Detection device, detection method, and program

Abstract

This invention provides a detection device (10) comprising: an acquisition unit (11) which acquires a vehicle state data on each of a plurality of vehicles when each vehicle travels at a measurement position; a generation unit (12) which generates a detection model for detecting an internal abnormality of the vehicle on the basis of the acquired vehicle state data; a detection unit (13) which executes processing for detecting the internal abnormality of a target vehicle on the basis of the detection model and the vehicle state data when the target vehicle traveled at the measurement position; and an output unit (14) which outputs a result of the detection.

Description

Technical Field

[0001] The present invention relates to a detection device, a detection method, and a program.

Background Art

[0002] There is a technology for detecting vehicle abnormalities and the like by using data obtained from sensors such as images captured by a fixed-point camera and millimeter-wave radars. Related technologies are disclosed in Patent Documents 1 and 2.

[0003] Patent Document 1 discloses a technique for generating a learning model that detects abnormal movements (such as dangerous driving) of a vehicle based on an image captured by a fixed-point camera that captures the movement of a vehicle within an intersection, and determining whether the movement of the vehicle within the intersection is abnormal or normal based on the learning model.

[0004] Patent Document 2 discloses a technique for generating a learning model that predicts vehicle failures based on data of a plurality of vehicles, and predicting vehicle failures based on the learning model.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0006] In recent years, various sensors have been installed in vehicles, and various internal data related to the vehicles have been collected. Based on the internal data, it has become possible to detect internal abnormalities of the vehicle.

[0007] Incidentally, the state of the internal data of a vehicle may vary depending on the characteristics of the position where the vehicle is traveling (curves, sharp curves, straight roads, slopes, flat roads, gravel roads, paved roads, narrow roads, wide roads, roads with many trucks passing, roads with many pedestrians, roads with many bicycles, roads with streetcars running in parallel, etc.). If changes according to such a traveling position are not considered, for example, in the case of means for detecting an abnormality in internal data based on the comparison result between the latest internal data and the past internal data of each vehicle, or the comparison result between the latest internal data of each vehicle and a reference value, etc., the accuracy of detecting internal abnormalities of the vehicle deteriorates. Neither Patent Document 1 nor 2 discloses this problem.

[0008] An object of the present invention is to improve the accuracy of detecting internal abnormalities of a vehicle based on internal data of the vehicle.

Means for Solving the Problems

[0009] According to the present invention, acquisition means for acquiring vehicle state data of each vehicle when each of a plurality of vehicles travels a measurement position; generation means for generating a detection model for detecting an internal abnormality of a vehicle based on the acquired vehicle state data; detection means for performing a process of detecting an internal abnormality of the target vehicle based on the detection model and the vehicle state data when the target vehicle travels the measurement position; output means for outputting the result of the detection; A detection device having the above is provided.

[0010] Also, according to the present invention, a computer acquires vehicle state data of each vehicle when each of a plurality of vehicles travels a measurement position, generates a detection model for detecting an internal abnormality of a vehicle based on the acquired vehicle state data, performs a process of detecting an internal abnormality of the target vehicle based on the detection model and the vehicle state data when the target vehicle travels the measurement position, and a detection method for outputting the result of the detection is provided.

[0011] Also, according to the present invention, a computer is caused to function as acquisition means for acquiring vehicle state data of each vehicle when each of a plurality of vehicles travels through a measurement position, generation means for generating a detection model for detecting internal abnormalities of a vehicle based on the acquired vehicle state data, detection means for performing a process of detecting internal abnormalities of the target vehicle based on the detection model and the vehicle state data when the target vehicle travels through the measurement position, output means for outputting the result of the detection, and a program is provided.

Advantages of the Invention

[0012] According to the present invention, the accuracy of detecting internal abnormalities of a vehicle based on internal data of the vehicle is increased.

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

Embodiments for Carrying Out the Invention

[0014] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all the drawings, the same reference numerals are given to the same components, and the description will be omitted as appropriate.

[0015] <First Embodiment> "Overview" In the present embodiment, at a location where vehicles travel such as a road or a parking lot, a measurement position is determined. The detection device acquires vehicle state data indicating the state of each vehicle when each of a plurality of vehicles travels through the measurement position. Then, the detection device generates a detection model for detecting internal abnormalities of the vehicle based on the acquired vehicle state data of the plurality of vehicles. By processing the vehicle state data of the plurality of vehicles when they travel through the measurement position, the general state of the vehicle state data when traveling through that measurement position can be specified. A state in which the vehicle state data deviates from the specified general state is detected as an internal abnormality.

