Factor analysis device and factor analysis method

Abstract

A factor analysis device (100) comprises: a data acquisition unit (110) that acquires a plurality of types of monitoring data pertaining to an object to be monitored; a variable setting unit (120) that generates, on the basis of the monitoring data, training-oriented monitoring data, factor analysis-oriented monitoring data, a training-oriented data set composed of explanatory variables and objective variables, and a factor analysis-oriented data set; a model training unit (130) that generates, on the basis of the training-oriented data set, a learning model that has been trained so as to receive an explanatory variable as input and output an objective variable; a contribution level calculation unit (150) that calculates a contribution level, which is the degree of influence an explanatory variable has on an objective variable, on the basis of causal relationship data indicating causal relationships for the plurality of types of monitoring data, the learning model, the training-oriented monitoring data, and the factor analysis-oriented monitoring data; a factor analysis unit (160) that calculates a factor level, which is the degree of being a factor, for each explanatory variable on the basis of the contribution level; and a factor analysis result output unit (170) that outputs a factor analysis result on the basis of the factor analysis-oriented data set, the contribution level, and the factor level.

Description

[Technical Field]

[0001] The disclosed technology relates to a factor analysis technology. [Background technology]

[0002] When a problem needs to be solved, it is important to take appropriate measures to address the problem in the problem in order to achieve the desired outcome. For example, in order to improve the productivity or efficiency of equipment such as a plant or factory, it is important to take appropriate measures or operations to address the factors that reduce productivity or efficiency. Thus, to solve the problem, it is necessary to identify the problem in the problem. However, the problem is often the result of multiple overlapping conditions, making it difficult to identify the problem. Therefore, factor analysis techniques have been known that use learning models to quantitatively analyze the relationship between the problem (objective variable) and several candidate problems (explanatory variables) that are thought to be related to it. Patent Document 1 describes a "defect factor analysis method and defect factor analysis device" that "utilizes a machine-learned learning model" to "extract factors that cause fluctuations in product quality." Specifically, the "Defective Factor Analysis Method and Defective Factor Analysis Device" of Patent Document 1 "performs the following steps on a computer: acquiring a plurality of manufacturing condition data or a plurality of monitoring data obtained by monitoring the operation of manufacturing equipment; predicting the quality of a manufactured product by inputting the acquired plurality of manufacturing condition data or monitoring data into a learning model that has been trained to output quality data indicating the quality of a product manufactured by the manufacturing equipment when the plurality of manufacturing condition data or monitoring data is input; and calculating, using the learning model, the contribution of each of the plurality of manufacturing condition data or monitoring data to the quality data or anomaly score data output from the learning model" (Patent Document 1 Abstract Solution). According to the "Defective Factor Analysis Method and Defective Factor Analysis Device" in Patent Document 1, a contribution indicating the degree to which each factor (explanatory variable in the learning model) directly contributes to product quality (target variable in the learning model) is calculated. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-043848 Summary of the Invention [Problem to be solved by the invention]

[0004] Multiple factors may have dependencies such that one factor affects the other factors. When multiple factors (explanatory variables) have a dependency relationship, conventional techniques do not take into account the indirect contribution based on the dependency relationship, and may present erroneous analysis results based on an incorrect degree of contribution. Such conventional techniques have had the problem that it is difficult to improve the accuracy of factor analysis.

[0005] The present disclosure is intended to solve the above-mentioned problems and aims to improve the accuracy of factor analysis. [Means for solving the problem]

[0006] The factor analysis device of the present disclosure includes: a data acquisition unit that acquires multiple types of monitoring data related to a monitoring target; a variable setting unit that generates, based on the monitoring data, training monitoring data, factor analysis monitoring data, a training dataset including explanatory variables and target variables, and a factor analysis dataset; a model learning unit that generates a learning model that is trained to input explanatory variables and output objective variables based on the learning dataset; a contribution calculation unit that calculates a contribution, which is the degree of influence that an explanatory variable has on a target variable, based on causal relationship data indicating causal relationships in multiple types of monitoring data, the learning model, the monitoring data for learning, and the monitoring data for factor analysis; a factor analysis unit that calculates a factor degree, which is the degree to which each of the explanatory variables is a factor, based on the contribution degree; a factor analysis result output unit that outputs a factor analysis result based on the factor analysis dataset, the contribution rate, and the factor rate; Equipped with: [Effects of the Invention]

[0007] The present disclosure provides an effect of improving the accuracy of factor analysis. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration of a factor analysis apparatus 100 according to the first embodiment of the present disclosure. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of a factor analysis system 10 including a factor analysis apparatus 100A according to the first embodiment of the present disclosure. [Figure 3] FIG. 3 is a flowchart showing an example of processing by the factor analysis device 100, 100A of the present disclosure. [Figure 4] FIG. 4 is a diagram showing a first example of causal relationship data used in the factor analysis apparatus 100, 100A of the present disclosure. [Figure 5] FIG. 5 is a diagram showing a second example of the causal relationship data used in the factor analysis apparatus 100, 100A of the present disclosure. [Figure 6] FIG. 6 is a diagram showing a third example of the causal relationship data used in the factor analysis apparatus 100, 100A of the present disclosure. [Figure 7] FIG. 7 is a diagram illustrating the contribution degree output by the contribution degree calculation section 150, 150A in the factor analysis apparatus 100, 100A of the present disclosure. [Figure 8]FIG. 8 is a diagram illustrating the factor levels output by the factor analysis units 160 and 160A in the factor analysis devices 100 and 100A of the present disclosure. [Figure 9] FIG. 9 is a diagram showing a first display example of the factor analysis result output by the factor analysis result output unit 170, 170A in the factor analysis device 100, 100A of the present disclosure. [Figure 10] FIG. 10 is a diagram showing a second display example of the factor analysis result output by the factor analysis result output unit 170, 170A in the factor analysis device 100, 100A of the present disclosure. [Figure 11] FIG. 11 is a diagram illustrating an example of the configuration of a factor analysis system 10 including a factor analysis apparatus 100B according to the second embodiment of the present disclosure. [Figure 12] FIG. 12 is a diagram showing an example of display of the factor analysis result output by the factor analysis result output unit 170B in the factor analysis apparatus 100B according to the second embodiment of the present disclosure. [Figure 13] FIG. 13 is a diagram illustrating a configuration example of a factor analysis system 10 including a factor analysis apparatus 100C according to the third embodiment of the present disclosure. [Figure 14] FIG. 14 is a diagram illustrating the aggregation conditions used in the factor analysis apparatus 100C according to the third embodiment of the present disclosure. [Figure 15] FIG. 15 is a diagram illustrating a configuration example of a factor analysis system 10 including a factor analysis apparatus 100D according to the fourth embodiment of the present disclosure. [Figure 16] FIG. 16 is a diagram showing a first display example of the factor analysis result output by the factor analysis result output unit 170B in the factor analysis apparatus 100D according to the fourth embodiment of the present disclosure. [Figure 17] FIG. 17 is a diagram showing a second display example of the factor analysis result output by the factor analysis result output unit 170B in the factor analysis apparatus 100D according to the fourth embodiment of the present disclosure. [Figure 18] FIG. 18 is a diagram illustrating a first example of a hardware configuration for realizing the functions according to the configuration of the present disclosure. [Figure 19]FIG. 19 is a diagram illustrating a second example of a hardware configuration for realizing the functions according to the configuration of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0009] In order to explain the present disclosure in more detail, embodiments of the present disclosure will be described below with reference to the accompanying drawings.

[0010] The present disclosure describes a technique for estimating the influence of explanatory variables on a target variable with higher accuracy than conventional techniques, using causal relationship data such as a causal graph.

[0011] Embodiment 1 The first embodiment will describe an embodiment relating to the basic configuration of a factor analysis device of the present disclosure.

[0012] FIG. 1 is a diagram illustrating an example of a configuration of a factor analysis apparatus 100 according to the first embodiment of the present disclosure. The factor analysis apparatus 100 quantifies the magnitude of the influence of the monitoring data on the target using a causal graph (causal relationship data) relating to the causal or dependent relationship between the objective variables, which are the target values, and the explanatory variables, which are the monitoring data.

[0013] The factor analysis device 100 includes a data acquisition unit 110, a variable setting unit 120, a model learning unit 130, a causal relationship data acquisition unit 140, a contribution calculation unit 150, a factor analysis unit 160, and a factor analysis result output unit 170.

[0014] The data acquisition unit 110 acquires multiple types of monitoring data relating to the monitoring target.

[0015] The variable setting unit 120 generates, based on the monitoring data, monitoring data for learning, monitoring data for factor analysis, a learning dataset, and a factor analysis dataset. The training dataset is a dataset consisting of explanatory variables and a response variable.

