Information processing apparatus

Abstract

The invention provides an information processing apparatus. Data for analyzing factors for a specific differential state of a differential device is extracted from raw data. An information processing device executes: a step (S110) for setting a plurality of time windows for cutting out data from raw data, using, as feature quantities, a rotational speed difference between a first rotational shaft and a second rotational shaft included in the raw data, and information relating to a factor for causing the differential device to be in a specific differential state; a step (S120) for cutting out data from the original data; a step (S130) for calculating the frequency distribution of the raw data and the frequency distribution of the extracted data for each feature amount; and a step (S140 and S150) for determining whether the original data and the extracted data are similar using an error in the frequency distribution. The information processing device repeatedly executes steps S110-S150 by changing settings of a plurality of time windows, and extracts extracted data similar to the original data from the original data.

Description

Technical Field

[0001] This invention relates to an information processing device. Background Technology

[0002] Patent Document 1 discloses an information processing device that reduces the size of the data to be analyzed by compressing the raw data. The raw data to be analyzed is data collected continuously for a predetermined period using sensors mounted on a vehicle.

[0003] The information processing device disclosed in Patent Document 1 compresses data by extracting data obtained at the time point when a certain vehicle speed is reached and data obtained at the time point when the vehicle speed inflection point from the original data.

[0004] Existing technical documents

[0005] Patent documents

[0006] Patent Document 1: Japanese Patent Application Publication No. 2008-108247 Summary of the Invention

[0007] The differential device mounted on the vehicle enables differential rotation between the first and second rotating shafts. When analyzing the factors that cause the differential device to reach a specific differential state, if data suitable for analyzing these factors can be extracted from the raw data, the factors can be analyzed in a shorter time compared to using the raw data. The aforementioned information processing device uses extracted data to analyze the driving speed pattern. Therefore, the aforementioned information processing device cannot extract data suitable for analyzing these factors as a specific differential state from the raw data.

[0008] An information processing apparatus for solving the above-mentioned problem acquires raw data collected continuously for a predetermined period using sensors mounted on a vehicle, and extracts data from the raw data for analyzing factors that constitute a specific differential state of a differential device mounted on the vehicle capable of differential rotation between a first rotating shaft and a second rotating shaft. The information processing apparatus includes a processing circuit. The processing circuit performs a first step of calculating, for each feature quantity, the frequency distribution of the raw data for the multiple feature quantities, including the rotational speed difference between the first and second rotating shafts and information related to factors constituting the specific differential state, contained in the raw data, and repeatedly performs the following steps: a second step of setting multiple time windows such that the sum of the periods of all the time windows is shorter than the predetermined period, from which a portion of the period of the raw data is cut out; and a third step of cutting data from the raw data through the multiple time windows. Step 4: Calculate the frequency distribution of the extracted data for each of the multiple features, which is formed by combining all data extracted through the multiple time windows; Step 5: Calculate the errors of the frequency distribution of each feature in the original data and the frequency distribution of each feature in the extracted data; and Step 6: Determine whether the original data and the extracted data are similar based on the errors, and extract the extracted data when the original data and the extracted data are determined to be similar as the data extracted for analyzing the factors that constitute the specific differential state.

[0009] According to the aforementioned information processing device, it is possible to extract data from the raw data that is suitable for analyzing the factors that cause the differential device to become a specific differential state. Attached Figure Description

[0010] Figure 1 This is a schematic diagram illustrating the relationship between a data center, a vehicle, and an information processing terminal as one embodiment of an information processing device.

[0011] Figure 2 The graph shows a portion of the raw data. (a) shows the shift of the first speed difference, (b) shows the shift of the acceleration operation amount, (c) shows the shift of the steering angle, and (d) shows the shift of the yaw rate.

[0012] Figure 3 This is a flowchart illustrating the processing flow performed by the processing circuitry of a data center.

[0013] Figure 4 It is the frequency distribution of the first rotational speed difference in the original data.

[0014] Figure 5 It is the frequency distribution of the acceleration operations in the original data. Detailed Implementation

[0015] The following is for reference Figures 1-5 This describes one implementation of an information processing device.

