Prediction device, system, method, and program

Abstract

Provided is a prediction device comprising: a time-series data acquisition unit that acquires time-series values obtained from an object; a prediction data generation unit that generates prediction values that follows the time-series values on the basis of the time-series values and a trained model; a regression line calculation unit that calculates a regression line on the basis of the time-series values and the prediction values; and a future prediction unit that performs future prediction pertaining to the object on the basis of the regression line.

Description

Prediction device, system, method and program

[0001] The present invention relates to a device for predicting the future of an object based on a signal obtained from the object, such as a device for predicting the lifespan of the object.

[0002] 2. Description of the Related Art There have been known techniques for predicting the future of an object, for example, predicting the lifespan of the object, based on a signal obtained from the object.

[0003] For example, a technique is known in which a regression line (or an approximation line) is calculated for data obtained from an object and a lifespan is predicted based on the regression line (see, for example, Patent Document 1). Another known technique is one in which the state of the object is input into a trained model to directly predict the lifespan (see, for example, Patent Document 2).

[0004] JP 2016-208773 A JP 2018-97723 A

[0005] However, while the former method, which uses linear regression from past data, allows predictions to be made using a clear calculation process and is therefore explainable, the accuracy of the predictions is not sufficient.

[0006] Furthermore, in the latter method, which directly predicts lifespan using machine learning technology, it is possible to expect improved prediction accuracy, but the prediction process becomes a so-called black box, and the prediction results cannot be explained.

[0007] The present invention has been made against the above-mentioned technical background, and its purpose is to provide a highly accurate yet explainable prediction technology for predicting the future of an object based on a signal obtained from the object.

[0008] The above-mentioned technical problems can be solved by a prediction device, a prediction system, a prediction method, a prediction program, etc. having the following configurations.

[0009] That is, the prediction device according to the present invention includes a time series data acquisition unit that acquires time series values ​​obtained from an object, a prediction data generation unit that generates a prediction value following the time series value based on the time series value and a trained model, a regression line calculation unit that calculates a regression line based on the time series value and the prediction value, and a future prediction unit that makes a future prediction regarding the object based on the regression line.

[0010] With this configuration, future predictions can be made based on predicted values ​​obtained using machine learning technology and previous time-series values. This allows for highly accurate future predictions. Furthermore, the use of regression lines can improve explainability compared to when predicted values ​​are obtained directly using machine learning technology. In other words, a prediction technology that is highly accurate and yet explainable can be provided for predicting the future of an object based on signals obtained from the object.

[0011] The trained model may include a plurality of trained models that predict different time steps, and the prediction data generation unit may generate a plurality of the prediction values ​​based on the time series values ​​and each of the trained models.

[0012] With this configuration, multiple trained models that predict different time steps are used, which improves the prediction accuracy of each time step, thereby enabling accurate future predictions.

[0013] The future prediction may be a prediction regarding the lifespan of the object.

[0014] With this configuration, the lifespan of the object can be predicted with high accuracy.

[0015] The regression line may be a straight line.

[0016] With this configuration, it is possible to suitably respond to linear changes in the object.

[0017] The prediction data generation unit may further include a preprocessing unit that extracts features of the time series values, and the prediction data generation unit may generate a prediction value following the time series values ​​based on the features extracted in the preprocessing unit and the trained model.

[0018] With this configuration, the characteristics of the time series values ​​can be further reflected when generating a predicted value.

[0019] The feature amount may include a moving average of the time series values ​​and / or a difference value between time steps of the time series values.

[0020] With this configuration, the characteristics of the time series values ​​can be further expressed.

[0021] The apparatus may further include a confidence interval calculation unit that calculates a confidence interval based on the regression line.

[0022] With this configuration, it is possible to provide a range for prediction based on the confidence interval.

[0023] The data analysis device may further include a display control unit that displays the time series values, the predicted values, and the regression line.

[0024] With this configuration, the user can visually check the time series values, the predicted values, the regression line, and the relationships between them.

[0025] The data analysis device may further include a confidence interval display control unit that displays the time series values, the predicted values, the regression line, and the confidence intervals.

[0026] With this configuration, the user can visually check the time series values, forecast values, regression lines, confidence intervals, and the relationships between them, and can therefore predict the future for the target object in the shortest and longest time periods based on the boundaries of the confidence interval.

