Information processing device, information processing method, and information processing program

Abstract

To enable training a model of a neural network by aligning the number of dimensions of data even when the number of dimensions of the data is different.SOLUTION: In an information processing method, a computer causes a processor to execute processing of: receiving vehicle data, which is vehicle data relating to a vehicle and is accumulated for each predetermined period and for each unit relating to a predetermined operation and in which the number of units relating to the operation is different for each predetermined period in accordance with use by a user; generating, by using principal components obtained by principal component analysis of the vehicle data, training data by reducing the number of units relating to the operation in the vehicle data and aligning the number of dimensions; and training a model of a neural network using the training data.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus, an information processing method, and an information processing program.

Background Art

[0002] Patent Document 1 discloses a technique for improving the prediction accuracy when predicting the remaining life of a vehicle battery. In this technique, a prediction model for predicting the remaining life of a vehicle battery is learned based on learning data including time-series data of deterioration indicators and the remaining life at a predetermined past time point of a learning vehicle battery that has reached the end of its life. Also, for the unmeasured part of the deterioration indicator, an estimated value of the deterioration indicator is inserted for prediction

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The prior art considers the unmeasured part. Here, in the learning of a neural network model, it is necessary to perform learning with the same number of dimensions of the data used for learning. However, the prior art does not consider the number of dimensions of the data.

[0005] Regarding the number of dimensions, vehicle data collected from a vehicle is collected, for example, in units of trips. A trip is a unit of vehicle movement, and is a unit counted when the period from the start of movement to the end of movement is defined as one trip, and the number of trips corresponds to the dimension of the data. The data regarding the vehicle may have different numbers of trips per day, resulting in different numbers of dimensions of the data. Therefore, when learning the model, it is necessary to align the number of dimensions for data with different numbers of dimensions.

[0006] This disclosure aims to provide an information processing device, an information processing method, and an information processing program that can train a neural network model by standardizing the data dimensions, even when the data dimensions differ. [Means for solving the problem]

[0007] The information processing method described in claim 1 is a computer process in which a processor takes vehicle data relating to a vehicle, which is accumulated at predetermined intervals and for predetermined units relating to operation, wherein the number of units relating to operation differs for each predetermined interval according to the user's usage, as input, generates training data by reducing the units relating to operation of the vehicle data and making the number of dimensions equal using principal components obtained by principal component analysis of the vehicle data, and learns a neural network model using the training data.

[0008] The information processing method described in claim 1 creates training data using principal component analysis. This allows for the generation of training data that includes more data properties without data loss, such as when using representative values. Furthermore, by using principal components as elements, the model can be trained with a dimensionality that corresponds to the input to the neural network.

[0009] The information processing method according to claim 2 is an information processing device according to claim 1, wherein the processor groups the vehicle data by the predetermined period on a daily basis, sets the maximum number of units related to operation and the number of days to be calculated within the grouped data, creates a first matrix for each item of the vehicle data using the maximum number and the number of days to be calculated, creates a second matrix using the principal components obtained by principal component analysis, and generates the training data by performing operations on the first matrix and the second matrix. According to the information processing device according to claim 2, training data can be generated in such a way that the number of operation data corresponding to a trip is reduced. By performing operations on the first matrix and the second matrix, the dimension of the maximum number is reduced, and training data is generated that is aligned to the dimension of the number of principal components in the second matrix.

[0010] The information processing method according to claim 3 is an information processing device according to claim 2, wherein the blank spaces in the first matrix are filled with values ​​by substituting the average value or zero. According to the information device according to claim 3, it is possible to create computable data even when the number of trips is small or when there are gaps in the data acquisition.

[0011] The information processing method according to claim 4 is an information processing device according to claim 1, wherein the processor uses a trained model trained using the training data to reshape the dimensions of the vehicle data to the number of dimensions of the training data used to train the trained model, inputs it, and outputs the estimation result of the trained model. According to the information processing device according to claim 4, simple reshaping of vehicle data is sufficient for input to the trained model.