[0016] <Structure of Information Processing Systems>

[0017] Figure 1 The structure of the information processing system is shown. The information processing system includes: a data center 500 with information processing devices, an information processing terminal 600, multiple vehicles 10, and a communication network 400. The data center 500 can communicate with the multiple vehicles 10 and the information processing terminal 600 via the communication network 400.

[0018] <Data Center 500 Structure>

[0019] like Figure 1 As shown, the data center 500 includes a processing circuit 510, a storage device 520, and a communication device 530. The processing circuit 510 is an information processing device, equipped with a CPU that executes processing according to a program and a ROM storing the program. The storage device 520 can store a large amount of data. The communication device 530 performs wired or wireless communication via a communication network 400. The communication device 530 includes hardware such as a network adapter, various communication software, or combinations thereof.

[0020] <Structure of Information Processing Terminal 600>

[0021] As shown in Figure 1, the information processing terminal 600 includes a processing circuit 610, a storage device 620, and a communication device 630. The processing circuit 610 includes a CPU that executes processing according to a program and a ROM storing the program. The storage device 620 can store a large amount of data. The communication device 630 performs wired or wireless communication via a communication network 400. The communication device 630 includes hardware such as a network adapter, various communication software, or combinations thereof. The information processing terminal 600 is, for example, a personal computer.

[0022] <Structure of Vehicle 10>

[0023] Vehicle 10 is equipped with a communication device 99. The communication device 99 transmits data acquired by vehicle 10 and identification information of vehicle 10 to data center 500 via communication network 400.

[0024] Vehicle 10 is a four-wheel drive vehicle with the right front wheel 11FR and the left front wheel 11FL as the front wheels 11F, and the right rear wheel 11RR and the left rear wheel 11RL as the rear wheels 11R.

[0025] As an example of the prime mover mounted on vehicle 10, the output shaft of internal combustion engine 21 is connected to transmission 30.

[0026] The output shaft of the transmission 30 is connected to the transfer case 40, which distributes the torque generated by the internal combustion engine 21 to the front wheels 11F and the rear wheels 11R.

[0027] The transfer case 40 connects a front driveshaft 22F, which is connected to the front wheel differential gear (hereinafter referred to as the front wheel differential) 23, and a rear driveshaft 22R, which is connected to the rear wheel differential gear (hereinafter referred to as the rear wheel differential) 26. The transfer case 40 is a differential device capable of realizing differential rotation between the front driveshaft 22F, which corresponds to the first rotating shaft, and the rear driveshaft 22R, which corresponds to the second rotating shaft.

[0028] The front wheel differential 23 connects a right front drive shaft 24R, which is connected to the right front wheel 11FR, and a left front drive shaft 24L, which is connected to the left front wheel 11FL. The front wheel differential 23 is a differential device that enables differential rotation between the right front drive shaft 24R, which corresponds to the first rotation axis, and the left front drive shaft 24L, which corresponds to the second rotation axis.

[0029] The rear wheel differential 26 connects a right rear drive shaft 27R connected to the right rear wheel 11RR and a left rear drive shaft 27L connected to the left rear wheel 11RL. The rear wheel differential 26 is a differential device capable of achieving differential rotation between the right rear drive shaft 27R, which corresponds to the first rotation axis, and the left rear drive shaft 27L, which corresponds to the second rotation axis.

[0030] The steering mechanism 81 of the vehicle 10 changes the rudder angle of the front wheel 11F, which is the steering wheel, according to the steering angle of the steering device 85.

[0031] The vehicle control unit 90 of the vehicle 10 includes a processing circuit 95. The processing circuit 95 includes a CPU that executes processing according to a program and a ROM storing the program. Furthermore, the vehicle control unit 90 includes multiple sensors that collect data related to the vehicle 10 and the internal combustion engine 21. The vehicle control unit 90 performs various controls related to the vehicle 10 and the internal combustion engine 21.

[0032] One example of the data collected by the vehicle control unit 90 is the travel distance and speed of the vehicle 10. Other examples of the data collected by the vehicle control unit 90 include engine speed difference, acceleration operation amount as the amount of accelerator pedal operation adjusting the output of the internal combustion engine 21, steering angle as the steering angle of the steering device 85, yaw rate of the vehicle 10, and position information of the vehicle 10.

