Route search device, route search system, route search method, and computer program

Abstract

In order to shorten the required time to a destination as well as to increase the reliability of a suggested route to the destination, a reception unit of this route retrieval device receives information about the destination. A retrieval unit uses the information about the destination and a route retrieval model to retrieve a recommended route to the destination. The route retrieval model is a model that outputs a recommended route to a destination, and is generated by performing machine learning of actual travel routes traveled by an expert using a vehicle, said expert having been selected on the basis of quantity of experience. An output unit outputs the retrieved recommended route.

Description

Technical Field

[0001] The present invention relates to a technology for route search of vehicles.

Background Art

[0002] Various technologies for route search that search for a route to guide a vehicle to a destination have been proposed. For example, Patent Document 1 (International Publication No. 2018 / 025393) discloses a technology for proposing a route according to a driver in consideration of the number of driving experiences of drivers who have passed through a route with a lot of large vehicle traffic and the frequency of dangerous driving in order to reduce the occurrence of vehicle accidents.

[0003] Patent Document 2 (Japanese Patent Application Laid-Open No. 2003-57054) discloses that when learning a driving tendency in order to be able to search for a route close to a driver's request, roads frequently used, around designated points, or driving data during a designated time period or on a specific day are not used. Patent Document 3 (Japanese Patent Application Laid-Open No. 2012-515325) discloses a technology for presenting a route suitable for large vehicles.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0005] By the way, in route search, it is often the case that the shorter the required time to the destination, the better. In particular, for emergency vehicles involved in emergency activities, shortening the required time from receiving a dispatch request notification to arriving at the scene is important for improving the survival rate.

[0006] Regarding various route search technologies such as Patent Documents 1 to 3, although they have been proposed, research and development on route search is being carried out in order to further shorten the required time to the destination.

[0007] The main object of the present invention is to provide a route search technology that can shorten the required time to the destination and can also improve the reliability of the proposed route to the destination.

Means for Solving the Problem

[0008] In order to achieve the above object, as one aspect, the route search device according to the present invention a receiving unit that receives information on the destination, a route search model that outputs a recommended route to the destination generated by machine learning the actual driving routes traveled by a skilled person selected based on experience using a vehicle, and a search unit that searches for the recommended route to the destination using the received information on the destination, an output unit that outputs the searched recommended route and includes.

[0009] Also, as one aspect, the route search system according to the present invention the above route search device, a terminal device that is mounted on a vehicle, outputs information on the destination representing the destination of the vehicle to the route search device, and presents the recommended route by receiving the recommended route output from the route search device and includes.

[0010] Furthermore, as one aspect, the route search method according to the present invention by a computer, receives information on the destination, A route search model that outputs a recommended route to a destination by machine learning the actual driving route traveled by a skilled driver selected based on the driving experience, and uses the received destination information to search for the recommended route to the destination. Output the searched recommended route.

[0011] Furthermore, as one aspect of the program storage medium according to the present invention, A process of receiving destination information, A route search model that outputs a recommended route to a destination by machine learning the actual driving route traveled by a skilled driver selected based on the driving experience, and uses the received destination information to search for the recommended route to the destination. A process of outputting the searched recommended route Stores a computer program that causes a computer to execute.

Effect of the Invention

[0012] According to the present invention, it is possible to provide a route search technology that can shorten the required time to the destination and improve the reliability of the proposed route to the destination.

Brief Description of the Drawings

[0013]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Embodiments for Carrying Out the Invention

[0014] Hereinafter, embodiments according to the present invention will be described with reference to the drawings.

[0015] <First Embodiment> FIG. 1 is a block diagram showing the configuration of a route search system including the route search device of the first embodiment according to the present invention. This route search system 1 is a system that provides a route until a vehicle reaches a destination. In the first embodiment, an emergency vehicle is targeted as the vehicle that provides the route. An emergency vehicle is a vehicle that is designated and permitted to have priority passage on a road or to preferentially use a road when performing an emergency duty. Emergency vehicles include ambulances, fire trucks, police vehicles, vehicles used for emergency operations in public utilities such as electricity, gas, and water supply. Here, in particular, ambulances and fire trucks are assumed.

[0016] The route search system 1 includes a route search device 2 and a terminal device 4. The route search device 2 is a computer device (such as a server) and can be connected to the terminal device 4 via an information communication network including a wireless communication network. In the example of FIG. 1, there is one terminal device 4 connected to the route search device 2, but it can be connected to a plurality of terminal devices 4.

[0017] Here, the configuration of the terminal device 4 will be described. The terminal device 4 is a computer device mounted on an emergency vehicle 8, has a communication function, and has a display control function for controlling a display device to display information. The terminal device 4 may be installed on the emergency vehicle 8 as an in-vehicle device, or may be a portable device such as a tablet terminal that can be brought into the emergency vehicle 8.

[0018] The terminal device 4 includes a control device 40, a display device 41, and a storage device 42. The display device 41 is a device that displays information in the form of characters, images, videos, etc. In the example of FIG. 1, the display device 41 is built into the terminal device 4, but it may also be external.

[0019] The storage device 42 includes a storage medium for storing data and a computer program (hereinafter also referred to as a program) 43. There are multiple types of storage devices, such as magnetic disk devices and semiconductor memory elements. Furthermore, there are multiple types of semiconductor memory elements, such as RAM (Random Access Memory) and ROM (Read Only Memory). The type of the storage device 42 provided in the terminal device 4 is not limited to one. A computer device often has multiple types of storage devices. Here, the type and number of the storage devices 42 provided in the terminal device 4 are not limited, and the description thereof is omitted. Also, when the terminal device 4 is provided with multiple types of storage devices 42, they are collectively referred to as the storage device 42.

