Information processing apparatus

Abstract

The invention relates to an information processing device which extracts data suitable for analyzing the grip performance of a tire. The information processing device executes: a step (S110) for setting a plurality of time windows for cutting data from raw data, using an accelerator operation amount and a slip amount of the vehicle at the time of starting the vehicle as feature amounts; a step (S120) of cutting the data from the raw data; a step (S130) for calculating the frequency distribution of the raw data and the frequency distribution of the extracted data for each of a plurality of feature quantities divided on the basis of information relating to a factor that affects the grip of the tire; and a step (S140 and S150) for determining whether or not 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 over 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 moment when a certain vehicle speed is reached and data obtained at the moment when the vehicle speed inflection point from the original data.

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2008-108247

[0005] When analyzing the grip performance of tires in a vehicle, if data suitable for analyzing grip performance can be extracted from the raw data, then by using the extracted data, the grip performance can be analyzed in a shorter time than when using the raw data. The aforementioned information processing device uses the extracted data to analyze driving speed patterns. Therefore, the aforementioned information processing device cannot extract data suitable for analyzing tire grip performance from the raw data. Summary of the Invention

[0006] An information processing device for solving the above-mentioned problems acquires raw data collected over a predetermined period using sensors mounted on a vehicle, and extracts data from the raw data for analyzing the grip performance of the tires in the vehicle. This information processing device includes processing circuitry. The processing circuit performs a first step of calculating the frequency distribution of multiple features in the original data for each feature, the multiple features including the accelerator operation amount and the vehicle's slip amount or slip ratio included in the original data. The processing circuit then repeatedly performs the following steps by varying the settings of multiple time windows: a second step of setting multiple time windows to cut a portion of the original data so that the sum of the periods of all the time windows is shorter than a predetermined period; a third step of cutting data from the original data according to the multiple time windows; a fourth step of calculating the frequency distribution of the extracted data, which combines all the data cut according to the multiple time windows, for each feature; a fifth step of calculating errors between the frequency distribution of each feature in the original data and the frequency distribution of each feature in the extracted data; and a sixth step of determining, based on the errors, whether the original data and the extracted data are similar, and extracting the extracted data when the original data and the extracted data are determined to be similar as data for analyzing the tire's grip performance.

[0007] According to the aforementioned information processing device, data suitable for analyzing tire grip performance can be extracted from raw data. Attached Figure Description

[0008] Figure 1 This is a schematic diagram illustrating the relationship between a data center, a vehicle, and an information processing terminal as one implementation of an information processing device.

[0009] Figure 2 These are charts representing a portion of the raw data. (a) represents the shift in accelerator operation, (b) represents the shift in slip, and (c) represents the shift in tire pressure.

[0010] Figure 3 It is a flowchart representing the processing flow performed by the processing circuitry of a data center.

[0011] Figure 4 It is the frequency distribution of accelerator operation and slip in the raw data when the tire pressure is above the set pressure.

[0012] Figure 5 It is the frequency distribution of accelerator operation and slip in the raw data when the tire pressure is less than the set pressure. Detailed Implementation

[0013] The following is for reference Figures 1-5 One embodiment of the information processing device will be described.

[0014] <The Composition of Information Processing Systems>

[0015] Figure 1 The structure of the information processing system is shown. The information processing system includes a data center 500 equipped 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.

[0016] <The Composition of Data Center 500>

[0017] 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 is capable of storing 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.

[0018] <Composition of Information Processing Terminal 600>

[0019] like Figure 1 As shown, 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.

[0020] <Composition of Vehicle 10>

[0021] Vehicle 10 is equipped with a communication device 99. The communication device 99 transmits data obtained by vehicle 10 and identification information of vehicle 10 to data center 500 via communication network 400.