[0033] The aforementioned speed difference includes the first speed difference, the second speed difference, and the third speed difference.

[0034] The first speed difference is the speed difference between the right front drive shaft 24R and the left front drive shaft 24L, which can achieve differential rotation by utilizing the front wheel differential 23.

[0035] The second speed difference is the speed difference between the right rear drive shaft 27R and the left rear drive shaft 27L, which can achieve differential rotation by utilizing the rear wheel differential 26.

[0036] The third speed difference is the speed difference between the front drive shaft 22F and the rear drive shaft 22R, which can achieve differential rotation using the transfer case 40.

[0037] For example, the first speed difference, the second speed difference, and the third speed difference are calculated based on the detection values ​​of the wheel speed sensors respectively installed on the right front wheel 11FR, the left front wheel 11FL, the right rear wheel 11RR, and the left rear wheel 11RL.

[0038] In this embodiment, regarding the steering angle, a positive value represents the steering angle facing the front of vehicle 10 in the right direction, and a negative value represents the steering angle facing the front of vehicle 10 in the left direction. Similarly, regarding the yaw rate, a positive value represents the yaw rate facing the front of vehicle 10 in the right direction, and a negative value represents the yaw rate facing the front of vehicle 10 in the left direction.

[0039] <Data Extraction>

[0040] The information processing terminal 600 is used to analyze the factors that cause the differential to become a specific differential state. Furthermore, the following description will explain the case where the differential being analyzed is the front wheel differential 23, but the differential being analyzed can also be the rear wheel differential 26 or the transfer case 40.

[0041] When analyzing the factors that cause a specific differential state in front wheel differential 23, information processing terminal 600 sends an instruction to data center 500. Upon receiving the instruction, processing circuit 510 of data center 500 performs analysis using a portion of the vast amount of data stored in storage device 520 of data center 500. In accordance with the purpose of analysis, data is selected for use from the vast amount of data stored in storage device 520. This data includes multiple data points collected using multiple sensors mounted on vehicle 10 related to the factors causing a specific differential state in front wheel differential 23. These data are referred to as feature quantities. Processing circuit 510 uses the feature quantities to analyze the factors causing a specific differential state in vehicle 10. In this case, the feature quantities are information related to the first speed difference and the factors causing a specific differential state in front wheel differential 23 within the vehicle 10 being analyzed. The information related to the factors causing this specific differential state includes acceleration operation amount, steering angle, yaw rate, and vehicle 10 position information.

[0042] In order for the processing circuit 510 to analyze the factors that cause the front wheel differential 23 to become a specific differential state in a specific vehicle 10 according to the program, the processing circuit 510 utilizes a large amount of data collected over a long period of time. In this analysis, the processing circuit 510 requires a long time to perform a large number of calculations.

[0043] Therefore, it is considered to extract extractable data that captures the overall characteristics of the original data from the large amount of data that serves as the original data. If such extractable data can be extracted, the processing circuit 510 can perform parsing in a shorter time by using the extracted data.

[0044] Figure 2 This shows a portion of the original data relating to the characteristic quantities that are factors that contribute to a particular differential state of the front wheel differential 23. Figure 2 The raw data shown is a portion of the data from 100,000 hours of data from one vehicle (10). Figure 2 The raw data shown includes, for example, the first speed difference, acceleration operation amount, steering angle, and yaw rate as characteristic quantities.

[0045] Figure 2 (a) shows the first speed difference. Figure 2 (b) shows the amount of acceleration operation. Figure 2 (c) shows the steering angle. Figure 2 (d) The yaw rate is shown. Furthermore, in this embodiment, regarding the steering angle, a positive value represents the steering angle facing the front of vehicle 10 in the right direction, and a negative value represents the steering angle facing the front of vehicle 10 in the left direction. Similarly, regarding the yaw rate, a positive value represents the yaw rate facing the front of vehicle 10 in the right direction, and a negative value represents the yaw rate facing the front of vehicle 10 in the left direction.

