Information processing apparatus

Abstract

To surely and accurately analyze an abnormal sound while reducing a load on processing.SOLUTION: A controller of the information processing device acquires object recorded data by a microphone provided in an object vehicle. The controller of the information processing device acquires the past recorded data recorded by the microphone provided in the vehicle that has traveled under the same condition as the traveling condition of the object vehicle in the object recorded data. Then, the controller of the information processing device analyzes the abnormal sound in the object vehicle when the difference between the sound indicated by the object recorded data and the sound indicated by the past recorded data exceeds the threshold.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device. [Background technology]

[0002] Patent Document 1 discloses a vehicle information provision system. The vehicle information provision system disclosed in Patent Document 1 includes a communication device, an execution device, and a storage device that stores an analysis model that, when analysis data based on audio recording data of abnormal sounds captured by a microphone mounted on the vehicle is input, determines whether the abnormal sounds recorded in the audio recording data are due to an abnormality requiring repair. In the vehicle information provision system, the execution device executes an acquisition process to acquire analysis data based on the audio recording data received by the communication device. The execution device also executes an abnormality determination process that inputs the analysis data into the analysis model and determines whether the abnormal sounds recorded in the audio recording data are due to an abnormality requiring repair. If the abnormality determination process determines that the abnormal sound is not due to an abnormality requiring repair, the execution device executes an information provision process to provide users who are expected to use the vehicle with abnormal sound information indicating that abnormal sounds may occur, even if they are not an abnormality requiring repair. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2022-95278 Summary of the Invention [Problem to be solved by the invention]

[0004] An object of the present disclosure is to reliably and accurately analyze abnormal noise while reducing the processing load. [Means for solving the problem]

[0005] The information processing device according to the present disclosure includes: An information processing device including a control unit, The control unit Acquiring target recording data using a microphone installed in the target vehicle; Obtaining past recording data from a microphone installed in a vehicle that has traveled under the same conditions as the target vehicle in the target recording data; and analyzing an abnormal sound in the target vehicle when a sound difference between the target recording data and the past recording data exceeds a threshold; is configured to execute [Effects of the Invention]

[0006] The present disclosure makes it possible to reliably and accurately analyze abnormal noise while reducing the processing load. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a diagram showing a schematic configuration of an abnormal sound detection system. [Figure 2] FIG. 2 is a diagram showing an example of a table configuration of vehicle information stored in the auxiliary storage unit. [Figure 3] FIG. 3 is a flowchart of the process executed by the processor. DETAILED DESCRIPTION OF THE INVENTION

[0008] Assume a case where an abnormal noise in a vehicle is analyzed. In this case, if an information processing device is made to perform a process of analyzing an abnormal noise every time the vehicle is driven (hereinafter, sometimes referred to as an "abnormal noise analysis process"), a greater load is placed on the information processing device than when this process is not performed. Furthermore, if there are multiple vehicles and all of the vehicles are subject to the abnormal noise analysis process, the heavy load placed on the information processing device may cause processing to slow down. Furthermore, in this case, it may be necessary to lower the calculation accuracy in order to reduce the load on the information processing device. Therefore, when the information processing device is made to perform the abnormal noise analysis process every time the vehicle is driven, or when the abnormal noise analysis process is performed for all vehicles, it may not be possible to perform a reliable and accurate analysis compared to when this process is not performed.

[0009] Therefore, a control unit of an information processing device according to the present disclosure acquires target recording data from a microphone installed in the target vehicle. The control unit also acquires previously recorded data from a microphone installed in a vehicle that has traveled under the same driving conditions as the target vehicle in the target recording data. If the difference in sound between the target recording data and the previously recorded data exceeds a threshold, the control unit executes an abnormal sound analysis process for the target vehicle.

[0010] If the difference in sound between the target recording data and the previously recorded data exceeds a threshold, it can be inferred that an unusual sound may be occurring in the target vehicle. In this case, an abnormal sound analysis process is executed, which allows for a more detailed analysis of the abnormal sound. This allows the abnormal sound analysis process to be executed for the target vehicle that requires the abnormal sound analysis process. As a result, it is possible to reliably and accurately identify the cause of the abnormal sound while reducing the load on the abnormal sound analysis process.

