-Suri LT is shown. The Re-Suri LT is information that forms the basis of the prediction model and may be stored in the prediction model storage unit 222.

We now turn to the explanation of Figure 6. Figure 6 shows a scene in which a prediction model is generated from information contained in the list LT. As shown in Figure 6, the prediction model generation unit 232 generates a three-dimensional graph G in which the relationship between the model ratio and the average driving time is expressed in three dimensions, with "BUSY" as the x-axis, "FREE" as the y-axis, and "predicted average time" as the z-axis. Specifically, the prediction model generation unit 232 generates the three-dimensional graph G using a combination of "BUSY"/"FREE"/"predicted average time".

In the example of list LT, the prediction model generation unit 232 generates a bar graph with the average running time "AV1" fitted to the z-axis for the x-y coordinate position where BUSY "100" and FREE "0" intersect. The prediction model generation unit 232 also generates a bar graph with the average running time "AV2" fitted to the z-axis for the x-y coordinate position where BUSY "90" and FREE "10" intersect. The prediction model generation unit 232 also generates a bar graph with the average running time "AV3" fitted to the z-axis for the x-y coordinate position where BUSY "80" and FREE "20" intersect. The same process is performed for the other model ratios. As a result, a three-dimensional graph G as shown in FIG. 6(a) is generated.

The prediction model generation unit 232 generates a prediction model from this three-dimensional graph G. For example, the prediction model generation unit 232 performs statistical processing on the three-dimensional graph G to generate a prediction model M as shown in FIG. 6(b). In a simple example, the prediction model generation unit 232 generates a planar prediction model M using the vertices of the three-dimensional graph G. The x-axis of the prediction model M represents "BUSY", the y-axis represents "FREE", and the z-axis represents "predicted driving time" (estimated driving time). The predicted driving time here is the time that the driver DX of the target vehicle VEx is predicted to drive continuously without taking a break.

Furthermore, although not shown in Figures 6(a) and 6(b), "IDEAL" may be used on the other y-axis opposite "FREE". Therefore, the driving load ratio is actually the ratio of the cumulative time or distance obtained for each of the "BUSY" section, the "FREE" section, and the "IDEAL" section. However, the proportion of the driving load ratio that is occupied by the "IDEAL" section may be treated as the remaining proportion of the proportions occupied by the "BUSY" section and the "FREE" section.

[Transmitting unit 233]
Returning to Fig. 3, the transmission unit 233 transmits the prediction model generated by the prediction model generation unit 232 to the first server device 100A. As described above, the driving load ratio acquisition unit 133 acquires the transmitted prediction model and inputs the driving load ratio to the prediction model. The driving load ratio acquisition unit 133 then calculates a predicted driving time based on the output result of the prediction model. In addition, the output control unit 134 uses the predicted driving time to predict the timing when the driver DX should take a rest.

Next, a specific example of a method for predicting rest timing will be described using the example of FIG. 6(b). For example, if the actual driving route traveled by continuous driving from the start of driving of the target vehicle VEx to the present time includes only "BUSY" sections as links, the driving load ratio, which is the ratio between the first accumulated time and the second accumulated time, is calculated as "100:0". In this example, the prediction model generation unit 232 inputs the driving load ratio of "100:0" to the prediction model M.

FIG. 6(b) shows an example in which a driving load ratio of "100:0" is input and a predicted driving time of "16 minutes" for the target vehicle VEx is predicted from the output information output by the prediction model M. This corresponds to an estimation that, assuming that the driver DX continues driving continuously with a driving load ratio of "100:0", it would be optimal to take a break "16 minutes" after the start of driving, since there is a statistical tendency to take a break at "16 minutes" when the driving load ratio, which is the ratio between the first accumulated time and the second accumulated time, is "100:0" (in other words, when the driver continues driving continuously through the "BUSY" section).

