Visualization device, visualization method, and visualization program

Abstract

To enable the selection of an optimal machine learning model on the basis of user's knowledge and know-how by confirming a change in an explanatory variable to be a factor of a change in an objective variable of machine learning models.SOLUTION: An acquisition unit 15a acquires time series data. A generation unitt 15b performs learning by using the acquired time series data, and generates a plurality of models having different parameter values. A presentation unit 15c presents a factor relation between each explanatory variable and an objective variable in time series about each generated model.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a visualization device, a visualization method, and a visualization program.

Background Art

[0002] In recent years, technologies that utilize machine learning models trained on the characteristics of time-series data from sensors and the like generated in various locations in urban spaces including plants have been expected. Conventionally, the machine learning models actually applied have been selected based on statistical indicators such as prediction accuracy.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, a machine learning model selected based on statistical indicators is not always accepted on-site as the optimal machine learning model. For example, on-site, by checking the changes in explanatory variables that are factors in the changes of the target variable of the machine learning model based on knowledge and know-how, there is a tendency to be accepted as the optimal machine learning model.

[0005] The present invention has been made in view of the above, and an object thereof is to be able to select an optimal machine learning model based on the user's knowledge and know-how by checking the changes in explanatory variables that are factors in the changes of the target variable of the machine learning model.

Means for Solving the Problems

[0006] In order to solve the above-described problems and achieve the object, a visualization device according to the present invention includes an acquisition unit that acquires time-series data, a generation unit that generates a plurality of models by learning using the acquired time-series data, and a presentation unit that presents, in time series, the causal relationship between each explanatory variable and the target variable for each generated model.

Effect of the Invention

[0007] According to the present invention, it is possible to confirm the change in the explanatory variable that causes the change in the target variable of the machine learning model and select an optimal machine learning model based on the user's knowledge and know-how.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Mode for Carrying Out the Invention

[0009] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. Note that the present invention is not limited by this embodiment. In the description of the drawings, the same parts are denoted by the same reference numerals.

[0010] [Configuration of Visualization Device] FIG. 1 is a schematic diagram illustrating a schematic configuration of the visualization device. As illustrated in FIG. 1, the visualization device 10 is realized by a general-purpose computer such as a personal computer and includes an input unit 11, an output unit 12, a communication control unit 13, a storage unit 14, and a control unit 15.

[0011] The input unit 11 is realized by using an input device such as a keyboard or a mouse, and inputs various instruction information such as start of processing to the control unit 15 in response to an input operation by an operator. The output unit 12 is realized by a display device such as a liquid crystal display, a printing device such as a printer, etc.

[0012] The communication control unit 13 is realized by a NIC (Network Interface Card) or the like, and controls the communication between an external device via a network and the control unit 15. For example, the communication control unit 13 controls the communication between the control unit 15 and a sensor that outputs time-series data to be processed in the visualization process described later, a management device that manages time-series data, etc.

[0013] The storage unit 14 is realized by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. In the storage unit 14, a processing program for operating the visualization device 10, data used during the execution of the processing program, etc. are stored in advance, or temporarily stored each time processing is performed.

[0014] In the present embodiment, in the storage unit 14, for example, a model generated in the visualization process described later, model parameters, etc. are stored. Note that the storage unit 14 may be configured to communicate with the control unit 15 via the communication control unit 13.

[0015] The control unit 15 is realized by using a CPU (Central Processing Unit) or the like, and executes a processing program stored in a memory. Thereby, the control unit 15 functions as an acquisition unit 15a, a generation unit 15b, a presentation unit 15c, a calculation unit 15d, and a specification unit 15e as illustrated in FIG. 1. Note that these functional units may be implemented on different hardware, either individually or partially. For example, the generation unit 15b may be implemented on a device different from other functional units. Also, the control unit 15 may include other functional units.

[0016] The acquisition unit 15a acquires time-series data. For example, the acquisition unit 15a acquires time-series data such as sensor values to be subjected to visualization processing described later from a management device that manages the input unit 11, or from a sensor, or via the communication control unit 13 from a management device that manages sensor values.