[0020] In the first embodiment, an application program related to route search (hereinafter also referred to as a route search application) is stored in the storage device 42 as one of the programs 43.

[0021] The control device 40 of the terminal device 4 is composed of a processor such as a CPU (Central Processing Unit). By reading and executing the program 43 stored in the storage device 42, the control device 40 can have various functions based on the program 43. Here, the control device 40 has a reception unit 44, a detection unit 45, a communication unit 46, and a presentation unit 47 as functional units based on the route search application.

[0022] The reception unit 44 receives information input by a user who operates the terminal device 4 (for example, a crew member driving an emergency vehicle) into the terminal device 4. Here, one of the information received by the reception unit 44 is information about the site where the emergency vehicle 8 has been requested to be dispatched, that is, the destination to which the emergency vehicle 8 is heading. For example, when the destination is specified by the user on the map displayed on the display device 41, the position on the specified screen is detected. The reception unit 44 receives the detected position on the screen as information related to the destination. Based on this received information and the information of the map displayed on the screen, position information representing the destination (for example, position information of the destination represented in a geographical coordinate system) is calculated. Note that the method of calculating position information representing the destination (hereinafter also referred to as destination information) using the position information on the screen specified on the screen where the map is displayed and the information of the map displayed on the screen is not limited here, and the description thereof is omitted.

[0023] The detection unit 45 detects the location of the terminal device 4 (in other words, the location of the emergency vehicle 8). As a method for detecting the location of the emergency vehicle 8, for example, there is a method that uses GNSS (Global Navigation Satellite System) such as GPS (Global Positioning System). As another method, there is also a method in which the user (the crew member driving the emergency vehicle 8) designates the location of the emergency vehicle 8 on the map displayed on the display device 41 to detect the location of the emergency vehicle 8. Thus, there are a plurality of methods for detecting the location of the emergency vehicle 8, and any method may be used here.

[0024] The communication unit 46 performs information communication with the route search device 2. Specifically, for example, when the reception unit 44 receives information regarding the destination, the communication unit 46 transmits destination information based on the received information to the route search device 2. Further, when transmitting the destination information, the communication unit 46 transmits information representing the location of the emergency vehicle 8 detected by the detection unit 45 (hereinafter also referred to as departure location information) to the route search device 2. The departure location information may be transmitted to the route search device 2 in association with the destination information, or may be transmitted to the route search device 2 separately from the destination information, such as after or before the transmission of the destination information. In the following description, the departure location information and the destination information are collectively referred to as search condition information.

[0025] When the route search device 2 receives the search condition information transmitted by the communication unit 46, the route search device 2 executes a route search process using the search condition information, and the result of the route search process is returned from the route search device 2 to the terminal device 4. The route search process is a process of executing a route search (calculation) for searching for a route from the departure location to the destination. That is, information representing a recommended route from the location of the emergency vehicle 8 (departure location) to the destination (hereinafter also referred to as recommended route information) is transmitted from the route search device 2 to the terminal device 4 as a result of the route search process. The communication unit 46 receives the recommended route information, which is the result of the route search process, from the route search device 2.

[0026] The prompting unit 47 causes the display device 41 to display the recommended route searched by the route search device 2 in a determined display mode based on the recommended route information.

[0027] Next, the route search device 2 will be described. As described above, when the route search device 2 receives the search condition information, it executes a route search process. The route search device 2 uses AI (Artificial Intelligence) technology in its route search process. The model (hereinafter referred to as the route search model) used in the route search process by AI technology in this first embodiment is a model generated by machine learning the actual driving routes of skilled operators. A skilled operator is, for example, an operator selected based on an experience level such that the number of dispatches in the assigned area in which they are responsible for their duties as an institutional employee is equal to or greater than a threshold value (for example, 100 times). When such a skilled operator actually dispatches, the actual driving routes traveled are accumulated and the route search model in the first embodiment is generated by machine learning the actual driving routes.

[0028] This route search model uses the search condition information (that is, the departure location information and the destination information) as input data and outputs a recommended route from the departure location (the location of the emergency vehicle 8) to the destination.

[0029] An example of the machine learning for generating the route search model is intention learning. Intention learning is a method of machine learning an objective function that maximizes actions using data representing what decision was made (action) at what time (state) with inverse reinforcement learning as the core technology. When generating a route search model using such intention learning, not only the actual driving routes but also information representing the situation in the assigned area, for example, when actually driving (hereinafter also referred to as situation information) is used in the generation of the model. Examples of the situation information include, for example, date and time information, the presence or absence of events, the location of event venues, the scale of events (such as the number of participants), road traffic conditions such as congestion, the presence or absence of disasters and disaster situations, weather, and the implementation status of construction work.

[0030] Note that, unlike general vehicles, emergency vehicles are special vehicles for which privileged driving (such as driving on the roadside strip, reverse driving on a one-way road, etc.) is permitted. It can be said that such privileged driving information is reflected in the actual driving route. Thus, when generating the route search model, it is possible to generate a model in which information on the roadside strip having a width that can be passed by emergency vehicles is reflected, even without inputting information related to privileged driving such as the existence of a roadside strip having such a width.