[0027] From another aspect, the present invention is a prediction system comprising: a time series data acquisition unit that acquires time series values ​​obtained from an object; a prediction data generation unit that generates a prediction value following the time series values ​​based on the time series values ​​and a trained model; a regression line calculation unit that calculates a regression line based on the time series values ​​and the prediction value; and a future prediction unit that makes a future prediction regarding the object based on the regression line.

[0028] From another aspect, the present invention is a prediction method that causes a computer to execute a time series data acquisition step of acquiring time series values ​​obtained from an object, a prediction data generation step of generating a prediction value following the time series values ​​based on the time series values ​​and a trained model, a regression line calculation step of calculating a regression line based on the time series values ​​and the prediction value, and a future prediction step of making a future prediction regarding the object based on the regression line.

[0029] From another aspect, the present invention is a prediction program that causes a computer to execute the following steps: a time series data acquisition step of acquiring time series values ​​obtained from an object; a prediction data generation step of generating a prediction value following the time series values ​​based on the time series values ​​and a trained model; a regression line calculation step of calculating a regression line based on the time series values ​​and the prediction value; and a future prediction step of making a future prediction regarding the object based on the regression line.

[0030] According to the present invention, it is possible to provide a highly accurate and explainable prediction technology for predicting the future of an object based on a signal obtained from the object.

[0031] Fig. 1 is a schematic configuration diagram of an information processing device. Fig. 2 is a functional block diagram. Fig. 3 is a diagram showing a flowchart relating to a lifespan prediction operation of the information processing device. Fig. 4 is a conceptual diagram of a lifespan prediction algorithm. Fig. 5 is a diagram showing an example of a screen displayed on a display device by a display control unit.

[0032] Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings.

[0033] 1 to 5, a first embodiment will be described. In the first embodiment, an example will be described in which the present invention is applied to a device that predicts the lifespan of an object based on a signal from a sensor attached so as to be able to observe the object.

[0034] 1 is a schematic diagram of an information processing device 1 (or a lifespan prediction device) according to this embodiment. The information processing device 1 may be, for example, a microcomputer, a PC, a tablet terminal, or the like.

[0035] As is clear from the diagram, the information processing device 1 includes a control unit 10, a storage unit 11, an input unit 12, a display control unit 15, a communication unit 16, and an I / O unit 17, which are connected via a bus. The information processing device 1 is connected to a display device 19 via the display control unit 15. It is also connected to a sensor 18 via the I / O unit 17. These components may be collectively referred to as the information processing device 1.

[0036] The control unit 10 is comprised of a calculation device such as a CPU, and executes computer programs read from the storage unit 11 to realize various operations described below. The storage unit 11 is comprised of various storage devices such as ROM / RAM, flash memory, and hard disk, and stores computer programs and data necessary for various operations described below.

[0037] The input unit 12 is configured to process input signals from predetermined input devices such as buttons, touch panels, mice, keyboards, etc., and provide the processed signals to the control unit 10. The display control unit 15 is configured with a CPU or GPU, and performs processing related to images / moving images to be displayed on the display device 19. Note that the control unit 10 may be responsible for some or all of the operations of the display control unit 15.

[0038] The communication unit 16 is configured as a communication unit for realizing wired or wireless communication with an external device. The I / O unit 17 functions as an input / output interface with the external device and is configured to be connectable to various devices. In this embodiment, a sensor 18 is connected to the I / O unit 17. This allows a sensor signal to be input into the information processing device 1. The type of sensor is not particularly limited. Therefore, it includes all kinds of sensors such as a strain sensor, a temperature sensor, an optical sensor, a sound sensor, and an image sensor. Furthermore, a device that includes a sensor element as a part may be considered as the sensor 18.

[0039] 2 is a functional block diagram of this embodiment. As is clear from the diagram, a sensor 18 and a display device 19 are connected to an information processing device 1, and the sensor 18 is attached to a target device 2 to be observed. This sensor 18 can detect at least the state of the target device 2 and its changes over time.

[0040] The target device 2 is not particularly limited and can be any type of device. For example, it may be a mechanical device such as a machine tool, or its component parts. Furthermore, it may not only perform mechanical operations, but also devices that perform electronic, electromagnetic, or chemical operations. Furthermore, it may not be a fixed device, but may be a mobile device such as a vehicle.