[0011] Specific embodiments of the present disclosure will be described below with reference to the accompanying drawings. Unless otherwise specified, the hardware configuration, module configuration, functional configuration, etc. described in each embodiment are not intended to limit the technical scope of the disclosure to those configurations.

[0012] <Embodiment> An abnormal sound detection system 1 in this embodiment will be described with reference to Fig. 1 and Fig. 2. Fig. 1 is a diagram showing a schematic configuration of the abnormal sound detection system 1. The abnormal sound detection system 1 is configured to include a plurality of on-board devices 100 and a server 200. In the abnormal sound detection system 1, the plurality of on-board devices 100 and the server 200 are connected to each other via a network N1. The network N1 may be, for example, a WAN (Wide Area Network), which is a global public communication network such as the Internet, or a telephone communication network such as a mobile phone.

[0013] (In-vehicle device) The in-vehicle device 100 is a device mounted on the vehicle 10. The in-vehicle device 100 is a recording device for recording sounds generated when the vehicle 10 is traveling. The in-vehicle device 100 transmits sound data (recorded data) recorded by at least one microphone to the server 200 in real time via the network N1. Here, the microphone in the vehicle 10 records sounds inside the cabin of the vehicle 10, sounds around the power source, sounds around the drive train, and / or sounds around the tires. The in-vehicle device 100 also transmits driving information of the vehicle 10 to the server 200 in real time via the network N1. The in-vehicle device 100 acquires driving information of the vehicle 10 from an electronic control unit (ECU) of the vehicle 10 via the in-vehicle network.

[0014] Here, the travel information of the vehicle 10 includes, for example, the speed, acceleration, steering angle, uphill / downhill conditions, brake operation amount, and gear position of the vehicle 10. The travel information of the vehicle 10 also includes moving images of the surroundings of the vehicle 10 captured by a camera mounted on the vehicle 10. In this embodiment, the vehicle 10 is a bus. The multiple vehicles 10 are, for example, vehicles of the same type. Vehicle The vehicle 10 travels along a predetermined route. The vehicle 10 does not necessarily have to be a bus. The vehicle 10 may be a vehicle other than a bus.

[0015] (server) The server 200 is a device that analyzes abnormal sounds generated in the vehicle 10. Here, the server 200 acquires data on sounds generated in the vehicle 10 and driving information of the vehicle 10, and uses these to perform an analysis process of the abnormal sounds generated in the vehicle 10 (hereinafter, may be referred to as "abnormal sound analysis process"). Here, the server 200 receives data on sounds (recorded data) generated in the vehicle 10 from the in-vehicle device 100 via the network N1. The server 200 also receives driving information on the vehicle 10 from the in-vehicle device 100 via the network N1. The abnormal sound analysis process is a process that determines whether or not an abnormal sound has occurred due to a malfunction or the like of the vehicle 10, and identifies the cause of the abnormal sound.

[0016] In this case, it is assumed that the server 200 executes the abnormal sound analysis process every time the vehicle 10 travels. If the server 200 executes the abnormal sound analysis process every time the vehicle 10 travels, the load on the server 200 will be greater than if the server 200 does not execute the abnormal sound analysis process every time the vehicle 10 travels. Furthermore, if there are multiple vehicles 10 that are targets for the abnormal sound analysis process by the server 200 and the abnormal sound analysis process is executed for all of the vehicles 10, the load on the server 200 may cause processing to slow down. Furthermore, in order to reduce the load on the server 200, it may be necessary to lower the calculation accuracy. In this case, it is expected that the accuracy of the abnormal sound analysis will be lower than if the calculation accuracy is not lowered. Therefore, if the server 200 executes the abnormal sound analysis process every time the vehicle 10 travels, or if the server 200 executes the abnormal sound analysis process for all of the vehicles 10, it may not be possible to perform a reliable and accurate analysis compared to if the server 200 does not execute the abnormal sound analysis process.

