Computer system and information processing method
The computer system generates a correction model to predict and assess risks in observed values, addressing the risk-related inaccuracies in system control, thus improving operational accuracy and stability.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- HITACHI LTD
- Filing Date
- 2024-11-11
- Publication Date
- 2026-05-21
AI Technical Summary
Conventional techniques for interpolating observed values to minimize errors in system control often lead to significant differences in system operation, necessitating a method that considers the risks associated with system control.
A computer system with a processor and storage device that generates a correction model by predicting observation data using a prediction algorithm, assessing risks, and updating the model to minimize both prediction errors and risk, using a risk assessment algorithm.
The system effectively supplements observed values while accounting for risks, reducing prediction errors and system control risks, thereby enhancing the accuracy and stability of system operations.
Smart Images
Figure 2026084501000001_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to a technique for complementing data loss.
Background Art
[0002] There is known a technique for controlling a system based on observed values obtained from a control target system composed of elements such as devices and software. For example, an EMS (Energy Management System) obtains, as observed values, the power generation amount or the charging amount of power generation / power facilities, and performs efficient operation of the facilities based on the observed values.
[0003] There are cases where observed values cannot be obtained due to various factors such as communication errors. As the number of connected devices and the communication frequency increase, many losses of observed values occur. In real-time control, the loss of observed values as described above becomes a major problem. As a technique for complementing the missing values, for example, the technique described in Patent Document 1 is known.
[0004] Patent Document 1 describes that "a data complementation server includes a receiving unit that receives power generation amount data indicating the power generation amount of a distributed power source that generates power using natural energy from the distributed power source, and a control unit that complements the loss of the power generation amount data during the loss period of the power generation amount data. When the model of the distributed power source is a target model in which the transmission of the power generation amount data is performed by the generated power of the distributed power source, the control unit performs zero complementation that complements the power generation amount during the loss period as zero."
Prior Art Documents
Patent Documents
[0005]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0006] Conventional techniques interpolate observed values with the aim of minimizing the error between the actual observed values and the interpolated values. However, even with small errors, significant differences in system control can occur. Therefore, it is necessary to interpolate observed values while also considering the risks related to system control.
[0007] The present invention aims to realize a method for supplementing observed values that takes into account the risks related to system control. [Means for solving the problem]
[0008] A typical example of the invention disclosed in this application is as follows: A computer system comprising a processor and a storage device connected to the processor, wherein the storage device stores a dataset consisting of a plurality of observation data, including observation values used to control a system to be controlled and the time when the observation values were acquired, and information of a prediction algorithm for predicting the observation values, the processor selects one target observation data from the dataset, replaces the observation values included in the target observation data with observation values calculated based on the prediction algorithm to generate predicted observation data, and uses the dataset and the predicted observation data to execute a model generation process for generating a model that corrects the observation values predicted based on the prediction algorithm, the model is the predicted observation data The model accepts a data set and at least one of the aforementioned observation data, excluding the predicted observation data, as input and outputs a correction result of the predicted observation value. The processor repeatedly performs the following steps in the model generation process: a first process of setting an initial model and replacing the observation value included in the predicted observation data with the correction result output from the model that has been input with at least one of the aforementioned observation data included in the dataset other than the predicted observation data and the target observation data; a second process of calculating a risk assessment value representing the risk related to the control of the system using the dataset and the predicted observation data; and a third process of updating the model to reduce the risk based on an update algorithm using the risk assessment value. [Effects of the Invention]
[0009] According to the present invention, observed values can be supplemented while taking into account risks related to system control. Other issues, configurations, and effects will be clarified by the following description of the embodiments. [Brief explanation of the drawing]
[0010] [Figure 1] This figure shows an example of the configuration of the correction model generation device in Example 1. [Figure 2] This figure shows an example of the data structure of the observation data database in Example 1. [Figure 3] This figure shows an example of the data structure of the prediction algorithm DB in Example 1. [Figure 4] This figure shows an example of the data structure of the risk assessment algorithm DB in Example 1. [Figure 5] This figure shows an example of the data structure of the correction model DB in Example 1. [Figure 6] This figure shows an example of a screen displayed by the correction model generation device of Example 1. [Figure 7] This flowchart illustrates an example of the process performed by the correction model generation device of Example 1. [Figure 8] This figure shows a specific example of the processing performed by the correction model generation device of Example 1. [Figure 9] This figure shows an example of a screen displayed by the correction model generation device of Example 1. [Figure 10] This flowchart illustrates an example of the correction model generation process performed by the correction model generation device of Example 1. [Figure 11] This figure illustrates an example of a method for calculating the risk assessment value in Example 1. [Figure 12] This figure shows an example of the system configuration of Example 2. [Figure 13] This figure shows an example of the system configuration of Example 3. [Modes for carrying out the invention]
[0011] The embodiments of the present invention will be described below with reference to the drawings. However, the present invention is not to be construed as being limited to the embodiments described below. It will be readily apparent to those skilled in the art that the specific configuration can be modified without departing from the spirit or intent of the present invention.