[0016] The model learning unit 130 generates a learning model that is trained to receive explanatory variables as input and output objective variables based on the learning dataset.

[0017] The causal relationship data acquisition unit 140 acquires causal relationship data that indicates causal relationships in multiple types of monitoring data.

[0018] The contribution calculation unit 150 calculates the contribution, which is the degree of influence that an explanatory variable has on a target variable, based on causal relationship data indicating causal relationships in multiple types of monitoring data, the learning model, the monitoring data for learning, and the monitoring data for factor analysis.

[0019] The factor analysis unit 160 calculates a factor degree, which is the degree to which each of the explanatory variables is a factor, based on the contribution degree.

[0020] The factor analysis result output unit 170 outputs the factor analysis result based on the factor analysis data set, the contribution degree, and the factor degree.

[0021] The factor analysis device 100 is used for all production facilities in a factory that consume resources such as electricity, gas, and oil. The monitoring data is collected from sensors installed in the production equipment and by monitoring the production equipment. For example, the factor analysis device 100 collects monitoring data obtained by monitoring the production equipment to be analyzed, that is, the production equipment for which resource consumption efficiency and productivity are to be improved. The monitoring data consists of sensor data such as resource consumption, temperature, and humidity collected by sensors installed in the equipment, as well as production management information such as product quality, production quantity, working hours, workers, and production conditions. From the monitoring data, one or more pieces of data that represent the consumption efficiency or productivity of some resource are set as the dependent variable, and two or more pieces of data that are related to the dependent variable, i.e., that are considered to be candidates for factors that cause the dependent variable to fluctuate, are set as explanatory variables. The factor analysis device 100 learns a learning model so that explanatory variables are input and response variables are output. The factor analysis device 100 calculates the degree of influence that the explanatory variables have on the target variable, that is, the "contribution of factors that cause fluctuations in resource consumption efficiency and productivity," for each data sample and explanatory variable, based on the learning model, the monitoring data, and the causal graph between the monitoring data. The factor analysis device 100 tallies the contribution degrees and calculates the factor degree for each explanatory variable. The factor analysis device 100 estimates factors that cause fluctuations in resource consumption efficiency and productivity, and presents information about the analysis results to users such as operators, such as on-site maintenance personnel, and resource managers of the target equipment. As a result, the factor analysis device 100 can support the operator in his or her work to improve resource consumption efficiency and productivity, thereby reducing the burden on the operator.

[0022] A configuration of a factor analysis system including the factor analysis device 100 will be described. FIG. 2 is a diagram illustrating an example of the configuration of a factor analysis system 10 including a factor analysis apparatus 100A according to the first embodiment of the present disclosure. FIG. 3 is a flowchart showing an example of processing by the factor analysis device 100, 100A of the present disclosure. FIG. 4 is a diagram showing a first example of causal relationship data used in the factor analysis apparatus 100, 100A of the present disclosure. FIG. 5 is a diagram showing a second example of the causal relationship data used in the factor analysis apparatus 100, 100A of the present disclosure. FIG. 6 is a diagram showing a third example of the causal relationship data used in the factor analysis apparatus 100, 100A of the present disclosure.

[0023] The factor analysis system 10 includes a factor analysis device 100A, a sensor 200, and a display device 300. The factor analysis device 100A uses a causal graph (causal relationship data) relating to the causal or dependent relationships between each target value (objective variable) and the monitoring data (explanatory variables) to quantify the magnitude of the impact that the monitoring data has on the target value, thereby supporting the consideration and prioritization of measures to improve resource consumption efficiency and productivity.

[0024] The sensor 200 is provided in a production facility that is a facility to be monitored. The sensor 200 outputs sensor data to the factor analysis device 100. The sensor data is, for example, time-series data of sensor measurement values ​​for a predetermined period of time obtained at predetermined intervals by a sensor 200 provided in the target facility. The sensor data may indicate, for example, at least one sensor measurement of temperature, humidity, power, gas, oil, water, or steam flow. This is merely an example, and the sensor data may include, for example, command values ​​or control values ​​such as reference values ​​obtained at predetermined intervals by a plurality of sensors 200 for a predetermined period of time.

[0025] The display device 300 is, for example, a display device. The display device 300 displays the factor analysis results output by the factor analysis device 100. The display device 300 may be an input / output device configured to include an input device, in which case the display device 300 is configured as an information processing terminal or the like.

[0026] An example of the configuration of the factor analysis devices 100 and 100A will be described. The factor analysis devices 100, 100A include data acquisition units 110, 110A, variable setting units 120, 120A, model learning units 130, 130A, causal relationship data acquisition units 140, 140A, contribution degree calculation units 150, 150A, factor analysis units 160, 160A, and factor analysis result output units 170, 170A.

[0027] The data acquisition units 110 and 110A acquire sensor data and production management information as monitoring data. The data acquisition units 110 and 110A acquire multiple types of monitoring data relating to the monitoring target. The data acquiring units 110 and 110A acquire, as monitoring data, a plurality of time-series sensor data collected by a plurality of sensors 200 provided in the target facility and production management information related to production of the target facility. The data acquisition units 110 and 110A acquire sensor data from the sensor 200. Furthermore, the data acquisition units 110 and 110A acquire production management information relating to production of the target equipment. The production management information is time-series data obtained at predetermined intervals for a predetermined period of time. The production management information is, for example, at least one of data on production conditions (production speed, product replacement, workers, etc.), production quantity, and work time (value production time, defect response time, setup time, etc.). Sensor data and production management information are acquired as monitoring data. That is, the data acquiring units 110 and 110A acquire, as the monitoring data, a plurality of time-series sensor data collected by a plurality of sensors provided in the monitored equipment, and production management information related to the production of the monitored equipment. Here, if the sampling period differs depending on the data, the resampling process may be performed based on the longest sampling period among the monitoring data. For example, if the quantity of monitored data is represented by n, the monitored data is represented as X1, X2, X3, X4, ..., Xn. Also, if data is collected at time 1, time 2, ..., time t, the monitored data is represented as a two-dimensional data frame with the number of times t as the row and the quantity n as the column. The value of time 1 of the first monitoring data X1 is represented as X11, the value of time 1 of the second monitoring data X2 is represented as X21, and the value of time 2 of the first monitoring data X1 is represented as X12.

[0028] The variable setting units 120 and 120A acquire monitoring data, and generate, based on the monitoring data, monitoring data for learning, monitoring data for factor analysis, a learning dataset consisting of explanatory variables and target variables, and a dataset for factor analysis. The variable setting units 120 and 120A generate, based on the monitoring data, monitoring data for learning, monitoring data for factor analysis, a learning data set consisting of explanatory variables and target variables, and a data set for factor analysis. The variable setting units 120 and 120A set one piece of data representing the consumption efficiency or productivity of some resource as the objective variable. Here, the monitoring data selected by the user may be used as the objective variable. The variable setting units 120 and 120A may set, for example, data representing the quality of the product as the objective variable. The variable setting units 120 and 120A may use, as the objective variable, data obtained by performing preprocessing on at least one or more pieces of monitoring data selected by the user. The variable setting units 120 and 120A may, for example, calculate a basic unit from the production volume and the resource consumption amount, and set it as the objective variable. The response variable may be discretized by one or more thresholds (e.g., when the monitored data is continuous). In this case, the threshold may be set manually by the user, or a statistical quantity such as the mean, median, or standard deviation of the objective variable may be used. Furthermore, the variable setting units 120 and 120A allow the user to select two or more pieces of data related to the objective variable, that is, two or more pieces of data that are considered to be candidates for factors that cause the objective variable to fluctuate, from the monitoring data and set them as explanatory variables. However, the explanatory variables should not include monitoring data that is affected by the objective variables. For example, the variable setting units 120 and 120A prevent the explanatory variables from including monitoring data on the result side (child, downstream) of the objective variable in a causal graph, which will be described later. Then, the variable setting units 120 and 120A generate a data set in which the response variables and the explanatory variables are paired. The variable setting units 120 and 120A extract data sets corresponding to some or all of the times at which the data sets were generated, and output these to the model learning units 130 and 130A as learning data sets. In addition, when the variable setting units 120 and 120A extract a data set corresponding to a certain time as a learning data set, they output a data set corresponding to a time other than the certain time to the factor analysis result output units 170 and 170A as a data set for factor analysis. When all the data sets are set as learning data sets, the variable setting units 120 and 120A output all the data sets as factor analysis data sets to the factor analysis result output units 170 and 170A. When the variable setting units 120 and 120A extract a data set corresponding to a certain time as a learning data set, they output the monitoring data corresponding to the certain time as learning monitoring data and the monitoring data corresponding to times other than the certain time as factor analysis monitoring data to the contribution calculation units 150 and 150A. When all the data sets are used as learning data sets, all the monitoring data are output to the contribution degree calculation units 150 and 150A as monitoring data for factor analysis and monitoring data for learning.

