Graph generation device, state prediction device, graph generation method, state prediction method, and program.

Abstract

To make it possible to illustrate a prediction of state change, and to show, in a figure, a relative length of a time period required for the state change.SOLUTION: A graph generation device includes: a graph generation unit which converts each piece of data contained in a time series of data regarding a prediction object into a coordinate value in a coordinate space being set so that a time period in the time series is proportional to a distance in the coordinate space, and generates a graph in the coordinate space; and a state information adding unit which adds information, to a part of the coordinate space, indicating a state of the prediction object at a time point in the time series of the data to be converted to a coordinate value contained in the part.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a graph generation device, a state prediction device, a graph generation method, a state prediction method, and a program. [Background technology]

[0002] Several technologies related to condition prediction have been proposed. For example, Patent Document 1 describes a method of acquiring dietary information and health condition information of multiple users, and predicting the future health condition of a first user based on the health condition information of the second user when the dietary habits of the first user and the second user who is older than the first user have a predetermined relationship. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2020-177469 Summary of the Invention [Problem to be solved by the invention]

[0004] If the predicted state change can be visualized, the state change can be visually grasped. In this case, it is preferable that the time required for the state change is also shown in the diagram.

[0005] An example of an object of the present invention is to provide a graph generation device, a state prediction device, a graph generation method, a state prediction method, and a program that can illustrate predictions of state changes and show the relative length of time it takes for a state change. [Means for solving the problem]

[0006] According to a first aspect of the present invention, a graph generating device includes: A data acquisition unit acquires a time series of data related to a prediction target, and a feature extraction method obtained by learning using an evaluation index in which the closer the distance in a feature space between two feature amounts obtained by extracting feature amounts from each of two pieces of data included in the same time series is to a value obtained by multiplying a predetermined proportional coefficient by the time interval in the time series of the two pieces of data, the higher the evaluation is, and each piece of data included in the time series is converted into the feature amount. do, The feature space is Coordinate Space Let's sayThe system includes a graph generation unit that generates a graph, and a state information addition unit that adds, to a portion of the coordinate space, information indicating the state of the prediction target at a time in the time series of the data that is converted into coordinate values ​​included in that portion. According to a second aspect of the present invention, a graph generation device includes a data acquisition unit that acquires a first graph in which a time series of data related to a prediction target is shown in a first coordinate space; a graph generation unit that performs coordinate transformation from the first coordinates to second coordinates using a distance index that is a weighted sum of the distance in the first coordinate space between two pieces of data included in the time series shown in the first coordinate space and the time interval in the time series of the two pieces of data, such that the smaller the value of the distance index, the closer the distance between the two pieces of data in the second coordinate space, thereby generating a second graph in which the time series is shown in the second coordinate space; and a state information addition unit that adds, to a portion of the coordinate space, information indicating the state of the prediction target at a time in the time series of the data converted to coordinate values ​​included in that portion.

[0007] The present invention 3 According to the aspect, the state prediction device is The feature space is a coordinate space obtained by converting each of the data included in the time series into a feature using a feature extraction method obtained by learning using an evaluation index in which the closer the distance in the feature space between two feature values ​​obtained by performing feature extraction on each of the two data included in the same time series is to a value obtained by multiplying the time interval in the time series of the two data by a predetermined proportional coefficient, the higher the evaluation. The system includes a prediction unit that uses a graph to predict the state of the prediction target.

[0008] The present invention 4 According to the aspect, the graph generation method includes: A time series of data related to a prediction target is acquired, and two feature quantities obtained by extracting feature quantities from each of two pieces of data included in the same time series are converted into feature quantities using a feature quantity extraction method obtained by learning using an evaluation index in which the closer the distance in feature quantity space between the two pieces of data is to a value obtained by multiplying a predetermined proportional coefficient by the time interval in the time series of the two pieces of data, the higher the evaluation. do, The feature space is Coordinate Space Let's say generating a graph; and adding to a portion of the coordinate space information indicating the state of the prediction target at a time in the time series of the data that is converted into coordinate values ​​included in that portion.

[0009] The present invention 5 According to the aspect, the state prediction method includes: The feature space is a coordinate space obtained by converting each of the data included in the time series into a feature using a feature extraction method obtained by learning using an evaluation index in which the closer the distance in the feature space between two feature values ​​obtained by performing feature extraction on each of the two data included in the same time series is to a value obtained by multiplying the time interval in the time series of the two data by a predetermined proportional coefficient, the higher the evaluation. The method includes using a graph to predict the state of the prediction target.