[0046] The first speed difference, acceleration operation amount, steering angle, yaw rate, and position information refer to data related to factors that constitute a specific differential state regarding the front wheel differential 23. The processing circuit 510 extracts data from the data, which includes the first speed difference and acceleration operation amount as characteristic quantities, to analyze the factors that constitute a specific differential state.

[0047] Extracted data is created by cutting data from the raw data using multiple time windows. Figure 2 In this example, using multiple time windows as an example, three time windows—W_1 (first time window), W_2 (second time window), and W_3 (third time window)—are represented by double-dotted lines. The start and end points of each time window are set in a way that ensures they do not overlap. In this example, 20,000 hours of data are extracted. Therefore, the start and end points of each time window are set so that the total length of the period formed by summing the durations of all time windows is 20,000 hours.

[0048] Data center 500 searches for the start and end points of each time window in the data extraction pattern used to extract features that capture the overall characteristics of the original data. Data center 500 stores the information of the data extraction pattern used to extract the above-mentioned data in storage device 520. The stored data extraction pattern information is the information on the settings of each time window found through the search.

[0049] The processing circuit 510 extracts data from the raw data based on the cutting mode information stored in the storage device 520.

[0050] <Search Processing in Cutout Mode>

[0051] Figure 3 This is a flowchart illustrating a series of processes related to the search process for the cut-out mode. The processing circuit 510 of the data center 500 executes this series of processes according to the program.

[0052] like Figure 3 As shown, in step S100, the processing circuit 510 obtains the raw data. The raw data is a portion of the data selected from the vast amount of data stored in the storage device 520 of the data center 500, in accordance with the purpose of parsing.

[0053] The raw data used to analyze the factors that make a specific differential state of the front wheel differential 23 of a vehicle 10 is the data of the object of the vehicle 10 selected from the huge data of multiple vehicles 10.

[0054] Next, in the processing of step S110, the processing circuit 510 sets multiple time windows in order to extract data from the raw data.

[0055] exist Figure 2 In the example shown, the duration of each time window is all equal. Figure 2 As shown, the data cut out using each cutout window are data of each feature quantity in the same period.

[0056] Each time step S110 is executed, the processing circuit 510 randomly sets the number of time windows, the start point of each time window, and the end point of each time window. At this time, the processing circuit 510 sets each time window in a manner that prevents them from overlapping. The processing circuit 510 randomly sets multiple time windows in such a way that the sum of the durations of all time windows becomes a preset period. The processing circuit 510 may also, during the processing in step S110, such as... Figure 2 As shown, the duration of each time window is fixed constant, and multiple time windows are set. Alternatively, in step S110, the processing circuit 510 can also set multiple time windows by fixing the number of time windows to a constant value.

[0057] Thus, by setting multiple time windows through step S110, the data cutting mode is determined from the raw data. After determining the cutting mode, the processing circuit 510 causes the processing to proceed to step S120.

[0058] In step S120, the processing circuit 510 extracts data from the original data using a determined extraction mode. That is, in step S120, the processing circuit 510 extracts data from the original data using multiple predefined time windows. Furthermore, the processing circuit 510 combines all the data extracted using the multiple time windows to create the extracted data.

[0059] Next, in step S130, the processing circuit 510 calculates the frequency distribution of the original data and the extracted data for each feature.

[0060] Regarding frequency distribution, the data for each feature quantity is classified into multiple levels, representing the frequency distribution of the number of data at each level. In this embodiment, the feature quantity data are the first speed difference and the acceleration operation amount. Therefore, the frequency distribution of the first speed difference and the frequency distribution of the acceleration operation amount are calculated separately.

[0061] Furthermore, the total frequencies of the features contained in the data differ between the original and extracted data, making it impossible to simply compare the frequency distributions of the original and extracted data. When 20,000 hours of extracted data are drawn from 100,000 hours of original data, the total frequency of the extracted data becomes approximately one-fifth of the total frequency of the original data. In this case, by multiplying the frequencies of each level of the extracted data by five, a frequency distribution of the extracted data with the same total frequency as the original data can be obtained. Even without relying on the above method, it is possible to compare the distribution of data in the original data with the distribution of data in the extracted data by calculating the relative frequency distributions of the original and extracted data. A relative frequency distribution represents the percentage of a particular level's frequency relative to the total frequency.