For example, if the driving time of the target vehicle VEx from the start of driving to the present time is "10 minutes", the output control unit 134 calculates "6 minutes", which is the difference between the driving time "10 minutes" and the predicted driving time "16 minutes". Then, the output control unit 134 predicts the timing when the driver DX should take a break based on the current time and the difference time "6 minutes". For example, if the current time is "14:00", the output control unit 134 predicts that the driver DX should take a break at "14:06", which is "6 minutes" after the current time "14:00".

In addition, FIG. 6(b) shows an example in which a driving load ratio of "0:100" is input and a predicted driving time of "78 minutes" for the target vehicle VEx is predicted from the output information output by the prediction model M. This corresponds to an estimation that, assuming that the driver DX continues driving continuously with a driving load ratio of "0:100", it would be optimal to take a break "78 minutes" after the start of driving, since there is a statistical tendency to take a break at "78 minutes" when the driving load ratio, which is the ratio between the first accumulated time and the second accumulated time, is "0:100" (in other words, when the driver drives continuously through the "FREE" section).

For example, if the driving time of the target vehicle VEx from the start of driving to the present time is "10 minutes", the output control unit 134 calculates "68 minutes", which is the difference between the driving time "10 minutes" and the predicted driving time "78 minutes". Then, the output control unit 134 predicts the timing when the driver DX should take a break based on the current time and the difference time "68 minutes". For example, if the current time is "14:00", the output control unit 134 predicts that the driver DX should take a break at "15:08", which is "68 minutes" after the current time "14:00".

The above example shows an example in which the actual driving route traveled by continuous driving from the start of driving of the target vehicle VEx to the present time is handled. However, for example, when the planned driving route that the driver DX plans to drive in the target vehicle VEx is handled, the output control unit 134 may predict the timing of the rest break by using "0 minutes" as the driving time of the target vehicle VEx.

3. Processing procedure between devices
Next, a procedure of processing performed between the first server device 100A and the second server device 200 will be described with reference to Fig. 7. Fig. 7 is a sequence diagram showing a procedure of processing performed between the server devices included in the system SyA according to the first embodiment.

First, the estimation unit 131 of the first server device 100A acquires the driving records (driving history) of an unspecified number of vehicles VEn (step S701). The estimation unit 131 also extracts information on the driving route for one trip from the driving route indicated by the driving records, and estimates the WL type for each link included in the driving route for one trip (step S702).

The estimation unit 131 transmits the WL type estimated for one trip of each vehicle VEn to the second server device 200 (step S703). The transmitted WL type is acquired by the WL type acquisition unit 231 of the second server device 200.

Once the WL type is obtained, the prediction model generation unit 232 calculates a model ratio, which is the ratio of links whose WL type is estimated to be "BUSY" to links whose WL type is estimated to be "FREE" among the links included in the driving route for one trip of each vehicle VEn (step S704).

Next, the prediction model generation unit 232 counts, for each model ratio, the time during which the vehicle VEn corresponding to that model ratio was continuously driven (the driving time required for the vehicle VEn to travel the driving route for one trip) (step S705).

The prediction model generation unit 232 calculates, for each model ratio, the average driving time, which is the average time that the vehicle VEn is continuously driven (step S706). The prediction model generation unit 232 then expresses the relationship between the model ratio and the average driving time in a three-dimensional graph (step S707), and generates a prediction model based on the three-dimensional graph (step S708).

The transmission unit 233 transmits the prediction model to the first server device 100A (step S709). The transmitted prediction model is acquired by the operating load ratio acquisition unit 133 (step S710).

<4. Break Timing Prediction Processing Procedure>
Next, a procedure for predicting rest timing using a prediction model will be described below. Fig. 8 is a flowchart showing the procedure for predicting rest timing.

First, the estimation unit 131 determines whether or not driving of the target vehicle VEx has started (step S801). While driving of the target vehicle VEx has not started (step S801; No), the estimation unit 131 waits until it can determine that driving of the target vehicle VEx has started.