[0041] The data acquisition unit 101 of the information processing device 1 acquires the signal obtained by the sensor 18 as a time-series signal and performs processing to provide the signal to the feature extraction unit 102 and the predicted data generation unit 103. The feature extraction unit 102 extracts features from the sensor signal obtained from the data acquisition unit 101 and provides the features to the predicted data generation unit 103. The predicted data generation unit 103 generates predicted data using a trained model based on current or past sensor values ​​and their features.

[0042] The data acquisition unit 101 and the prediction data generation unit 103 provide current or past data and prediction data to the regression line calculation unit 105. The regression line calculation unit 105 performs calculations to calculate a regression line and provides the calculation results to the future prediction unit 106, the confidence interval calculation unit 107, and the display control unit 151. The future prediction unit 106 predicts the lifespan of the target device 2 based on the provided regression line and a predetermined criterion and provides the results to the display control unit 151. The confidence interval calculation unit 107 performs processing to calculate a confidence interval based on the provided regression line and provides the results to the display control unit 151.

[0043] The display control unit 151 performs processing to display on the display device 19, in addition to a predetermined basic screen, current or past data obtained from the data acquisition unit 101, future prediction data obtained from the prediction data generation unit 103, the regression line provided from the regression line calculation unit 105, the future prediction results provided from the future prediction unit 106, and the confidence interval provided from the confidence interval calculation unit 107.

[0044] Note that the configurations of the respective functional blocks shown in this embodiment, i.e., the data acquisition unit 101, the feature extraction unit 102, the predicted data generation unit 103, the regression line calculation unit 105, the future prediction unit 106, the confidence interval calculation unit 107, etc., are realized by the control unit 10 or the control unit 10 and the storage unit 11. Also, the configuration shown in this embodiment is an example, and it goes without saying that other hardware configurations may be used. For example, it may be configured as a system (or a server-client system) via a network.

[0045] (1.2 Operation) FIG. 3 is a flowchart showing the life expectancy prediction operation of the information processing device 1.

[0046] As is clear from the figure, when the process starts, the data acquisition unit 101 performs a process of acquiring values ​​(sensor values) detected by the sensor 18 in chronological order (S1). This allows sensor values ​​from the past to the present to be acquired. The data acquisition unit 101 provides the acquired data to the feature extraction unit 102, the predicted data generation unit 103, and the regression line calculation unit 105.

[0047] After acquiring the sensor values, the feature extraction unit 102 extracts (or generates) feature values ​​from the time-series sensor values ​​as preprocessing (S2). In this embodiment, the feature values ​​include a moving average value for a predetermined time step, a difference between adjacent time steps, etc. Note that other quantities may be used as long as they represent the characteristics of the time-series data. The feature extraction unit 102 provides the extracted feature values ​​to the prediction data generation unit 103.

[0048] With this configuration, the characteristics of the time series values ​​can be further reflected when generating a predicted value.

[0049] After the feature extraction process, the predicted data generation unit 103 performs a process of generating a predicted value based on the data obtained from the data acquisition unit 101 and the data obtained from the feature extraction unit 102 (S3). More specifically, in this embodiment, the predicted data generation unit 103 is provided with N trained models that receive the sensor values ​​obtained from the data acquisition unit 101 and the feature values ​​obtained from the feature extraction unit 102 as input, and output predicted values ​​for one step ahead, two steps ahead, ..., N steps ahead in time steps. The predicted data generation unit 103 receives the sensor values ​​obtained from the data acquisition unit 101 and the feature values ​​obtained from the feature extraction unit 102 as input, and outputs predicted values ​​for one step ahead, two steps ahead, ..., N steps ahead in time steps. The predicted data generation unit 103 provides the output predicted values ​​to the regression line calculation unit 105.

[0050] With this configuration, multiple trained models that predict different time steps are used, which improves the prediction accuracy of each time step, thereby enabling accurate future predictions.

[0051] After the process of generating the predicted values, the regression line calculation unit 105 performs a process of calculating a regression line from the current and past time-series sensor values ​​and the predicted values ​​obtained from the data acquisition unit 101 (S5). More specifically, in this embodiment, a simple linear regression is performed on the current or past time-series sensor values ​​and the predicted values. That is, a linear function expressed by the following equation is calculated as the regression line.