[0022] The vehicle 10 includes an internal combustion engine 21, two electric generators 23, a planetary gear mechanism 50 constituting a power splitting device, a power control unit (hereinafter referred to as "PCU (Power Control Unit)") 24, a battery 25, and a vehicle control unit 90. The two electric generators 23 are referred to below as the first electric generator 23A and the second electric generator 23B.

[0023] The crankshaft of the internal combustion engine 21 is mechanically connected to the planet carrier C of the planetary gear mechanism 50. The sun gear S of the planetary gear mechanism 50 is mechanically connected to the rotating shaft of a first electric generator 23A, which serves as an electric motor. Additionally, the ring gear R of the planetary gear mechanism 50 is mechanically connected to the rotating shaft of a second electric generator 23B, which also serves as an electric motor, and to the drive wheel 60 of the vehicle 10. The drive wheel 60 includes a wheel and a tire 61 mounted on it.

[0024] The battery 25 exchanges power with the electric generator 23. That is, when the first electric generator 23A and the second electric generator 23B function as motors that output torque, the power from the battery 25 is supplied to each electric generator after being converted by the PCU 24. On the other hand, when the first electric generator 23A and the second electric generator 23B function as generators, the power generated by each electric generator is supplied to the battery 25 after being converted by the PCU 24.

[0025] The vehicle control unit 90 includes a first control device 91 for controlling the internal combustion engine 21 and a second control device 92 for controlling the PCU 24.

[0026] The vehicle control unit 90 is equipped with multiple sensors for data collection. The first control unit 91 has a CPU that controls the operating state of the internal combustion engine 21. The first control unit 91 controls the internal combustion engine 21 based on data collected by the sensors. The second control unit 92 has a CPU that controls the PCU 24. The second control unit 92 controls the PCU 24 based on data collected by the sensors.

[0027] One example of data collected by the vehicle control unit 90 is the travel distance, vehicle speed V, and position information of the vehicle 10. Another example of data collected by the vehicle control unit 90 is the accelerator pedal operation amount (which adjusts the acceleration of the vehicle 10), the vehicle 10's slip amount, the tire pressure of the tires 61, and the tire temperature of the tires 61. The slip amount is the value obtained by subtracting the vehicle speed V from the wheel speed ω of the drive wheels 60. Another example of data collected by the vehicle control unit 90 is the steering angle of the steering wheel, which controls the steering wheel of the vehicle 10. Finally, another example of data collected by the vehicle control unit 90 is weather information obtained via the communication network 400 based on position information. Weather information includes, for example, information on sunny, cloudy, rainy, and snowy weather.

[0028] Data Extraction

[0029] The information processing terminal 600 is used to analyze the grip performance of the tires 61 in the vehicle 10. While analyzing the grip performance of the tires 61, the information processing terminal 600 sends instructions to the data center 500.

[0030] Upon receiving the instruction, the processing circuit 510 of the data center 500 analyzes a portion of the vast amount of data stored in the storage device 520 of the data center 500. Depending on the purpose of the analysis, it selects data to be used from the vast amount of data stored in the storage device 520. This data includes multiple data related to the grip performance of the tires 61, collected using multiple sensors mounted on the vehicle 10. These data are referred to as feature quantities. The processing circuit 510 uses these feature quantities to analyze the grip performance of the tires 61 of a specific vehicle 10. In this case, the feature quantities are the accelerator input, slippage, and tire pressure of the vehicle 10 at startup.

[0031] In order for the processing circuit 510 to analyze the grip performance of the tires 61 in a specific vehicle 10 according to a program, the processing circuit 510 utilizes a large amount of data collected over a long period of time. This analysis requires a long time because the processing circuit 510 performs a massive amount of calculations.

[0032] Therefore, it is possible to extract data that captures the overall characteristics of the original data from the large amount of data that serves as the original data. If such extracted data can be extracted, the processing circuit 510 can perform parsing in a shorter time by using the extracted data.

[0033] Figure 2 The raw data shown is a portion of the data from 100,000 starts performed on 1 vehicle in chronological order. Figure 2 The raw data shown includes accelerator operation, slip, and tire pressure as characteristic quantities when the vehicle starts.