[0016] "Configuration" Next, the configuration of the detection device will be described. First, an example of the hardware configuration of the detection device will be described. Each functional unit of the detection device is realized by an arbitrary combination of hardware and software centered around a CPU (Central Processing Unit), a memory, a program loaded into the memory, a storage unit such as a hard disk for storing the program (in addition to a program stored in advance at the stage of shipping the device, a program downloaded from a storage medium such as a CD (Compact Disc) or a server on the Internet can also be stored), and a network connection interface. And it is understood by those skilled in the art that there are various modification examples for the realization method and the device.

[0017] FIG. 1 is a block diagram illustrating the hardware configuration of the detection device. As shown in FIG. 1, the detection device includes a processor 1A, a memory 2A, an input / output interface 3A, a peripheral circuit 4A, and a bus 5A. The peripheral circuit 4A includes various modules. The detection device may not have the peripheral circuit 4A. Note that the detection device may be composed of a plurality of physically and / or logically divided devices, or may be composed of one physically and / or logically integrated device. When the detection device is composed of a plurality of physically and / or logically divided devices, each of the plurality of devices can include the above hardware configuration.

[0018] The bus 5A is a data transmission path for the processor 1A, the memory 2A, the peripheral circuit 4A, and the input / output interface 3A to transmit and receive data to and from each other. The processor 1A is an arithmetic processing device such as a CPU or a GPU (Graphics Processing Unit). The memory 2A is a memory such as a RAM (Random Access Memory) or a ROM (Read Only Memory). The input / output interface 3A includes an interface for acquiring information from an input device, an external device, an external server, an external sensor, a camera, etc., and an interface for outputting information to an output device, an external device, an external server, etc. The input device is, for example, a keyboard, a mouse, a microphone, a physical button, a touch panel, etc. The output device is, for example, a display, a speaker, a printer, a mailer, etc. The processor 1A can issue commands to each module and perform operations based on their operation results.

[0019] Next, the functional configuration of the detection device will be described. FIG. 2 shows an example of a functional block diagram of the detection device 10. As shown in the figure, the detection device 10 includes an acquisition unit 11, a generation unit 12, a detection unit 13, an output unit 14, and a storage unit 15. Note that the detection device 10 may not have the storage unit 15. In this case, an external device configured to be communicable with the detection device 10 includes the storage unit 15.

[0020] The acquisition unit 11 acquires the vehicle state data of each vehicle when each of the plurality of vehicles travels through the measurement position. The acquisition unit 11 stores the acquired vehicle state data in, for example, the storage unit 15.

[0021] In the present embodiment, at a location where a vehicle travels, such as a road or a parking lot, the measurement position is determined. One measurement position may be determined, or a plurality of measurement positions may be determined. When a plurality of measurement positions are determined, the acquisition unit 11 acquires the vehicle state data of each vehicle when each of the plurality of vehicles travels through each measurement position for each measurement position. Then, as shown in FIG. 3, the acquired vehicle state data is stored in the storage unit 15 in association with each measurement position. In the example shown in FIG. 3, the latitude and longitude of the measurement position are shown as the position information indicating each measurement position, but other information may also be used. Other examples of the position information include identification information attached to each measurement position, identification information of a device installed at each measurement position, etc., but are not limited thereto.

[0022] Examples of the measurement position include a ticket dispenser at a parking lot, a fuel dispenser, a railroad crossing, an ETC (Electronic Toll Collection System) toll gate, a stop position at an intersection, etc. Such measurement positions are suitable for detecting abnormalities in the deceleration mechanism (brake). Other examples of the measurement position include a right-turn / left-turn area at an intersection, a curve, etc. Such measurement positions are suitable for detecting abnormalities in the steering mechanism (steering wheel, etc.). Note that the measurement positions exemplified here are merely examples and are not limited thereto.