[0017] However, for example, when abnormal sound analysis processing is performed on a randomly selected vehicle 10, the abnormal sound analysis processing will not be performed even if an abnormal sound is occurring in a vehicle 10 that was not selected. Also, for example, when abnormal sound analysis is performed on a vehicle 10 that has been driven a predetermined number of times, the abnormal sound analysis processing will not be performed even if an abnormal sound is occurring in a vehicle 10 that has been driven less than the predetermined number of times. In this case, particularly when the vehicle 10 does not have a driver or manager on board, there is a risk that the vehicle 10 will continue to operate while an abnormal sound is occurring.

[0018] Therefore, the server 200 executes an abnormal sound analysis process when the difference in sound between the recorded data received from the in-vehicle device 100 (hereinafter sometimes referred to as "target recorded data") and the previously recorded data exceeds a threshold. Here, the target recorded data is data recorded by the in-vehicle device 100 in the vehicle 10 that is the target of the abnormal sound analysis process (hereinafter sometimes referred to as "target vehicle 10"). The previously recorded data is data previously recorded by the in-vehicle device 100 in the target vehicle 10 or a vehicle 10 other than the target vehicle 10. The previously recorded data is data recorded when the target vehicle 10 or a vehicle 10 other than the target vehicle 10 traveled under the same driving conditions as the target vehicle 10. In other words, before executing the abnormal sound analysis process, which has a high computational cost, the server 200 executes a process of determining whether the difference in sound exceeds a threshold, which is a process with a lower computational cost than the abnormal sound analysis process. The method by which the server 200 determines whether the difference in sound between the recorded data received from the in-vehicle device 100 and the previously recorded data exceeds a threshold, and the method of the abnormal sound analysis process will be described in detail below.

[0019] The server 200 includes a computer having a processor 210, a main memory 220, an auxiliary memory 230, and a communication interface (communication I / F) 240. The processor 210 is, for example, a CPU (Central Processing Unit) or a DSP (Digital Signal Processor). The main memory 220 is, for example, a RAM (Random Access Memory). Auxiliary memory The auxiliary storage unit 230 is, for example, a ROM (Read Only Memory). The auxiliary storage unit 230 is, for example, a hard disk drive (HDD) or a disk recording medium such as a CD-ROM, a DVD disk, or a Blu-ray disk. The auxiliary storage unit 230 may also be a removable medium (portable storage medium). Examples of removable media include a USB memory or an SD card. The communication I / F 240 is, for example, a LAN (Local Area Network) interface board or a wireless communication circuit for wireless communication.

[0020] In the server 200, the auxiliary storage unit 230 stores an operating system (OS), various programs, various information tables, and the like. In addition, in the server 200, the processor 210 loads the programs stored in the auxiliary storage unit 230 into the main storage unit 220 and executes them, thereby realizing various functions as described below. However, some or all of the functions of the server 200 may be realized by hardware circuits such as ASICs or FPGAs. Note that the server 200 does not necessarily have to be realized by a single physical configuration, and may be configured by multiple computers that work together.

[0021] Fig. 2 is a diagram showing an example of a table configuration of vehicle information stored in the auxiliary storage unit 230. As shown in Fig. 2, the vehicle information has a vehicle ID field, a date and time field, a route ID field, a weather field, a recording data field, and a driving information field.

[0022] The vehicle ID field stores an identifier (vehicle ID) for identifying the vehicle 10. The vehicle field stores vehicle IDs for multiple vehicles 10. The date and time field stores information indicating the date and time (period) when the vehicle 10 with the corresponding vehicle ID traveled. The route ID field stores an identifier (route ID) for identifying the route traveled by the vehicle 10 with the corresponding vehicle ID.

[0023] The weather ID field stores information indicating the weather when the vehicle 10 with the corresponding vehicle ID traveled along the route with the corresponding route ID at the corresponding date and time. Here, the weather field stores information such as the amount of rainfall or temperature at the corresponding date and time. The audio recording data field stores audio recording data when the vehicle 10 with the corresponding vehicle ID traveled along the route with the corresponding route ID at the corresponding date and time. The driving information field stores driving information when the vehicle 10 with the corresponding vehicle ID traveled along the route with the corresponding route ID.