[0010] The present invention 6 According to the embodiment, the program causes a computer to A time series of data related to a prediction target is acquired, and two feature quantities obtained by extracting feature quantities from each of two pieces of data included in the same time series are converted into feature quantities using a feature quantity extraction method obtained by learning using an evaluation index in which the closer the distance in feature quantity space between the two pieces of data is to a value obtained by multiplying a predetermined proportional coefficient by the time interval in the time series of the two pieces of data, the higher the evaluation. do, The feature space is Coordinate Space Let's say This is a program for generating a graph and adding, to a portion of the coordinate space, information indicating the state of the target to be predicted at a time in the time series of the data that is converted into coordinate values ​​contained in that portion.

[0011] The present invention 7 According to the embodiment, the program causes a computer to The feature space is a coordinate space obtained by converting each of the data included in the time series into a feature using a feature extraction method obtained by learning using an evaluation index in which the closer the distance in the feature space between two feature values ​​obtained by performing feature extraction on each of the two data included in the same time series is to a value obtained by multiplying the time interval in the time series of the two data by a predetermined proportional coefficient, the higher the evaluation. This is a program for executing state prediction of the prediction target using a graph. [Effects of the Invention]

[0012] The graph generation device, state prediction device, graph generation method, state prediction method, and program described above make it possible to visualize predictions of state changes and to show the relative length of time required for a state change on a graph. [Brief explanation of the drawings]

[0013] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of a graph generation device according to a first embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of a graph generation unit according to the first embodiment. [Figure 3] FIG. 10 is a diagram illustrating an example of a graph in which the time represented by the distance in the feature space differs depending on the position in the feature space. [Figure 4] FIG. 2 is a diagram illustrating a first example of the configuration of a feature extraction unit according to the first embodiment. [Figure 5] FIG. 4 is a diagram illustrating a second example of the configuration of the feature amount extraction unit according to the first embodiment. [Figure 6] FIG. 2 is a diagram showing an example of a graph output by the graph generation device according to the first embodiment. [Figure 7] FIG. 4 is a diagram showing a first example of a state indicated by a state change graph according to the first embodiment. [Figure 8] FIG. 10 is a diagram showing a second example of a state indicated by a state change graph according to the first embodiment. [Figure 9] FIG. 10 is a diagram showing a third example of a state indicated by a state change graph according to the first embodiment. [Figure 10] FIG. 10 is a diagram showing a fourth example of a state indicated by a state change graph according to the first embodiment. [Figure 11] FIG. 10 is a diagram showing a fifth example of a state indicated by a state change graph according to the first embodiment. [Figure 12] FIG. 10 is a diagram showing an example of a state change graph in which the display area of ​​an edge is determined depending on the direction of the edge in the first embodiment. [Figure 13]FIG. 2 is a diagram showing an example in which a state change graph is displayed in a three-dimensional feature amount space in the first embodiment. [Figure 14] 10 is a flowchart showing an example of a processing procedure for learning a graph generation unit 192 by the graph generation device according to the first embodiment. [Figure 15] FIG. 10 is a diagram illustrating an example of the configuration of a graph generation device according to a second embodiment. [Figure 16] FIG. 10 is a diagram illustrating an example of the configuration of a feature amount extraction unit according to the second embodiment. [Figure 17] FIG. 10 is a diagram illustrating an example of the configuration of a state prediction system according to a third embodiment. [Figure 18] FIG. 10 is a diagram illustrating an example of the configuration of a state prediction device according to a third embodiment. [Figure 19] FIG. 11 is a diagram illustrating an example of nodes in a state change graph that are referenced by a state prediction device in the third embodiment. [Figure 20] 10 is a flowchart illustrating an example of a process in which a state prediction device according to a third embodiment predicts a state of a prediction target. [Figure 21] FIG. 10 is a diagram illustrating an example of the configuration of a graph generation device according to a fourth embodiment. [Figure 22] FIG. 13 is a diagram illustrating an example of a graph before conversion in the fourth embodiment. [Figure 23] FIG. 13 is a diagram illustrating an example of a graph after conversion in the fourth embodiment. [Figure 24] FIG. 10 is a diagram showing a first example in which the graph generation device according to the fourth embodiment generates a graph from a power flow diagram of a state change speed vector. [Figure 25] FIG. 10 is a diagram showing a second example in which the graph generation device according to the fourth embodiment generates a graph from a power flow diagram of a state change speed vector. [Figure 26] FIG. 1 is a schematic block diagram illustrating an example configuration of a computer according to at least one embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0014] The following describes embodiments of the present invention, but the following embodiments do not limit the scope of the invention as claimed. Furthermore, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0015] First Embodiment Fig. 1 is a diagram showing an example of the configuration of a graph generation device according to the first embodiment. In the configuration shown in Fig. 1, the graph generation device 100 includes a communication unit 110, a display unit 120, an operation input unit 130, a storage unit 180, and a control unit 190. The control unit 190 includes a data acquisition unit 191, a graph generation unit 192, a state information addition unit 193, and a learning control unit 194.