[0012] In the configuration of the invention described below, identical or similar components or functions are denoted by the same reference numerals, and redundant descriptions are omitted.
[0013] The notations such as "first", "second", "third", etc. in this specification and the like are for identifying components and do not necessarily limit numbers or order.
Example
[0014] FIG. 1 is a diagram showing an example of the configuration of the correction model generation device of Example 1.
[0015] The correction model generation device 100 includes a processor 101, a storage device 102, an input device 103, an output device 104, and a network interface 105. Each hardware element is connected via a bus 106.
[0016] The processor 101 executes a program stored in the storage device 102. By the processor 101 executing processing according to the program, it operates as a functional unit (module) that realizes a specific function. In the following description, when explaining the processing with the functional unit as the subject, it indicates that the processor 101 is executing a program that realizes the functional unit.
[0017] The processor 101 of Example 1 functions as a learning data generation unit 110, a complementation unit 111, a risk evaluation unit 112, and a correction model generation unit 113. Regarding each functional unit included in the correction model generation device 100, a plurality of functional units may be grouped into one functional unit, or one functional unit may be divided into a plurality of functional units for each function.
[0018] The storage device 102 is a memory or the like and stores a program executed by the processor 101 and various data. Further, the storage device 102 includes a work area used by the program. Note that the correction model generation device 100 may include a large-capacity storage device such as an HDD (Hard Disk Drive) and an SSD (Solid State Drive).
[0019] The input device 103 is a device that accepts input such as data and commands, and is an example of a keyboard, mouse, or touch panel. The output device 104 is a device that outputs various types of data, and is an example of a display. The network interface 105 communicates with external devices via a network.
[0020] The storage device 102 stores the observation data DB120, the prediction algorithm DB121, the risk assessment algorithm DB122, and the correction model DB123.
[0021] The observation data DB120 is a database for managing observation data acquired from the controlled system. The observation data includes the observed values used to control the system, and the date and time when the observed values were acquired.
[0022] The system to be controlled is a power system that includes elements such as power generation equipment, charging equipment, power grids, and demand generation. The observed values are, for example, the amount of power generated by a power generation device and the amount of energy stored by an energy storage device.
[0023] The prediction algorithm DB121 is a database for managing prediction algorithms used to predict missing observations.
[0024] The Risk Assessment Algorithm DB122 is a database for managing algorithms for evaluating the risks to system control based on observational data supplemented with predicted observations.
[0025] Risks include, for example, financial losses in the operation of the system, the stability of the system, and the security of the system.
[0026] The Correction Model DB123 is a database for managing correction models that correct interpolated observations. A correction model is a mathematical formula or a machine learning model such as a neural network. The correction model takes observation data containing the interpolated observation data and at least one observation data from the training data used for training, excluding the interpolated observation data, as input, and outputs a corrected value for the interpolated observations.
[0027] The training data generation unit 110 generates training data for generating a correction model. The interpolation unit 111 predicts missing observations based on a prediction algorithm and performs interpolation using the predicted observations. The risk assessment unit 112 assesses the risk based on a risk assessment algorithm. The correction model generation unit 113 generates a correction model.