[0029] The model learning units 130 and 130A generate a model that is trained to receive explanatory variables as input and output objective variables based on a learning data set. The model learning units 130 and 130A generate a learning model based on a learning data set. In detail, when explanatory variables of a learning dataset are input, the model learning units 130 and 130A optimize the parameters constituting the learning model so that the values ​​output from the learning model approach the objective variables of the learning dataset. The model learning units 130 and 130A can use the following as known learning models. When the objective variable is a continuous value, the model learning units 130 and 130A can use, for example, a regression tree, a random forest regression, a neural network, or a support vector regression. When the objective variable is a discrete value, the model learning units 130 and 130A can use, for example, a decision tree, a random forest, a neural network, a support vector machine, or the like. The learning model may be configured by combining at least one or more methods.

[0030] The causal relationship data acquiring units 140 and 140A acquire causal relationship data indicating causal relationships in multiple types of monitoring data. Causal relationship data is data that indicates dependencies between data. The causal relationship data indicates the causal relationships and dependencies between multiple types of monitoring data. The causal relationship data indicates the causal relationships and dependencies between input data that are input to the learning model. The causal relationship data is data manually created by a user. Alternatively, the causal data is data inferred from monitoring data. Alternatively, the causal relationship data is data that is given in advance using both data manually created by a user and data estimated from monitoring data. The causal relationship data is data that can be expressed, for example, in a causal graph (FIG. 4, FIG. 5, or FIG. 6) described later. In the following description, the causal relationship data will also be referred to as a causal graph.

[0031] The contribution calculation units 150 and 150A calculate the contribution, which is the degree of influence that an explanatory variable has on a target variable, based on causal relationship data indicating causal relationships in multiple types of monitoring data, the learning model, the monitoring data for learning, and the monitoring data for factor analysis. The contribution degree calculation units 150 and 150A acquire the causal graph, the learning model, the learning monitoring data, and the factor analysis monitoring data, and calculate the contribution degree that quantifies the influence of the explanatory variables on the target variable for each data sample. Here, the causal graph may be stored in advance in, for example, a causal graph storage unit, and may be configured to be output from the causal graph storage unit to the contribution degree calculation units 150 and 150A. If the contribution degree calculation units 150 and 150A are configured to directly receive the causal graph from the causal graph storage unit, the configuration may not include the causal relationship data acquisition unit. The contribution calculation units 150 and 150A calculate the contribution that indicates the degree of influence that the explanatory variables have on the objective variable for each data sample based on the input causal graph, learning model, learning monitoring data, and factor analysis monitoring data.

[0032] The contribution calculation units 150 and 150A are an extension of the conventional contribution calculation method, which takes into account a causal graph. The contribution degree calculation units 150 and 150A have a function of calculating the degree of influence that an explanatory variable has on a response variable, taking into consideration indirect influences as well, based on the inter-data dependency relationships indicated by the causal graph. For example, XAI (Explainable AI) such as SHAP value and LIME can be used as a method for quantifying the magnitude of the impact. The contribution degree calculation units 150 and 150A calculate the contribution degree of the explanatory variables to the objective variable using the trained learning model, the monitoring data for factor analysis, the monitoring data for learning, and the causal graph (causal relationship data). The contribution degree calculated by the contribution degree calculation units 150 and 150A is a contribution degree that takes into consideration not only the direct contribution degree but also the indirect contribution based on the causal graph (causal relationship data). For example, the contribution is a SHAP value that can be calculated using a learning model. The SHAP value of a given explanatory variable in a given data sample is a value corresponding to the difference between the output value of the learning model when the explanatory variable is included in the input of the learning model and the output value of the learning model when the explanatory variable is not included. Here, a data sample refers to data corresponding to a given time. Furthermore, the sum of the SHAP values ​​of all explanatory variables for a data sample is equal to the difference between the output value of the learning model for the data sample and the average output value of the learning model for all data samples. Therefore, the SHAP value is a value that quantifies the influence that the explanatory variables have on the dependent variable for each data sample, that is, the extent to which the dependent variable changes depending on the presence or absence of the explanatory variables.

[0033] In detail, for example, the SHAP value is expressed by the following formulas (1) and (2). The contribution degree calculation units 150 and 150A use the SHAP value to calculate the contribution degree based on the difference between the expected values ​​of the learning model output values ​​with and without the explanatory variable i. TIFF0007760097000001.tif111166 The term A in equation (2) represents the learning model f. In the calculation of v(S) shown in equation (2), the input to the learning model f is the explanatory variables selected by the user. Furthermore, the probability distribution P (term B in equation (2)) that takes into account the dependency is always defined based on all monitoring data including those other than the explanatory variables. Therefore, whether the explanatory variables are narrowed down in advance by the user's judgment or based on the analysis results, factor analysis can be performed while taking into consideration the dependencies between the monitoring data. That is, factors can be narrowed down by utilizing the user's knowledge. For example, when there are five explanatory variables, the relationship between the output value of the learning model and the SHAP value is expressed by the following equation (3). Here, “Φ0” in equation (3) is the average value of the output values ​​of the learning model, and “x” is all the explanatory variables. TIFF0007760097000002.tif23166

[0034] When explanatory variables included in a set S are given, contribution calculation units 150 and 150A define a probability distribution P (term B in equation (2)) of explanatory variables for calculating a value function v(S) based on a causal graph. The causal graph is assumed to be given. It may be created manually by the user, or it may be estimated from data using a known causal graph estimation method (PC algorithm, GES, LiNGAM, etc.), or both may be used. The causal graph is assumed to be given in the following format: Here, the causal graph may be stored in advance in, for example, a causal graph storage unit.

[0035] Explain causal graphs. FIG. 4 is a diagram showing a first example of causal relationship data (causal graph) used in the factor analysis apparatus 100, 100A of the present disclosure. FIG. 5 is a diagram showing a second example of the causal relationship data (causal graph) used in the factor analysis apparatus 100, 100A of the present disclosure. FIG. 6 is a diagram showing a third example of the causal relationship data (causal graph) used in the factor analysis apparatus 100, 100A of the present disclosure. A causal graph is a directed acyclic graph (DAG) that represents the relationships between monitoring data. The causal graph is specified in the form of, for example, a graph, a matrix, or a parent-child relationship. Graph: The nodes represent the monitored data Xi, and the arrows represent the relationship between monitored data Xi and Xj. The starting point of the arrow represents the parent monitored data Xi, and the end point represents the child monitored data Xj, representing the parent-to-child relationship (Figure 4). Matrix: Rows represent parent monitored data Xi, and columns represent child monitored data Xj. If a parent-to-child relationship exists, the element in row i and column j of the matrix is ​​set to 1, and if no relationship exists, the element is set to 0 (Figure 5). Parent-child relationship: The set of parent monitoring data of child monitoring data Xj is represented as pa(Xj) to represent the parent-child relationship (Figure 6). For example, for five monitored data X1, ..., X5, the causal graphs are specified as shown in Figures 4, 5, and 6. Here, Figures 4, 5, and 6 all represent the same causal graph.

[0036] For example, when a causal graph representing the relationship between monitoring data is given, the contribution calculation units 150 and 150A express the probability distribution P of the explanatory variables (term B in equation (2)) as in the following equations (4) and (5). TIFF0007760097000003.tif73166 The term C in equation (4) indicates the relationship between the monitored data. In the relationship between the monitored data, the result (child) depends only on the cause (parent). (When the parent is given, the child and everything else except the parent are independent.) For example, suppose that the causal graph for five monitored data X1, ..., X5 is given as follows: pa(X1)=Φ pa(X2)=Φ pa(X3)={X1,X2} pa(X4)={X2} pa(X5)={X3,X4} For example, if the objective variable is X5 and the explanatory variables are X1, X2, and X4, that is, N={1,2,4} and S∈{1,4}, the probability distribution P (term B in equation (2)) can be expressed as follows: P(X2│x1,x4,x3,x5)=P(X2) ···(6) For example, if the objective variable is X5 and the explanatory variables are X1, X2, and X4, that is, N={1, 2, 4}, and S∈Φ, then P (term B in equation (2)) can be expressed as follows: P(X1,X2,X4│x3,x5)=P(X1)P(X2)P(X4│X2) ···(7) For example, if the objective variable is X5 and the explanatory variables are X1, X3, and X4, that is, N={1, 3, 4}, and S∈Φ, then P (term B in equation (2)) can be expressed as follows: P(X1,X3,X4│x2,x5)=P(X1)P(X3│X1,x2)P(X4│x2) ···(8)

[0037] Contribution calculation units 150 and 150A can use, for example, a normal distribution, a Dirichlet distribution, a t-distribution, an empirical distribution, or the like as the probability distribution P (term B in equation (2)). When a distribution having parameters is used as the probability distribution, each parameter can be determined using the training monitoring data. For example, when a normal distribution is used as the probability distribution, the expected value and the variance-covariance matrix can be calculated using the training monitoring data.