[0023] Vehicle state data is data generated by various processors such as ECUs (electronic control units) and various sensors installed in each vehicle. Examples of such vehicle state data include vehicle speed, travel distance, travel time, accelerator opening, brake angle, steering angle, fuel consumption, shift position, gear / wheel speed, DTC (Diagnostic Trouble Code), FFD (freeze frame data), maintenance date and time, tire air pressure, outside air temperature, images taken of the passenger compartment where passengers and cargo are located, images taken of the outside of the vehicle including other vehicles, pedestrians, and signs, analysis results of these images, sensing results of LIDAR and radar, etc. Examples of analysis results of images and sensing results of LIDAR and radar include the number of passengers, the state of passengers (face and line of sight), the amount of cargo, the state of cargo, the type of object detected outside the vehicle (vehicle / pedestrian / sign / white line, etc.), the position of the object, the distance to the object, text information (license plate / guide sign), etc.

[0024] "Vehicle state data when traveling at the measurement position" is data sensed, images taken, and analysis results of those data and images when traveling at the measurement position (which may include its surroundings).

[0025] The vehicle state data acquired by the acquisition unit 11 may further include user identification information. The user identification information may be stored in advance in an in-vehicle device or the like. The user identification information is information for identifying users of the services provided by the detection device 10 from each other.

[0026] Next, a specific example of the means by which the acquisition unit 11 acquires vehicle state data of each vehicle will be described.

[0027] -First acquisition example- The configuration of the first acquisition example is shown in FIG. 4. In this acquisition example, the detection device 10, the fixed-point observation device 20, and the in-vehicle device 30 cooperate. The fixed-point observation device 20 is a device installed at each measurement position. The in-vehicle device 30 is a device installed in each vehicle. The fixed-point observation device 20 and the in-vehicle device 30 are configured to be able to communicate with each other via vehicle-road communication.

[0028] The fixed-point observation device 20 communicates with the in-vehicle device 30 traveling at the measurement position where the self-device is installed, and receives vehicle state data when traveling at the measurement position from the in-vehicle device 30. Then, the fixed-point observation device 20 transmits the vehicle state data received from the in-vehicle device 30 to the detection device 10. The data transmission from the fixed-point observation device 20 to the detection device 10 may be performed in real-time processing or in batch processing (transmitted collectively at predetermined time intervals (e.g., every 15 minutes, every hour, every 24 hours)).

[0029] As a modification, the fixed-point observation device 20 and Detection the device 10 may be integrally configured. In the case of this modification, the Detection device 10 integrated with the fixed-point observation device 20 is installed at each measurement position. Then, each Detection device 10 communicates with the in-vehicle device 30 traveling at each measurement position, and receives vehicle state data when traveling at the measurement position from the in-vehicle device 30. Then, each Detection device 10 processes the vehicle state data acquired at each measurement position, and generates a detection model and detects internal abnormalities of the vehicle.

[0030] -Second acquisition example- The configuration of the second acquisition example is shown in FIG. 5. In this acquisition example, the detection device 10 and the in-vehicle device 30 cooperate. The in-vehicle device 30 is a device mounted on each vehicle. The detection device 10 and the in-vehicle device 30 are configured to be able to communicate with each other via a communication network such as the Internet.

[0031] The in-vehicle device 30 stores in advance the position information (latitude and longitude information) of the measurement position. Then, the in-vehicle device 30 collates the current position information (such as GPS (Global Positioning System) information) of its own device with the position information of the measurement position in real-time processing, and monitors whether the current position of its own device is the measurement position. When the in-vehicle device 30 detects that the current position of its own device has become the measurement position, it associates the position information at that time with the vehicle state data when traveling at that measurement position, and transmits it to the detection device 10. The transmission of the vehicle state data from the in-vehicle device 30 to the detection device 10 may be performed in real-time processing, or may be performed in batch processing (transmitted collectively at predetermined time intervals (e.g., every 15 minutes, every 1 hour, every 24 hours)).

[0032] As a modification example of the acquisition example, the in-vehicle device 30 may perform the above collation in batch processing. In this modification example, the in-vehicle device 30 accumulates the vehicle state data in association with the traveling position at that time. Then, the in-vehicle device 30 processes the accumulated information in batch processing, detects that the current position of its own device has become the measurement position, and transmits the vehicle state data to the detection device 10.