On the other hand, when the estimation unit 131 determines that driving of the target vehicle VEx has started (step S801; Yes), it determines whether it is time to predict the timing of a break (step S802). For example, the estimation unit 131 may determine that it is time to predict the timing of a break when a predetermined time has elapsed since driving of the target vehicle VEx has started, or when a certain amount of driving history has been accumulated by driving a predetermined distance since driving of the target vehicle VEx has started. When it is not time to predict the timing of a break (step S802; No), the estimation unit 131 waits until it is time to predict the timing of a break.

In addition, when it is time to predict the rest timing (step S802; Yes), the estimation unit 131 acquires driving route information indicating the driving route of the target vehicle VEx (step S803). For example, the estimation unit 131 acquires information on the actual driving route traveled by the target vehicle VEx during continuous driving from the start of driving to the present time.

Then, the estimation unit 131 estimates the WL type for each link included in the travel route of the target vehicle VEx (step S804). The method for estimating the WL type is as described in FIG. 4.

The calculation unit 132 calculates a first cumulative time, which is the cumulative time that the target vehicle VEx has traveled through the "BUSY" section during continuous driving from the start of driving to the current time (step S805). The calculation unit 132 also calculates a second cumulative time, which is the cumulative time that the target vehicle VEx has traveled through the "FREE" section during continuous driving from the start of driving to the current time (step S806).

The calculation unit 132 calculates the operating load ratio, which is the ratio between the first cumulative time and the second cumulative time, and transmits it to the operating load ratio acquisition unit 133 (step S807).

According to the example of FIG. 7, at this point, the driving load ratio acquisition unit 133 has already acquired the prediction model from the second server device 200. Therefore, the driving load ratio acquisition unit 133 inputs the driving load ratio into the prediction model and calculates the predicted driving time of the target vehicle VEx (step S808).

The output control unit 134 predicts the timing when the driver DX should take a rest based on the difference between the driving time of the target vehicle VEx so far, i.e., the time spent continuously driving from the start of driving to the present time, and the predicted driving time, and controls the output so that the information on the predicted rest timing is notified from the in-vehicle device 10 (step S809). The notification may be by voice or a screen display.

Second Embodiment
1. System configuration
From here, the second embodiment will be described. In the information processing according to the first embodiment, an appropriate timing for the driver DX to take a rest was predicted. In the information processing according to the second embodiment, the purpose is to present an estimated range that the driver DX can reach without taking a rest by the time of the rest, using information on the rest timing predicted by the information processing according to the first embodiment. By presenting the range that can be reached without taking a rest, the driver DX can grasp the rough position where he/she should take a rest, for example, before driving, which makes it easier to make a driving plan.

First, the configuration of a system according to the second embodiment will be described with reference to FIG. 9. FIG. 9 is a diagram showing an example of a system according to the second embodiment. FIG. 9 shows a system SyB as an example of a system according to the second embodiment. Information processing according to the second embodiment is realized in system SyB.

Compared to system SyA (FIG. 1), system SyB differs in that it has a first server device 100B according to the second embodiment instead of server device 100A according to the first embodiment, but is otherwise similar.

The first server device 100B is a central device that handles the information processing according to the second embodiment. For example, the first server device 100B identifies a reachable range that is the range that the target vehicle VEx can reach from the driving start point based on the prediction result predicted by the information processing according to the first embodiment, i.e., the timing when the driver DX should take a rest, and a predetermined route centered on the driving start point of the target vehicle VEx. Specifically, the first server device 100B identifies, as the reachable range, the range that the driver DX is estimated to be able to reach without taking a rest by the time it is time to take a rest.

<2. Functional configuration>
From here, a configuration example of the first server device 100B will be described. The first server device 100B is configured by adding a processing unit that realizes information processing according to the second embodiment to the first server device 100A.

[First server device 100B]
Fig. 10 is a diagram showing an example of the configuration of a first server device 100B according to the second embodiment. As shown in Fig. 10, the first server device 100B includes a communication unit 110, a storage unit 120B, and a control unit 130B.

[Memory unit 120B]
The storage unit 120B is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120B may store, for example, data and programs related to the information processing according to the embodiment. In addition, according to the example of FIG. 10, the storage unit 120B may further include a range information storage unit 124.