[0031] Here, the configuration of the route search device 2 will be described. As shown in FIG. 1, the route search device 2 includes a control device 20 and a storage device 22. The storage device 22 includes a storage medium that stores data and a computer program (program) 23. There are a plurality of types of storage devices in the storage device, such as a magnetic disk device and a semiconductor memory element. Furthermore, there are a plurality of types of semiconductor memory elements, such as RAM (Random Access Memory) and ROM (Read Only Memory), and there are many types in total. The type of the storage device 22 included in the route search device 2 is not limited to one. A computer device often includes a plurality of types of storage devices. Here, the type and number of the storage devices 22 included in the route search device 2 are not limited, and the description thereof is omitted. Also, when the route search device 2 includes a plurality of types of storage devices 22, they are collectively referred to as the storage device 22. Note that the route search device 2 may be connected to an external storage device (database) 6, and the route search device 2 may appropriately execute writing of data and programs to the storage device 6 and reading of data and programs from the storage device 6. Also, in the following description, when it is described as "reading from the storage device 22" or "storing in the storage device 22", it is assumed that it may also include reading from the storage device 6 or storing in the storage device 6, and the description of such a storage device 6 is omitted.

[0032] In the first embodiment, a computer program for executing route search processing is stored in the storage device 22 as one of the programs 23. Further, a route search model as described above is stored in the storage device 22 as one of the programs 23. Furthermore, the storage device 22 stores performance data in which the actual travel route, the situation information at the time of travel, and information representing the experience level of the driver who has traveled are associated with each other. Furthermore, the storage device 22 stores information on the experience level used when selecting a skilled person (such as information indicating that the number of dispatches in the responsible area is 100 or more), information on the number of data of the actual travel route used for generating the route search model, and the like.

[0033] The control device 20 is composed of a processor such as a CPU or a GPU (Graphics Processing Unit). By reading and executing the program 23 stored in the storage device 22, the control device 20 can have various functions based on the program 23. Here, the control device 20 has a reception unit 24, an acquisition unit 25, an output unit 26, and a search unit 27 as functional units related to route search processing.

[0034] The reception unit 24 receives information transmitted from the terminal device 4. Examples of the information to be received include search condition information (information on the location of the emergency vehicle 8 (departure location information) and destination information).

[0035] The acquisition unit 25 acquires information to be referred to when performing route search. Here, the information acquired by the acquisition unit 25 is information representing the current situation in the area including the departure place and the destination of the route search (hereinafter also referred to as current situation information). Examples of the current situation information include traffic jam information on roads, information on road construction sites and road closures, weather information, emergency information related to disasters caused by earthquakes, storms, fires, etc., and information transmitted via SNS (Social Networking Service).

[0036] When the acquisition unit 25 acquires information transmitted by the SNS (hereinafter also referred to as SNS information), the acquisition unit 25 further has a function of extracting information of a predetermined type from the acquired SNS information. Examples of the information to be extracted from the SNS information include information indicating abnormal situations such as road flooding, fires, and traffic accidents, and information indicating a situation where road traffic is obstructed due to a crowd caused by an event. As a method for extracting information to be extracted from the SNS information, for example, there is a method using AI (Artificial Intelligence) technology. When using AI technology, a model for extracting information to be extracted from the SNS information is further stored in the storage device 22 in advance as one of the programs 23. This model is generated by machine learning. The acquisition unit 25 extracts the information to be extracted from the SNS information using the model.

[0037] The search unit 27 searches for a recommended route regarding the emergency vehicle 8 on which the terminal device 4 that transmitted the search condition information is mounted, using the search condition information received by the reception unit 24, the current situation information acquired by the acquisition unit 25, and the route search model stored in the storage device 22.

[0038] In addition, when it is assumed that there is a route passing through a level crossing as one of the routes from the departure place to the destination, for example, the acquisition unit 25 may acquire train operation information. Then, a configuration may be adopted in which, using the train operation information, it is determined whether the train passes through the level crossing at a time when it is estimated that the emergency vehicle 8 passes through the level crossing, and the determination result is used in the search process of the recommended route. Also, there is a traffic signal that controls the lighting of red and blue lights to detect the emergency vehicle and prevent it from obstructing the passage of the emergency vehicle. Information on the installation locations of such traffic signals may also be used in the search process of the recommended route.

[0039] The recommended route searched by the search unit 27 is the route searched using a route search model generated by machine learning of the actual driving routes of experts, so it is not necessarily just the shortest route from the departure point to the destination. For example, if a level crossing is included in the shortest route with the shortest driving distance, there is a possibility that a situation where one has to wait for a train to pass at that level crossing may occur, and it is conceivable that the arrival at the destination may be delayed due to waiting for the train to pass. On the other hand, a route search model based on the actual driving routes of experts outputs, as the recommended route, a route that, for example, is a detour with a longer driving distance than the shortest route but can utilize a grade-separated intersection without a level crossing. This recommended route is a route that can avoid delays caused by waiting for a train to pass at a level crossing.

[0040] Incidentally, intention learning, which is cited as one type of machine learning for generating a route search model, is so-called explainable AI (Artificial Intelligence). Therefore, when the route search model is generated by intention learning, the route search model can also output an explanation such as the reason why the recommended route is recommended (hereinafter also referred to as recommended basis information). Thus, when using a route search model generated by intention learning, the search unit 27 may also output the recommended basis information about the recommended route.