[0038] The contribution calculation units 150 and 150A calculate the contribution of the explanatory variable i of the n-th data sample of the monitoring data for factor analysis as Φin, and output it to the factor analysis units 160 and 160A and the factor analysis result output units 170 and 170A.

[0039] The factor analysis units 160 and 160A acquire and tally the contribution degrees, and calculate the factor degrees. The factor analysis units 160 and 160A calculate a factoriality, which is the degree to which each explanatory variable is a factor, based on the contribution degree. The factoriality calculated for each explanatory variable can also be said to be a value indicating the degree to which the explanatory variable is a factor that affects the objective variable. FIG. 7 is a diagram illustrating the contribution degree output by the contribution degree calculation section 150, 150A in the factor analysis apparatus 100, 100A of the present disclosure. Specifically, the contribution factor Φin calculated for each data sample of explanatory variable i is aggregated, and the factor factor Ci of explanatory variable i is calculated (Figure 7). For example, the average value of the absolute values ​​of Φin can be set as the factor degree Ci of the explanatory variable i. TIFF0007760097000004.tif21166 The factor analysis units 160 and 160A output the calculated factor levels to the factor analysis result output units 170 and 170A.

[0040] The factor analysis result output units 170 and 170A output the factor analysis results based on the factor analysis data set, the contribution degree, and the factor degree. The factor analysis result output units 170 and 170A acquire the factor analysis data set, the contribution rate, and the factor rate, and output information relating to the factor analysis result. FIG. 8 is a diagram illustrating the factor levels output by the factor analysis units 160 and 160A in the factor analysis devices 100 and 100A of the present disclosure. The factor analysis result output units 170 and 170A use the factor degrees to output information relating to the factor degrees. FIG. 9 is a diagram showing a first display example of the factor analysis result output by the factor analysis result output unit 170, 170A in the factor analysis device 100, 100A of the present disclosure. FIG. 9 shows an example of an output screen relating to the factor degrees when the number of explanatory variables is six. Information indicating the explanatory variable i and the factor level Ci are displayed (Figure 9). In the initial state, the explanatory variables are displayed in the order in which they were input or in a pre-stored order. A sort button is displayed to rearrange the results in descending order based on the factor level. When you press the sort button, the items are sorted in descending order and the sort button turns black. Pressing the sort button again will sort the explanatory variables in the order they were entered or stored. In the initial state, the results may be sorted in descending order of the factor degree. In this case, the sort button is filled in black.

[0041] The factor analysis result output units 170 and 170A use the contribution degree and the factor analysis data set to output information indicating the relationship between the contribution degree, the explanatory variable, and the response variable. FIG. 10 is a diagram showing a second display example of the factor analysis result output by the factor analysis result output unit 170, 170A in the factor analysis device 100, 100A of the present disclosure. FIG. 10 shows an example of an output screen showing the relationship between explanatory variables, contributions, and response variables for explanatory variable 1. Display a scatter plot with the explanatory variable value on the horizontal axis and the contribution rate on the vertical axis. Alternatively, the axes of the explanatory variable values ​​and the degree of contribution may be reversed to display a scatter diagram with the degree of contribution on the horizontal axis and the value of the explanatory variable on the vertical axis. In the scatter plot, the straight line indicating a contribution of 0 is shown as a dashed line. In a scatter plot, one point corresponds to one data sample. The density of the points indicates the magnitude relationship of the response variable values ​​of the factorial analysis dataset. Clicking the Expand button will display a list of explanatory variables, and selecting an explanatory variable will display a scatter plot corresponding to the selected explanatory variable. When the response variable is discretized data, that is, categorical data, the shape of the points may be changed instead of the density of the points.

[0042] In addition to the above configuration, the factor analysis devices 100 and 100A may also be configured to include a control unit (not shown) and a storage unit (not shown). A control unit (not shown) controls the entire factor analysis apparatus 100, 100A. The control unit (not shown) starts up the factor analysis apparatus 100, 100A in accordance with an external command, for example, or shuts down or puts the factor analysis apparatus 100, 100A into a sleep state. A storage unit (not shown) stores each piece of data used in the factor analysis devices 100 and 100A. The storage unit (not shown) stores, for example, the output (output data) from each component in the factor analysis devices 100 and 100A, and outputs data requested by each component to the requesting component. This also applies to the other embodiments.

[0043] An example of processing by the factor analysis devices 100 and 100A will be described. The process shown in FIG. 3 is a factor analysis method by the factor analysis apparatus 100, 100A, and includes a data acquisition step in which the data acquisition unit 110, 110A of the factor analysis apparatus 100, 100A acquires multiple types of monitoring data related to a monitoring target; a variable setting step in which the variable setting unit 120, 120A of the factor analysis apparatus 100, 100A generates, based on the monitoring data, monitoring data for learning, monitoring data for factor analysis, a learning data set consisting of explanatory variables and dependent variables, and a factor analysis data set; a model learning step in which the model learning unit 130, 130A of the factor analysis apparatus 100, 100A generates, based on the learning data set, a learning model that is trained to input explanatory variables and output dependent variables; and a causal relationship data acquisition unit 140, 140A of the factor analysis apparatus 100, 100A generates a causal relationship data in the multiple types of monitoring data. a contribution calculation step in which a contribution calculation unit 150, 150A of the factor analysis device 100, 100A calculates a contribution, which is the degree of influence that an explanatory variable has on a target variable, based on the causal relationship data indicating the causal relationship in multiple types of monitoring data, the learning model, the monitoring data for learning, and the monitoring data for factor analysis; a factor analysis step in which a factor analysis unit 160, 160A of the factor analysis device 100, 100A calculates a factor degree, which is the degree to which each explanatory variable is a factor, based on the contribution degree; and a factor analysis result output step in which a factor analysis result output unit 170, 170A of the factor analysis device 100, 100A outputs a factor analysis result based on the factor analysis dataset, the contribution degree, and the factor degree. In addition, if the contribution calculation unit 150, 150A is configured to directly receive the causal graph from the causal graph storage unit, the factor analysis method may include a step in which the contribution calculation unit 150, 150A receives the causal graph from the causal graph storage unit instead of the causal relationship data acquisition step.

[0044] 3, the factor analysis device 100, 100A first executes a monitoring data acquisition process (step ST110). In the monitoring data acquisition process, the data acquisition units 110 and 110A of the factor analysis devices 100 and 100A acquire multiple types of monitoring data related to the monitoring target. The data acquisition units 110 and 110A acquire sensor data and production management information from the sensor 200 as monitoring data, and output them to the variable setting units 120 and 120A.

[0045] Next, the factor analysis device 100, 100A executes a variable setting process (step ST120). In the variable setting process, the variable setting units 120, 120A of the factor analysis devices 100, 100A generate learning monitoring data, factor analysis monitoring data, a learning dataset, and a factor analysis dataset based on the monitoring data. The variable setting units 120, 120A perform variable setting processing on the monitoring data output by the data acquisition units 110, 110A in step ST110, and output a learning data set to the model learning units 130, 130A, the learning monitoring data and the factor analysis monitoring data to the contribution calculation units 150, 150A, and the factor analysis data set to the factor analysis result output units 170, 170A.

[0046] Next, the factor analysis device 100, 100A executes a model learning process (step ST130). In the model learning process, the model learning units 130 and 130A of the factor analysis devices 100 and 100A generate a learning model that is trained to input explanatory variables and output objective variables based on a learning dataset. The model learning units 130 and 130A learn the learning data set output by the variable setting units 120 and 120A in step ST120 so that explanatory variables are input and objective variables are output, and output the learning model to the contribution degree calculation units 150 and 150A.

[0047] Next, the factor analysis device 100, 100A executes a causal relationship data acquisition process (step ST140). In the causal relationship data acquisition process, the causal relationship data acquisition units 140, 140A of the factor analysis devices 100, 100A acquire causal relationship data indicating causal relationships in multiple types of monitoring data.

[0048] Next, the factor analysis device 100, 100A executes a contribution calculation process (step ST150). In the contribution calculation process, the contribution calculation unit 150, 150A of the factor analysis device 100, 100A calculates the contribution, which is the degree of influence that the explanatory variable has on the target variable, based on the causal relationship data indicating the causal relationships in multiple types of monitoring data, the learning model, the monitoring data for learning, and the monitoring data for factor analysis. The contribution calculation units 150, 150A acquire the causal graph, and perform a contribution calculation process on the learning model output by the model learning units 130, 130A in step ST130, the learning monitoring data output by the variable setting units 120, 120A in step ST120, and the monitoring data for factor analysis, and output the contributions to the factor analysis units 160, 160A and the factor analysis result output units 170, 170A.