[Range information storage unit 124]
The range information storage unit 124 stores information on a reachable range. Specifically, the range information storage unit 124 stores information on a range that is estimated to be reachable by the driver DX without taking a break until it is time to take a break.

[Control unit 130B]
The control unit 130B is realized by a CPU or the like executing various programs (e.g., an information processing program according to the embodiment) stored in a storage device inside the first server device 100B using a RAM as a working area. The control unit 130B is also realized by an integrated circuit such as an ASIC or an FPGA.

As shown in FIG. 10, the control unit 130B has an estimation unit 131, a calculation unit 132, an operating load ratio acquisition unit 133, an output control unit 134, and a search unit 135, similar to the first server device 100A. In addition, the control unit 130B has a start point acquisition unit 136, a prediction unit 137, and a range identification unit 138 as additional functions to the first server device 100A.

These processing units realize or execute the information processing functions and actions described below. Note that the internal configuration of control unit 130B is not limited to the configuration shown in FIG. 10, and may be other configurations that perform the information processing described below. Also, the connection relationships between the processing units in control unit 130B are not limited to the connection relationships shown in FIG. 10, and may be other connection relationships.

[Starting point acquisition unit 136]
The start point acquisition unit 136 corresponds to a first acquisition unit, and acquires information on a travel start point, which is a point where the travel of the target vehicle VEx starts. For example, the start point acquisition unit 136 acquires information on the travel start point of the target vehicle VEx. When the engine is started, information on the position where the engine is started may be acquired as information on the travel start point.

[Estimation unit 131]
The estimation unit 131 estimates the WL type for each link included in the searched route (hereinafter, abbreviated as "searched route") obtained by route search when a destination is set as a predetermined route centered on the travel start point, which is a point in each direction centered on the travel start point and is a point located a predetermined distance from the travel start point. The method of estimating the WL type is as described in FIG. 4. The route search when a destination is set as a point located a predetermined distance from the travel start point is performed by the search unit 135.

[Calculation unit 132]
The calculation unit 132 calculates a first cumulative time, which is the cumulative time that the target vehicle VEx has traveled on links included in the route search that are estimated to have a WL type of "BUSY" (first type indicating that the WL is high compared to a reference value). The calculation unit 132 also calculates a second cumulative time, which is the cumulative time that the target vehicle VEx has traveled on links included in the search route of the target vehicle VEx that are estimated to have a WL type of "FREE" (second type indicating that the WL is low compared to a reference value).

The calculation unit 132 also calculates the operating load ratio, which is the ratio between the first cumulative time and the second cumulative time, and transmits it to the operating load ratio acquisition unit 133.

The calculation unit 132 may calculate the first cumulative distance by accumulating the distances of the links included in the route search whose WL type is estimated to be "BUSY" (first type indicating that the WL is high compared to a reference value). The calculation unit 132 may calculate the second cumulative distance by accumulating the distances of the links included in the route search whose WL type is estimated to be "FREE" (second type indicating that the WL is high compared to a reference value).

[Operating load ratio acquisition unit 133]
The driving load ratio acquisition unit 133 corresponds to the second acquisition unit, and acquires a driving load ratio indicating the ratio between a high driving load state and a low driving load state for each route in the search results obtained by route search when a destination is set to a point in each direction centered on the starting point of driving, and located a predetermined distance from the starting point of driving.

Specifically, the driving load ratio acquisition unit 133 acquires a driving load ratio indicating the ratio between the first cumulative time (information indicating a high driving load state) calculated by the calculation unit 132 for each search route and the second cumulative time (information indicating a low driving load state) calculated by the calculation unit 132 for each search route.

As another example, the driving load ratio acquisition unit 133 acquires a driving load ratio indicating the ratio between the first cumulative distance (information indicating a high driving load state) calculated by the calculation unit 132 for each search route and the second cumulative distance (information indicating a low driving load state) calculated by the calculation unit 132 for each search route.