[0041] Furthermore, when performance data (information including actual driving routes and situation information) is stored in the storage device 22, the search unit 27 may also search for the following data from the actual driving routes stored in the storage device 22 when searching for a recommended route. That is, the search unit 27 searches for an actual driving route with a combination of departure point and destination similar to or the same as that included in the search condition information as a reference route. More preferably, the search unit 27 searches for an actual driving route of performance data including situation information (such as time zone, day of the week, weather, etc.) close to the current situation at the time of search, not only the combination of departure point and destination, as a reference route from the performance data in the storage device 22. In this case, the search unit 27 reads out, for example, the situation information associated with the reference route (actual driving route) from the storage device 22 as well.

[0042] Furthermore, the route search model may be configured to output not only the recommended route but also the estimated time required to reach the destination when traveling on the recommended route. In this case, the search unit 27 may also output information on the required time.

[0043] The output unit 26 returns (outputs) information (recommended route information) representing the recommended route searched by the search unit 27 to the terminal device 4 that has transmitted the search condition information. Also, when the search unit 27 outputs the recommended basis information of the route, the output unit 26 transmits the recommended basis information to the terminal device 4 as well. Furthermore, when the search unit 27 searches for a reference route as well, the output unit 26 transmits the reference route to the terminal device 4. Furthermore, when the search unit 27 reads out not only the reference route but also the situation information associated with the reference route from the storage device 22, the output unit 26 transmits the performance data including the situation information and the reference route read out by the search unit 27 to the terminal device 4. Furthermore, when the search unit 27 outputs information on the required time, the output unit 26 may also transmit the information on the required time to the terminal device 4.

[0044] Furthermore, when transmitting the recommended route to the terminal device 4, the output unit 26 may also transmit the number of data of the actual traveled routes used for generating the route search model and the information on the amount of experience used when selecting an expert.

[0045] When the communication unit 46 of the terminal device 4 receives the information transmitted by the output unit 26, the received information is displayed by the presentation unit 47 of the terminal device 4.

[0046] FIG. 2 shows an example of the display of the recommended route on the display device 41 of the terminal device 4. In the example of FIG. 2, information representing the recommended route is superimposed on the map, and further, information representing the location (departure point) and destination of the emergency vehicle 8 is also superimposed on the map. Also, when the data number of the actual traveled routes used for generating the route search model and the information on the amount of experience used when selecting experts are transmitted from the output unit 26 to the terminal device 4, the information may be displayed on the display device 41 as in the portion surrounded by the dotted line A in FIG. 2. Such information is assumed to lead to obtaining trust in the recommended route from the vehicle crew who have seen the recommended route (in other words, enhancing the reliability of the recommended route).

[0047] The display mode of the recommended route is not limited to the example of FIG. 2. For example, as shown in FIG. 3, in addition to the recommended route, characters and symbols for explaining the recommended route may also be displayed. Further, when the route recommendation basis information is also output from the route search device 2 to the terminal device 4, as shown in FIG. 4, an explanation based on the route recommendation basis information may also be displayed on the display device 41 of the terminal device 4. Further, the explanation of the recommended route and the explanation of the basis of the recommended route may be configured to be able to select whether to display or not display them. Displaying the route recommendation basis information is considered to lead to giving the vehicle crew who have seen the recommended route a sense of acceptance.

[0048] Furthermore, when the actual driving route as the reference route searched by the search unit 27 is transmitted to the terminal device 4, the terminal device 4 may display the reference route together with the recommended route on the display device 41 as shown in FIG. 5. Further, when not only the reference route but also the situation information when the emergency vehicle 8 actually travels on the reference route is transmitted to the terminal device 4 by the output unit 26, the terminal device 4 may display the situation information on the display device 41 as shown in FIG. 6. Also, a configuration in which the display and non-display of the situation information can be selected may be adopted. Further, information indicating the experience level of the crew member who has traveled on the reference route may be displayed. Such information indicating the experience level of the crew member is included in the performance data and is transmitted from the route search device 2 to the terminal device 4 in association with the reference route. Displaying the reference route is also considered to lead to obtaining the trust of the crew member who has seen the recommended route with respect to the recommended route.

[0049] Furthermore, when information on the estimated required time when traveling on the recommended route is also output from the route search device 2 to the terminal device 4, the information on the required time may also be displayed.

[0050] Furthermore, the display mode of the recommended route on the terminal device 4 may differ according to the experience level in the area in charge of the crew member (driver) who drives the emergency vehicle 8 with reference to the recommended route. For example, when the experience level (number of deployments) of the driver is less than the threshold value, as shown in FIG. 7, not only the recommended route is displayed on the display device 41, but also explanations and photos of points to be noted on and around the recommended route are displayed, or an explanation of the basis of the recommended route is displayed. On the other hand, when the experience level (number of deployments) of the driver is equal to or more than the threshold value, as shown in FIG. 2, the explanation of the points to be noted on and around the recommended route is omitted on the display device 41. Even when the experience level (number of deployments) of the driver is equal to or more than the threshold value, explanations and photos of points to be noted on and around the recommended route may be pop-up displayed on the display device 41 according to the driver's request. Also, the experience level of the driver may be divided into three or more ranks, and the display mode of the recommended route on the display device 41 may differ for each division.