[0024] When processor 210 receives audio recording data from in-vehicle device 100 via communication I / F 240, it stores the audio recording data in the audio recording data field of the vehicle information. When processor 210 receives driving information from in-vehicle device 100 via communication I / F 240, it stores the driving information in the driving information field of the vehicle information. In this way, processor 210 updates the vehicle information as it receives audio recording data and driving information.

[0025] The processor 210 acquires the past recording data from the vehicle information stored in the auxiliary storage unit 230. Specifically, the processor 210 refers to the route ID field of the vehicle information and identifies vehicles 10 that have traveled the same route as the route on which the target vehicle 10 is traveling (hereinafter, may be referred to as the "target route"). Furthermore, the processor 210 identifies, from among the identified vehicles 10, vehicles 10 that have traveled in the same weather and time period as when the target vehicle 10 traveled. In this way, the processor 210 identifies vehicles 10 that have traveled under the same driving conditions as the target vehicle 10. Then, the processor 210 acquires the recording data from when the identified vehicle 10 traveled as the past recording data.

[0026] Here, there may be a plurality of vehicles 10 that have traveled on the target route in the same weather and at the same time as the target vehicle 10. In this case, the processor 210 may, for example, acquire audio recording data from the in-vehicle device 100 mounted on the target vehicle 10 among the plurality of vehicles 10 as the past audio recording data. Furthermore, the processor 210 may, for example, acquire audio recording data from the plurality of in-vehicle devices 100 mounted on each vehicle 10 as the past audio recording data. In other words, the processor 210 may acquire a plurality of audio recording data as the past audio recording data.

[0027] Here, the previously recorded data is data recorded by a vehicle 10 that traveled under the same travel conditions as the target vehicle 10 in the target recorded data, and therefore it is assumed that the data is similar to the sound made when the target vehicle 10 is traveling along the target route. Specifically, since the vehicle 10 is the same model of bus as the target vehicle 10, it is assumed that the sound represented by the acquired previously recorded data is similar to the sound made when the target vehicle 10 is traveling along the target route. Furthermore, since the previously recorded data is acquired under the same weather conditions and time of day as when the target vehicle 10 is traveling along the target route, it is assumed that the sound represented by the previously recorded data is similar to the sound made when the target vehicle 10 is traveling along the target route.

[0028] In this embodiment, the driving conditions are that the vehicles are the same type, that they are traveling on the target route, that the weather is the same, and that they are traveling at the same time of day. However, the driving conditions may be at least one of that the vehicles are the same type, that they are traveling on the target route, that the weather is the same, and that they are traveling at the same time of day. The driving conditions may also include other conditions. The driving conditions may include, for example, that the road surface conditions are the same, or that the tire wear conditions are the same, etc.

[0029] Therefore, the processor 210 refers to the target recording data and the previously recorded data installed in the target vehicle 10, and compares the sounds of the target recording data and the previously recorded data. The processor 210 then determines whether the difference in sound between the target recording data and the previously recorded data exceeds a threshold value.

[0030] Here, when a plurality of pieces of recorded data are acquired as previously recorded data, the processor 210 determines whether the difference in sound between the target recorded data and each piece of previously recorded data exceeds a threshold. Then, for example, when a predetermined percentage or more of previously recorded data have a sound difference with the target recorded data that exceeds the threshold, the processor 210 determines that the difference in sound between the target recorded data and the previously recorded data exceeds the threshold.

[0031] The processor 210 determines whether the difference in sound between the target recorded data and the previously recorded data exceeds a threshold, for example, by determining whether a sound of a frequency not included in the sound represented by the previously recorded data exists for a predetermined period of time or more. The processor 210 also determines whether the loudness of a specific sound included in the sound represented by the target recorded data is equal to or greater than a threshold, compared to the sound represented by the previously recorded data. In this manner, it may be determined whether the difference in sound between the target recorded data and the previously recorded data exceeds a threshold. The processor 210 may also use voice recognition software to remove sounds such as conversations by passengers in the vehicle 10 or in-car announcements from the previously recorded data and the target recorded data. This allows for determination processing based on sounds generated from the vehicle 10 (target vehicle 10).