[0028] The functions of the correction model generation device 100 may also be implemented using a computer system consisting of multiple computers.
[0029] Figures 2 to 5 illustrate the database managed by the correction model generation device 100.
[0030] Figure 2 shows an example of the data structure of the observation data DB120 in Example 1.
[0031] The observation data DB120 stores, for example, tables 200, as shown in Figure 2, for each type of element constituting the controlled system. Table 200 stores records containing the date and time 201 and the observed value 202. Each record corresponds to one observation data.
[0032] Observation value 202 is a field that stores the observed value. Date and time 201 is a field that stores the date and time when the observed value was obtained.
[0033] Figure 3 shows an example of the data structure of the prediction algorithm DB121 in Example 1.
[0034] The prediction algorithm DB121 stores, for example, a table 300 as shown in Figure 3. Table 300 stores records containing algorithm ID 301, type 302, and prediction algorithm 303. Each record corresponds to one prediction algorithm.
[0035] Algorithm ID 301 is a field that stores the ID of the prediction algorithm. Type 302 is a field that stores the type of prediction algorithm. Possible types of prediction algorithms include rule-based algorithms, statistical methods, and machine learning models. Prediction algorithm 303 is a field that stores the program (tool) and configuration information for implementing the prediction algorithm.
[0036] If type 302 is "machine learning model", the prediction algorithm 303 stores hyperparameters and neural network weights, etc.
[0037] Figure 4 shows an example of the data structure of the risk assessment algorithm DB122 in Example 1.
[0038] The risk assessment algorithm DB122 stores, for example, a table 400 as shown in Figure 4. Table 400 stores records containing algorithm ID 401 and risk assessment algorithm 402. Each record corresponds to one prediction algorithm.
[0039] Algorithm ID 401 is a field that stores the ID of the risk assessment algorithm. Risk assessment algorithm 402 is a field that stores the program (tool) and configuration information for implementing the risk assessment algorithm.
[0040] The risk assessment algorithm 402 stores, for example, a simulator that simulates system control using observational data including complementary observations, and a risk assessment formula based on the simulation results of the system control.
[0041] Figure 5 shows an example of the data structure of the correction model DB123 in Example 1.
[0042] The correction model DB123 stores, for example, a table 500 as shown in Figure 5. Table 500 stores records containing model ID 501, characteristic 502, type 503, and correction model 504. Each record corresponds to one correction model.
[0043] Model ID 501 is a field that stores the ID of the correction model. Characteristics 502 is a field that stores the characteristics of the correction model. For example, the seasonality of the input observation data and the type of observed value are stored here. Type 503 is a field that stores the type of correction model. Possible types of correction models include machine learning models and mathematical formulas.
[0044] The correction model 504 is a field that stores information defining the correction model. If the correction model is a machine learning model, the correction model 504 stores hyperparameters and neural network weights, etc. If the correction model is a mathematical formula, the correction model 504 stores the formula and definitions of the formula's parameters, etc.
[0045] The processes performed by the correction model generation device 100 will be explained using Figures 6 to 9.
[0046] Figure 6 shows an example of a screen displayed by the correction model generation device 100 of Example 1. Figure 7 is a flowchart illustrating an example of a process performed by the correction model generation device 100 of Example 1. Figure 8 shows a specific example of the process performed by the correction model generation device 100 of Example 1. Figure 9 shows an example of a screen displayed by the correction model generation device 100 of Example 1.
[0047] When the correction model generation device 100 receives access from a user, it displays a screen 600. The screen 600 includes input fields 601, 602, 603, 604, 605 and a button 606.
[0048] Input field 601 is for inputting training data. Here, the training data consists of observational data arranged in chronological order. The observational data included in the training data is collected in advance by the system. Input field 601 is used to enter the path to the file where the training data is stored.
[0049] Input field 602 is for entering the prediction algorithm. If a prediction algorithm has been set in advance, the prediction algorithm will be displayed in a dropdown menu in input field 602. If no prediction algorithm has been set in advance, the path to the file containing the prediction algorithm will be entered in input field 602.