The driving load ratio acquisition unit 133 may also perform a process of calculating a predicted driving time of the target vehicle VEx for each search route based on the driving load ratio and the prediction model generated by the second server device 200. Specifically, the driving load ratio acquisition unit 133 predicts the time for which the target vehicle VEx will be continuously driven (the time for which the driver DX will drive continuously without a break) for each search route based on the driving load ratio and the prediction model. The prediction model used here is the one generated by the second server device 200.

[Prediction unit 137]
The prediction unit 137 predicts the arrival time at which the target vehicle VEx will arrive at each change point where the WL type changes on each search route. Specifically, the prediction unit 137 predicts the arrival time at which the target vehicle VEx will arrive at each change point where the WL type changes on each search route, based on the distance between the travel start point and each link included in the search route, and the WL type estimated for each link. This point will be described using the example of FIG. 4.

If the travel route RT shown in Figure 4 is the search route, then position PT1 is the travel start point of the target vehicle VEx, and position PT2 is the destination that is determined based on a specified distance from the travel start point.

For example, the prediction unit 137 detects a node that connects links of different WL types as a change point where the WL type changes. According to the example of FIG. 4(b), node ND23 is a node that connects link 102 of WL type "FREE" and link 103 of WL type "BUSY". Node ND34 is a node that connects link 103 of WL type "BUSY" and link 104 of WL type "FREE". Node ND45 is a node that connects link 104 of WL type "FREE" and link 105 of WL type "BUSY". For this reason, the prediction unit 137 detects nodes ND23, ND34, and ND45 as nodes that connect links of different WL types as change points where the WL type changes.

Then, the prediction unit 137 predicts the arrival time at which the target vehicle VEx will reach node ND23 based on the average speed from position PT1 to node ND23 (connection point) and the distance from position PT1 to node ND23 (connection point). The prediction unit 137 also predicts the arrival time at which the target vehicle VEx will reach node ND34 based on the average speed from position PT1 to node ND34 (connection point) and the distance from position PT1 to node ND34 (connection point). The prediction unit 137 also predicts the arrival time at which the target vehicle VEx will reach node ND45 based on the average speed from position PT1 to node ND45 (connection point) and the distance from position PT1 to node ND45 (connection point). Furthermore, the prediction unit 137 predicts the arrival time at which the target vehicle VEx will arrive at position PT2 based on the average speed from position PT1 to position PT2 and the distance from position PT1 to position PT2.

[Range Identification Unit 138]
The range specifying unit 138 extracts, as rest candidate points, those change points whose calculated arrival times are within a predetermined range of the timing when it is predicted that the driver DX should take a rest, from among the change points detected by the prediction unit 137. The range specifying unit 138 then specifies, as a reachable range, a polygon formed by connecting the rest candidate points. As an example, the range specifying unit 138 may extract, as rest candidate points, those change points whose calculated arrival times are later than the timing when it is predicted that the driver DX should take a rest.

[Output control unit 134]
The output control unit 134 controls output so that the in-vehicle device 10 displays a screen on which information about the reachable range is superimposed on a map.

3. Range Identification Processing Procedure
The procedure of the range specification process for specifying a reachable range will be described with reference to Fig. 11. Fig. 11 is a flowchart showing the procedure of the range specification process. A specific example of the range specification process will be described with reference to Fig. 12. Fig. 12 is a diagram showing a specific example of the range specification process.

First, the start point acquisition unit 136 acquires information on the travel start point of the target vehicle VEx (step S1101). FIG. 12(a) shows an example in which the start point acquisition unit 136 detects the travel start point BA as the travel start point of the target vehicle VEx and acquires information on the travel start point BA (e.g., position information).

Next, the search unit 135 sets destinations at a predetermined distance in each direction of 360 degrees from the travel start point BA (step S1102). Figure 12(a) shows an example in which the search unit 135 has set seven destinations (destinations G1 to G7), namely, destination G1, destination G2, destination G3, destination G4, destination G5, destination G6, and destination G7.