[0034] Figure 2 (a) represents the accelerator operation amount at each start of vehicle 10. Figure 2 (b) represents the slip when the accelerator operation is collected. Figure 2 (c) represents the tire pressure collected when the accelerator operation is reached.

[0035] The accelerator input, slippage, and tire pressure at the start of vehicle 10 are data related to the grip performance of tire 61. Processing circuit 510 extracts data from the data including accelerator input, slippage, and tire pressure at the start of vehicle 10 as feature values ​​to analyze the grip performance of tire 61.

[0036] Extracted data is created by cropping the raw data according to multiple time windows. Figure 2In this example, as multiple time windows, the first time window W_1, the second time window W_2, and the third time window W_3 are represented by double-dotted lines. The start and end dates of each time window are set to ensure that they do not overlap. In this example, data from 20,000 vehicle starts are used as the extracted data. Therefore, the start and end dates of each time window are set to the sum of the periods of all time windows, resulting in 20,000 vehicle starts.

[0037] Data center 500 sets the start and end times of each time window for representing the clipping pattern used to extract features captured from the original data as a whole. Data center 500 stores the information of the clipping pattern used to extract the above-mentioned data in storage device 520. The stored clipping pattern information is the information of the settings of each time window found through the search.

[0038] The processing circuit 510 extracts data from the raw data based on the cutting pattern information stored in the storage device 520.

[0039] <Search Processing in Crop Mode>

[0040] Figure 3 This is a flowchart illustrating a series of processes related to the search process for the clipping mode. The processing circuit 510 of the data center 500 executes this series of processes according to the program.

[0041] like Figure 3 As shown, the processing circuit 510 obtains the raw data in step S100. 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 according to the purpose of parsing.

[0042] The raw data used to analyze the grip performance of the tires 61 of a vehicle 10 is the data of the selected vehicle 10 from a large dataset of multiple vehicles 10.

[0043] Next, in the processing step S110, the processing circuit 510 sets multiple time windows to extract data from the raw data.

[0044] exist Figure 2 In the example shown, the duration of each time window is all equal. Figure 2 As shown, the data cropped according to each cropping window is the data of each feature quantity in the same period.

[0045] During each execution of step S110, processing circuit 510 randomly sets the number of time windows, the start period of each time window, and the end period of each time window. At this time, processing circuit 510 sets each time window in a manner where they do not overlap. Processing circuit 510 randomly sets multiple time windows in such a way that the total duration of all time windows is used as a preset period. Processing circuit 510 can, during the processing of step S110, such as... Figure 2 As shown, multiple time windows are set by fixing the duration of each time window to a constant. Alternatively, the processing circuit 510 can also set multiple time windows by fixing the number of time windows to a constant value during the processing in step S110.

[0046] Thus, multiple time windows are set through the processing in step S110, thereby determining the trimming mode for cutting data from the original data. If the processing circuit 510 determines the trimming mode in this way, it causes the processing to proceed to step S120.

[0047] In step S120, the processing circuit 510 trims data from the original data according to a determined trimming mode. That is, in step S120, the processing circuit 510 trims data from the original data according to multiple set time windows. Then, the processing circuit 510 combines all the data trimmed according to the multiple time windows to create extracted data.

[0048] Next, in step S130, the processing circuit 510 calculates the frequency distribution of the raw data and the extracted data. The raw data contains multiple feature quantities. The accelerator operation quantity and the slip quantity are used as the first feature quantity. In addition, information related to factors affecting the grip of the tire 61 among other feature quantities that are different from the first feature quantity is defined as the second feature quantity. In this embodiment, the second feature quantity is the tire pressure.

[0049] In step S130, the processing circuit 510 divides the data of the first feature quantity contained in the original data into multiple data based on the data of the second feature quantity when the first feature quantity is collected. In this embodiment, the second feature quantity is tire pressure. Therefore, the data of the first feature quantity is divided according to the tire pressure. The processing circuit 510 calculates the frequency distribution of each first feature quantity in the original data for each division of tire pressure.