[0012] The information processing device according to claim 5 takes vehicle data relating to a vehicle, which is accumulated at predetermined intervals and for predetermined units relating to operation, and the number of units relating to operation differs for each predetermined interval according to the user's usage, as input, and the processor generates training data by reducing the units relating to operation of the vehicle data and making the number of dimensions equal using principal components obtained by principal component analysis of the vehicle data, and learns a neural network model using the training data. [Effects of the Invention]

[0013] The technology disclosed herein allows for training a neural network model by standardizing the dimensionality of the data. [Brief explanation of the drawing]

[0014] [Figure 1] Figure 1 shows the configuration of an information processing system, including an information processing device. [Figure 2] Figure 2 is a block diagram showing the hardware configuration of the information processing device. [Figure 3] Figure 3 schematically represents the vehicle data for each trip, which was acquired and grouped by day. [Figure 4A] Figure 4A schematically represents the data to be calculated from vehicle data within a given range. [Figure 4B] Figure 4B schematically shows training data generated by standardizing the dimensionality of vehicle data for each day. [Figure 5] Figure 5 is a flowchart illustrating the flow of information processing during model learning, which is an information processing method performed by the information processing device of this embodiment. [Figure 6] Figure 6 is a flowchart illustrating the information processing flow during estimation, which is an information processing method performed by the information processing device of this embodiment. [Modes for carrying out the invention]

[0015] An overview of embodiments of the present invention will be described. In battery degradation estimation in a vehicle, if there are multiple trips in a day, a representative value such as the lowest voltage at startup on that day is selected for the calculation. There are limitations on the data that can be input to the neural network for the calculation. For example, since the neural network inputs the sum-of-products calculation into the activation function, the sum-of-products calculation cannot be performed using the coefficients of the learned values ​​unless the number of dimensions is the same. Also, calculations cannot be performed with blank values. If data can be acquired at equal intervals throughout the day, the number of dimensions can be standardized, and learning and analysis can be performed. However, at equal intervals, data would be acquired even when the ignition is off and the engine is not running, which is inefficient in terms of energy efficiency.

[0016] Therefore, data acquisition is expected to be done on a trip basis. However, the number of trips per day is not constant and depends on the user's vehicle usage, making it impossible to determine. Consequently, if a neural network model is trained to match the maximum number of trips, the weight map changes depending on the period, resulting in a problem where the trained coefficients cannot be used directly. Furthermore, we want to utilize the information for each trip not only as a representative value of a single trip, such as the maximum or minimum value for each day. In addition, the number of dimensions needs to be reduced to prevent the computational load from becoming too large.

[0017] Therefore, in the present embodiment, while using the information of each trip, a method for shaping data using the principal component analysis method to align the number of dimensions and a method that can be used for learning the neural network model are proposed.

[0018] FIG. 1 is a diagram showing the configuration of the information processing system 100. As shown in FIG. 1, the information processing system 10 is connected to a plurality of vehicles 102 and an information processing device 110 via a network N.

[0019] The vehicle 102 transmits vehicle data related to the vehicle 102 to the information processing device 110. In the vehicle 102, for each trip, the numerical value of each item of vehicle data is acquired based on the time point when the ignition is turned on. The items of vehicle data to be acquired are data such as voltage (starting voltage is an example), temperature (outside air temperature is an example), driving distance (cumulative driving distance is an example), and parking time. Note that the items acquired for each trip are variable according to the acquisition status of various sensors, and there are also items that are not acquired. Therefore, in the processing of the analysis unit 122 described later, a process of filling in the values of the items that were not acquired is performed. A trip is an example of a unit related to a predetermined operation.

[0020] FIG. 2 is a block diagram showing the hardware configuration of the information processing device 110. As shown in FIG. 2, the information processing device 110 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a storage 14, an input unit 15, a display unit 16, and a communication interface (I / F) 17. Each configuration is connected to be communicable with each other via a bus 19.

[0021] The CPU 11 is a central processing unit that executes various programs and controls various components. Specifically, the CPU 11 reads programs from the ROM 12 or storage 14 and executes them using the RAM 13 as a working area. The CPU 11 controls each of the above components and performs various calculations according to the programs stored in the ROM 12 or storage 14. In this embodiment, the ROM 12 or storage 14 stores information processing programs. The other components can be the same as the hardware configuration of a typical computer, so their explanation is omitted.