[0049] Next, the factor analysis device 100, 100A executes the factor analysis process (step ST160). In the factor analysis process, the factor analysis units 160 and 160A of the factor analysis devices 100 and 100A calculate a factor degree, which is the degree to which each explanatory variable is a factor, based on the contribution degree. The factor analysis sections 160 and 160A perform factor analysis processing on the contribution degrees output by the contribution degree calculation sections 150 and 150A in step ST150, and output the factor degrees to the factor analysis result output sections 170 and 170A.

[0050] Next, the factor analysis device 100, 100A executes a factor analysis result output process (step ST170). In the factor analysis result output process, the factor analysis result output unit 170, 170A of the factor analysis device 100, 100A outputs the factor analysis result based on the factor analysis data set, the contribution degree, and the factor degree. The factor analysis result output units 170, 170A acquire the factor analysis data set output by the variable setting units 120, 120A in step ST120, the contributions output by the contribution calculation units 150, 150A in step ST150, and the factor degrees output by the factor analysis units 160, 160A in step ST160, and present information related to the factor analysis results.

[0051] Next, the factor analysis device 100, 100A ends the processing shown in FIG.

[0052] The factor analysis device of the present disclosure is configured as follows. a data acquisition unit that acquires multiple types of monitoring data related to a monitoring target; a variable setting unit that generates, based on the monitoring data, training monitoring data, factor analysis monitoring data, a training dataset including explanatory variables and target variables, and a factor analysis dataset; a model learning unit that generates a learning model that is trained to input explanatory variables and output objective variables based on the learning dataset; a contribution calculation unit that calculates a contribution, which is the degree of influence that an explanatory variable has on a target variable, based on causal relationship data indicating causal relationships in multiple types of monitoring data, the learning model, the monitoring data for learning, and the monitoring data for factor analysis; a factor analysis unit that calculates a factor degree, which is the degree to which each explanatory variable is a factor, based on the contribution degree; a factor analysis result output unit that outputs a factor analysis result based on the factor analysis dataset, the contribution rate, and the factor rate; A factor analysis device equipped with As a result, the present disclosure has an effect of providing a factor analysis device that can improve the accuracy of factor analysis.

[0053] The factor analysis method of the present disclosure is configured as follows. A factor analysis method using a factor analysis device, a data acquisition step in which a data acquisition unit of the factor analysis device acquires multiple types of monitoring data related to a monitoring target; a variable setting step in which a variable setting unit of the factor analysis device generates, based on the monitoring data, training monitoring data, factor analysis monitoring data, a training dataset including explanatory variables and target variables, and a factor analysis dataset; a model learning step in which a model learning unit of the factor analysis device generates a learning model that is trained to input explanatory variables and output a target variable based on the learning dataset; a contribution calculation step in which a contribution calculation unit of the factor analysis device calculates a contribution, which is the degree of influence that an explanatory variable has on a target variable, based on causal relationship data indicating causal relationships in multiple types of monitoring data, the learning model, the learning monitoring data, and the factor analysis monitoring data; a factor analysis step in which a factor analysis unit of the factor analysis device calculates a factor degree, which is the degree to which each explanatory variable is a factor, based on the contribution degree; a factor analysis result output step in which a factor analysis result output unit of the factor analysis device outputs a factor analysis result based on the factor analysis dataset, the contribution degree, and the factor degree; A factor analysis method with. As a result, the present disclosure has an effect of providing a factor analysis method that can improve the accuracy of factor analysis.

[0054] The factor analysis system of the present disclosure is configured as follows. A sensor, a data acquisition unit that acquires multiple types of monitoring data related to the monitoring target measured by the sensor; a variable setting unit that generates, based on the monitoring data, training monitoring data, factor analysis monitoring data, a training dataset including explanatory variables and target variables, and a factor analysis dataset; a model learning unit that generates a learning model that is trained to input explanatory variables and output objective variables based on the learning dataset; a contribution calculation unit that calculates a contribution, which is the degree of influence that an explanatory variable has on a target variable, based on causal relationship data indicating causal relationships in multiple types of monitoring data, the learning model, the monitoring data for learning, and the monitoring data for factor analysis; a factor analysis unit that calculates a factor degree, which is the degree to which each explanatory variable is a factor, based on the contribution degree; a factor analysis result output unit that outputs a factor analysis result based on the factor analysis dataset, the contribution rate, and the factor rate; a display device that displays the factor analysis result output by the factor analysis result output unit; A factor analysis system with As a result, the present disclosure has an effect of providing a factor analysis system that can improve the accuracy of factor analysis.

[0055] The factor analysis program of the present disclosure is configured as follows. Computer, a data acquisition unit that acquires multiple types of monitoring data related to a monitoring target; a variable setting unit that generates, based on the monitoring data, training monitoring data, factor analysis monitoring data, a training dataset including explanatory variables and target variables, and a factor analysis dataset; a model learning unit that generates a learning model that is trained to input explanatory variables and output objective variables based on a learning dataset; a contribution calculation unit that calculates a contribution, which is the degree of influence that an explanatory variable has on a target variable, based on causal relationship data indicating causal relationships in multiple types of monitoring data, the learning model, the monitoring data for learning, and the monitoring data for factor analysis; a factor analysis unit that calculates a factor degree, which is the degree to which each explanatory variable is a factor, based on the contribution degree; a factor analysis result output unit that outputs a factor analysis result based on the factor analysis dataset, the contribution rate, and the factor rate; A factor analysis program characterized by causing the program to operate as a factor analysis device comprising: As a result, the present disclosure has an effect of providing a factor analysis program that can improve the accuracy of factor analysis.

[0056] The factor analysis device of the present disclosure is further configured as follows. The factor analysis device further comprises: The data acquisition unit Obtaining, as the monitoring data, a plurality of time-series sensor data collected by a plurality of sensors provided in the monitored equipment and production management information related to production of the monitored equipment; characterized in that Factor analysis device. As a result, the present disclosure has an effect of providing a factor analysis device that can improve the accuracy of factor analysis related to production equipment. Furthermore, the present disclosure achieves the same effects as the above by applying the above configuration to the above factor analysis method, the above factor analysis system, or the above factor analysis program.

[0057] The factor analysis device of the present disclosure is further configured as follows. The factor analysis device further comprises: The contribution calculation unit calculates the contribution using XAI (Explainable AI). Factor analysis device. As a result, the present disclosure has the effect of providing a factor analysis device that can calculate the contribution using XAI and thus further improve the accuracy of factor analysis. The present disclosure also has the effect of providing a factor analysis device that makes it easy for a user to interpret the process of factor analysis. Furthermore, the present disclosure achieves the same effects as the above by applying the above configuration to the above factor analysis method, the above factor analysis system, or the above factor analysis program.

[0058] Embodiment 2 In the second embodiment, an embodiment will be described that allows the evaluation results regarding the validity of explanatory variables to be reflected. In the description of the second embodiment, the same content as that already explained in the first embodiment may be omitted as appropriate.

[0059] An example of the configuration of a factor analysis system including the factor analysis device 100B will be described. FIG. 11 is a diagram illustrating an example of the configuration of a factor analysis system 10 including a factor analysis apparatus 100B according to the second embodiment of the present disclosure. 11 shows only the configuration characteristic of the second embodiment compared to the configuration shown in the first embodiment. In the second embodiment, the configuration shown in the first embodiment but not shown in FIG. 11 may be added.

[0060] The factor analysis device of the factor analysis system may be configured to accept an evaluation of the validity of the explanatory variables from a user on an output screen relating to the factor levels output by the factor analysis result output unit. The factor analysis system 10 includes a factor analysis device 100B, a sensor 200, and a display device 300.

[0061] The factor analysis device 100B includes a data acquisition unit 110B, a variable setting unit 120B, a model learning unit 130B, a causal relationship data acquisition unit 140B, a contribution calculation unit 150B, a factor analysis unit 160B, and a factor analysis result output unit 170B. 11 shows the variable setting unit 120B, the model learning unit 130B, the causal relationship data acquisition unit 140B, the contribution calculation unit 150B, the factor analysis unit 160B, and the factor analysis result output unit 170B. The following mainly describes the contents not described in the above-mentioned embodiment.