[0050] Input field 603 is for entering the risk assessment algorithm. If a risk assessment algorithm has been set in advance, the risk assessment algorithm will be displayed in a dropdown menu in input field 603. If a risk assessment algorithm has not been set in advance, the path to the file containing the risk assessment algorithm will be entered in input field 603.
[0051] Input field 604 is for entering parameters used in the correction model generation process.
[0052] Input field 605 is for entering the output destination for information regarding the correction model. Input field 605 is where the path to the file where the correction model will be saved will be entered.
[0053] Button 606 is used to instruct the correction model generation device 100 to execute a process.
[0054] The user enters various information into input fields 601, 602, 603, 604, and 605, and then presses button 606. The correction model generation device 100 starts processing when button 606 is pressed.
[0055] The correction model generation device 100 performs initial setup according to the inputs in input fields 601, 602, 603, 604, and 605 (step S101).
[0056] Specifically, the correction model generation device 100 stores the training data in the observation data DB 120 and sets the prediction algorithm and the risk assessment algorithm.
[0057] As shown in Figure 8, the training data generation unit 110 generates missing training data by deleting the observed value of one of the observed data included in the training data (step S102). The observed data from which the observed value is deleted may be selected randomly or based on any arbitrary rule.
[0058] In the following explanation, observation data from which observation values have been removed will be referred to as target observation data, observation data from which observation values have been removed will be referred to as missing observation data, observation data from which observation values have been filled in will be referred to as filled observation data, and observation data from which observation values have been corrected will be referred to as corrected observation data. Furthermore, training data in which target observation data has been replaced with missing observation data will be referred to as missing training data, training data in which target observation data has been replaced with filled observation data will be referred to as filled training data, and training data in which target observation data has been replaced with corrected observation data will be referred to as corrected training data.
[0059] The interpolation unit 111 generates interpolated learning data by interpolating the observed values of missing observed data included in the missing learning data, as shown in Figure 8, based on the prediction algorithm set in the input field 602 (step S103).
[0060] The correction model generation unit 113 performs a correction model generation process using the training data and complementary training data (step S104). Details of the correction model generation process will be described later.
[0061] The correction model generation unit 113 generates output information including information about the correction model and outputs the output information to the output destination according to the settings in the input field 605 (step S105).
[0062] For example, the correction model generation unit 113 calculates the prediction error and risk assessment value when using only the prediction algorithm, and also calculates the prediction error and risk assessment value when using both the prediction algorithm and the correction model, and includes the calculation results in the output information.
[0063] Based on the output information, a screen 900 as shown in Figure 9 is presented. Screen 900 includes tables 901 and 902 and a display field 903.
[0064] Table 901 displays the training data, supplementary training data, and corrective training data.
[0065] Table 902 displays prediction accuracy and risk assessment values. Specifically, Table 902 displays the error (prediction accuracy) of the observed values of the target observation data and the supplementary observation data, and the risk assessment value when the system is controlled based on the supplementary learning data.
[0066] Display field 903 shows the difference between the observed values when using only the prediction algorithm and the observed values when using both the prediction algorithm and the correction model. If the prediction algorithm is one that determines the interpolated values based on the probability distribution of the interpolated values, the probability distribution of the interpolated values will be displayed in display field 903, as shown in Figure 9.
[0067] Figure 10 is a flowchart illustrating an example of the correction model generation process performed by the correction model generation device 100 of Example 1.
[0068] Here, the correction model is described as a machine learning model. In this case, the correction model accepts complementary training data as input and outputs corrected values of the observed values of the complementary observation data included in the complementary training data.
[0069] The correction model generation unit 113 initializes the parameters θ of the correction model (step S201). The parameters θ are, for example, weights. Note that any method can be used to initialize the parameters θ.
[0070] The correction model generation unit 113 initializes the variable j to 1 (step S202). The variable j represents the number of parameter candidate values θ_j to be generated, and is an integer from 1 to J. J is an integer greater than 1.