[0062] Figure 4 The frequency distribution of the first speed difference in the original data is shown. In the frequency distribution of the first speed difference, the first speed difference is divided into m levels from "1" to "m". The frequency distribution of the extracted data of the first speed difference is also calculated using the levels corresponding to those in the original data.

[0063] Figure 5 The frequency distribution of accelerated operations in the original data is shown. In the frequency distribution of accelerated operations, the accelerated operations are divided into m levels from "1" to "m". The frequency distribution of the extracted data of accelerated operations is also calculated using the levels corresponding to those in the original data.

[0064] In execution Figure 3Following the processing in step S130, the processing circuit 510 then executes step S140. In step S140, the processing circuit 510 calculates the error between the frequency distribution of each feature in the original data and the frequency distribution of each feature in the extracted data. For example, the processing circuit 510 calculates the Mean Absolute Error (MAE). The Mean Absolute Error (MAE) is expressed by the following formula.

[0065] Formula 1

[0066]

[0067] In the above formula, "n" is the number of features. In this embodiment, the features are the first speed difference and the acceleration operation amount, so "n" is "2". "m" is the total number of levels in the frequency distribution. "Y" is the frequency of the corresponding feature in the corresponding level in the original data. "y" is the frequency of the corresponding feature in the corresponding level in the extracted data.

[0068] As shown in the formula above, the processing circuit 510 calculates the sum of the errors of the frequencies in each level of each feature quantity of the frequency distribution in the original data and the frequency distribution in the extracted data as the error.

[0069] After calculating the error, the processing circuit 510 proceeds to step S150. In step S150, the processing circuit 510 determines whether the calculated error is below a threshold. The threshold is a value used to determine whether extracted data with a frequency distribution close to the frequency distribution in the original data has been extracted through a set cutting mode. The size of this threshold is preset in a way that allows determination based on whether extracted data with a frequency distribution close to the frequency distribution in the original data has been extracted based on the error being below the threshold.

[0070] In step S150, if the error is determined to be below a threshold (step S150: "Yes"), the processing circuit 510 records the cut-out pattern. Specifically, the processing circuit 510 stores the start and end data of each time window in the cut-out pattern as information for determining the cut-out pattern in the storage device 520. After recording the cut-out pattern, the processing circuit 510 proceeds to step S160.

[0071] On the other hand, in the processing of step S150, if it is determined that the error is greater than the threshold (step S150: "No"), the processing circuit 510 returns the processing to step S110. That is, in order to reset the time window and extract the extracted data from the original data, the processing circuit 510 starts the process of setting multiple new time windows.

[0072] Thus, the processing circuit 510 repeats steps S110 to S150 until it can extract data similar to the original data using the frequency distribution of each feature. As a result, in the storage device 520, the storage error becomes a cut-out mode below the threshold.

[0073] In step S160, the processing circuit 510 extracts data from the original data according to the data extraction pattern stored in the storage device 520, which is similar to the original data.

[0074] After the processing in step S160 is performed, the processing circuit 510 terminates the above-mentioned series of program-based processes.

[0075] In this way, the processing circuit 510 extracts data for analyzing the factors that determine the specific differential state of the front wheel differential 23.

[0076] <The function of this implementation method>

[0077] The data center 500, which is the information processing device in this embodiment, acquires raw data collected continuously over a predetermined period using multiple sensors mounted on the vehicle 10. Furthermore, the data center 500 extracts data from the raw data to analyze factors that determine the specific differential state of the front wheel differential 23.

[0078] Data center 500 includes processing circuitry 510. In the raw data, multiple characteristic quantities are included, such as a first speed difference and information related to factors affecting a specific differential state regarding the front wheel differential 23. In this data center 500, processing circuitry 510 performs a search process. This search process includes a first step (step S130) of calculating the frequency distribution in the raw data for each characteristic quantity.

[0079] The search process includes a second step (step S110) in which multiple time windows are cut from a portion of the original data in such a way that the sum of the periods of all time windows is shorter than the overall period of the original data.