[0022] When executing the above computer program, the information processing device 110 uses the above hardware resources to implement various functions. The functional configuration implemented by the information processing device 110 will now be described.

[0023] As shown in Figure 1, the information processing device 110 has a functional configuration consisting of a storage unit 112, a data setting unit 120, an analysis unit 122, a learning unit 124, and an estimation unit 130. Each functional configuration is realized by the CPU 11 reading and executing a computer program stored in the ROM 12 or storage 14.

[0024] The memory unit 112 stores vehicle data acquired from the vehicle 102. The vehicle data is stored with an acquisition date and time assigned to each vehicle ID. The vehicle ID is the Vehicle Identification Number (VIN). The acquisition date and time corresponds to the time the ignition is turned on. The vehicle data is stored with the acquisition date and time as rows and each item as a column. The vehicle data stores a different number of trips each day, depending on the user's use of the vehicle 102. This is because the number of trips varies depending on the user's use of the vehicle 102 on that day. The memory unit 112 also stores the trained model.

[0025] The data setting unit 120 takes vehicle data as input and sets the data to be calculated from the vehicle data. The number of days to acquire can be determined by user input or within a pre-set range, and the vehicle data can be grouped by day and acquired for a certain period based on the calculation time. In addition, the data to be calculated is set to the maximum number of trips a and the number of days to be calculated b. For example, the maximum number of trips a is used for the acquired period. For example, the number of days to be calculated b is treated as a predetermined number of days prior to the day the calculation is performed. The data to be calculated is also grouped by day and by trip. One day is an example of a predetermined period in this disclosure. The maximum number of trips is an example of a maximum number in this disclosure.

[0026] Figure 3 schematically represents vehicle data for each trip, grouped by day. Each circle represents vehicle data acquired in one trip. In each circle, the numerical values ​​for each item are acquired as vehicle data. The horizontal axis represents time, and the vertical axis represents the magnitude of the item's value. Since there are multiple items, this is a schematic representation of a trip focusing on a single item. In the example in Figure 3, it represents trips acquired on each day from 7 / 1 to 7 / 4. 7 / 1 has 1 trip, 7 / 2 has 3 trips, 7 / 3 has 0 trips, and 7 / 4 has 1 trip. In this range group, the maximum number of trips is represented by the direction of the arrow tr, and the maximum number of trips a is 3. In this way, the maximum number of trips in a selected range changes depending on the vehicle data in that range.

[0027] Figure 4A schematically represents the data to be calculated from vehicle data within a range. Each block contains the value of each item. The x-axis represents the date, the y-axis represents the item, and the z-axis represents the trip. For example, in each row in the y-direction, (y1) stores the value of voltage, (y2) stores the distance traveled, (y3) stores the temperature, and (y4) stores the value of parking time. Since the number of trips differs from day to day, the number of blocks extending in the direction of the number of trips on the z-axis will differ. Therefore, parts where there is no value for an item will be blank (missing value: NA). Note that the number of blocks is a schematic example and differs from the example in Figure 3.

[0028] The analysis unit 122 obtains principal components from the analysis data using principal component analysis. Using the principal components obtained from the principal component analysis, the analysis unit 122 standardizes the dimensionality of the daily vehicle data and generates training data. The details of the process are explained in the flowchart.

[0029] Figure 4B schematically shows training data generated by standardizing the dimensionality of daily vehicle data. The example in Figure 4B is an example where blocks for each trip along the z-axis, as shown in Figure 4A, are grouped together and reduced to one dimension. For each day's trip, normalization is performed, and the mean is set to zero according to the value of each item. By projecting the principal components (PC) along one axis using principal component analysis, the data for the number of trips is reduced to one-dimensional data. Note that the efficiency of the reduction depends on the contribution rate of the principal component analysis. The contribution rate indicates how well the principal components explain the entire data. In this embodiment, the number of dimensions of the vehicle data to be standardized is n (n≧1), and n-dimensional training data is generated. For example, the number of dimensions may be set so that the number of dimensions increases until the contribution rate reaches 90%, or any number of n that is less than the original number of trips may be set. In addition, for parts where the value of an item cannot be obtained and is missing, the mean or zero is substituted so that the variance of the values ​​is zero.