[0071] The correction model generation unit 113 calculates the parameter candidate θ_j (step S203).
[0072] For example, the correction model generation unit 113 calculates a candidate parameter θ_j by adding a random perturbation Δθ to the parameter θ.
[0073] The correction model generation unit 113 generates correction learning data using a correction model in which the parameter candidate θ_j has been set (step S204).
[0074] Specifically, the correction model generation unit 113 calculates correction values for observed values of the complementary observation data included in the complementary learning data by inputting the complementary learning data into a correction model in which the parameter candidate θ_j has been set. The correction model generation unit 113 generates the correction learning data by replacing the observed values of the complementary observation data included in the complementary learning data with the correction values.
[0075] The correction model generation unit 113 calculates the difference between the observed values of the target observation data included in the training data and the observed values of the correction observation data included in the correction training data as the prediction error e_j (step S205).
[0076] The correction model generation unit 113 calls the risk assessment unit 112. The risk assessment unit 112 calculates the risk assessment value r_j based on the risk assessment algorithm set in the input field 603 (step S206). The risk assessment unit 112 outputs the risk assessment value r_j to the correction model generation unit 113.
[0077] For example, the risk assessment unit 112 calculates a risk assessment value r_j based on the simulation results of system control using complementary learning data and the simulation results of system control using corrected learning data. A specific example of how to calculate the risk assessment value r_j will be described later. Alternatively, the risk assessment unit 112 may calculate the risk assessment value r_j using a machine learning model that takes learning data and complementary learning data as input and outputs a risk assessment value r_j.
[0078] In this embodiment, it is assumed that the magnitude of the risk and the magnitude of the risk assessment value are proportional. That is, a large risk assessment value indicates a large risk, and a small risk assessment value indicates a small risk.
[0079] The correction model generation unit 113 calculates the loss l_j of the parameter candidate θ_j based on the prediction error e_j and the risk assessment value r_j (step S207).
[0080] For example, the loss l_j can be defined as shown in equation (1). Here, w is the weight set in input field 604, and is a value greater than 0 and less than 1. w is a parameter for adjusting the balance between prediction accuracy and risk assessment value. When generating a correction model that prioritizes prediction accuracy, the user sets w to a small value, and when generating a correction model that prioritizes risk assessment value, the user sets w to a large value.
[0081]
number
[0082] The correction model generation unit 113 determines whether the variable j is J or not (step S208).
[0083] If variable j is not J, the correction model generation unit 113 sets the value obtained by adding 1 to variable j as the new variable j (step S209), and then returns to step S203.
[0084] If the variable j is J, the correction model generation unit 113 selects N parameter candidates θ_j based on the loss l_j of the parameter candidate θ_j (step S210). Here, N is an integer less than J.
[0085] Specifically, the correction model generation unit 113 selects N parameter candidates θ_j in order of increasing loss l_j.
[0086] The correction model generation unit 113 updates the parameter θ using N parameter candidates θ_j (step S211).
[0087] For example, the correction model generation unit 113 updates the parameter θ using equation (2). Here, U is the set of variables j of the selected parameter candidate θ_j.
[0088]
number
[0089] By updating the parameter θ with a parameter candidate θ_j that has a small loss l_j, i.e., a small prediction error and risk assessment value, a corrected model with a small prediction error and risk can be generated.
[0090] The correction model generation unit 113 determines whether or not the termination condition is met (step S212).
[0091] There are various possible termination conditions. For example, if the number of parameter updates θ is greater than a threshold, the correction model generation unit 113 determines that the termination condition is met. Also, if the average value of the loss l_j of the N parameter candidates θ_j is less than a threshold, the correction model generation unit 113 determines that the termination condition is met.
[0092] If the termination conditions are not met, the correction model generation unit 113 returns to step S202. If the termination conditions are met, the correction model generation unit 113 terminates the series of processes.
[0093] Note that the method for generating the correction model shown in Figure 10 is just one example and is not limited to this. For example, the correction model may be generated using reinforcement learning techniques.