[0033] -Third acquisition example- The configuration of the third acquisition example is shown in FIG. 5. In this acquisition example, the detection device 10 and the in-vehicle device 30 cooperate. The in-vehicle device 30 is a device mounted on each vehicle. The detection device 10 and the in-vehicle device 30 are configured to be able to communicate with each other via a communication network such as the Internet.

[0034] The in-vehicle device 30 transmits the current position information (such as GPS information) of its own device to the detection device 10. The detection device 10 collates the position information (latitude and longitude information) of the measurement position with the received current position information, and monitors whether the current position of the in-vehicle device 30 is the measurement position. When the detection device 10 detects that the current position of the in-vehicle device 30 has become the measurement position, it requests the vehicle state data when traveling at that measurement position from the in-vehicle device 30. The in-vehicle device 30 transmits the vehicle state data when traveling at that measurement position to the detection device 10 in response to the request.

[0035] Note that the transmission of the current position information from the in-vehicle device 30 to the detection device 10, the request for vehicle state data from the detection device 10 to the in-vehicle device 30, and the transmission of the vehicle state data from the in-vehicle device 30 to the detection device 10 may be performed in real-time processing or in batch processing.

[0036] Also, as a modification of the acquisition example, the in-vehicle device 30 may transmit all the vehicle state data to the detection device 10 in association with the traveling position. Then, the detection device 10 may extract the vehicle state data at the time of traveling at the measurement position from the received vehicle state data.

[0037] -Fourth acquisition example- The configuration of the fourth acquisition example is shown in FIG. 6. In this acquisition example, the detection device 10, the in-vehicle device 30, and the user terminal 40 cooperate. The in-vehicle device 30 is a device mounted on each vehicle. The user terminal 40 is a terminal possessed by the user, and examples include, but are not limited to, a smartphone, a tablet terminal, a smartwatch, a mobile phone, a portable game machine, etc. The detection device 10 and the user terminal 40 are configured to be able to communicate with each other via a communication network such as the Internet. The in-vehicle device 30 and the user terminal 40 are configured to be able to communicate with each other by short-range wireless communication, wired communication via a cable, etc.

[0038] This acquisition example is different from the second and third acquisition examples in that the detection device 10 and the in-vehicle device 30 communicate via the user terminal 40. Other configurations are the same as those of the second and third acquisition examples.

[0039] Note that, as a modification of the fourth acquisition example, at least a part of the processing performed by either the detection device 10 or the in-vehicle device 30 described in the second and third acquisition examples (acquisition of current position information, collation with the measurement position, request for vehicle state data, etc.) may be performed by the user terminal 40.

[0040] Returning to FIG. 2, the generation unit 12 generates a detection model for detecting internal anomalies of the vehicle based on the vehicle state data acquired by the acquisition unit 11 (for example, by performing statistical processing). The generation unit 12 stores the generated detection model in, for example, the storage unit 15. When the acquisition unit 11 acquires vehicle state data for each of a plurality of measurement positions, the generation unit 12 processes the vehicle state data of each measurement position for each measurement position and generates the detection model for each measurement position. Then, as shown in FIG. 7, the generation unit 12 stores each detection model in, for example, the storage unit 15 in association with the measurement position.

[0041] By processing the vehicle state data of a plurality of vehicles when traveling at each measurement position, it is possible to identify the general state (values, numerical ranges, trends of time-series changes, relationships between data, etc.) of the vehicle state data when traveling at each measurement position. The detection model is a model that detects a state in which the vehicle state data deviates from the identified general state as an internal anomaly. The detection model is generated, for example, by machine learning using the vehicle state data acquired by the acquisition unit 11 as learning data. Also, the detection model may be generated, for example, by performing statistical processing on the vehicle state data acquired by the acquisition unit 11. The detection model can be expressed in any form including mathematical formulas, conditional expressions, tables, or combinations thereof.

[0042] Returning to FIG. 2, the detection unit 13 performs a process of detecting an internal anomaly of the target vehicle based on the detection model generated by the generation unit 12 and the vehicle state data when the target vehicle travels through the measurement position. When detection models are generated for each of a plurality of measurement positions, the detection unit 13 performs a process of detecting an internal anomaly of the target vehicle based on the detection model associated with the measurement position through which the target vehicle has traveled.