[0017] The generation unit 15b learns using the acquired time-series data and generates a plurality of models with different parameter values. Specifically, the generation unit 15b uses the acquired time-series data as teacher data and generates a plurality of models for predicting the target variable from a plurality of explanatory variables by changing the parameter values.

[0018] The presentation unit 15c presents the causal relationship between each explanatory variable and the target variable for each generated model in time series. Here, FIGS. 2 and 3 are diagrams for explaining the processing of the presentation unit 15c. For example, as illustrated in FIG. 2, the presentation unit 15c presents to the user the time-series change of the causal relationship between the value of each explanatory variable of each model and the value of the target variable predicted using the model. Note that the causal relationship includes correlations and attributions representing the causal relationship of actions.

[0019] FIG. 2 illustrates the time-series change of the causal relationship between each of the feature quantities A, B,... I as the values of the explanatory variables and the target variable for each of the models 1, 2,..., N. In the example shown in FIG. 2, the greater the causal relationship, the darker the color. The presentation unit 15c outputs the causal relationship between each explanatory variable and the target variable of each model to a user terminal or the like via the output unit 12 or the communication control unit 13 and presents it to the user.

[0020] By checking the presented results, the user can check the explanatory variables that are the factors for the change of the target variable in each model. Therefore, it becomes possible for the user to check or select a model based on his or her own knowledge and know-how.

[0021] In addition, the presentation unit 15c may accept input of evaluation values by the user for each model. For example, the user designates and inputs an evaluation value such that a model closer to the user's knowledge and know-how has a higher evaluation value. Thereby, a high evaluation value is set according to the acceptance of a user with knowledge and know-how.

[0022] As illustrated in FIG. 3, for each model, the presentation unit 15c may further present the causal relationship between each explanatory variable. In the example shown in FIG. 3, in addition to the factor relationship between each explanatory variable and the objective variable of each model, a causal graph representing the causal relationship between each explanatory variable and the time-series change of the prediction result of the model are presented. Thereby, the user can more easily confirm the factor relationship between each explanatory variable and the objective variable in more detail, and it becomes easier for the user to confirm or select an optimal model according to the user's own knowledge and know-how.

[0023] Returning to the description of FIG. 1, the calculation unit 15d calculates an evaluation value representing the smoothness of the change in the time-series direction of the factor relationship between each presented explanatory variable and the objective variable.

[0024] Here, it is considered that the smoother the change in the time-series direction of the factor relationship between the explanatory variable and the objective variable, the easier it is to perceive as a factor in the change of the objective variable, and the higher the acceptance of a knowledgeable user. Therefore, by evaluating an explanatory variable with a smooth change in the time-series direction of the factor relationship with the objective variable as a major factor in the change of the objective variable, it is considered that an explanatory variable with a high acceptance of the user can be highly evaluated.

[0025] Therefore, the calculation unit 15d calculates the smoothness of the change in the time-series direction of the factor relationship between each explanatory variable and the objective variable as an evaluation value. For example, the calculation unit 15d calculates the evaluation value such that the smaller the change in the factor relationship at adjacent times of the time-series data, the higher the evaluation value representing the smoothness of the change. In the example shown in FIG. 2, the smoother the color change, the higher the evaluation value.

[0026] As a result, it becomes possible to evaluate, as a major factor in the change in the target variable, an explanatory variable whose change in the causal relationship with the target variable in the time series direction is smooth. Therefore, it becomes possible to objectively evaluate a model with which the user has a high sense of acceptance based on knowledge and know-how.

[0027] The specifying unit 15e selects a model based on the evaluation value. Specifically, the specifying unit 15e selects, as an optimal model, for example, a model with the maximum evaluation value based on the evaluation value input by the user or the calculated evaluation value. Then, the specifying unit 15e outputs the selected model to a user terminal or the like via the output unit 12 or the communication control unit 13.

[0028] Note that in an actual environment, it is not always necessary to specify one model, and a plurality of models may be applied and run in parallel. Alternatively, the model may be switched and applied according to the situation.