[0016] The graph generation device 100 generates a graph showing changes in the state of a graph generation target. The graph generation device 100 may be configured using a computer such as a workstation or personal computer (PC). Specifically, the graph generation device 100 acquires a time series of m-dimensional data (time series data) related to the state of the graph generation target, extracts n-dimensional features for each piece of data (each piece of data at each time in the time series of data), and generates a time series of the n-dimensional features. The graph generation device 100 represents each feature as a node in the feature space, and generates a graph in which edges represent the chronological relationship of the feature in the time series.

[0017] The feature amounts referred to here are data converted from the original data. They are called "features" because the state can be determined based on the position where the feature amounts are plotted in the feature amount space. Here, m and n are positive integer constants. Typically, m>n, but m≦n is also acceptable. A variable representing the value of each dimension of a feature is also called a latent variable. The feature space is an n-axis coordinate space with n latent variables. When n=2, the graph generated by the graph generation device 100 is a planar (two-dimensional) graph. When n=3, the graph generated by the graph generation device 100 is a cubic (three-dimensional) graph.

[0018] The graph generation target here is not limited to a specific one, but can be various ones whose state can be determined based on the obtained data. Furthermore, the graph generation target here may be a single one, or a set, such as a set of the same type of thing. In particular, the graph generation target may be the same as the prediction target. Alternatively, the graph generation target may be another one or a set that is thought to undergo a state change similar to that of the prediction target. The graph generation target here is a target whose state is referred to in order to generate a graph by the graph generation device 100. The prediction target here is a target whose state is predicted using the graph generated by the graph generation device 100.

[0019] For example, the graph generation target may be a person, and the graph generation device 100 may generate a graph for predicting the person's health state, various disease states, etc. Furthermore, for example, the graph generation target may be measurement data of microRNA (miRNA), and the graph generation device 100 may generate a graph for predicting cancer.

[0020] When the graph generation target is a person, the graph generation device 100 may acquire time-series data of each of multiple people and generate a graph. This is expected to enable the graph generation device 100 to generate a graph for a wider area in the feature space, which is the coordinate space of the graph display target. Here, although changes in conditions such as illness vary from person to person, there are certain trends, and it is expected that the graph generation device 100 can generate graphs that are useful for predicting the condition of illness, etc. The graph generation device 100 may generate a graph using time-series data of a group of people whose changes in condition are thought to be relatively similar, such as data categorized by age.

[0021] Alternatively, the graph generation target may be a specific machine, and the graph generation device 100 may generate a graph for predicting the normal state and various abnormal states of the machine. If the graph generation target is a specific machine and there are multiple machines of the same model that are used in similar environments, the graph generation device 100 may acquire time-series data from each of these multiple machines to generate a graph. This is expected to enable the graph generation device 100 to generate a graph for a wider area in the feature space, which is the coordinate space of the graph display target.

[0022] Alternatively, the graph generation target may be a specific mechanical system such as a factory production line, and graph generation device 100 may generate a graph for predicting the normal state and various abnormal states of the mechanical system. Alternatively, the graph generation target may be a specific plant such as a chemical plant or a power plant, and graph generation device 100 may generate a graph for predicting the normal state and various abnormal states of the plant.