[0051] Thus, when the display mode of the recommended route in the display device 41 is made different according to the driver's experience level, for example, a screen as shown in FIG. 8 may be displayed on the display device 41 in order to have the driver input their experience level to the terminal device 4. Also, in the following manner, the terminal device 4 may acquire information representing the driver's experience level (hereinafter also referred to as experience level information). For example, in the storage device 22 of the route search device 2, data (hereinafter also referred to as crew member data) in which crew member identification information for identifying a crew member and the experience level information of the crew member are associated is pre-generated and stored. The terminal device 4 first has a function of acquiring the crew member identification information of the crew member driving the emergency vehicle 8 when the emergency vehicle 8 is dispatched. Specifically, for example, when the emergency vehicle 8 is dispatched, by causing the display device 41 to display a screen for the crew member driving the emergency vehicle 8 to input their own crew member identification information to the terminal device 4, the terminal device 4 acquires the crew member identification information input manually by the driver. Alternatively, for example, the terminal device 4 is equipped with a camera, and may photograph the face of the crew member who is the driver with the camera, and acquire the crew member identification information of the driver from the photographed image of the face using face recognition technology. Also, the terminal device 4 may acquire the crew member identification information of the driver using biometric authentication other than face recognition (authentication using fingerprint, iris, vein, voice, ear acoustics, behavior, etc.). In this case, the terminal device 4 is provided with an acquisition device for acquiring the driver's biometric information for biometric authentication other than face recognition. Further, for example, assume a configuration in which a two-dimensional code including crew member identification information is described on the identification card carried by the crew member. The terminal device 4 may photograph the two-dimensional code with a camera and acquire the crew member identification information from the photographed image using a two-dimensional code reading application. After acquiring the crew member identification information in this way, the terminal device 4 transmits the acquired crew member identification information to the route search device 2. Thereby, the route search device 2 reads out the experience level information of the crew member data including the received crew member identification information from the storage device 22 and returns it to the terminal device 4. Thereby, the terminal device 4 can acquire the experience level information.In addition, when biometric authentication is performed as described above, data in which biometric information of an institutional member used for biometric authentication is associated with institutional member identification information is stored in the storage device 42 of the terminal device 4 or the storage device 22 of the route search device 2.

[0052] The various displays of the recommended route on the display device 41 of the terminal device 4 as described above are realized by the route search application and the control device 40 that executes the application.

[0053] The route search system 1 in the first embodiment is configured as described above. Next, an example of the operation of the route search process in the route search device 2 of the first embodiment will be described with reference to FIG. 9. FIG. 9 is a flowchart for explaining an example of the operation of the route search process in the route search device 2.

[0054] For example, when the receiving unit 24 of the control device 20 receives search condition information from the terminal device 4 (step 101 in FIG. 9), the acquisition unit 25 acquires current situation information (step 102). Thereafter, the search unit 27 uses the search condition information, the current situation information, and the route search model to search for a recommended route from the departure point to the destination based on the search condition information (step 103). Then, the output unit 26 returns (outputs) the recommended route to the terminal device 4 (step 104).

[0055] In the first embodiment, the route search system 1 and the route search device 2 output a recommended route using a route search model based on the actual driving routes of skilled drivers. Therefore, the route search system 1 and the route search device 2 can shorten the required time to the destination, and can also improve the reliability of the recommended route to the destination. That is, the required time to the destination is related to many factors such as time zones, days of the week, weather related to people's movements, road widths related to the driving speed of vehicles, and the presence or absence of level crossings. It is considered that skilled drivers have acquired through experience the relationship between many such factors related to the required time to the destination and the required time to the destination, and drive on a route based on such experience. By using a route search model that has learned the actual driving routes based on the tacit knowledge of such skilled drivers, the route search system 1 and the route search device 2 can shorten the required time to the destination. In addition, since the route search system 1 and the route search device 2 search (propose) a route based on the actual driving route of a skilled driver as a recommended route, the reliability of the recommended route can also be enhanced by the trust in the skilled driver.

[0056] In particular, for the emergency vehicle 8, priority driving is recognized and it can drive on a different route from general vehicles. Therefore, in determining the driving route for the emergency vehicle 8 to reach the destination, the driving experience of the emergency vehicle 8 is considered to work more effectively than the determination of the driving route of general vehicles. Thus, it is considered more effective to utilize a route search model based on the actual driving routes of skilled drivers in determining the driving route of the emergency vehicle 8.

[0057] <Second Embodiment> Hereinafter, a second embodiment of the present invention will be described. In the description of this second embodiment, the same reference numerals are given to the same named components constituting the route search system 1 of the first embodiment, and the overlapping description of the common parts is omitted.

[0058] FIG. 10 is a block diagram showing the configuration of the route search system 1 in the second embodiment. In the second embodiment, in addition to the configuration of the first embodiment, the route search device 2 further includes a learning unit 28 as a functional unit in the control device 20. The learning unit 28 acquires information representing the actual driving route from the terminal device 4 mounted on the emergency vehicle 8 and stores (accumulates) it in the storage device 22. Further, the learning unit 28 updates the route search model stored in the storage device 22 by performing machine learning (relearning) on the actual driving routes of skilled drivers newly acquired after the previous update at a predetermined update timing. The update timing may be every time a predetermined period (for example, three months) has elapsed, or every time the number of accumulated actual driving routes of skilled drivers accumulated after the previous update reaches a preset number, and here, it may be set appropriately.