[0043] The output unit 14 outputs the result of the detection. Specifically, the output unit 14 notifies the user of the result of the detection. The output unit 14 may notify the user of all results regardless of the content of the detection result, or may notify the user only when an internal anomaly is detected. Hereinafter, means for notifying the user will be exemplified.

[0044] -First notification example- The configuration of the first notification example is shown in FIG. 4. In this notification example, the detection device 10, the fixed-point observation device 20, and the in-vehicle device 30 cooperate with each other. The fixed-point observation device 20 is a device installed at each measurement position. The in-vehicle device 30 is a device mounted on each vehicle. The fixed-point observation device 20 and the in-vehicle device 30 are configured to be able to communicate with each other through road-vehicle communication.

[0045] The detection device 10 transmits the detection result to the in-vehicle device 30 via the fixed-point observation device 20. The in-vehicle device 30 outputs the received detection result via an output device such as a display or a speaker.

[0046] For example, the detection result based on the vehicle state data obtained from the in-vehicle device 30 of the target vehicle via the fixed-point observation device 20 installed at the first measurement position is transmitted to the in-vehicle device 30 of the target vehicle via the fixed-point observation device 20 installed at another measurement position. Examples of the means for identifying the target vehicle at another measurement position include means for collating user identification information included in the vehicle state data received from the in-vehicle device 30 of the target vehicle at the first measurement position and another measurement position, and means for collating the number (information described on the license plate) of the target vehicle identified by analyzing the images of the target vehicle taken at the first measurement position and another measurement position, but are not limited thereto.

[0047] -Second notification example- In this notification example, the output unit 14 can notify the user of the detection result by using functions such as sending an e-mail, presenting information on a web page or an application page, and the push notification function of the application.

[0048] Next, an example of the processing flow for detecting an internal abnormality of the target vehicle will be described using the flowchart of FIG. 8. Before the processing of FIG. 8 is executed, vehicle state data of each vehicle when each of a plurality of vehicles travels through a measurement position is acquired, and a detection model for detecting an internal abnormality of the vehicle based on the acquired vehicle state data is generated.

[0049] When the detection device 10 acquires the vehicle state data when the target vehicle travels to the first measurement position (S 5 0), based on the detection model generated in advance associated with the first measurement position and the vehicle state data acquired at S 5 0, it executes a process of detecting internal abnormalities of the target vehicle (S 5 1). Then, the detection device 10 outputs the result of the detection (S 5 2).

[0050] "Operational Effect" The state of the internal data of a vehicle can vary depending on the characteristics of the position where the vehicle is traveling (curves, sharp curves, straight roads, slopes, flat roads, gravel roads, paved roads, narrow roads, wide roads, roads with many trucks passing, roads with many pedestrians, roads with many bicycles, roads where streetcars run parallel, etc.). Without considering such changes according to the traveling position, for example, in the case of a means for detecting abnormalities in internal data based on the comparison result between the latest internal data and past internal data of each vehicle, or the comparison result between the latest internal data of each vehicle and a reference value, etc., the accuracy of detecting internal abnormalities of the vehicle deteriorates.

[0051] In this embodiment, for each measurement position, the detection device 10 acquires the vehicle state data of each vehicle when each of a plurality of vehicles travels to each measurement position, and based on the vehicle state data, generates a detection model for detecting internal abnormalities of the vehicle. By processing the vehicle state data of a plurality of vehicles when traveling to each measurement position, the general state of the vehicle state data when traveling to each measurement position can be specified. A state in which the vehicle state data deviates from the specified general state is detected as an internal abnormality.

[0052] According to the detection device 10 of this embodiment as described above, the accuracy of detecting internal abnormalities of the vehicle is improved.

[0053] <Second Embodiment> In this embodiment, the detection device 10 groups vehicles based on the attribute data of the vehicles. Then, the detection device 10 generates the detection model generated for each measurement position for each group as well. The following will explain in detail.

[0054] The acquisition unit 11 acquires vehicle information data indicating the vehicle type, model year, model, vehicle classification (four-wheel / two-wheel, etc.) of the vehicle, and the like.

[0055] The acquisition unit 11 may acquire the vehicle information data by the same means as the acquisition of the vehicle state data described in the first embodiment. In this case, the vehicle information data is stored in the in-vehicle device 30 in advance.