[0094] Here, we will explain an example of a method for calculating risk assessment values. Figure 11 is a diagram illustrating an example of a method for calculating risk assessment values in Example 1.
[0095] Figure 11 illustrates the control of battery charging and discharging by an Energy Management System (EMS). Solar panels supply power to the battery. When power supply to the battery is not needed, the solar panels supply power to electricity consumers. The battery stores power supplied by the solar panels or the power grid and supplies power to electricity consumers.
[0096] The EMS acquires observational data, including the amount of power generated by the solar panels, and controls the charging and discharging of the battery. Let x_t be the actual amount of power generated by the solar panels at time t. The observational data includes the amount of power generated at time t, x_t. If the amount of power generated in the observational data for time t is missing, let x^_t be the amount of power generated calculated using the prediction algorithm and correction model. Let B_t be the remaining charge of the battery at time t. Let d_t be the amount of power requested by the electricity consumer at time t.
[0097] The EMS controls the charging and discharging of the battery at time t based on the difference between x_t or x^_t and d_t. Here, let b_t be the difference between x_t or x^_t and d_t. Also, let v_t be the absolute value of the difference between x_t and x^_t.
[0098] (Case 1) Battery charging control (b_t>0) If x_t is less than x^_t, then v_t of electricity needs to be purchased from the power grid. In this case, the cost of purchasing electricity multiplied by v_t is the expense. If x_t is greater than x^_t, then v_t of electricity can be sold to electricity consumers. In this case, the cost of selling electricity multiplied by v_t is the income.
[0099] (Case 2) Battery discharge control (b_t<0) If the battery charge level is insufficient, that is, if B_t is less than (-b_t), the cost is calculated by adding the sum of B_t and b_t to the purchase price C(-).
[0100] When the expenditure or income at time t is defined as cost c_t, the risk assessment unit 112 calculates the sum of costs c_t over the time range in the training data as a risk index, as shown in equation (3).
[0101]
number
[0102] According to Example 1, the correction model generation device 100 generates a correction model that corrects the interpolated values to reduce the risk using a risk assessment value representing the risk related to system control. By using this correction model, it is possible to suppress the risk related to system control and achieve highly accurate interpolation of defect values. [Examples]
[0103] Example 2 describes a system that actually corrects missing values using a correction model. Below, we will describe Example 2, focusing on the differences from Example 1.
[0104] Figure 12 shows an example of the system configuration of Example 2.
[0105] The system consists of a correction model generation device 100 and a complementary device 1200. The correction model generation device 100 and the complementary device 1200 are connected via a network 1201 such as a LAN (Local Area Network).
[0106] The hardware and software configurations of the correction model generation device 100 in Example 2 are the same as those in Example 1. The method for generating the correction model in Example 2 is the same as in Example 1.
[0107] The supplementary device 1200 acquires correction model information from the correction model generation device 100 in advance. The correction model to be acquired can be selected according to the type of observation data included in the observation data and the timing of the observation data acquisition.
[0108] The interpolation device 1200 accepts the input of observational data. If there is observational data with missing values, the interpolation device 1200 predicts the observed values based on the prediction algorithm, corrects the predicted observed values using the correction model generated by the correction model generation device 100, and interpolates the observed values of the observational data.
[0109] The hardware configuration of the interpolation device 1200 is the same as that of the correction model generation device 100, so its description is omitted. Functionally, the interpolation device 1200 has an interpolation unit 1210 and a correction unit 1211, and also holds a correction model DB 1220. The correction model DB 1220 stores information on the correction model acquired from the correction model generation device 100.
[0110] The interpolation unit 1210 interpolates the observed values of the observation data based on a pre-set prediction algorithm. The correction unit 1211 corrects the interpolated observed values using a correction model.
[0111] The functional configuration of the correction model generation device 100 and the interpolation device 1200 may be implemented using a single computer or using a computer system consisting of multiple computers.
[0112] According to Example 2, the prediction error is small, and the observed values can be supplemented to reduce the risk related to the control of the controlled system. [Examples]
[0113] Example 3 describes a correction method for controlling a system using prediction results from a prediction algorithm. Examples of systems to be controlled include logistics systems and manufacturing systems.