[0059] When the learning unit 28 as described above is provided in the route search device 2, the terminal device 4 mounted on the emergency vehicle 8 is configured to output information representing the route actually traveled as actual driving route information to the route search device 2. Such a configuration (function) can be provided to the terminal device 4 by a route search application, and is realized by the route search application, for example, a function for acquiring vehicle position information using GNSS, and a communication function. Here, the method for generating the actual driving route information representing the actually traveled route (actual driving route) is not limited, and the description thereof is omitted.

[0060] Also, in this second embodiment, the actual driving route information output from the terminal device 4 to the route search device 2 is associated with information (experience amount information) representing the experience amount (here, the number of dispatches in the responsible area) of the driver (crew member) of the vehicle actually traveling on the driving route included in the information.

[0061] The experience amount information may be information manually input to the terminal device 4 by the driver, or may be information acquired by the terminal device 4 by a method using biometric authentication or two-dimensional code as described above.

[0062] The driver experience information obtained as described above is associated with the actual driving route information and output from the terminal device 4 to the route search device 2. When driver crew identification information is transmitted from the terminal device 4 to the route search device 2, the route search device 2 may be provided with a function of counting up the experience information of crew data including the driver's crew identification information, that is, the number of deployments by "1" here.

[0063] When the learning unit 28 of the route search device 2 updates the route search model, it reads out the actual driving route of the expert from the storage device 22 using the experience information from among the actual driving route information accumulated after the previous update. Then, the learning unit 28 retrains the route search model using the read actual driving route of the expert and updates the route search model in the storage device 22.

[0064] The configuration of the route search system 1 in the second embodiment other than the above is the same as the configuration of the route search system 1 in the first embodiment.

[0065] Since the route search system 1 of the second embodiment has the same configuration as the first embodiment, it can achieve the same effects as the first embodiment. Also, in the second embodiment, the route search device 2 further has a function of acquiring and storing the actual driving route information from the terminal device 4 and updating the route search model using the stored actual driving route of the expert. As a result, since the route search model is updated, the route search system 1 can improve the reliability of the recommended route output from the route search device 2.

[0066] <Third Embodiment> Hereinafter, a third embodiment of the present invention will be described. In the description of the third embodiment, the same reference numerals are given to the same name parts as the constituent parts constituting the route search system 1 of the first or second embodiment, and the overlapping description of the common parts is omitted.

[0067] In addition to the configuration of the first or second embodiment, the route search system 1 according to the third embodiment further has a function of outputting information that is useful when determining the emergency vehicle 8 to be dispatched when there is a request for the dispatch of the emergency vehicle 8. That is, in the third embodiment, as shown in FIG. 11, the route search device 2 is connected to the command post 9. Here, the command post 9 is a command and control device used when issuing a dispatch command for a fire and emergency emergency vehicle or giving instructions to the scene where the vehicle has been dispatched. The command post 9 is connected to the display device 10.

[0068] In the third embodiment, when the location information of the dispatch destination (the destination to be dispatched), which is obtained from a call made to the fire and emergency emergency telephone (i.e., the 119 reporting telephone), is input to the command post 9, the location information of the dispatch destination is output from the command post 9 to the route search device 2. The receiving unit 24 of the control device 20 of the route search device 2 receives the location information (destination information) of the dispatch destination. Further, when the receiving unit 24 receives the destination information, for example, it acquires the identification information and location information of the emergency vehicle 8 within the area including the dispatch destination and in the surrounding areas, which are areas (cells) set based on the base stations of the wireless information communication network, from the terminal device 4. The location information of the emergency vehicle 8 is departure location information, for example, information obtained by the terminal device 4 using GNSS including GPS. It can be said that the emergency vehicle 8 whose such location information has been acquired by the route search device 2 is a candidate vehicle heading for the dispatch destination. When a plurality of emergency vehicles 8 are located in the area including the dispatch destination and its surrounding areas, the receiving unit 24 will receive the information of a plurality of departure locations and the information of a common destination.

[0069] The search unit 27 uses the position of the emergency vehicle 8 based on the acquired position information as the departure location information, and the position of the dispatch destination received from the command station 9 as the destination information, and searches for the recommended route of the emergency vehicle 8 that has acquired the position information using a route search model. Also, in the third embodiment, the search unit 27 outputs the estimated required time when traveling on the recommended route using the route search model. That is, when a plurality of emergency vehicles 8 are located in the area including the dispatch destination and the surrounding areas, the search unit 27 searches for a plurality of recommended routes with different departure locations, and calculates the required time for each of the recommended routes.

[0070] The output unit 26 associates the identification information and position information of the emergency vehicle 8 with the recommended route recommended when the emergency vehicle 8 travels toward the dispatch destination (destination) and the information on the estimated required time, and transmits (outputs) it to the command station 9 as vehicle position information. When a plurality of emergency vehicles 8 are located in the area including the dispatch destination and the surrounding areas, the vehicle position information regarding each of the plurality of emergency vehicles 8 is transmitted to the command station 9.

[0071] The command station 9 uses the received vehicle position information to cause the display device 10 to display information such as the position of the emergency vehicle 8 as a candidate for traveling toward the dispatch destination (destination) and the estimated required time to the destination, as shown in FIG. 11 for example. Also, the recommended route for the emergency vehicle 8 as a dispatch candidate to travel toward the destination may be displayed on the display device 10. Furthermore, the command station 9 may cause the display device 10 to display information indicating whether the emergency vehicle 8 as a dispatch candidate is in the process of dispatching or is waiting for dispatch. The information indicating whether it is in the process of dispatching or waiting is held by the command station 9, for example.