[0056] Alternatively, in advance, the user may perform a process of registering the vehicle information data. Then, the vehicle information data may be stored in, for example, the storage unit 15 in association with the user identification information of each user. In this case, when the acquisition unit 11 extracts the user identification information included in the vehicle state data received from the in-vehicle device 30, the acquisition unit 11 reads out the vehicle information data associated with the user identification information from, for example, the storage unit 15.

[0057] The generation unit 12 groups the vehicles based on the attribute data of the vehicles and generates a detection model for each group.

[0058] The attribute data of the vehicle includes the above-described vehicle information data. In addition, the attribute data of the vehicle may include the vehicle interior state specified based on the vehicle state data. 。 The vehicle interior state is the number of passengers, the amount of cargo, and the like.

[0059] The generation unit 12 groups the vehicles by putting together those with matching or similar attribute data of the vehicles. In advance, as shown in FIG. 9, the values of the attribute data of each group are defined. The generation unit 12 groups a plurality of vehicles based on the definition.

[0060] Then, the generation unit 12 generates a detection model for each group based on the vehicle state data of the vehicles belonging to each group. As a result, as shown in FIG. 10, a detection model is generated for each measurement position and for each group.

[0061] The detection unit 13 performs a process of detecting an internal abnormality of the target vehicle using the detection model associated with the group to which the target vehicle belongs.

[0062] The other configurations of the detection device 10 are the same as those in the first embodiment.

[0063] As described above, according to the detection device 10 of the present embodiment, the same operational effects as those in the first embodiment are achieved.

[0064] The state of the internal data of the vehicle when traveling at each measurement position may vary depending on the vehicle type, model year, model, vehicle classification (four - wheel / two - wheel, etc.), interior state of the vehicle, and the like. According to the detection device 10 of the present embodiment that groups together those with matching or similar attributes and processes the vehicle state data for each measurement position and for each group of vehicles to generate a detection model for detecting internal abnormalities of the vehicle, the accuracy of detecting internal abnormalities of the vehicle is further improved.

[0065] <Third Embodiment> In the present embodiment, when the detection device 10 detects an internal abnormality of the target vehicle, it specifies the type of the internal abnormality and notifies the user. Details are described below.

[0066] When the detection unit 13 detects an internal abnormality of the target vehicle based on the detection model and the vehicle state data when the target vehicle travels through the measurement position, it specifies the type of the internal abnormality of the vehicle. In advance, as shown in Table 1 below, association information associating the detected internal abnormality with the type of the internal abnormality is generated and stored, for example, in the storage unit 15. The detection unit 13 specifies the type of the internal abnormality based on the association information.

[0067]

Table 1

[0068] The output unit 14 further notifies the user of the specified type of the internal abnormality. The output unit 14 can output Information indicating the type of the internal abnormality by the same means as the output of the detection result described in the first embodiment.

[0069] Other configurations of the detection device 10 are the same as those in the first and second embodiments.

[0070] As described above, according to the detection device 10 of the present embodiment, the same operational effects as those in the first and second embodiments are achieved.

[0071] In addition, according to the detection device 10 of the present embodiment, the user can more precisely grasp the content (type) of the internal abnormality occurring in the vehicle. As a result, it is possible to easily grasp what measures should be taken for the internal abnormality.

[0072] <Fourth Embodiment> In this embodiment, the detection device 10 integrates the detection results at a plurality of measurement positions to detect an internal abnormality of the target vehicle. This will be described in detail below.

[0073] The detection unit 13 detects an internal abnormality of the target vehicle based on each piece of vehicle state data when the target vehicle travels through each of the plurality of measurement positions. Then, the detection unit 13 associates the result of each detection with predetermined identification information (user identification information, the number of the vehicle specified by image analysis (information described on the license plate), etc.) and stores it in, for example, the storage unit 15. Then, the detection unit 13 integrates the results of multiple detections to detect an internal abnormality of the target vehicle.

[0074] For example, when the same internal abnormality is detected multiple times in a certain target vehicle, the detection unit 13 may determine that the internal abnormality has occurred in the target vehicle. Then, the output unit 14 may notify the user that the internal abnormality has occurred.

[0075] Other configurations of the detection device 10 are the same as those in the first to third embodiments.

[0076] As described above, according to the detection device 10 of the present embodiment, the same operational effects as those in the first to third embodiments are achieved.