[0050] Similarly, the processing circuit 510 divides the data of the first feature quantity contained in the extracted data into multiple data corresponding to the multiple data divisions of the original data. Then, the processing circuit 510 calculates the frequency distribution of each first feature quantity in the extracted data for each data division.

[0051] The frequency distribution categorizes the data for each first characteristic quantity into multiple levels, representing the frequency distribution of the number of data items at each level. In this embodiment, the data for the first characteristic quantity are accelerator operation quantities and slip quantities. Therefore, the frequency distributions of the accelerator operation quantities and the slip quantities are calculated separately.

[0052] Furthermore, because the total frequencies of the primary characteristic contained in the data differ between the original and extracted data, it is impossible to simply compare the frequency distributions of the original and extracted data. For example, if 20,000 vehicle starts are extracted from 100,000 original vehicle starts, the total frequency of the extracted data becomes one-fifth of the total frequency of the original data. In this case, by multiplying the frequency of each level of the extracted data by 5, a frequency distribution of the extracted data with the same total frequency as the original data can be obtained. Regardless of the method described above, by calculating the relative frequency distribution as the frequency distribution of the original and extracted data, it is possible to compare the distribution of data in the original data and the distribution of data in the extracted data. The relative frequency distribution represents the percentage of a particular level's frequency relative to the total frequency.

[0053] Figure 4 These represent the frequency distributions of accelerator operation and slippage during vehicle start-up in the raw data when the tire pressure is above the set pressure.

[0054] Figure 5 These represent the frequency distributions of accelerator operation and slippage during vehicle start-up in the raw data when the tire pressure is less than the predetermined pressure.

[0055] like Figure 4 as well as Figure 5 As shown, in these frequency distributions, the accelerator operation amount and slip amount are divided into m levels from "1" to "m". The frequency distribution of the extracted data is also calculated based on the levels corresponding to the original data. The processing circuit 510 divides the accelerator operation amount and slip amount contained in the original data and the extracted data into two categories: those with tire pressure above a predetermined value and those with tire pressure below a predetermined value. The processing circuit 510 calculates the frequency distribution as described above for each of the two tire pressure categories.

[0056] If executed 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 the first feature in the original data and the frequency distribution of the first feature in the extracted data for each of the multiple divisions involving the second feature. For example, the processing circuit 510 calculates the Mean Absolute Error (MAE). The Mean Absolute Error (MAE) is expressed by the following mathematical formula.

[0057] [Mathematical Expression 1]

[0058]

[0059] In the above mathematical formula, "n" is the number of the first feature quantity. In this embodiment, since the first feature quantity is the accelerator operation quantity and the slip quantity, "n" is "2". "m" is the total number of levels in the frequency distribution. "Y" is the frequency of the corresponding feature quantity in the corresponding level in the original data. "y" is the frequency of the corresponding feature quantity in the corresponding level in the extracted data.

[0060] As shown in the mathematical formula above, the processing circuit 510 calculates the sum of the errors of the frequency distribution in the original data and the frequency distribution of the first feature in the extracted data at each level as the error.

[0061] If errors are calculated for all partitions, the processing circuit 510 proceeds to step S150. In step S150, the processing circuit 510 determines whether the calculated errors for each partition are all 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 is extracted according to the set clipping pattern. The size of this threshold is preset to determine whether extracted data with a frequency distribution close to the frequency distribution in the original data is extracted based on the condition that the error is below the threshold. This threshold can be set to a different value for each partition.

[0062] When it is determined in step S150 that the error of each division is below the threshold (step S150: Yes), the processing circuit 510 records the trimming pattern. Specifically, the processing circuit 510 stores the start and end times of each time window in the trimming pattern as information for determining the trimming pattern in the storage device 520. If the trimming pattern is recorded in this way, the processing circuit 510 proceeds to step S160.