[0023] Alternatively, the graph generation target may be market conditions (trading conditions in a market such as the stock market), and the graph generation device 100 may generate a graph for predicting conditions such as an increase or decrease in trading prices. In the following, an example will be described in which the prediction target is a person, and the graph generation device 100 generates a graph for predicting the person's health state and various disease states. A graph that represents a change in state and is generated by the graph generation device 100 is also called a state change graph.

[0024] The communication unit 110 communicates with other devices. For example, the communication unit 110 may communicate with a database that stores data related to the graph generation target, and receive time series data related to the state of the graph generation target.

[0025] The display unit 120 has a display screen such as a liquid crystal panel or an LED (Light Emitting Diode) panel, and displays various images. For example, the display unit 120 may display the state change graph generated by the graph generation device 100. The operation input unit 130 includes input devices such as a keyboard and a mouse, and receives user operations. For example, the operation input unit 130 may receive a user operation to instruct the generation of a state change graph and a user operation to indicate a data acquisition source.

[0026] The storage unit 180 stores various data. For example, the storage unit 180 may store a time series of m-dimensional data related to the state of the graph generation target and a time series of n-dimensional feature quantities. The storage unit 180 may also store a learning model for learning a feature quantity extraction method. The storage unit 180 is configured using a storage device included in the graph generation device 100.

[0027] The control unit 190 performs various processes by controlling each unit of the graph generation device 100. The functions of the control unit 190 are performed, for example, by a CPU (Central Processing Unit) included in the graph generation device 100 reading and executing a program from the storage unit 180.

[0028] The data acquiring unit 191 acquires various data for the graph generation device 100 to generate a state change graph. In particular, the data acquiring unit 191 acquires a time series of data related to the prediction target. For example, as described above, when the communication unit 110 receives a time series of data related to the state of the graph generation target from another device, the data acquiring unit 191 may read out data related to the state of the graph generation target from the data received by the communication unit 110.

[0029] The graph generation unit 192 generates the state change graph described above for the graph generation device 100. In doing so, the graph generation unit 192 generates a state change graph in which the length of an edge connecting two nodes with a straight line is proportional to the length of time in the time-series data. In other words, the graph generation unit 192 converts each piece of data included in the time series of data related to the prediction target into coordinate values ​​in a coordinate space set so that the length of time in the time series is proportional to the distance in the coordinate space, and generates a graph in the coordinate space.

[0030] As described above, the data conversion by the graph generation unit 192 can be regarded as feature extraction, and the coordinate space of the state change graph can be regarded as feature space. In the first embodiment, the graph generation unit 192 learns a feature extraction method. The learning here refers to machine learning, and the graph generation unit 192 adjusts parameter values ​​of a learning model for the feature extraction process based on training data.

[0031] Fig. 2 is a diagram showing an example of the configuration of the graph generation unit 192. In the configuration shown in Fig. 2, the graph generation unit 192 includes a feature extraction unit 210 and a graph formation unit 220. Also shown in Fig. 2 is a learning control unit 194. The feature extraction unit 210 performs the data conversion described above for the graph generation unit 192. The time series data input to the feature extraction unit 210 can be expressed as a vector as shown in equation (1).

[0032]

number

[0033] fts represents the time series data input to the feature extraction unit 210. The time series data input to the feature extraction unit 210 is also referred to as input time series data. i is an identification number that identifies the time series data. Here, it is assumed that k pieces of time series data (k is a positive integer) are input to the feature extraction unit, where 1≦i≦k. The graph generation device 100 may use multiple pieces of time series data obtained for different graph generation targets, or may use multiple pieces of time series data obtained at different times for the same graph generation target.

[0034] An example of a case where the graph generation device 100 uses multiple time-series data obtained for different graph generation targets is when the graph generation device 100 generates a graph for predicting a person's health state, various disease states, etc., based on data of multiple people.An example of a case where the graph generation device 100 uses multiple time-series data obtained at different times for the same graph generation target is when the graph generation device 100 generates a state change graph for predicting the normal state, various abnormal states, etc., of a single plant, based on data of the plant. In the following, an example will be described in which the graph generation device 100 uses time-series data of k people. It is assumed that i is also used as an identification number for identifying the graph generation target (here, person), and that the i-th time-series data is obtained for the i-th graph generation target.

[0035] The time series data used by the graph generation device 100 during learning and the time series data used during graph generation may be the same or different. The time when the graph generation device 100 is generating the graph is also referred to as the time when the graph generation device 100 is operating. The following describes an example in which the graph generation device 100 uses the same time series data during learning and graph generation.