[0072] By looking at the display of such a display device 10, the dispatcher who issues the dispatch command can shorten the time required until the dispatcher determines the emergency vehicle 8 to be dispatched and gives the dispatch instruction.

[0073] Note that, as described in the first embodiment, search condition information including destination information and departure place information is transmitted from the terminal device 4 of the emergency vehicle 8 instructed to depart to the route search device 2, and a recommended route is output from the route search device 2 to the terminal device 4 and displayed on the display device 41 of the terminal device 4. Alternatively, the command post 9 may output the recommended route received from the route search device 2 to the terminal device 4 of the emergency vehicle 8 that is instructed to depart. In this case, the terminal device 4 can also receive the recommended route from the route search device 2, but at the time of departure, it can receive the recommended route from the command post 9 without transmitting the search condition information to the route search device 2. Alternatively, after the emergency vehicle 8 that is instructed to depart is determined, identification information representing the determined emergency vehicle 8 may be transmitted from the command post 9 to the route search device 2, and the route search device 2 may transmit the recommended route to the terminal device 4 of the emergency vehicle 8 corresponding to the identification information. Also in this case, at the time of departure, the terminal device 4 can acquire the recommended route without transmitting the search condition information to the route search device 2.

[0074] The configuration of the route search system 1 in the third embodiment other than the above is the same as the configuration of the first or second embodiment.

[0075] In the third embodiment, when there is a call for departure, it is possible to output an estimated value of the time required for the emergency vehicle 8 as a departure candidate to head to the departure destination to the command post 9. That is, the route search system 1 (route search device 2) can provide information to support the judgment of the commander who determines the emergency vehicle 8 to depart.

[0076] <Other Embodiments> The present invention is not limited to the first to third embodiments and can adopt various embodiments. For example, the route search model may be generated so as to be able to output a plurality of recommended routes with priorities. In this case, the search unit 27 may also search for a plurality of recommended routes with priorities by using such a route search model. Thus, when the search unit 27 searches for information on a plurality of recommended routes and priorities, the output unit 26 returns the information on the plurality of recommended routes and priorities to the terminal device 4. In this case, the terminal device 4, for example, sequentially switches and displays the recommended routes on the map in descending order of priority on the display device 41. In this case, information representing the priority of the displayed recommended route may also be displayed on the display device 41 together with the recommended route. Note that the mode of displaying a plurality of recommended routes on the display device 41 is not limited to the above example.

[0077] Also, when the recommended route is displayed on the display device 41, information indicating the confidence level (degree of recommendation) of the recommended route may be displayed. In this case, relationship data between the number of actual driving routes used to generate the route search model and the confidence level (degree of recommendation) for the recommended route output by the route search model is given in advance to the route search device 2. From such data, the confidence level (degree of recommendation) of the recommended route corresponding to the number of actual driving routes used to generate the route search model is read out, and information representing the confidence level of the recommended route is stored in the storage device 22 of the route search device 2. When a learning unit 28 as in the second embodiment is provided in the route search device 2, the information representing the confidence level of the recommended route is updated each time the route search model is updated. The information representing the confidence level of the recommended route is output in association with the recommended route information when the output unit 26 of the route search device 2 outputs the recommended route information. The terminal device 4 displays on the display device 41, together with the recommended route, information representing the confidence level of the recommended route obtained from the received information. When the recommended route passes through a plurality of pre-classified regions, the confidence level of the recommended route for each region may be represented. That is, it is assumed that the number of actual driving routes of the vehicle used to generate the route search model differs depending on the region, such that one region has a large number of driving records of the vehicle, while another region has few driving records of the vehicle. Thus, it is considered that the confidence level of the route search model may differ depending on the region through which the recommended route output by the route search model passes. In such a case, when the recommended route passes through a plurality of regions, the confidence level for each region may be displayed on the display device 41.

[0078] Furthermore, when generating the route search model, the actual driving routes used may be weighted according to the experience level of the skilled driver who drove on those routes. Further, the route search model may be generated by machine learning using, in addition to the actual driving routes of skilled drivers, data on the comparison results between the actual driving routes of those with an experience level less than a predetermined value (less experienced drivers) and the actual driving routes of skilled drivers.

[0079] Furthermore, the terminal device 4 may be provided with a function of navigating to a destination by, for example, voice according to a recommended route while the vehicle is running.

[0080] Furthermore, in the first to third embodiments, the search condition information transmitted from the terminal device 4 to the route search device 2 includes departure location information, and the search unit 27 searches for a recommended route using the search condition information including the received departure location information. Instead of this, for example, when the available emergency vehicle 8 is a vehicle waiting at a fire station and the departure location is fixed to the location of the waiting fire station, for example, the route search device 2 may not need to receive the departure location information from the terminal device 4. In other words, the receiving unit 24 may receive only the destination information out of the departure location information and the destination information.

[0081] Furthermore, in the first to third embodiments, an example of an emergency vehicle is given as the vehicle for which a route is searched, and the configuration of the route search system is described. Instead of the emergency vehicle, for example, the route search system 1 in the first to third embodiments can also be applied to route search of, for example, a taxi, which is a vehicle in which the experience of a skilled person is utilized for route search. When applied to a taxi, for example, as information on the amount of experience, information representing the number of years of experience as a taxi driver is used. Thus, the information on the amount of experience is not limited to the number of times of deployment of the emergency vehicle. Also, in such a case, the terminal device is mounted on a taxi, which is a vehicle.