In this state, the search unit 135 executes a route search to search for a route from the travel start point BA to each of the destinations G1 to G7 (step S1103).

FIG. 12(a) shows an example in which the search unit 135 acquires search route SR1 as a route in the search results by performing a route search from the driving start point BA to destination G1. FIG. 12(a) also shows an example in which the search unit 135 acquires search route SR2 as a route in the search results by performing a route search from the driving start point BA to destination G2. FIG. 12(a) also shows an example in which the search unit 135 acquires search route SR31 and search route SR32 as routes in the search results by performing a route search from the driving start point BA to destination G3.

FIG. 12(a) also shows an example in which the search unit 135 performs a route search from the driving start point BA to the destination G4, and acquires search route SR41, search route SR42, and search route SR43 as routes in the search results. FIG. 12(a) also shows an example in which the search unit 135 performs a route search from the driving start point BA to the destination G5, and acquires search route SR51 and search route SR52 as routes in the search results.

FIG. 12(a) also shows an example in which the search unit 135 acquires a search route SR6 as a route resulting from a route search from the driving start point BA to the destination G6. FIG. 12(a) also shows an example in which the search unit 135 acquires a search route SR7 as a route resulting from a route search from the driving start point BA to the destination G7.

The estimation unit 131 estimates the WL type for each link included in each search route acquired by the search unit 135 (step S1104).

Next, the prediction unit 137 predicts the arrival time at which the target vehicle VEx will arrive at each change point where the WL type changes on each search route (step S1105). The method of detecting the change point and the method of predicting the arrival time are as described using the example in FIG. 4(b).

Here, the calculation unit 132 calculates the driving load ratio for each searched route (step S1106). For example, the calculation unit 132 calculates a first cumulative time, which is a cumulative time estimated when it is assumed that the target vehicle VEx has traveled through links included in the route search and for which the WL type is estimated to be "BUSY". The calculation unit 132 also calculates a second cumulative time, which is a cumulative time estimated when it is assumed that the target vehicle VEx has traveled through links included in the route search and for which the WL type is estimated to be "FREE". For example, the calculation unit 132 can calculate the first cumulative time and the second cumulative time based on statistical information known in advance about the BUSY sections.

The calculation unit 132 calculates the operating load ratio, which is the ratio between the first cumulative time and the second cumulative time, and transmits it to the operating load ratio acquisition unit 133 (step S1107).

At this point, the driving load ratio acquisition unit 133 has already acquired the prediction model from the second server device 200. Therefore, the driving load ratio acquisition unit 133 inputs the driving load ratio into the prediction model and calculates the predicted driving time of the target vehicle VEx for each search route (step S1108). Specifically, the driving load ratio acquisition unit 133 calculates the predicted driving time for each search route in which the driver DX is predicted to drive the search route continuously without taking a break.

The output control unit 134 predicts, for each search route, the timing of rest (the timing when the driver DX should take a rest) for that search route based on the predicted travel time obtained for that search route (step S1109). Specifically, the output control unit 134 predicts the time of the rest timing based on the current time and the predicted travel time.

The range determination unit 138 extracts, from among the change points detected for each search route, change points whose arrival times are predicted to exceed within a predetermined time range based on the time of the predicted rest timing for that search route as candidate rest points (step S1110). Note that the range determination unit 138 does not need to extract candidate rest points if there is no arrival time that exceeds within the predetermined time range from the time of the rest timing.

As another example, the range determination unit 138 may extract, from among the change points detected for each search route, change points whose arrival times are predicted to be below within a predetermined time range based on the time of the predicted rest timing for that search route, as candidate rest points.

In FIG. 12(a), the candidate rest points extracted for each of the 11 search routes, including search route SR11, are indicated by "X" marks. In this state, the range determination unit 138 determines a reachable range based on the 11 candidate rest points (step S1111). For example, as shown in FIG. 12(b), the range determination unit 138 determines an area AR obtained by connecting the 11 candidate rest points as the reachable range that is estimated to be reachable by the driver DX without taking a break by the time of the break timing predicted in step S1109.