[0063] On the other hand, if it is determined in step S150 that any one of the errors is greater than the threshold (step S150: No), the processing circuit 510 returns the processing to step S110. That is, the processing circuit 510 starts the process of setting multiple new time windows in order to reset the time windows and extract data from the original data.

[0064] Thus, the processing circuit 510 repeatedly performs steps S110 to S150 using the frequency distribution of the first feature value divided by the second feature value until it can extract data similar to the original data. As a result, the storage device 520 stores the cutting patterns where the error of each division is below the threshold.

[0065] In step S160, the processing circuit 510 extracts data by cutting data from the original data based on a data cutting pattern similar to the original data stored in the storage device 520.

[0066] If step S160 is executed, the processing circuit 510 terminates the above series of processes based on the program.

[0067] In this way, the processing circuit 510 extracts the data used to analyze the grip performance of the tire 61.

[0068] <The function of this implementation method>

[0069] The data center 500, which is the information processing device in this embodiment, acquires raw data created by collecting data from multiple sensors mounted on the vehicle 10 over a predetermined period. Then, the data center 500 extracts data from the raw data for analyzing the grip performance of the tire 61.

[0070] Data center 500 includes processing circuitry 510. The raw data contains accelerator operation and slippage amounts during vehicle start-up as multiple feature quantities. In data center 500, processing circuitry 510 performs a search process. This search process includes a first step (step S130) of calculating the frequency distribution of the multiple feature quantities in the raw data for each feature quantity.

[0071] The search process includes a second step (step S110) of setting multiple time windows to prune data for a portion of the original data, such that the sum of the periods of all time windows is shorter than the overall period of the original data.

[0072] The search process includes a third step (step S120) of pruning data from the original data according to multiple time windows. The extracted data is the data that combines all the data pruned according to the multiple time windows.

[0073] The search process includes a fourth step (step S130) that calculates the frequency distribution in the extracted data for each feature.

[0074] The search process includes a fifth step (step S140) which involves calculating the frequency distribution of each feature in the original data and extracting the errors of the frequency distribution of each feature in the extracted data.

[0075] The search process includes a sixth step (step S150) to determine whether the original data and the extracted data are similar based on the aforementioned errors.

[0076] After executing the first step, the processing circuit 510 performs a search process by changing the settings of multiple time windows to repeatedly execute the processing from the second to the sixth step. Then, the processing circuit 510 extracts the extracted data when it is determined that the original data and the extracted data are similar, and uses this data as the data used to analyze the grip performance of the tire 61 (step S160).

[0077] According to the data center 500, such analysis can be performed using extracted data whose distribution of feature quantities related to the grip performance of tire 61 is similar to that of the original data. Therefore, the aforementioned data center 500 can obtain analysis results that are close to the analysis results of the grip performance of tire 61 performed using the original data.

[0078] The extracted data from data center 500 is a cropped portion of the original data. Therefore, the amount of extracted data is smaller compared to the original data. The more data used for parsing, the longer the processing time required to analyze the grip performance of tire 61. By using extracted data, data center 500 can reduce the parsing time compared to using the original data.

[0079] <Effects of this implementation method>

[0080] (1) Based on data center 500, the similarity between the original data and the extracted data is determined by multiple features, including the accelerator operation and slippage when the vehicle 10 starts. Therefore, data suitable for analyzing the grip performance of tire 61 can be extracted from the original data.

[0081] (2) In the first step described above, the processing circuit 510 of the data center 500 divides the original data into multiple data based on information about factors affecting the grip of the tire 61 contained in the original data. Then, the processing circuit 510 calculates the frequency distribution of each of the aforementioned characteristic quantities, including the accelerator operation amount and the slip amount when the vehicle 10 starts, in the original data for each data division.