[0062] The factor analysis result output section 170B outputs information on at least one explanatory variable that has been determined to be invalid by the evaluation of validity to the variable setting section 120B as explanatory variable removal information. FIG. 12 is a diagram showing an example of display of the factor analysis result output by the factor analysis result output unit 170B in the factor analysis apparatus 100B according to the second embodiment of the present disclosure. The factor analysis result output unit 170B, for example, provides a check box in the removal decision column on the output screen relating to the factor degree, and accepts input from the user. For example, the initial state of a check box is unchecked. If an input operation (pressing or pressing) is performed on the check box when it is unchecked, it will become checked. Also, if an input operation (pressing or pressing) is performed on the check box when it is checked, it will become unchecked. For example, explanatory variables corresponding to checked check boxes can be used as explanatory variable removal information. In the figure, explanatory variables 3 and 4 are set as explanatory variable removal information. When at least one check box is checked and the user clicks the button to re-run the factor analysis, the factor analysis result output unit 170B outputs the information to the variable setting unit 120B as explanatory variable removal information, and performs processing related to updating based on the user's evaluation of validity.

[0063] The variable setting unit 120B uses the explanatory variable removal information output by the factor analysis result output unit 170B and the information of the monitoring data set as explanatory variables among the monitoring data to newly set the monitoring data that is not included in the "monitoring data included in the explanatory variable removal information" among the "monitoring data set as explanatory variables" as explanatory variables after updating. Here, it is assumed that the information on the monitoring data set as the explanatory variables is stored in the variable setting unit 120B.

[0064] The factor analysis device 100B is configured to thereafter replace the explanatory variables with the updated explanatory variables and perform the same processing as in embodiment 1, obtain the updated learning model, the updated contribution rate, and the updated factor rate, and output information related to the updated factor analysis.

[0065] The processing in the above configuration will be explained. The factor analysis result output section 170B outputs information on at least one explanatory variable that has been determined to be invalid by the evaluation of validity to the variable setting section 120B as explanatory variable removal information. The variable setting unit 120B uses the explanatory variable removal information output by the factor analysis result output unit 170B and the information of the monitoring data set as explanatory variables among the monitoring data to newly set the monitoring data that is not included in the "monitoring data included in the explanatory variable removal information" among the "monitoring data set as explanatory variables" as explanatory variables after updating. Hereafter, in the processing described in embodiment 1, the explanatory variables are replaced with the updated explanatory variables, and processing similar to embodiment 1 is performed to obtain the updated learning model, updated contribution rate, and updated factor rate, and output information regarding the updated factor analysis. The above-described process of updating based on the user's evaluation of validity may be repeated.

[0066] In the second embodiment, a configuration has been described in which the user evaluates the factor analysis results based on the information on the factor analysis output on the display device, examines the factor candidates, removes the factor candidates that are determined to be unnecessary, and performs the factor analysis process again, thereby improving the accuracy of the factor analysis.

[0067] The factor analysis device of the present disclosure is further configured as follows. The factor analysis device according to another embodiment further includes: The factor analysis result output unit receiving an evaluation of the validity of the explanatory variables based on the result of the factor analysis; The variable setting unit setting the explanatory variables without using the monitoring data that indicates that the explanatory variables should be removed based on the results of the evaluation regarding the validity of the explanatory variables; Factor analysis device. As a result, the present disclosure has an effect of providing a factor analysis device that can further improve the accuracy of factor analysis. Furthermore, the present disclosure achieves the same effects as the above by applying the above configuration to the above factor analysis method, the above factor analysis system, or the above factor analysis program.

[0068] Embodiment 3 In the third embodiment, a form will be described in which results that satisfy aggregation conditions indicating conditions related to response variables and explanatory variables can be output. In the description of the third embodiment, the same content as that already explained in the first and second embodiments may be omitted as appropriate.

[0069] Fig. 13 is a diagram illustrating a configuration example of a factor analysis system 10 including a factor analysis apparatus 100C according to a third embodiment of the present disclosure. Note that Fig. 13 illustrates only the configuration characteristic of the third embodiment, in contrast to the configurations illustrated in the first and second embodiments. In the third embodiment, the configurations illustrated in the first and second embodiments but not illustrated in Fig. 13 may be added. FIG. 14 is a diagram illustrating the aggregation conditions used in the factor analysis apparatus 100C according to the third embodiment of the present disclosure.

[0070] The factor analysis device 100C may be configured to calculate, in the factor analysis unit 160C, a factor degree for a contribution degree that satisfies a condition, based on aggregation condition information indicating a condition related to a response variable or an explanatory variable input by a user.

[0071] The factor analysis system 10 includes a factor analysis device 100C, a sensor 200, and a display device 300. The factor analysis device 100C includes a data acquisition unit 110C, a variable setting unit 120C, a model learning unit 130C, a causal relationship data acquisition unit 140C, a contribution calculation unit 150C, a factor analysis unit 160C, a factor analysis result output unit 170C, and a calculation condition acquisition unit 180C. 13 shows a variable setting unit 120C, a contribution calculation unit 150C, a factor analysis unit 160C, a factor analysis result output unit 170C, and a tallying condition acquisition unit 180C. The following mainly describes the contents not described in the above-mentioned embodiment.

[0072] The tallying condition acquisition unit 180C acquires the tallying conditions. The tallying condition information indicating the tallying conditions can be given in a format such as that shown in FIG. 14, for example. The format shown in FIG. 14 is a format in which lower and upper limits are set for each response variable and explanatory variable.

[0073] The factor analysis unit 160C acquires the aggregation conditions, and outputs the conditional contribution degree, the conditional factor degree, and the conditional factor analysis data set corresponding to the monitoring data indicated in the aggregation conditions in the factor analysis data set so as to satisfy the aggregation conditions.

[0074] The factor analysis result output unit 170C outputs the factor analysis result using the conditional contribution degree, the conditional factor degree, and the conditional factor analysis data set output by the factor analysis unit 160C.

[0075] An example of processing by the factor analysis device 100C will be described. First, the tallying condition acquisition unit 180C of the factor analysis apparatus 100C acquires the tallying conditions.

[0076] Next, the factor analysis unit 160C acquires the aggregation conditions, and outputs the conditional contribution degree, the conditional factor degree, and the conditional factor analysis data set corresponding to the monitoring data indicated in the aggregation conditions in the factor analysis data set so as to satisfy the aggregation conditions. The factor analysis unit 160C of the factor analysis apparatus 100C uses the tallying condition information acquired by the tallying condition acquisition unit 180C to calculate the factor degree for the contribution degree that satisfies the predetermined condition in the same manner as in the first embodiment. For example, the contribution degree that satisfies a predetermined condition can be determined by extracting data sample numbers of a factorial analysis dataset that are equal to or greater than the lower limit and equal to or less than the upper limit for each of the dependent variable and the explanatory variable, and determining the contribution degree corresponding to the extracted data sample numbers for all of the dependent variable and the explanatory variable.Furthermore, the factorial analysis dataset corresponding to the extracted data sample numbers for all of the dependent variable and the explanatory variable can be determined to be the factorial analysis dataset that satisfies the predetermined condition. If only an upper limit or a lower limit is set, data sample numbers that are less than the upper limit or greater than the lower limit are extracted; if neither an upper limit nor a lower limit is set, all data sample numbers are extracted. For example, as shown in FIG. 14, the contributions corresponding to the data sample numbers that satisfy all of the following conditions are extracted. The target variable is 2 or more and 4 or less Explanatory variable 1 is 0 or more Explanatory variable 3 is 10 or less Explanatory variable 4 is between 0.5 and 0.7 Explanatory variable 5 is 5 or more

[0077] Next, the factor analysis unit 160C acquires the aggregation conditions, and outputs the conditional contribution degree, the conditional factor degree, and the conditional factor analysis data set corresponding to the monitoring data indicated in the aggregation conditions in the factor analysis data set so as to satisfy the aggregation conditions. Specifically, the factor analysis unit 160C outputs the factor degree calculated from the contribution degree that satisfies the predetermined condition as a conditional factor degree, the contribution degree that satisfies the predetermined condition as a conditional contribution degree, and the factor analysis dataset that satisfies the predetermined condition as a conditional factor analysis dataset to the factor analysis result output unit 170C. More specifically, the factor analysis unit 160C calculates the contribution degree that satisfies predetermined conditions for the contribution degree output by the contribution degree calculation unit 150C, the factor analysis data set output by the variable setting unit 120C, and the aggregation condition information, and outputs the calculated conditional factor degree, conditional contribution degree, and conditional factor analysis data set to the factor analysis result output unit 170C.

[0078] The factor analysis result output unit 170C outputs the factor analysis result using the conditional contribution degree, the conditional factor degree, and the conditional factor analysis data set output by the factor analysis unit 160C. Specifically, the factor analysis result output unit 170C replaces the contribution degree with a conditional contribution degree, the factor degree with a conditional factor degree, and the factor analysis dataset with a conditional factor analysis dataset, and performs the same processing as in the first embodiment.

[0079] In the third embodiment, conditions are set for the objective variable and the explanatory variables, and only the contributions under certain conditions are tallied to calculate the factoriality, thereby further improving the accuracy of the factor analysis.