[0082] FIG. 12 is a block diagram showing the basic configuration of the route search device according to the present invention. This route search device 50 constitutes a route search system together with, for example, a terminal device 55 mounted on a vehicle. The route search device 50 is, for example, a computer device, and includes, as functional units, a receiving unit 52, a search unit 53, and an output unit 54 by the operation of the computer based on a computer program. The receiving unit 52 receives information on the destination. The information on the destination is transmitted, for example, from the terminal device 55. The search unit 53 searches for a recommended route to the destination using the destination information and a route search model. The route search model is a model that generates a recommended route to the destination by machine learning the actual driving routes traveled by a skilled person selected based on the amount of experience, and outputs the recommended route to the destination. The output unit 54 outputs the searched recommended route to, for example, the terminal device 55.

[0083] Next, an example of the operation related to the route search of the route search device 50 will be described with reference to FIG. 13. For example, the receiving unit 52 of the route search device 50 receives information on the destination (step 201 in FIG. 13). Then, the search unit 53 searches for a recommended route to the destination using the received destination information and the route search model (step 202). The output unit 54 outputs the recommended route (step 203).

[0084] The above-described route search device 50 and the route search system including the route search device 50 output a recommended route using a route search model based on the actual driving routes of skilled persons. Thereby, it is possible to shorten the required time to the destination, and moreover, it is possible to improve the reliability of the proposed route (recommended route) to the destination.

[0085] As described above, the present invention has been described by taking the above-described embodiments as exemplary examples. However, the present invention is not limited to the above-described embodiments. That is, the present invention can be applied to various aspects understandable by those skilled in the art within the scope of the present invention.

[0086] This application claims priority based on Japanese Patent Application No. 2021-154007 filed on September 22, 2021, and incorporates the entire disclosure thereof herein.

Explanation of Signs

[0087] 1 Route search system 2,50 Route search device 4,55 Terminal device 24,52 Receiver 26,54 Output unit 27,53 Search unit

Claims

[

1. ] A receiving means for receiving destination information; An acquisition means for acquiring current situation information representing the current situation in the area including the destination; A route search model that outputs a recommended route to the destination, which is generated by machine learning the actual driving route traveled by a skilled person selected based on experience, and uses the received destination information and the acquired current situation information to search for a recommended route to the destination and search for the data of the actual driving route related to the acquired current situation information as a reference route; An output means for outputting the searched recommended route to a terminal device, The output means further outputs at least one of the number of data of the actual driving route used for generating the route search model and information representing the condition of the experience amount used for selecting the skilled person to the terminal device, and further outputs the reference route. A route search device. [

2. ] The vehicle is an emergency vehicle permitted to drive ahead. The route search device according to claim 1. [

3. ] The route search model is a model capable of outputting an explanation of the basis for recommending the recommended route, The search means outputs an explanation of the basis for recommending the recommended route, The output means outputs the searched recommended route and an explanation of the basis for recommending the recommended route. The route search device according to claim 1 or 2. [

4. ] The learning means further includes a learning means for updating the route search model by acquiring the actual driving route of the skilled person and re-learning the route search model at predetermined timings using the acquired actual driving route. The route search device according to any one of claims 1 to 3. [

5. ] The receiving means receives information on a plurality of departure places and information on the common destination, The route search model outputs a recommended route from each of the plurality of departure places to the destination and an estimated required time when driving on the recommended route, The search means uses the information on the plurality of departure places, the information on the common destination, and the route search model to search for a plurality of recommended routes with different departure places, and calculates the required time for each of the recommended routes, The output means outputs the plurality of searched recommended routes and the required time. The route search device according to any one of claims 1 to 4. [

6. ] The route search device according to any one of claims 1 to 5, a terminal device that is mounted on a vehicle, outputs information on a destination representing the destination of the vehicle to the route search device, and presents the recommended route and the reference route by receiving the recommended route and the reference route output from the route search device A route search system comprising:

7. by a computer, receives information on a destination, acquires current situation information representing the current situation in the area including the destination, a route search model that outputs a recommended route to the destination, which is generated by machine learning the actual driving routes traveled by a skilled person selected based on experience using a vehicle, and uses the received destination information and the acquired current situation information to search for a recommended route to the destination, and searches for the data of the actual driving routes related to the acquired current situation information as a reference route, outputs the searched recommended route and reference route to a terminal device, outputs at least one of the number of data of the actual driving routes used for generating the route search model and information representing the conditions of the experience amount used for selecting the skilled person to the terminal device Route search method.

8. a process of receiving information on a destination, a process of acquiring current situation information representing the current situation in the area including the destination, a route search model that outputs a recommended route to the destination, which is generated by machine learning the actual driving routes traveled by a skilled person selected based on experience using a vehicle, and uses the received destination information and the acquired current situation information to search for a recommended route to the destination, a process of searching for the data of the actual driving routes related to the acquired current situation information as a reference route, a process of outputting the searched recommended route and reference route to a terminal device, and outputting at least one of the number of data of the actual driving routes used for generating the route search model and information representing the conditions of the experience amount used for selecting the skilled person to the terminal device A computer program that causes a computer to execute.

Images