[0052]

[0053] where a_hat is the sum of squared deviations of x, S xx , the sum of the products of the deviations of x and y xy , the average value of y, y_ave, and the average value of x, x_ave, are expressed as follows:

[0054]

[0055] Also, b_hat is the sum of squared deviations of x, S xx , the sum of the products of the deviations of x and y xy Using this, it is expressed as follows:

[0056]

[0057] Such a configuration using a linear regression line can suitably accommodate linear changes in the object.

[0058] The regression line calculation unit 105 provides information about the regression line to the future prediction unit 106 , the display control unit 151 , and the confidence interval calculation unit 107 .

[0059] Although a regression line is calculated in this embodiment, an approximate line may be calculated, and a second or higher order regression line may also be calculated.

[0060] After the regression line calculation process, the confidence interval calculation unit 107 calculates the confidence interval (S6). More specifically, in this embodiment, the confidence interval calculation unit 107 calculates a straight line corresponding to the confidence interval based on the following equation:

[0061]

[0062] where t is the t value, N is the number of samples, α is the reliability coefficient, and V_hat ε represents the unbiased variance of the regression line with N-2 degrees of freedom. The reliability coefficient α is 0.9 in this embodiment.

[0063] The confidence interval calculation unit 107 provides the display control unit 151 with a straight line corresponding to the confidence interval, which is the calculation result.

[0064] With this configuration, it is possible to provide a range for prediction based on the confidence interval.

[0065] After the confidence interval calculation process, the future prediction unit 106 performs a future prediction process, which in this embodiment is a lifespan prediction process for the target device 2 (S7). More specifically, the lifespan is determined based on the relationship between the regression line and a predetermined threshold (or standard). For example, in this embodiment, the time when the regression line is equal to or less than the predetermined threshold is taken as the predicted lifespan. The future prediction unit 106 provides the predicted lifespan to the display control unit 151.

[0066] After the future prediction process, the display control unit 151 performs a process of displaying the predicted lifespan obtained from the future prediction unit 106, the regression line obtained from the regression line calculation unit 105, and the confidence interval obtained from the confidence interval calculation unit 107 on the display device 19 (S8) (see also FIG. 5 for an example). After this display process, the process ends.

[0067] With this configuration, the user can visually check the time series values, predicted values, regression lines, confidence intervals, and the relationships between them. Therefore, for example, from the boundaries of the confidence interval, future predictions for the target object can be made for the shortest and longest time periods.

[0068] FIG. 4 is a conceptual diagram of a lifespan prediction algorithm according to this embodiment. Note that, for ease of understanding, the illustration of feature quantities has been omitted. As is clear from the figure, sensor data from the sensor 18 spanning (M+1) steps from the present to the past is provided directly to a lifespan prediction model. Furthermore, the sensor data is provided as input to a trained model for one-step future prediction, a trained model for two-step future prediction, ..., an trained model for N-step future prediction, which respectively generate a one-step future sensor prediction value, a two-step future sensor prediction value, ..., an N-step future sensor prediction value. These generated prediction values ​​are also provided to the lifespan prediction model.

[0069] In the life prediction model, the predicted life is generated from the relationship between the regression line generated from the current (sensor value 0 steps in the past) and past sensor values ​​of (M+1) steps and the predicted value of N steps, and a predetermined threshold value.

[0070] 5 is a diagram showing an example of a screen displayed on the display device 19 by the display control unit 151. The screen includes an xy two-dimensional graph, where x represents time (steps) and y represents the sensor value. ０ represents the current sensor value (or the sensor value 0 steps in the past), past sensor values ​​are displayed to the left of it, and predicted values ​​are displayed to the right of it. Note that the number of past sensor values ​​and the number of predicted values ​​in the figure are merely examples.

[0071] The graph also displays two lines: a regression line (shown as a solid line in the figure) obtained based on the current or past sensor values ​​and predicted values, and a straight line (shown as a dashed line in the figure) corresponding to the confidence interval boundary.

[0072] In this embodiment, the threshold value is y=0. Therefore, in the example shown in the figure, x １ is the predicted lifespan. １１ indicates the shortest predicted lifespan with a confidence interval, and x １２ By displaying these values, the user can be shown the predicted lifespan, the minimum predicted lifespan, and the maximum predicted lifespan.