[0082] Furthermore, in the fourth step described above, the processing circuit 510 divides the extracted data into multiple data points corresponding to the division of the original data into multiple data points. Then, the processing circuit 510 calculates the frequency distribution of each of the aforementioned feature quantities, including accelerator operation amount and slip amount, in the extracted data for each data division.

[0083] Then, in the fifth step described above, the processing circuit 510 calculates the frequency distribution of each feature in the original data and the error of the frequency distribution of each feature in the extracted data according to each division of the data.

[0084] Therefore, when analyzing the grip performance of tire 61, data on factors that affect the grip of tire 61 can be extracted.

[0085] (3) The information mentioned above concerning the factors affecting the grip of tire 61 is the tire pressure of tire 61. Therefore, data on the tire pressure of tire 61, which can be taken into account as a factor affecting the grip of tire 61, can be extracted.

[0086] <Example of Change>

[0087] Furthermore, the following elements exist as common modifications to the above-described embodiments. The following modification examples can be combined and implemented within a technically compatible framework.

[0088] Tire temperature is data related to the grip performance of tire 61. Therefore, the aforementioned information concerning factors affecting the grip of tire 61 could be the temperature of tire 61 when vehicle 10 starts. In this case, for example, the accelerator operation amount and slip amount included in the raw data and extracted data are divided into two categories: tire temperature above a predetermined temperature and tire temperature below a predetermined temperature. Moreover, the processing circuit 510 can calculate the aforementioned frequency distribution for each of the two tire temperature categories. According to this modified example, data on the temperature of tire 61 that can be considered as a factor affecting the grip of tire 61 can be extracted.

[0089] The weather information is data related to the grip performance of tire 61. Therefore, the aforementioned information concerning factors affecting the grip of tire 61 can be the weather information at the time of vehicle 10 start-up. In this case, for example, the accelerator operation amount and slip amount included in the raw data and extracted data are divided into three categories: sunny or cloudy weather, rainy weather, and snowy weather. Moreover, the processing circuit 510 can calculate the aforementioned frequency distribution for each of the three weather categories. According to this modified example, weather data that can be considered as factors affecting the grip of tire 61 can be extracted. In the above embodiment, the vehicle control unit 90 obtains the weather information via the communication network 400 based on location information. In addition, for example, the data center 500 can also obtain the weather information via the communication network 400 based on the collected location information.

[0090] The steering wheel angle is data related to the grip performance of tire 61. Therefore, the aforementioned information concerning factors affecting the grip of tire 61 can be the steering wheel angle when vehicle 10 starts. In this case, for example, the amount of accelerator operation and slippage contained in the raw data and extracted data are divided into two categories: a division of the steering wheel angle within a predetermined range and a division of the steering wheel angle outside the predetermined range. Moreover, the processing circuit 510 can calculate the aforementioned frequency distribution for each of the two divisions of the steering wheel angle. According to this modified example, data on the steering wheel angle that can take into account factors affecting the grip of tire 61 can be extracted.

[0091] • Information related to the ease of slippage on the road surface can be obtained based on the position information of vehicle 10. This ease of slippage is data related to the grip performance of tire 61. Therefore, as the aforementioned information related to factors affecting the grip of tire 61, processing circuit 510 obtains the position information of vehicle 10 at the time of start-up. Processing circuit 510 divides the driving area into, for example, urban and rural areas based on the position information. Similarly, processing circuit 510 divides the original data and extracted data into two divisions: urban and rural areas, based on the accelerator operation amount and slippage amount contained in the original data and extracted data. Furthermore, processing circuit 510 can calculate the aforementioned frequency distribution for each of the two driving areas. According to this modified example, data on the position information of vehicle 10 that takes into account factors affecting the grip of tire 61 can be extracted.

[0092] The processing circuit 510 divides the original data into multiple data sets based on information contained in the original data related to factors affecting the grip of the tire 61. On the other hand, the processing circuit 510 can also calculate the frequency distribution in the original data and extract the frequency distribution in the data without performing such data division. In this case, effects other than those described in (2) can also be obtained.