[0032] The processor 210 may change the threshold value according to the moving image of the surroundings of the target vehicle 10 included in the driving information. In this case, the processor 210 changes the threshold value according to, for example, the roughness of the road surface on which the target vehicle 10 is driving, which is acquired by image recognition processing. This makes it possible to prevent the sound difference between the target recording data and the past recording data from being easily determined to exceed the threshold value when an unusual sound is generated due to a rough road surface. The processor 210 also changes the threshold value according to the weather at the location where the target vehicle 10 is located. The threshold value may be changed accordingly. This makes it possible to prevent the likelihood of determining that the difference in sound between the target recorded data and the previously recorded data exceeds the threshold value when an unusual sound such as wipers or rain is occurring. The processor 210 may also change the threshold value according to deterioration over time in the target vehicle 10. This makes it possible to prevent the likelihood of determining that the difference in sound between the target recorded data and the previously recorded data exceeds the threshold value when a sound other than an abnormal sound that occurs due to deterioration over time is occurring.

[0033] If the difference in sound between the target recorded data and the previously recorded data exceeds a threshold, the processor 210 executes an abnormal sound analysis process using the target recorded data stored in the vehicle information held in the auxiliary storage unit 230 and the driving information of the target vehicle 10 as analysis data. Specifically, the processor 210 inputs the analysis data into an analysis model to identify whether or not an abnormal sound has occurred and the cause of the abnormal sound. Here, the analysis model is, for example, a machine learning model that has been trained in advance using training data that associates the recorded data and driving information with the whether or not an abnormal sound has occurred and the cause of the abnormal sound.

[0034] If an abnormal noise is occurring in the target vehicle 10, the processor 210 outputs abnormal noise information indicating the occurrence of the abnormal noise and the cause of the abnormal noise. The processor 210 may, for example, output the abnormal noise information to an external device via the communication I / F 240, or may output (display) malfunction information on a display or the like connected to the processor 210. In this way, the manager or the like of the target vehicle 10 can know that an abnormal noise is occurring in the target vehicle 10. The abnormal noise information may also include a request for maintenance to a maintenance shop. In this case, the abnormal noise information may include, for example, a request to replace a malfunctioning part that is thought to be the cause of the abnormal noise.

[0035] (flowchart) Next, the processing executed by the processor 210 in the server 200 in the abnormal sound detection system 1 will be described with reference to Fig. 3. Fig. 3 is a flowchart of the processing executed by the processor 210. This processing is for determining whether or not to execute abnormal sound analysis processing. Furthermore, this processing is for executing the abnormal sound analysis processing when it is determined that the abnormal sound analysis processing should be executed. Execution of this processing is initiated, for example, when the target vehicle 10 has finished traveling along the target route.

[0036] 3, first, in S101, target recorded data is acquired. Here, the target recorded data may be acquired directly from the target vehicle 10 via the communication I / F 240. Alternatively, the target recorded data may be acquired from the vehicle information in the auxiliary storage unit 230. In this case, the processor 210 stores the target recorded data received in real time in the vehicle information in real time. Furthermore, in S102, past recorded data is acquired from the vehicle information stored in the auxiliary storage unit 230.

[0037] Next, in S103, it is determined whether the difference in sound between the target recorded data and the previously recorded data exceeds a threshold value based on the target recorded data and the previously recorded data. If a negative determination is made in S103, it is assumed that no abnormal noise is occurring in the target vehicle 10. Therefore, if a negative determination is made in S103, the processing shown in FIG. 3 is terminated.

[0038] Furthermore, if a positive determination is made in S103, the driving information is acquired in the process of S104. Here, the driving information may be acquired directly from the target vehicle 10 via the communication I / F 240. Alternatively, the driving information may be acquired from the vehicle information in the auxiliary storage unit 230. In this case, the processor 210 stores the driving information received in real time in the vehicle information in real time. Next, in S105, an abnormal sound analysis process is executed using the target recorded data and the driving information.