[0114] Figure 13 shows an example of the system configuration of Example 3.
[0115] The system consists of a correction model generation device 100 and a prediction device 1300. The correction model generation device 100 and the prediction device 1300 are connected via a network 1301 such as a LAN (Local Area Network).
[0116] The hardware configuration of the correction model generation device 100 in Example 3 is the same as that of Example 1. The software configuration of the correction model generation device 100 in Example 3 differs in part from that of Example 1. Specifically, the correction model generation device 100 in Example 3 has a prediction unit 1311 instead of a interpolation unit 111. The prediction unit 1311 predicts future observed values based on a prediction algorithm. Other functional units are the same as those in Example 1. Furthermore, the method for generating the correction model in Example 3 is the same as that in Example 1.
[0117] The prediction algorithm DB121 in Example 3 manages prediction algorithms for predicting observed values from past observation data.
[0118] The correction model of Example 3 takes observational data, including observational values predicted based on the prediction algorithm, and at least one historical observational data as input, and outputs a corrected value for the predicted observational value.
[0119] The prediction device 1300 acquires correction model information from the correction model generation device 100 in advance. The correction model to be acquired can be selected according to the type of observation data included in the observation data and the timing of the observation data acquisition.
[0120] The prediction device 1300 accepts the input of observation data. The prediction device 1300 predicts the observed values based on the prediction algorithm and corrects the predicted observed values using the correction model generated by the correction model generation device 100.
[0121] The hardware configuration of the prediction device 1300 is the same as that of the correction model generation device 100, so a description will be omitted. The prediction device 1300 has a prediction unit 1320 and a correction unit 1321 as its functional configuration, and also holds a correction model DB 1330. The correction model DB 1330 stores information on the correction model acquired from the correction model generation device 100.
[0122] The prediction unit 1320 predicts observed values based on a pre-set prediction algorithm. The correction unit 1321 corrects the predicted observed values using a correction model.
[0123] The functional configuration of the correction model generation device 100 and the prediction device 1300 may be implemented using a single computer or using a computer system consisting of multiple computers.
[0124] According to Example 3, it is possible to predict observed values that have a small prediction error and reduce the risk related to the control of the controlled system.
[0125] It should be noted that the present invention is not limited to the embodiments described above, and various modifications are included. Furthermore, for example, the embodiments described above are detailed explanations of the configuration in order to clearly illustrate the present invention, and are not necessarily limited to those having all the configurations described. In addition, some of the configurations in each embodiment can be added to, deleted from, or replaced with other configurations.
[0126] Furthermore, each of the above-mentioned configurations, functions, processing units, processing means, etc., may be implemented in hardware, either partially or entirely, by designing them as integrated circuits, for example. The present invention can also be implemented by software program code that realizes the functions of the embodiment. In this case, a storage medium on which the program code is recorded is provided to a computer, and the processor of that computer reads the program code stored in the storage medium. In this case, the program code read from the storage medium itself realizes the functions of the embodiment described above, and the program code itself and the storage medium on which it is stored constitute the present invention. Examples of storage media used to supply such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs (Solid State Drives), optical disks, magneto-optical disks, CD-Rs, magnetic tapes, non-volatile memory cards, ROMs, and the like.
[0127] Furthermore, the program code that implements the functions described in this embodiment can be implemented in a wide range of programming or scripting languages, such as assembler, C / C++, Perl, Shell, PHP, Python, and Java (registered trademark).
[0128] Furthermore, the program code of the software that realizes the functions of the embodiment may be distributed via a network and stored in a storage means such as a computer's hard disk or memory, or in a storage medium such as a CD-RW or CD-R, and the computer's processor may read and execute the program code stored in the storage means or storage medium.