[0077] Further, according to the detection device 10 of the present embodiment, the results of multiple detections can be integrated to detect internal abnormalities of the target vehicle. As a result, the detection accuracy is further improved.

[0078] <Modification Example> In the first to fourth embodiments, internal abnormalities of the target vehicle were detected based on the vehicle state data when the target vehicle traveled at the measurement position. As a modification example, internal abnormalities of the target vehicle may be detected based on the vehicle state data when the target vehicle is stopped at the measurement position.

[0079] For example, the detection unit 13 may detect, as an internal abnormality, that the target vehicle has continued idling for a predetermined time or more based on the vehicle state data of the target vehicle. In this case, the output unit 14 notifies the user that there may be a battery overcharge.

[0080] As described above, the embodiments of the present invention have been described with reference to the drawings, but these are examples of the present invention, and various configurations other than the above can also be adopted.

[0081] In this specification, "acquisition" means, based on user input or based on a program instruction, "the act of the own device going to obtain data stored in another device or storage medium (active acquisition)", for example, making a request or inquiry to another device and receiving the data, accessing another device or storage medium and reading out the data, etc., and, based on user input or based on a program instruction, "the act of the own device inputting data output from another device (passive acquisition)", for example, receiving data distributed (or transmitted, push-notified, etc.), also, selecting and acquiring from the received data or information, and, "generating new data by editing (textualizing, rearranging data, extracting partial data, changing file format, etc.) the data and acquiring the new data", including at least any one of these.

[0082] Some or all of the above embodiments can also be described as follows in the appended claims, but are not limited thereto. 1. An acquisition means for acquiring vehicle state data of each vehicle when each of a plurality of vehicles travels through a measurement position; A generation means for generating a detection model for detecting internal abnormalities of a vehicle based on the acquired vehicle state data; A detection means for performing a process of detecting an internal abnormality of the target vehicle based on the detection model and the vehicle state data when the target vehicle travels through the measurement position; An output means for outputting the result of the detection; A detection device having the above. 2. The acquisition means acquires vehicle state data of each vehicle when each of a plurality of vehicles travels through each of the plurality of measurement positions, The generation means generates the detection model for each measurement position. The detection device according to 1. 3. The output means notifies the user of the detection result when an internal abnormality is detected. The detection device according to 1 or 2. 4. The generation means groups vehicles based on vehicle attribute data and generates the detection model for each group. The detection device according to any one of 1 to 3. 5. The vehicle attribute data includes at least one of vehicle type, model year, model, vehicle classification, and vehicle interior state. The detection device according to 4. 6. The detection means specifies the type of internal abnormality of the vehicle. The detection device according to any one of 1 to 5. 7. The detection means detects an internal abnormality of the target vehicle based on each of the vehicle state data when the target vehicle travels through each of the plurality of measurement positions, and integrates the results of the plurality of detections to detect an internal abnormality of the target vehicle. The detection device according to any one of 1 to 6. 8. The acquisition means acquires vehicle state data acquired by a fixed-point observation device installed at the measurement position from a vehicle traveling through the measurement position via vehicle-to-roadside communication. The detection device according to any one of 1 to 7. 9. A computer, acquires vehicle state data of each vehicle when each of a plurality of vehicles travels through a measurement position, generates a detection model for detecting an internal abnormality of a vehicle based on the acquired vehicle state data, Based on the detection model and the vehicle state data when the target vehicle travels through the measurement position, perform a process of detecting internal abnormalities of the target vehicle, A detection method for outputting the result of the detection. 10. A computer, An acquisition means for acquiring vehicle state data of each vehicle when each of a plurality of vehicles travels through the measurement position, A generation means for generating a detection model for detecting internal abnormalities of a vehicle based on the acquired vehicle state data, A detection means for performing a process of detecting internal abnormalities of the target vehicle based on the detection model and the vehicle state data when the target vehicle travels through the measurement position, An output means for outputting the result of the detection, A program that functions as such.