The output control unit 134 controls the in-vehicle device 10 so that the reachable range AR is provided to the driver DX with the reachable range AR superimposed on the map (step S1112). Note that while FIG. 12(b) shows an example in which a shape generated by simply connecting candidate rest points is identified as the reachable range AR, the method of generating the reachable range AR is not limited to this example. For example, the range identification unit 138 may identify as the reachable range AR a shape that is smoother than the shape generated by simply connecting candidate rest points. The range identification unit 138 may also identify as the reachable range AR a polygon obtained by applying a convex hull algorithm to the candidate rest points.

In the above example, the range determination unit 138 determines a reachable range that is a range that the driver DX is estimated to be able to reach without taking a break. However, the range determination unit 138 may also determine a range that the driver DX is estimated to be able to reach with one break in between. This point will be explained using FIG. 12.

In the example of FIG. 12(a), the range determination unit 138 extracts one candidate rest point for each of the eleven search routes, but the range determination unit 138 regards these candidate rest points as the starting point of travel and executes steps S1101 to S1111 again. Specifically, the range determination unit 138 assumes that the candidate rest points are the starting point of travel and further determines a reachable range, which is the range that can be reached from the candidate rest points by the target vehicle VEx, and determines a range that the driver DX is estimated to be able to reach with one rest break in between, based on the reachable range.

According to this example, for example, among the change points on the multiple search routes that are further extended from each of the 11 candidate rest points, the change points whose predicted arrival times are greater than the rest timing within a predetermined time range are extracted as the candidate rest points. Therefore, in a simple example, 11 reachable ranges are identified according to the 11 candidate rest points. In this state, the range identification unit 138 may, for example, identify one polygon that covers the 11 reachable ranges as the range that is estimated to be reachable by the driver DX with one rest break in between.

(Hardware configuration)
The above-described information processing devices (e.g., the first server device 100A, the first server device 100B, and the second server device 200) may be realized, for example, by a computer 1000 having a configuration as shown in Fig. 13. Fig. 13 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, a HDD 1400, a communication interface (I/F) 1500, an input/output interface (I/F) 1600, and a media interface (I/F) 1700.

The CPU 1100 operates based on the programs stored in the ROM 1300 or the HDD 1400, and controls each component. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, and programs that depend on the hardware of the computer 1000, etc.

HDD 1400 stores programs executed by CPU 1100 and data used by such programs. Communication interface 1500 receives data from other devices via a specified communication network and sends it to CPU 1100, and transmits data generated by CPU 1100 to other devices via the specified communication network.

The CPU 1100 controls an output device such as a display and an input device such as a keyboard via the input/output interface 1600. The CPU 1100 acquires data from the input device via the input/output interface 1600. The CPU 1100 also outputs generated data to the output device via the input/output interface 1600.

The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

For example, when the computer 1000 functions as the first server device 100A according to the first embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 130A. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a specified communication network.

Furthermore, when the computer 1000 functions as the first server device 100B according to the second embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 130B. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a specified communication network.

Furthermore, when the computer 1000 functions as the second server device 200 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 230. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a specified communication network.

(others)
Furthermore, among the processes described in each of the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

Furthermore, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

In addition, the above embodiments can be combined as appropriate to the extent that the processing content is not contradictory.

　Although several embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be embodied in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the "present invention" section.

SyA System 100A First server device 120A Storage unit 121 Map information storage unit 122 WL type estimation result storage unit 123 Ratio information storage unit 130A Control unit 131 Estimation unit 132 Calculation unit 133 Operation load ratio acquisition unit 134 Output control unit 135 Search unit SyB System 100B First server device 120B Storage unit 124 Range information storage unit 130B Control unit 136 Start point acquisition unit 137 Prediction unit 138 Range specification unit

Claims (14)