[0073] As described above, the configuration according to this embodiment allows future prediction to be performed based on predicted values ​​obtained using machine learning technology and previous time series values. This allows future prediction to be performed with high accuracy. Furthermore, the use of a regression line allows for greater explainability than when predicted values ​​are obtained directly using machine learning technology. In other words, a prediction technology that is highly accurate and yet explainable can be provided for predicting the future of an object based on a signal obtained from the object.

[0074] (2. Modification) In the above-described embodiment, the prediction data generation unit 103 is configured to output multiple prediction values ​​using multiple trained models, but the present invention is not limited to such a configuration. Therefore, a number of trained models that is smaller than the number of prediction values ​​may be prepared. For example, a single trained model may be used to simultaneously generate prediction values ​​for multiple different time steps.

[0075] In the above embodiment, the future prediction unit 106 is described as performing a lifespan prediction, but the present invention is not limited to such a configuration. Therefore, a threshold value may not be set and future performance may simply be predicted.

[0076] In the above-described embodiment, a regression line is calculated based on a plurality of predicted values, but the present invention is not limited to such a configuration. Therefore, a single predicted value may be generated, and a regression line may be calculated from the current or past value and the single predicted value.

[0077] Although the embodiments of the present invention have been described above, the above embodiments merely illustrate some of the application examples of the present invention, and the technical scope of the present invention is not intended to be limited to the specific configurations of the above embodiments. Furthermore, the above embodiments can be combined as appropriate within the scope of not causing any contradiction.

[0078] The present invention can be used in various industries that utilize machine learning technology.

[0079] REFERENCE SIGNS LIST 1 Information processing device 10 Control unit 11 Storage unit 12 Input unit 15 Display control unit 16 Communication unit 17 I / O unit 18 Sensor 19 Display device

Claims

1. A prediction device comprising: a time series data acquisition unit that acquires time series values ​​obtained from an object; a prediction data generation unit that generates a prediction value following the time series value based on the time series value and a trained model; a regression line calculation unit that calculates a regression line based on the time series value and the prediction value; and a future prediction unit that makes a future prediction regarding the object based on the regression line.

2. The prediction device described in claim 1, wherein the trained model includes a plurality of trained models that predict different time steps, and the prediction data generation unit generates a plurality of the prediction values ​​based on the time series values ​​and each of the trained models.

3. The prediction device according to claim 1, wherein the future prediction is a prediction regarding the lifespan of the object.

4. The prediction device according to claim 1, wherein the regression line is a straight line.

5. The prediction device according to claim 1, wherein the prediction data generation unit further comprises a pre-processing unit that extracts features of the time series values, and the prediction data generation unit generates a prediction value following the time series values ​​based on the features extracted in the pre-processing unit and the trained model.

6. The prediction device according to claim 5, wherein the feature value includes a moving average of the time series values ​​and / or a difference value between time steps of the time series values.

7. The prediction device according to claim 1, further comprising a confidence interval calculation unit that calculates a confidence interval based on the regression line.

8. The prediction device according to claim 1, further comprising a display control unit that displays the time series values, the predicted values, and the regression line.

9. The prediction device according to claim 7, further comprising a confidence interval display control unit that displays the time series values, the predicted values, the regression line, and the confidence intervals.

10. A prediction system comprising: a time series data acquisition unit that acquires time series values ​​obtained from an object; a prediction data generation unit that generates a prediction value following the time series value based on the time series value and a trained model; a regression line calculation unit that calculates a regression line based on the time series value and the prediction value; and a future prediction unit that makes a future prediction regarding the object based on the regression line.

11. A prediction method in which a computer is caused to execute the following steps: a time series data acquisition step of acquiring time series values ​​obtained from an object; a prediction data generation step of generating a prediction value following the time series values ​​based on the time series values ​​and a trained model; a regression line calculation step of calculating a regression line based on the time series values ​​and the prediction value; and a future prediction step of making a future prediction regarding the object based on the regression line.

12. A prediction program that causes a computer to execute the following steps: a time series data acquisition step of acquiring time series values ​​obtained from an object; a prediction data generation step of generating a prediction value following the time series values ​​based on the time series values ​​and a trained model; a regression line calculation step of calculating a regression line based on the time series values ​​and the prediction value; and a future prediction step of making a future prediction regarding the object based on the regression line.

Images