[0029] [Visualization processing procedure] Next, with reference to FIG. 4, an example of the visualization processing by the visualization device 10 according to the present embodiment will be described. FIG. 4 is a flowchart illustrating the visualization processing procedure. The flowchart of FIG. 4 starts, for example, at the timing when an input instructing the start of the visualization processing is given.

[0030] First, the acquisition unit 15a acquires time series data. For example, the acquisition unit 15a acquires time series data such as sensor values to be subjected to the visualization processing (step S1).

[0031] Next, the generation unit 15b learns using the acquired time series data and generates a plurality of models with different parameter values (step S2). Specifically, the generation unit 15b uses the acquired time series data as teacher data and generates a plurality of models for predicting the target variable from a plurality of explanatory variables by changing the parameter values.

[0032] Next, the presentation unit 15c presents, for each generated model, the causal relationship between each explanatory variable and the objective variable over time (step S3). For example, the presentation unit 15c presents to the user the temporal change in the causal relationship between the value of each explanatory variable of each model and the value of the objective variable predicted using the model.

[0033] Then, the visualization device 10 evaluates each model (step S4). For example, the presentation unit 15c receives an input of an evaluation value by the user. Alternatively, the calculation unit 15d calculates an evaluation value representing the smoothness of the change.

[0034] Also, the specifying unit 15e selects a model based on the evaluation value. For example, the one with the highest evaluation value is selected as the optimal model. Thereby, a series of visualization processes is completed.

[0035] [Effect] As described above, in the visualization device 10 of the above embodiment, the acquisition unit 15a acquires time-series data. Also, the generation unit 15b learns using the acquired time-series data and generates a plurality of models with different parameter values. Further, the presentation unit 15c presents, for each generated model, the causal relationship between each explanatory variable and the objective variable over time.

[0036] Thereby, for example, a user at a site such as a plant can confirm the explanatory variables that are the causes of the change in the objective variable in each model. Therefore, it becomes possible for the user to confirm or select an optimal model based on their own knowledge and know-how. Also, it becomes possible to present the models to the user and have the user select them within a shorter period than when the developer selects the optimal model and presents it to the user.

[0037] Also, the presentation unit 15c receives an input of an evaluation value by the user for each model. Thereby, it becomes possible to evaluate each model reflecting the knowledge and know-how of the user.

[0038] In addition, the presentation unit 15c further presents the causal relationships among the explanatory variables for each model. As a result, the user can more easily confirm the causal relationship between each explanatory variable and the target variable in more detail, and can more easily confirm or select an optimal model based on the user's own knowledge and know-how.

[0039] In addition, the calculation unit 15d calculates an evaluation value representing the smoothness of the change in the time series direction of the causal relationship between each presented explanatory variable and the target variable. As a result, for example, an explanatory variable with a smooth change in the time series direction of the causal relationship with the target variable can be evaluated as a major factor in the change of the target variable. Therefore, it becomes possible to objectively evaluate a model that the user can accept based on knowledge and know-how as an optimal model.

[0040] [System configuration, etc.] Each component of each illustrated device is a functional concept, and does not necessarily have to be physically configured as illustrated. That is, the specific form of distribution and integration of each device is not limited to that illustrated, and all or part of it can be functionally or physically distributed and integrated in any unit according to various loads, usage situations, etc. Furthermore, each processing function performed by each device can be realized in whole or in any part by a CPU, GPU, and a program analyzed and executed by the CPU or GPU, or can be realized as hardware by wired logic.

[0041] In addition, among the processes described in this embodiment, all or part of the processes described as being automatically performed can also be performed manually, or all or part of the processes described as being manually performed can be automatically performed by a known method. In addition, regarding the processing procedures, control procedures, specific names, and information including various data and parameters shown in the above documents and drawings, they can be arbitrarily changed unless otherwise specified.