An acquisition unit that acquires a driving load ratio indicating a ratio between a state in which a driving load of a driver is high and a state in which a driving load of a driver is low on a travel route of the target vehicle;
and an output control unit that uses at least the driving load ratio to output a timing when the driver should take a break. The information processing device according to claim 1 , wherein the travel route of the target vehicle is an actual travel route traveled by continuous driving of the target vehicle from a start of travel to a current time. The information processing device according to claim 1 , wherein the driving route of the target vehicle is a planned driving route that the driver of the target vehicle plans to drive. An estimation unit that estimates a type of driving load for each road section included in a travel route of the target vehicle;
a calculation unit that calculates a first cumulative time, which is a cumulative time that the target vehicle has traveled on road sections included in a driving route of the target vehicle, in which a first type, which indicates that the driving load is high compared to a reference value, is estimated as a type of the driving load, and a second cumulative time, which is a cumulative time that the target vehicle has traveled on road sections included in a driving route of the target vehicle, in which a second type, which indicates that the driving load is low compared to a reference value, is estimated as a type of the driving load,
The information processing device according to claim 1 , wherein the acquisition unit acquires the driving load ratio indicating a ratio between the first accumulated time in a state where the driving load is high and the second accumulated time in a state where the driving load is low. A generating unit that generates a prediction model for predicting a driving time by continuous driving based on a driving record of a specific vehicle, the driving record being a driving record by continuous driving from the start of driving to the end of driving,
The acquisition unit calculates a predicted traveling time of the target vehicle based on the driving load ratio and the prediction model,
The information processing device according to claim 4 , wherein the output control unit predicts a timing for the driver to take a rest based on a predicted traveling time of the target vehicle. The estimation unit estimates a type of driving load for each road section included in the driving route indicated by the driving record,
the generation unit calculates an average driving time, which is an average of the time that the predetermined vehicle was driven continuously, for each model ratio, which is a ratio between a road section in which a first type indicating that the driving load is high compared to a reference value and a road section in which a second type indicating that the driving load is low compared to a reference value, as the type of the driving load, among road sections included in the driving route indicated by the driving record, and generates the prediction model based on the model ratio and the average driving time;
The information processing device according to claim 5 , wherein the acquisition unit calculates a predicted travel time of the target vehicle based on output information output by the prediction model using the driving load ratio as an input. The information processing device according to claim 6 , wherein the generation unit generates the prediction model based on a three-dimensional graph in which a relationship between the model ratio and the average running time is expressed in three dimensions. The information processing device according to claim 5 , wherein the output control unit predicts a timing for the driver to take a rest based on a difference between a travel time of the target vehicle and the predicted travel time. A search unit is further provided to search for a rest spot that the target vehicle can reach by the time when the driver should take a rest,
The information processing device according to claim 1 , wherein the output control unit outputs suggestion information that suggests the rest spot. The information processing device according to claim 9, characterized in that the search unit searches for the rest spot within a range of a predicted driving distance, which is a distance that the target vehicle is predicted to travel until the time to take the rest, and calculates a predicted arrival time, which is a time that the target vehicle is predicted to arrive at the rest spot. the search unit uses the driving load ratio corresponding to a planned driving route along which the driver is scheduled to drive the target vehicle as a driving route of the target vehicle, and when a timing at which the driver should take a rest is predicted, searches for rest spots within a range corresponding to a point on the planned driving route at which the driver is estimated to take a rest;
The information processing device according to claim 9 , wherein the output control unit outputs, together with the planned driving route, proposal information proposing the rest spots. The information processing device according to claim 11 , wherein the planned driving route is a guide route searched based on a destination of the target vehicle. An information processing method executed by an information processing device,
An acquisition step of acquiring a driving load ratio indicating a ratio between a state in which the driver's driving load is high and a state in which the driver's driving load is low on a travel route of the target vehicle;
and an output control step of outputting a timing when the driver should take a rest, using at least the driving load ratio. An information processing program executed by an information processing device,
An acquisition step of acquiring a driving load ratio indicating a ratio between a state in which the driver's driving load is high and a state in which the driver's driving load is low on a travel route of the target vehicle;
and an output control procedure for outputting a timing for the driver to take a rest, using at least the operating load ratio.

Images