[0080] The factor analysis device of the present disclosure is further configured as follows. The factor analysis device according to another embodiment further includes: The factor analysis unit acquire a counting condition, and output a conditional contribution degree, a conditional factor degree, and a conditional factor analysis data set corresponding to the monitoring data indicated in the counting condition among the factor analysis data sets so as to satisfy the counting condition; The factor analysis result output unit outputting a factor analysis result using the conditional contribution degree, the conditional factor degree, and the conditional factor analysis dataset output by the factor analysis unit; Factor analysis device. As a result, the present disclosure has an effect of providing a factor analysis device that can further improve the accuracy of factor analysis. Furthermore, the present disclosure achieves the same effects as the above by applying the above configuration to the above factor analysis method, the above factor analysis system, or the above factor analysis program.

[0081] Embodiment 4 The fourth embodiment describes a form that can evaluate the fitness of a learning model to monitoring data. In the description of the fourth embodiment, the same content as that already explained in the first, second and third embodiments may be omitted as appropriate.

[0082] Fig. 15 is a diagram illustrating a configuration example of a factor analysis system 10 including a factor analysis apparatus 100D according to a fourth embodiment of the present disclosure. Note that Fig. 15 illustrates only the configuration characteristic of the fourth embodiment, in contrast to the configurations illustrated in the first, second, and third embodiments. In the fourth embodiment, the configurations illustrated in the first, second, and third embodiments but not illustrated in Fig. 15 may be added. FIG. 16 is a diagram showing a first display example of the factor analysis result output by the factor analysis result output unit 170D in the factor analysis apparatus 100D according to the fourth embodiment of the present disclosure. FIG. 17 is a diagram showing a second display example of the factor analysis result output by the factor analysis result output unit 170D in the factor analysis apparatus 100D according to the fourth embodiment of the present disclosure. The factor analysis system 10 includes a factor analysis device 100D, a sensor 200, and a display device 300.

[0083] The factor analysis device 100D may include a model fitness evaluation unit 190D that evaluates the fitness of the learning model to the monitoring data. The factor analysis device 100D includes a data acquisition unit 110D, a variable setting unit 120D, a model learning unit 130D, a causal relationship data acquisition unit 140D, a contribution calculation unit 150D, a factor analysis unit 160D, a factor analysis result output unit 170D, a counting condition acquisition unit 180D, and a model fitness evaluation unit 190D. 15 shows variable setting unit 120D, model learning unit 130D, factor analysis result output unit 170D, and model fitness evaluation unit 190D. The following mainly describes the contents not described in the above-mentioned embodiment.

[0084] The model fitness evaluation unit 190D calculates the fitness of the learning model using the factor analysis data set and the learning model.

[0085] The factor analysis result output unit 170D outputs the factor analysis result by further using the goodness of fit calculated by the model goodness of fit evaluation unit 190D.

[0086] An example of processing by the factor analysis device 100D will be described. The model fitness evaluation unit 190D of the factor analysis device 100D uses the factor analysis dataset output by the variable setting unit 120D and the learning model output by the model learning unit 130D to generate a learning model output value, which is the output when the explanatory variables of the factor analysis dataset are input into the learning model. The model fitness evaluation unit 190D calculates the fitness using the generated learning model output value and the objective variable of the data set for factor analysis. The model fitness evaluation unit 190D outputs the generated learning model output value and the calculated fitness to the factor analysis result output unit 170D.

[0087] The factor analysis result output unit 170D of the factor analysis device 100D outputs information about the fitness using the fitness output by the model fitness evaluation unit 190D. In addition, the factor analysis result output unit 170D outputs information about the learning model output using the learning model output value output by the model fitness evaluation unit 190D and the factor analysis dataset output by the variable setting unit 120D. The model fitness evaluation unit 190D inputs the explanatory variables of the factor analysis dataset into the learning model, generates a learning model output value, and compares the learning model output value with the objective variable of the factor analysis dataset to calculate the fitness. Here, the degree of conformance is determined by using at least one accuracy evaluation index set by the user. When the response variable is continuous, for example, the mean absolute error (MAE), the mean squared error (MSE), the root mean squared error (RMSE), the coefficient of determination, etc. can be used. When the objective variable is binary categorical data, for example, accuracy, precision, recall, F1 value, etc. can be used. When the objective variable is categorical data with three or more values, for example, accuracy, average F1 value, etc. can be used. However, if the training data set and the factor analysis data set are equal, the goodness of fit may be calculated by cross-validation. In this case, the training model used is not the training model output from the model training unit 130D, but a new training model trained for cross-validation. Here, for cross validation, for example, leave-one-out cross validation, k-fold cross validation, or stratified k-fold cross validation can be used. If two or more goodness of fit values ​​are calculated for one accuracy evaluation index through cross-validation, one representative value for the accuracy evaluation index is calculated using, for example, the average, maximum value, minimum value, or median value. The model fitness evaluation unit 190D outputs the generated learning model output value and the fitness calculated using at least one or more accuracy evaluation indexes to the factor analysis result output unit 170D.

[0088] The factor analysis result output unit 170D uses the fitness output by the model fitness evaluation unit 190D to output information relating to the fitness. For example, assume that the types of accuracy evaluation indices and the corresponding degrees of fit are displayed in a table format as shown in FIG. FIG. 16 shows a case where the objective variable is binary categorical data, and the F1 value, accuracy, and precision are selected by the user as the accuracy evaluation indexes.

[0089] The factor analysis result output unit 170D outputs information related to the learning model output using the learning model output value output by the model fitness evaluation unit 190D and the factor analysis data set output by the variable setting unit 120D. For example, a scatter plot is displayed with the data sample number of the factor analysis dataset on the horizontal axis and the response variable and model output value on the vertical axis, as shown in Figure 17. Instead of a scatter plot, it may also be displayed as a line graph. In FIG. 17, black circles represent the values ​​of the objective variables, and white circles represent the learning model output values.

[0090] The fourth embodiment shows a configuration that can evaluate the fitness of a learning model. This improves the reliability of factor analysis by determining whether the learning model is good or bad. For example, if the fitness is poor, the settings of explanatory variables can be revised.

[0091] The factor analysis device of the present disclosure is further configured as follows. The factor analysis device according to another embodiment further includes: a model fitness evaluation unit that calculates a fitness of the learning model using the factor analysis dataset and the learning model, The factor analysis result output unit and outputting a factor analysis result by further using the fitness calculated by the model fitness evaluation unit. Factor analysis device. As a result, the present disclosure has an effect of providing a factor analysis device that can further improve the reliability of factor analysis. Furthermore, the present disclosure achieves the same effects as the above by applying the above configuration to the above factor analysis method, the above factor analysis system, or the above factor analysis program.

[0092] Here, a hardware configuration for realizing the functions according to the configuration of the present disclosure described above will be described. Fig. 18 is a diagram illustrating a first example of a hardware configuration for realizing the functions of the configuration of the present disclosure. The hardware configuration illustrated in Fig. 18 realizes the functions of factor analysis devices 100, 100A, 100B, 100C, and 100D. 19 is a diagram illustrating a second example of a hardware configuration for implementing the functions of the configuration of the present disclosure. The hardware configuration illustrated in FIG. 19 executes software that implements the functions of factor analysis devices 100, 100A, 100B, 100C, and 100D. The auxiliary storage device 1010 is a storage device having a storage area for reading and writing data. A storage unit (not shown) is realized by the auxiliary storage device 1010 or other memory (not shown). The information input device 1030 is a device for inputting data to the factor analysis devices 100, 100A, 100B, 100C, and 100D, and is, for example, a touch panel, a mouse, and a keyboard. Data input using the information input device 1030 is input to the factor analysis device via the information input IF 1020 . The display IF 1040 is an IF that relays data output from the factorial analyzers 100, 100A, 100B, 100C, and 100D to the display 1050. The display 1050 displays the data. For example, the factor analysis result output units 170, 170A, 170B, 170C, and 170D output the results to the display 1050 via the display IF 1040. The display 1050 displays the estimation results input via the display IF 1040 on the screen. When the processing circuitry is dedicated hardware, the processing circuitry 1060 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a combination thereof. The above processing circuit uses the above hardware to realize the functions of data acquisition units 110, 110A, 110B, 110C, 110D, variable setting units 120, 120A, 120B, 120C, 120D, model learning units 130, 130A, 130B, 130C, 130D, causal relationship data acquisition units 140, 140A, 140B, 140C, 140D, contribution calculation units 150, 150A, 150B, 150C, 150D, factor analysis units 160, 160A, 160B, 160C, 160D, factor analysis result output units 170, 170A, 170B, 170C, 170D, aggregation condition acquisition units 180C, 180D, model fitness evaluation unit 190D, and a control unit not shown. When the processing circuit is the processor 1070, the functions of the factor analysis devices 100, 100A, 100B, 100C, and 100D are realized by software, firmware, or a combination of software and firmware. The software or firmware is written as a program and stored in memory 1080 . The processor 1070 reads and executes the programs stored in the memory 1080 to realize the functions of the factor analysis devices 100, 100A, 100B, 100C, and 100D. These programs cause a computer to execute each procedure or method of the functions of the factorial analyzers 100, 100A, 100B, 100C, and 100D. Processor 1070 executes software that realizes the functions of data acquisition units 110, 110A, 110B, 110C, 110D, variable setting units 120, 120A, 120B, 120C, 120D, model learning units 130, 130A, 130B, 130C, 130D, causal relationship data acquisition units 140, 140A, 140B, 140C, 140D, contribution calculation units 150, 150A, 150B, 150C, 150D, factor analysis units 160, 160A, 160B, 160C, 160D, factor analysis result output units 170, 170A, 170B, 170C, 170D, aggregation condition acquisition units 180C, 180D, model fitness evaluation unit 190D, and a control unit (not shown). The memory 1080 may be a computer-readable storage medium that stores a program for causing the factor analyzers 100, 100A, 100B, 100C, and 100D to function. Memory 1080 includes, for example, non-volatile or volatile semiconductor memory such as RAM (Random Access Memory), ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable Read Only Memory), EEPROM (Electrically-EPROM), magnetic disk, flexible disk, optical disk, compact disk, mini disk, DVD, etc.