[0042] [Program] It is also possible to create a program that describes the processing executed by the visualization device described in the above embodiment in a language that can be executed by a computer. For example, it is also possible to create a program that describes the processing executed by the visualization device 10 according to the embodiment in a language that can be executed by a computer. In this case, by having the computer execute the program, the same effects as those of the above embodiment can be obtained. Further, such a program may be recorded on a computer-readable recording medium, and the same processing as that of the above embodiment may be realized by having the computer read and execute the program recorded on this recording medium.

[0043] FIG. 5 is a diagram showing an example of a computer that executes a visualization program. The computer 1000 includes, for example, a memory 1010, a CPU 1020, a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.

[0044] The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012. The ROM 1011 stores, for example, a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to a hard disk drive 1031. The disk drive interface 1040 is connected to a disk drive 1041. A removable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive 1041. For example, a mouse 1051 and a keyboard 1052 are connected to the serial port interface 1050. For example, a display 1061 is connected to the video adapter 1060.

[0045] Here, the hard disk drive 1031 stores, for example, the OS 1091, application programs 1092, program modules 1093, and program data 1094. Each piece of information described in the above embodiments is stored, for example, in the hard disk drive 1031 or the memory 1010.

[0046] Also, the visualization program is stored in the hard disk drive 1031 as a program module 1093 in which instructions executed by the computer 1000 are described, for example. Specifically, a program module 1093 in which each process executed by the visualization device 10 described in the above embodiments is described is stored in the hard disk drive 1031.

[0047] Also, the data used for information processing by the visualization program is stored in the hard disk drive 1031 as program data 1094, for example. Then, the CPU 1020 reads out the program module 1093 and program data 1094 stored in the hard disk drive 1031 into the RAM 1012 as needed and executes each of the above-described procedures.

[0048] Note that the program module 1093 and program data 1094 related to the visualization program are not limited to being stored in the hard disk drive 1031. For example, they may be stored in a removable storage medium and read out by the CPU 1020 via a disk drive 1041 or the like. Alternatively, the program module 1093 and program data 1094 related to the visualization program may be stored in another computer connected via a network such as a LAN (Local Area Network) or WAN (Wide Area Network) and read out by the CPU 1020 via the network interface 1070.

[0049] The embodiments to which the invention made by the present inventor has been applied have been described above. However, the present invention is not limited by the description and the drawings that form part of the disclosure of the present invention according to the present embodiment. That is, all other embodiments, examples, operation techniques, etc. made by those skilled in the art based on the present embodiment are included in the scope of the present invention.

Explanation of Reference Numerals

[0050] 10 Visualization device 11 Input unit 12 Output unit 13 Communication control unit 14 Storage unit 15 Control unit 15a Acquisition unit 15b Generation unit 15c Presentation unit 15d Calculation unit 15e Identification unit

Claims

1. An acquisition unit that acquires time-series data; A generation unit that learns using the acquired time-series data and generates a plurality of models with different parameter values; A presentation unit that presents, in time series, the causal relationship between each explanatory variable and the target variable for each generated model; A calculation unit that calculates an evaluation value representing the smoothness of the change in the time series direction of the causal relationship between each presented explanatory variable and the target variable; A visualization device characterized by comprising the above.

2. The visualization device according to claim 1, wherein the presentation unit receives input of an evaluation value by a user for each model.

3. The visualization device according to claim 1, wherein the presentation unit further presents the causal relationship between the explanatory variables for each model.

4. A visualization method executed by a visualization device, comprising: An acquisition step of acquiring time-series data; A generation step of learning using the acquired time-series data and generating a plurality of models with different parameter values; A presentation step of presenting, in time series, the causal relationship between each explanatory variable and the target variable for each generated model; A calculation step of calculating an evaluation value representing the smoothness of the change in the time series direction of the causal relationship between each presented explanatory variable and the target variable; A visualization method characterized by including the above.

5. An acquisition step of acquiring time-series data; A generation step of learning using the acquired time-series data and generating a plurality of models with different parameter values; A presentation step of presenting, in time series, the causal relationship between each explanatory variable and the target variable for each generated model; A calculation step of calculating an evaluation value representing the smoothness of the change in the time series direction of the causal relationship between each presented explanatory variable and the target variable; A visualization program for causing a computer to execute.

Images