[0030] The learning unit 124 trains a neural network model using the generated training data. The model is designed to estimate the remaining battery life from vehicle data. The learning unit 124 stores the trained model in the storage unit 112. It may also be trained as a model for anomaly detection.

[0031] The estimation unit 130 uses the trained model learned by the learning unit 124 to estimate the remaining battery life of a vehicle from the vehicle data. Here, the vehicle data is preprocessed to match the dimensions of the training data used to train the trained model before being input into the trained model. The estimation unit 130 inputs the preprocessed vehicle data into the trained model and obtains the output of the battery remaining life estimation result from the trained model.

[0032] (Control flow) Figures 5 and 6 are flowcharts illustrating the information processing flow as an information processing method performed by the information processing device 110 of this embodiment. Figure 5 shows the information processing during model learning, and Figure 6 shows the information processing during estimation. The information processing device 110 receives vehicle data from the vehicle 102 for each trip and stores the vehicle data in the storage unit 112. The information processing device 110 performs information processing during model learning at regular intervals. The information processing device 110 performs information processing during estimation when the target for estimation is being considered.

[0033] This explains the information processing involved in model training.

[0034] In step S100, the CPU 11 groups vehicle data by day and creates data to be calculated. The data to be calculated is created by adding a dimension for each trip in the trip number direction to the vehicle data stored in a matrix and arranging the data. The trip number direction corresponds to the z-axis direction in Figure 4A above, and the data should be arranged by assigning a trip number. The number of dimensions to be added is set to the maximum number of trips a included in the grouping range.

[0035] In step S102, the CPU 11 sets the number of days b to be calculated for the data to be calculated.

[0036] In step S104, the CPU 11 normalizes (or standardizes) the data to be calculated item by item using the following formula (1).

number

[0037] In step S106, the CPU 11 substitutes zero for the items in the data to be calculated where the standard deviation is zero.

[0038] In step S108, the CPU 11 substitutes zeros into the blank spaces of the data to be calculated.

[0039] In step S110, the CPU 11 sets the matrix a×b of the data to be calculated, the eigenfunction matrix A(a×a), and the eigenvalues ​​λ.

[0040] In step S112, the CPU 11 searches for the eigenfunction matrix A that is minimized by equation (2) below.

number

[0041] In step S114, the CPU 11 extracts a principal component matrix (PC(n×a)) from the searched eigenfunction matrix A(a×a) and the dimension n of the principal component to be extracted using principal component analysis. To determine n in n dimensions, the contribution rate for each principal component is obtained using the eigenvalue λ, and n is calculated by cumulative summing up to a predetermined contribution rate. PC is an example of the second matrix in this disclosure.

[0042] In step S116, the CPU 11 generates training data in which vehicle data for b days is arranged in n dimensions by performing calculations with matrix X and the extracted principal component matrix PC. The training data (S) is obtained by performing S = PC·X and is represented by an n × b matrix. X is the matrix of items in the data to be calculated. Matrix X will be described later.

[0043] In step S118, the CPU 11 uses the generated training data to train a neural network model and stores the trained model in the memory unit 112.

[0044] This explains the information processing during estimation.

[0045] In step S200, the CPU 11 acquires the vehicle data to be estimated and formats it to the same number of dimensions as the training data used to train the trained model. By formatting the data to the number of dimensions corresponding to the input of the trained model, it is possible to handle cases where the number of trips differs or where there are missing data points for each item.

[0046] In step S202, the CPU 11 inputs the formatted vehicle data into the trained model and outputs the estimation results of the trained model. The trained model calculates the network weight matrix according to the label data and outputs the estimation results.

[0047] Here, we will explain a specific example of the training data that will be generated.

[0048] As an example, let's consider a case where the maximum number of trips per day (a) within the range selected by the grouping is 8 trips, and the number of days (b) used for calculation is 5 days.

[0049] The vehicle data for each trip is in matrix X{x 11 ,x 12 ...,x ij This is represented by the value of}. i is treated as the number corresponding to the trip, and j is treated as the number corresponding to each day. Here, we assume that X is reduced to 2 dimensions, i.e., n=2. Also, when matrix X is extended to the maximum number of trips a, there are blank spaces for days with no values ​​or for which values ​​could not be obtained. The blank spaces in matrix X are filled with values ​​by substituting the average value or zero.