[0036] In the learning data, data for each time included in the time-series data may be linked to information indicating the state of the target for graph generation at that time. The information indicating the state of the target for graph generation here may be information indicating the name of a class determined using a state change graph, such as "healthy," "pre-illness," or the name of a variety of diseases.

[0037] Input time series data fts i The data for each time included in is also called input data for each time.i,j The input data at f i (t i,j ) is also written as f i (t i,j ) can be expressed as a vector as in equation (2).

[0038]

number

[0039] xmax is a positive integer constant representing the number of measurement items. The coordinate space of the input data is constructed as a coordinate space of the xmax dimension. The measurement items here are not limited to specific items. For example, when the graph generation device 100 generates a state change graph for predicting the state of cancer, the measurement items may be various tumor markers obtained by blood or urine sampling.

[0040] x l (i,t i,j ) is the time t i,j indicates the value of the lth measurement item in (1), where l is an integer in the range 1≦l≦xmax. j is an integer 1≦j≦tmax_i that identifies a time in the time series data. tmax_i represents the number of data items at each time included in the i-th time series data. In other words, tmax_i represents the number of data measurement times in the i-th time series data. The number of data items at each time included in each time series data may differ for each time series data.

[0041] The time-series data output by the feature extraction unit 210 can be expressed as a vector as shown in equation (3).

[0042]

number

[0043] f *ts represents the time series data output by the feature extraction unit 210. The time series data output by the feature extraction unit 210 is also referred to as feature time series data. The feature extraction unit 210 extracts the input time series data fts i Receive the input of feature time series data f * ts i Output. The feature extraction unit 210 extracts the input time series data fts i At time t i,j Input data f in i (t i,j ) to extract features from f * i (t i,j ) is written as f * i (t i,j ) can be expressed as a vector, for example, as in equation (4).

[0044]

number

[0045] [z1(i,t i,j ),z2(i,t i,j )] is the feature extraction unit 210 i,j The input data [x1(i,t i,j ),x2(i,t i,j ),···,x xmax (i,t i,j z1(i,t) is a vector representing the feature quantity extracted from the input data. Equation (4) shows an example in which the feature quantity extraction unit 210 converts xmax-dimensional input data into two-dimensional feature quantities. i,j ), z2(i,t i,j ) represent the coordinate value of the z1 coordinate and the coordinate value of the z2 coordinate, respectively.

[0046] However, as described above, the feature extraction performed by the feature extraction unit 210 is not limited to obtaining two-dimensional features. The feature extraction unit 210 extracts the input time series data fts i The input data for each time [x1(i,t i,j ),x2(i,ti,j ),···,x xmax (i,t i,j )] is used as the feature [z1(i,t i,j ),z2(i,t i,j )], the input time series data fts i The feature time series data f * ts i Convert to.

[0047] The graph forming unit 220 generates a state change graph that shows in a feature space the feature time-series data output by the feature extraction unit 210. In the state change graph generated by the graph forming unit 220, each feature included in the feature time-series data is plotted in the feature space, and a time series is shown by connecting temporally adjacent feature values ​​on the feature time-series data with directed edges.

[0048] Specifically, the graph creation unit 220 converts the data representation format of the feature time series data output by the feature extraction unit 210 so that it can search for feature time series data at which features are plotted from coordinate values ​​in the feature space. When the graph generation device 100 generates a condition change graph to be presented to a user such as a doctor, the graph forming unit 220 may generate image data showing the condition change graph.

[0049] The learning control unit 194 controls the feature extraction unit 210 to cause the graph generation unit 192 to learn the above-described feature extraction method. At this time, the learning control unit 194 may control the learning of the feature extraction unit 210 so that a specific state determined using the state change graph appears in a specific region in the feature space.

[0050] To this end, the learning control unit 194 may control the learning of the feature extraction unit 210 using an evaluation function that is highly evaluated when a feature classified into a specific class is plotted within an area associated with that class. For example, consider a case where a feature is represented by a vector [z1, z2] and the range of possible coordinate values ​​in the feature space is 0≦z1≦1 and 0≦z2≦1. In this case, we want the feature when a person is healthy to be plotted at the origin [0,0] or nearby.