[0093] In the above embodiments, an example of embodying the information processing device as a data center 500 is shown. In contrast, the above-described information processing device can also be embodyed 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. Then, the processing circuit 610 executes... Figure 3 The processing after step S110 shown. Alternatively, the aforementioned information processing device can also be embodied as a control device for the vehicle 10. In this case, for example, the processing circuitry of the vehicle control unit 90 of the vehicle 10... Figure 3 In step S100, raw data is retrieved from the data center 500. Then, the processing circuitry of the vehicle control unit 90 executes... Figure 3 The processing after step S110 shown.

[0094] The aforementioned data center 500 determines the similarity between the original and extracted data by calculating the error in the frequency distribution. Alternatively, data center 500 can also determine the similarity between the original and 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 and extracted data is not significant.

[0095] Alternatively, the slip quantity included in the above-mentioned characteristic quantity can be changed to the slip ratio of vehicle 10. The slip ratio is a value calculated from the formula "(wheel speed ω - vehicle speed V) / wheel speed ω".

[0096] • The number of electric generators 23 in vehicle 10 can be appropriately changed.

[0097] • As a vehicle 10, it is not limited to being equipped with Figure 1 The hybrid vehicle with the series / parallel system shown can also be a hybrid vehicle equipped with other systems.

[0098] • Vehicle 10 may also be a vehicle equipped only with an electric motor as the prime mover.

[0099] • Vehicle 10 may also be a vehicle equipped only with an internal combustion engine as its prime mover.

[0100] Explanation of reference numerals in the attached figures

[0101] 10…vehicle; 21…internal combustion engine; 23…electric generator; 23A…first electric generator; 23B…second electric generator; 24…PCU; 25…battery; 50…planetary gear mechanism; 60…drive wheel; 61…tire; 90…vehicle control unit; 91…first control device; 92…second control device; 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, wherein, Raw data collected over a predetermined period using sensors mounted on the vehicle is acquired, and data used to analyze the grip performance of the tires in the vehicle is extracted from the raw data. The information processing device includes a processing circuit. The processing circuit performs a first step of calculating the frequency distribution of a plurality of features in the raw data for each feature, the plurality of features including the accelerator operation amount at vehicle start-up and the vehicle's slip amount or slip ratio contained in the raw data. Furthermore, the processing circuit modifies the settings of multiple time windows to repeatedly execute the following steps: The second step is to set multiple time windows for cropping a portion of the original data, such that the sum of the periods of all the time windows is shorter than the predetermined period. The third step is to cut data from the original data according to the multiple time windows; The fourth step is to calculate the frequency distribution of the extracted data that combines all data clipped according to the multiple time windows for each of the multiple features. The fifth step is to calculate the errors between the frequency distribution of each feature in the original data and the frequency distribution of each feature in the extracted data. as well as The sixth step is to determine, based on the aforementioned errors, whether the original data and the extracted data are similar. When the original data is determined to be similar to the extracted data, the extracted data is extracted as data for analyzing the tire's grip performance.

2. The information processing apparatus according to claim 1, wherein, The processing circuit is configured as follows: In the first step, the original data is divided into multiple data sets based on information contained in the original data related to factors affecting the tire's grip. The frequency distribution of each feature quantity in the original data is then calculated for each data set. In the fourth step, the extracted data is divided into multiple data points corresponding to the multiple data points of the original data, and the frequency distribution of each feature quantity in the extracted data is calculated for each data point. In the fifth step, the errors between the frequency distribution of each feature in the original data and the frequency distribution of each feature in the extracted data are calculated for each partition of the data.

3. The information processing apparatus according to claim 2, wherein, The information is the tire pressure.

4. The information processing apparatus according to claim 2, wherein, The information is the temperature of the tire.

5. The information processing apparatus according to claim 2, wherein, The information described is weather information.

Images