Explanation of Signs

[0083] 10 Vehicle-mounted device 11 Acquisition unit 12 Generation unit 13 Detection unit 14 Output unit 15 Storage unit 1A Processor 2A Memory 3A Input / output I / F 4A Peripheral circuit 5A Bus

Claims

1. Acquisition means for acquiring vehicle state data of each of a plurality of vehicles when each of the plurality of vehicles travels through a plurality of measurement positions that are predetermined as a ticket vending machine for a parking lot, a fuel dispenser, a railroad crossing, an ETC (Electronic Toll Collection System) toll gate, a stop position at an intersection, a right-turn / left-turn area at an intersection, or a curve position; Generation means for generating, for each of the measurement positions, a detection model for detecting an internal abnormality of a vehicle based on the acquired vehicle state data; Detection means for performing a process of detecting an internal abnormality of the target vehicle based on the detection model and the vehicle state data when the target vehicle travels through the measurement position; Output means for outputting the result of the detection; having; The generation means performs a process of generating, for each of the measurement positions, the detection model for detecting an abnormality of a speed reduction mechanism based on vehicle state data acquired at a ticket vending machine for a parking lot, a fuel dispenser, a railroad crossing, an ETC toll gate, or a stop position at an intersection, or a detection device that executes a process of generating, for each of the measurement positions, the detection model for detecting an abnormality of a steering mechanism based on vehicle state data acquired at a right-turn / left-turn area at an intersection or a curve position.

2. The output means notifies the user of the detection result when an internal abnormality is detected. The detection device according to claim 1.

3. The generation means groups vehicles based on vehicle attribute data and generates the detection model for each group. The detection device according to claim 1 or 2.

4. The vehicle attribute data includes at least one of vehicle type, model year, model, vehicle classification, and vehicle interior state. The detection device according to claim 3.

5. The detection means specifies the type of internal abnormality of the vehicle. The detection device according to any one of claims 1 to 4.

6. The detection means detects internal anomalies of the target vehicle based on each of the vehicle state data when the target vehicle travels through each of the plurality of measurement positions, and integrates the results of the multiple detections to detect internal anomalies of the target vehicle. The detection device according to any one of claims 1 to 5.

7. The acquisition means acquires vehicle state data obtained by a fixed-point observation device installed at the measurement position from a vehicle traveling through the measurement position via vehicle-road communication. The detection device according to any one of claims 1 to 6.

8. A computer A plurality of measurement positions that are pre-determined as a ticket dispenser in a parking lot, a fuel dispenser, a railroad crossing, an ETC toll gate, a stop position at an intersection, a right-turn / left-turn area at an intersection, or a curve position are provided, and vehicle state data of each vehicle when each of the plurality of vehicles travels through the measurement position is acquired. Based on the acquired vehicle state data, a detection model for detecting internal anomalies of the vehicle is generated for each of the measurement positions. Based on the detection model and the vehicle state data when the target vehicle travels through the measurement position, a process for detecting internal anomalies of the target vehicle is performed. The result of the detection is output. In the process of generating the detection model, Based on the vehicle state data acquired at a ticket dispenser in a parking lot, a fuel dispenser, a railroad crossing, an ETC toll gate, or a stop position at an intersection, a process of generating the detection model for detecting anomalies in the reduction mechanism for each of the measurement positions, or Based on the vehicle state data acquired in a right-turn / left-turn area at an intersection or a curve position, a detection method for executing a process of generating the detection model for detecting anomalies in the steering mechanism for each of the measurement positions.

9. A computer A plurality of measurement positions that are pre-determined as a ticket dispenser in a parking lot, a fuel dispenser, a railroad crossing, an ETC toll gate, a stop position at an intersection, a right-turn / left-turn area at an intersection, or a curve position are provided, and an acquisition means for acquiring vehicle state data of each vehicle when each of the plurality of vehicles travels through the measurement position. Generating means for generating a detection model for detecting internal abnormalities of the vehicle for each of the measurement positions based on the acquired vehicle state data; Detection means for performing a process of detecting internal abnormalities of the target vehicle based on the detection model and the vehicle state data when the target vehicle travels through the measurement position; Output means for outputting the result of the detection; Functioning as; The generating means; A process of generating, for each of the measurement positions, the detection model for detecting an abnormality in the deceleration mechanism based on the vehicle state data acquired at a ticket dispenser, a fuel dispenser, a railroad crossing, an ETC tollgate, or a stop position at an intersection, or A program for executing a process of generating, for each of the measurement positions, the detection model for detecting an abnormality in the steering mechanism based on the vehicle state data acquired in a right-turn / left-turn area or a curve position at an intersection.

Images