[0050] The matrix X of the items in the data to be calculated for each trip is as follows (3) 11~X 85 This results in data in an 8x5 matrix.

[0051]

number

[0052] Next, create a matrix PC using the following equation (4) obtained from PC1 and PC2. The number of elements in matrix PC is determined by the dimension n to be compressed.

number

[0053] The training data S can be calculated as follows: 5 days' worth of data compressed into two dimensions, as shown in equation (5) below. This means that the vehicle data for 8 trips has been compressed into two dimensions.

number

[0054] Furthermore, if n=1, it is also possible to compress the training data S into a one-dimensional matrix consisting only of PC1.

[0055] As described above, the information processing device 110 of this embodiment can train a neural network model by standardizing the number of dimensions of the data.

[0056] In addition, the various processes that the CPU 11 reads and executes in the above embodiment may be executed by various processors other than the CPU. Examples of such processors include PLDs (Programmable Logic Devices) such as FPGAs (Field-Programmable Gate Arrays) whose circuit configuration can be changed after manufacturing, GPUs (Graphics Processing Units), and ASICs (Application Specific Integrated Circuits), which are dedicated electrical circuits that have a circuit configuration specifically designed to execute a particular process. Furthermore, each of the above processes may be executed by one of these various processors, or by a combination of two or more processors of the same or different types (for example, multiple FPGAs, and a combination of a CPU and an FPGA). More specifically, the hardware structure of these various processors is an electrical circuit that combines circuit elements such as semiconductor elements.

[0057] Furthermore, in the above embodiment, the information processing program was described as being pre-stored (installed) on a computer-readable non-temporary recording medium. For example, the information processing program is pre-stored on ROM 12 or storage 14. However, it is not limited to this, and each program may be provided in a form recorded on a non-temporary recording medium such as CD-ROM (Compact Disc Read Only Memory), DVD-ROM (Digital Versatile Disc Read Only Memory), and USB (Universal Serial Bus) memory. Alternatively, the information processing program may be downloaded from an external device via a network.

[0058] The processing flow described in the above embodiment is just one example, and unnecessary steps may be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose. [Explanation of symbols]

[0059] 100 Information Processing Systems 102 vehicles 110 Information Processing Device 112 Storage section 120 Data Setting Section 122 Analysis Department 124 Learning Department 130 Estimation part

Claims

1. Vehicle data relating to a vehicle, accumulated at predetermined intervals and for predetermined operational units, wherein the number of operational units varies for each predetermined interval according to the user's usage, is used as input. The processor, Training data is generated by using the principal components obtained from principal component analysis of the aforementioned vehicle data, and by reducing the units related to the operation of the vehicle data and standardizing the number of dimensions. Using the aforementioned training data, a neural network model is trained. An information processing method in which a computer performs the processing.

2. The aforementioned processor, The vehicle data is grouped into days based on the predetermined period, and the maximum number of units related to the operation and the number of days to be calculated are set within the grouped period. For each item of the vehicle data, a first matrix is ​​created using the maximum number and the number of days to be calculated. A second matrix is ​​created using the principal components obtained by principal component analysis. The information processing method according to claim 1, wherein the training data is generated by performing operations on the first matrix and the second matrix.

3. The information processing method according to claim 2, wherein the blank spaces in the first matrix are filled with values ​​by substituting the average value or zero.

4. The aforementioned processor, The information processing method according to claim 1, wherein the dimensions of the vehicle data are reshaped to the number of dimensions of the training data used to train the trained model, and input using a trained model trained using the aforementioned training data, and the estimation result of the trained model is output.

5. Vehicle data relating to a vehicle, accumulated at predetermined intervals and for predetermined operational units, wherein the number of operational units varies for each predetermined interval according to the user's usage, is used as input. The processor, Training data is generated by using the principal components obtained from principal component analysis of the aforementioned vehicle data, and by reducing the units related to the operation of the vehicle data and standardizing the number of dimensions. Using the aforementioned training data, a neural network model is trained. Information processing device.

Images