[0129] In the above-described embodiment, the control lines and information lines shown are those deemed necessary for explanation and do not necessarily represent all control lines and information lines in the actual product. All components may be interconnected. [Explanation of Symbols]
[0130] 100 Correction Model Generation Device 101 Processors 102 Storage device 103 Input device 104 Output device 105 Network Interfaces 106 Bus 110 Training Data Generation Unit 111, 1210 Supplementary section 112 Risk Assessment Department 113 Correction Model Generation Unit 120 Observation Data Database 121 Predictive Algorithm DB 122 Risk Assessment Algorithm Database 123, 1220, 1330 Correction Model DB 600, 900 screens 1200 Complementary device Networks 1201 and 1301 1211, 1321 Correction section 1300 Prediction device 1311, 1320 Prediction section
Claims
1. A computer system, The system comprises a processor and a storage device connected to the processor, The storage device stores a dataset consisting of multiple observation data, including observed values used to control the system to be controlled and the time when the observed values were acquired, and information on a prediction algorithm for predicting the observed values. The aforementioned processor, Select one target observation data from the dataset, replace the observed values included in the target observation data with the observed values calculated based on the prediction algorithm to generate predicted observation data. Using the dataset and the predicted observation data, a model generation process is performed to generate a model that corrects the predicted observation values based on the prediction algorithm. The aforementioned model accepts the predicted observation data and at least one of the aforementioned observation data excluding the said predicted observation data as input, and outputs the corrected result of the predicted observation value. In the model generation process, the aforementioned processor Setting the initial model, A computer system characterized by repeatedly performing the following: a first process of replacing the observed values included in the predictive observation data with the correction result output from the model into which at least one of the observed data included in the dataset other than the predictive observation data and the target observation data is input; a second process of calculating a risk assessment value representing the risk related to the control of the system using the dataset and the predictive observation data; and a third process of updating the model to reduce the risk based on an update algorithm using the risk assessment value.
2. A computer system according to claim 1, In the second process, the processor Using the aforementioned dataset and the aforementioned predictive observation data, the control of the system to be controlled is simulated. A computer system characterized by calculating the risk assessment value based on the results of the simulation.
3. A computer system according to claim 2, The aforementioned model is a machine learning model, The computer system is characterized in that the update algorithm is a machine learning algorithm that uses the loss calculated using the risk assessment value.
4. A computer system according to claim 3, In the second process, the processor calculates the error between the observed value included in the target observation data and the observed value included in the prediction observation data. The computer system is characterized in that the update algorithm is a machine learning algorithm that uses the error and the risk assessment value to calculate the loss.
5. A computer system according to claim 3, The aforementioned processor, New observational data is obtained, Based on the new observation data and the prediction algorithm, the observed values are predicted. A computer system characterized by outputting the correction result using the aforementioned model.
6. A computer system according to claim 3, The computer system is characterized in that the prediction algorithm is an algorithm for predicting observed values in order to supplement the observation data in which the observed values are missing.
7. A computer system according to claim 3, The aforementioned risk is characterized in that it is at least one of the following: financial loss in the operation of the system, stability of the system, and safety of the system.
8. A method of information processing performed by a computer system, The computer system has a processor and a storage device connected to the processor. The storage device stores a dataset consisting of multiple observation data, including observed values used to control the system to be controlled and the time when the observed values were acquired, and information on a prediction algorithm for predicting the observed values. The aforementioned information processing method is The first step is for the processor to select one target observation data from the dataset, and to generate predicted observation data by replacing the observed values included in the target observation data with observed values calculated based on the prediction algorithm, A second step in which the processor uses the dataset and the predicted observation data to generate a model generation process for generating a model that corrects the predicted observation values based on the prediction algorithm, Includes, The aforementioned model accepts the predicted observation data and at least one of the aforementioned observation data excluding the said predicted observation data as input, and outputs the corrected result of the predicted observation value. The second step described above is: The processor performs the steps of setting the initial model, The processor repeatedly performs the following steps: replacing the observed values included in the predictive observation data with the correction results output from the model that has been input with at least one of the observed data included in the dataset other than the predictive observation data and the target observation data; calculating a risk assessment value representing the risk related to the control of the system using the dataset and the predictive observation data; and updating the model to reduce the risk based on an update algorithm using the risk assessment value. An information processing method characterized by including