[0080] The search process includes a third step (step S120) which involves extracting data from the original data using multiple time windows. The extracted data is the data obtained by combining all the data extracted using the multiple time windows.

[0081] The search process includes a fourth step (step S130) that calculates the frequency distribution in the extracted data for each feature.

[0082] The search process includes step 5 (step S140), which calculates the errors of the frequency distribution of each feature in the original data and the frequency distribution of each feature in the extracted data.

[0083] The search process includes step 6 (step S150) which determines whether the original data and the extracted data are similar based on the aforementioned errors.

[0084] After executing step 1, processing circuit 510 performs a search process that repeatedly executes steps 2 to 6 by changing the settings of multiple time windows. Furthermore, processing circuit 510 extracts data that is determined to be similar to the original data and the extracted data as data for analyzing factors that contribute to the specific differential state of the front wheel differential 23 (step S160).

[0085] The data center 500 is capable of using extracted data, similar to the distribution of characteristic quantities related to the factors contributing to a specific differential state of the front wheel differential 23, to perform analysis of the factors contributing to such a specific differential state. Therefore, the data center 500 can obtain analytical results that closely approximate the results of analysis of the factors contributing to a specific differential state of the front wheel differential 23 using the original data.

[0086] The extracted data from data center 500 is data obtained by cutting out a portion of the original data. Therefore, the extracted data is less in size compared to the original data. The more data used in the analysis, the longer the processing time required to analyze the factors that make the front wheel differential 23 a specific differential state. By using extracted data, data center 500 can shorten the analysis time compared to using the original data.

[0087] <Effects of this implementation method>

[0088] (1) Based on the data center 500, based on multiple feature quantities including the first speed difference and information related to the factors that make the front wheel differential 23 a specific differential state, it is determined whether the original data and the extracted data are similar. Therefore, it is possible to extract data from the original data that is suitable for analyzing the factors that make the front wheel differential 23 a specific differential state.

[0089] (2) The information related to the factors that constitute the specific differential state mentioned above is the acceleration operation amount. Therefore, it is possible to extract data suitable for analyzing whether the factors that constitute the specific differential state are caused by the driver's acceleration operation.

[0090] <Example of Change>

[0091] Furthermore, this embodiment can be implemented with modifications as described below. This embodiment and the following modifications can be combined with each other to the extent that they are not technically contradictory.

[0092] ■The information related to the factors that constitute the specific differential state mentioned above when extracting data can also be the steering angle. In this case, during the processing in step S130, the processing circuit 510 calculates the frequency distribution of the steering angle instead of the frequency distribution of the acceleration operation amount in the original data and the extracted data. Furthermore, during the error calculation in step S140, the processing circuit 510 calculates the error between the frequency distribution of the steering angle in the original data and the frequency distribution of the steering angle in the extracted data instead of the error in the frequency distribution of the acceleration operation amount. According to this modified example, data suitable for analyzing whether the factors that constitute the specific differential state of the front wheel differential 23 are caused by the driver's turning operation can be extracted.

[0093] ■The information related to the factors that constitute the specific differential state described above when extracting data may also be the yaw rate of vehicle 10. In this case, during the processing in step S130, the processing circuit 510 calculates the frequency distribution of the yaw rate instead of the frequency distribution of the acceleration operation amount in the original data and the extracted data. Furthermore, during the error calculation in step S140, the processing circuit 510 calculates the error between the frequency distribution of the yaw rate in the original data and the frequency distribution of the yaw rate in the extracted data instead of the error in the frequency distribution of the acceleration operation amount. According to this modified example, data suitable for analyzing whether the factors that constitute the specific differential state of the front wheel differential 23 are caused by the turning of vehicle 10 can be extracted.

[0094] ■The information related to the factors that cause the aforementioned specific differential state when extracting data can also be the position information of vehicle 10. According to this modified example, it is possible to extract data suitable for analyzing whether the factors that cause the specific differential state of the front wheel differential 23 are caused by the location of vehicle 10.