[0093] It should be noted that some of the functions of the factor analysis devices 100, 100A, 100B, 100C, and 100D may be realized by dedicated hardware and some by software or firmware. The functions of data acquisition units 110, 110A, 110B, 110C, 110D, variable setting units 120, 120A, 120B, 120C, 120D, model learning units 130, 130A, 130B, 130C, 130D, causal relationship data acquisition units 140, 140A, 140B, 140C, 140D, contribution calculation units 150, 150A, 150B, 150C, 150D, factor analysis units 160, 160A, 160B, 160C, 160D, factor analysis result output units 170, 170A, 170B, 170C, 170D, aggregation condition acquisition units 180C, 180D, model fitness evaluation unit 190D, and a control unit (not shown) may be realized by separate processing circuits, or may be realized together by a processing circuit.

[0094] Or, data acquisition units 110, 110A, 110B, 110C, 110D, variable setting units 120, 120A, 120B, 120C, 120D, model learning units 130, 130A, 130B, 130C, 130D, causal relationship data acquisition units 140, 140A, 140B, 140C, 140D, contribution degree calculation units 150, 150A, 150B, 150C, 150D, factor analysis units 160, 160A , 160B, 160C, 160D, factor analysis result output units 170, 170A, 170B, 170C, 170D, aggregation condition acquisition units 180C, 180D, model fitness evaluation unit 190D, and some of the functions of a control unit not shown may be realized by processor 10001 and memory 10002, and the remaining functions may be realized by processing circuit 20001.

[0095] Thus, the processing circuitry may implement each of the above functions through hardware, software, firmware, or a combination thereof.

[0096] It should be noted that the present disclosure allows for free combination of the embodiments, modification of any of the components of the embodiments, or omission of any of the components of the embodiments. [Industrial Applicability]

[0097] The present disclosure can improve the accuracy of factor analysis by calculating the contribution of each factor while taking into consideration the dependency relationships or causal relationships between multiple factors, and is therefore suitable for use in, for example, factor analysis devices, factor analysis methods, factor analysis systems, and factor analysis programs used in factor analysis of production equipment. [Explanation of symbols]

[0098] 10 Factor analysis system, 100, 100A, 100B, 100C, 100D Factor analysis device, 110, 110A, (110B, 110C, 110D) Data acquisition section, 120, 120A, 120B, 120C, 120D Variable setting section, 130, 130A, 130B, 130C, 130D Model learning section, 140, 140A, 140B, (140C, 140D) Causal relationship data acquisition section, 150, 150A, 150B, 150C, (150D) Contribution calculation section, 160, 160A, 160B, 160C, (160D) Factor analysis section, 170, 170A, 170B, 170C, 170D Factor analysis result output unit, 180C, (180D) aggregation condition acquisition unit, 190D model fitness evaluation unit, 200 sensor, 300 display device, 1010 auxiliary storage device, 1020 information input interface (information input IF), 1030 information input device, 1040 display interface (display IF), 1050 display, 1060 processing circuit, 1070 processor, 1080 memory.

Claims

1. a data acquisition unit that acquires multiple types of monitoring data related to a monitoring target; a variable setting unit that generates, based on the monitoring data, training monitoring data, factor analysis monitoring data, a training dataset including explanatory variables and target variables, and a factor analysis dataset; a model learning unit that generates a learning model that is trained to input explanatory variables and output objective variables based on the learning dataset; a contribution calculation unit that calculates a contribution, which is the degree of influence that an explanatory variable has on a target variable, based on causal relationship data indicating causal relationships in multiple types of monitoring data, the learning model, the monitoring data for learning, and the monitoring data for factor analysis; a factor analysis unit that calculates a factor degree, which is the degree to which each of the explanatory variables is a factor, based on the contribution degree; a factor analysis result output unit that outputs a factor analysis result based on the factor analysis dataset, the contribution rate, and the factor rate; A factor analysis device equipped with

2. The data acquisition unit Obtaining, as the monitoring data, a plurality of time-series sensor data collected by a plurality of sensors installed in the monitored equipment and production management information related to production of the monitored equipment; characterized in that The factor analysis device according to claim 1 .

3. The contribution degree calculation unit calculates the contribution degree using XAI (Explainable AI). characterized in that 3. The factor analysis device according to claim 1 or 2.

4. the factor analysis result output unit receives an evaluation of the validity of the explanatory variables based on the factor analysis result; the variable setting unit sets the explanatory variables without using the monitoring data that is the explanatory variable that has been evaluated to be removed based on the result of the evaluation regarding the validity of the explanatory variables.

3. The factor analysis device according to claim 1 or 2.

5. The factor analysis unit acquire a counting condition, and output a conditional contribution degree, a conditional factor degree, and a conditional factor analysis data set corresponding to the monitoring data indicated in the counting condition among the factor analysis data sets so as to satisfy the counting condition; The factor analysis result output unit outputting a factor analysis result using the conditional contribution degree, the conditional factor degree, and the conditional factor analysis dataset output by the factor analysis unit; 3. The factor analysis device according to claim 1 or 2.

6. a model fitness evaluation unit that calculates a fitness of the learning model using the factor analysis dataset and the learning model, The factor analysis result output unit and outputting a factor analysis result by further using the fitness calculated by the model fitness evaluation unit.

3. The factor analysis device according to claim 1 or 2.

7. A factor analysis method using a factor analysis device, a data acquisition step in which a data acquisition unit of the factor analysis device acquires multiple types of monitoring data related to a monitoring target; a variable setting step in which a variable setting unit of the factor analysis device generates, based on the monitoring data, training monitoring data, factor analysis monitoring data, a training dataset including explanatory variables and target variables, and a factor analysis dataset; a model learning step in which a model learning unit of the factor analysis device generates a learning model that is trained to input explanatory variables and output a target variable based on the learning dataset; a contribution calculation step in which a contribution calculation unit of the factor analysis device calculates a contribution, which is the degree of influence that an explanatory variable has on a target variable, based on causal relationship data indicating causal relationships in multiple types of monitoring data, the learning model, the learning monitoring data, and the factor analysis monitoring data; a factor analysis step in which a factor analysis unit of the factor analysis device calculates a factor degree, which is the degree to which each explanatory variable is a factor, based on the contribution degree; a factor analysis result output step in which a factor analysis result output unit of the factor analysis device outputs a factor analysis result based on the factor analysis dataset, the contribution degree, and the factor degree; A factor analysis method with.

8. A computer, a data acquisition unit that acquires multiple types of monitoring data related to a monitoring target; a variable setting unit that generates, based on the monitoring data, training monitoring data, factor analysis monitoring data, a training dataset including explanatory variables and target variables, and a factor analysis dataset; a model learning unit that generates a learning model that is trained to input explanatory variables and output objective variables based on the learning dataset; a contribution calculation unit that calculates a contribution, which is the degree of influence that an explanatory variable has on a target variable, based on causal relationship data indicating causal relationships in multiple types of monitoring data, the learning model, the monitoring data for learning, and the monitoring data for factor analysis; a factor analysis unit that calculates a factor degree, which is the degree to which each explanatory variable is a factor, based on the contribution degree; a factor analysis result output unit that outputs a factor analysis result based on the factor analysis dataset, the contribution rate, and the factor rate; A program that operates as a factor analysis device equipped with the

Images