[0039] In this embodiment, the processor 210 determines whether the difference in sound between the target recording data and the previously recorded data exceeds a threshold in the process of S103. At this time, there are cases where the difference in sound between the target recording data and the previously recorded data is equal to the threshold. In this case, the processor 210 may make a negative determination or a positive determination in the process of S103.

[0040] Next, in S106, it is determined whether or not the occurrence of an abnormal sound has been detected in the abnormal sound analysis process. If a negative determination is made in S106, no abnormal sound is occurring in the target vehicle 10. The process shown in FIG. 3 is then terminated. If a positive determination is made in S106, the cause of the abnormal sound is identified in S107. Next, in S108, abnormal sound information indicating the occurrence of the abnormal sound and the identified cause of the abnormal sound is output. Then, the process shown in FIG. 3 is terminated.

[0041] As described above, in the abnormal sound detection system 1, the abnormal sound analysis process is executed when the difference in sound between the target recorded data and the previously recorded data exceeds a threshold. Furthermore, the abnormal sound analysis process is not executed when the difference in sound between the target recorded data and the previously recorded data is less than a threshold. In other words, the abnormal sound analysis process is executed when a difference exceeding a threshold exists between the sound produced when the vehicle 10 is traveling under the same driving conditions as the target vehicle 10 and the sound recorded by a microphone in the target vehicle 10, suggesting that an unusual sound may be occurring in the target vehicle 10. This makes it possible to execute the abnormal sound analysis process for the target vehicle 10 that is generating an unusual sound. As a result, it is possible to reliably and accurately identify the cause of the abnormal sound while reducing the load on the abnormal sound analysis process.

[0042] (Variation) In this embodiment, the processing shown in Fig. 3 begins when the target vehicle 10 finishes traveling along the target route. On the other hand, in this modified example, the processing shown in Fig. 3 is executed in real time. In this case, the processor 210 uses the target recorded data received in real time and the previously recorded data obtained from the vehicle information stored in the auxiliary storage unit 230 to determine whether the difference in sound between the target recorded data and the previously recorded data exceeds a threshold. Then, the processor 210 executes abnormal sound analysis processing if the difference in sound between the target recorded data and the previously recorded data exceeds the threshold. Even in this way, it is possible to reliably and accurately identify the cause of the abnormal sound while reducing the load on the abnormal sound analysis processing.

[0043] <Other embodiments> The above-described embodiment is merely an example, and the present disclosure may be modified as appropriate within the scope of the present disclosure. Furthermore, the processes and means described in the present disclosure may be freely combined and implemented as long as no technical contradiction occurs.

[0044] Furthermore, a process described as being performed by one device may be shared and executed by multiple devices. Alternatively, a process described as being performed by different devices may be executed by a single device. In a computer system, the hardware configuration (server configuration) by which each function is realized can be flexibly changed.

[0045] The present disclosure can also be realized by supplying a computer program that implements the functions described in the above embodiments to a computer, and having one or more processors in the computer read and execute the program. Such a computer program may be provided to the computer by a non-transitory computer-readable storage medium connectable to the system bus of the computer, or may be provided to the computer via a network. A non-transitory computer-readable storage medium includes any type of medium suitable for storing electronic instructions, such as, for example, a magnetic disk (such as a floppy disk or a hard disk drive (HDD)), any type of disk, such as an optical disk (such as a CD-ROM, a DVD disk, or a Blu-ray disk), a read-only memory (ROM), a random-access memory (RAM), an EPROM, an EEPROM, a magnetic card, a flash memory, or an optical card. [Explanation of symbols]

[0046] 1. Abnormal noise detection system 10. Vehicle 100...In-vehicle equipment 200 Server 210 processor 220 Main memory 230...Auxiliary storage section 240··Communication I / F

Claims

[Claim 1] An information processing device including a control unit, The control unit Acquiring target recording data using a microphone installed in the target vehicle; Obtaining past recording data from a microphone installed in a vehicle that has traveled under the same conditions as the target vehicle in the target recording data; and analyzing an abnormal sound in the target vehicle when a sound difference between the target recording data and the past recording data exceeds a threshold; configured to perform Information processing device.

Images