[0095] ■The processing circuit 510 described above calculates the frequency distribution using the first speed difference as a characteristic quantity. Alternatively, the processing circuit 510 may use the second speed difference as a characteristic quantity instead of the first speed difference to calculate the frequency distribution. Furthermore, the processing circuit 510 may use the third speed difference as a characteristic quantity instead of the first speed difference to calculate the frequency distribution.

[0096] ■ In the above embodiment, an example of embodying the information processing device as a data center 500 is shown. Alternatively, the information processing device can also be embodying as an information processing terminal 600. In this case, the processing circuit 610 of the information processing terminal 600... Figure 3 In step S100, raw data is obtained from the data center 500. Furthermore, the processing circuit 610 executes... Figure 3The processing after step S110 shown. Alternatively, the aforementioned information processing device can also be implemented as a control device for the vehicle 10. In this case, for example, the processing circuit 95 of the vehicle control unit 90 of the vehicle 10... Figure 3 In step S100, raw data is obtained from the data center 500. Furthermore, the processing circuit 95 executes... Figure 3 The processing after step S110 shown.

[0097] ■ The aforementioned data center 500 determines the similarity between the original data and the extracted data by calculating the error in the frequency distribution. Alternatively, the data center 500 can determine the similarity between the original data and the extracted data without calculating the error. For example, statistical methods such as goodness-of-fit tests can be used to determine similarity when the difference between the original data and the extracted data is not significant.

[0098] ■The prime mover mounted on vehicle 10 can also be an electric motor.

[0099] ■ Vehicle 10 can also be a front-wheel drive vehicle. Alternatively, vehicle 10 can also be a rear-wheel drive vehicle.

[0100] (Symbol Explanation)

[0101] 10: Vehicle; 11FL: Left front wheel; 11FR: Right front wheel; 11RL: Left rear wheel; 11RR: Right rear wheel; 21: Internal combustion engine; 22F: Front drive shaft; 22R: Rear drive shaft; 23: Front wheel differential gear; 24L: Left front drive shaft; 24R: Right front drive shaft; 26: Rear wheel differential gear; 27L: Left rear drive shaft; 27R: Right rear drive shaft; 30: Transmission; 40: Transfer case; 81: Steering mechanism; 85: Steering device; 90: Vehicle control unit; 95: Processing circuit; 99: Communication device; 400: Communication network; 500: Data center; 510: Processing circuit; 520: Storage device; 530: Communication device; 600: Information processing terminal; 610: Processing circuit; 620: Storage device; 630: Communication device.

Claims

1. An information processing device, Raw data collected continuously over a predetermined period using sensors mounted on the vehicle is acquired. From this raw data, data is extracted to analyze factors constituting a specific differential state of the differential device mounted on the vehicle, capable of differential rotation between a first rotating shaft and a second rotating shaft. The information processing device includes a processing circuit. The processing circuit: The first step involves calculating the frequency distribution of the original data for each of the multiple feature quantities, including the speed difference between the first and second rotating axes and information related to factors constituting the specific differential state, contained in the original data, and repeating this process by varying the settings of multiple time windows. Step 2 involves setting multiple time windows to cut out data from a portion of the original data in such a way that the sum of the periods of all the time windows is shorter than the predetermined period. Step 3: Extract data from the original data through the multiple time windows; Step 4: Calculate the frequency distribution of the extracted data, which is formed by combining all the data extracted through the multiple time windows for each feature; Step 5: Calculate the errors of the frequency distribution of each feature in the original data and the frequency distribution of each feature in the extracted data. And in step 6, based on the aforementioned errors, determine whether the original data and the extracted data are similar. The extracted data, when determined to be similar to the original data and the extracted data, is used as the data extracted to analyze the factors that constitute the specific differential state.

2. The information processing apparatus according to claim 1, wherein, The information related to the factors that constitute the specific differential state is the vehicle's acceleration operation amount.

3. The information processing apparatus according to claim 1, wherein, The information related to the factors that constitute the specific differential state is the vehicle's steering angle.

4. The information processing apparatus according to claim 1, wherein, The information related to the factors that constitute the specific differential state is the vehicle's yaw rate.

5. The information processing apparatus according to claim 1, wherein, The information related to the factors that constitute the specific differential state is the position of the vehicle.

Images