[0051] At this time, the learning control unit 194 calculates the distance √(z1 2 +z2 2 Alternatively, the learning control unit 194 may use an evaluation function that gives a higher evaluation as √(z1 2 +z2 2 An evaluation function that gives a high evaluation when THr is satisfied may be used, where THr is a positive real number that represents the threshold value of the distance between the feature value [z1, z2] and the origin [0, 0].

[0052] Furthermore, the learning control unit 194 controls the learning of the feature extraction unit 210 so that the feature extraction unit 210 extracts features such that the length of time in the time-series data is proportional to the distance in the feature space. This allows the feature space to be set such that the length of time in the time-series data is proportional to the distance in the feature space.

[0053] 3 is a diagram showing an example of a graph in which the time represented by the distance in the feature space varies depending on the position in the feature space. In the example of FIG. 3, points P111, P112, and P113 each represent a feature. Furthermore, the time interval from when the data associated with point P111 (data converted into the feature represented by point P111) is observed to when the data associated with point P112 is observed is equal to the time interval from when the data associated with point P112 is observed to when the data associated with point P113 is observed.

[0054] On the other hand, on the graph, the distance from point P112 to point P113 is longer than the distance from point P111 to point P112. For example, consider a case where the condition of a patient, a target of condition prediction, has changed from the condition represented by point P111 to the condition represented by point P112, and a doctor is predicting the future condition of this patient by referring to the graph shown in Figure 3. In this case, if the doctor views the graph assuming that distance on the graph is proportional to time, he or she may interpret the time it takes for the patient's condition to reach the condition represented by point P113 as longer than the actual time. This may result in treatment for the patient being delayed.

[0055] In contrast, if a graph is generated so that distance on the graph is proportional to time, such as when point P113 is plotted so that the distance between points P112 and P113 is equal to the distance between points P111 and P112 in the example of Figure 3, it is expected that doctors will be able to more accurately read the time it takes for a patient's condition to change, which will enable them to provide treatment to the patient at the appropriate time.

[0056] To make the distance on the graph proportional to time, the learning control unit 194 may control the learning of the feature extraction unit 210 using an evaluation index that evaluates more highly the closer the distance in feature space between two features obtained by extracting features from data at two times included in the same input time series data is to the value obtained by multiplying the time interval between those two times by a predetermined proportionality coefficient. For example, the learning control unit 194 may control the learning of the feature extraction unit 210 using an evaluation index that increases the evaluation as the value of equation (5) decreases.

[0057]

number

[0058] "a" is a positive real number and represents the proportionality coefficient between the distance in the feature space and the time interval in the time series data. "||f * i (t i,j+1 )-f *i (t i,j )||2" is the feature f in the feature space * i (t i,j+1 ) and feature f * i (t i,j ) and is expressed as, for example, Equation (6).

[0059]

number

[0060] Equation (6) shows an example where the number of dimensions of the feature is two. However, as described above, the number of dimensions of the feature used in the state change graph is not limited to two. Furthermore, a distance other than the L2 norm may be used as the distance in the feature space. Feature f * i (t i,j+1 ) and f * i (t i,j ) is the same input time series data fts i Two times t included in i,j+1 and t i,j Data f in each i (t i,j+1 ) and f i (t i,j These correspond to the two features obtained by extracting features for each of a(t i,j+1 -t i,j ) 2 " is two data f i (t i,j+1 ) and f i (t i,j ) input time series data fts i At time t i,j and t i,j+1 The time interval between i,j+1 -t i,j " is the value obtained by multiplying this by the proportional constant "a".

[0061] Fig. 4 is a diagram illustrating a first example of the configuration of the feature extraction unit 210. In the configuration illustrated in Fig. 4, the graph generation unit 192 includes an autoencoder (AE) 210a and a graph formation unit 220. The autoencoder 210a includes an encoder 211a, a relay layer 212a, and a decoder 213a.

[0062] The autoencoder 210a is an example of the feature extractor 210. Specifically, the encoder 211a receives input data for each time and outputs a feature. The relay layer 212a outputs the feature amount extracted by the encoder 211a from the input data for each time to both the decoder 213a and the graph forming unit 220. The decoder 213a performs data conversion on the feature extracted from the input data for each time by the encoder 211a. i The decoder 213a outputs the time series data gts i can be expressed as a vector as in equation (7).

[0063]

number

[0064] g i (t i,j ) is the feature f i (t i,j ) is the data that is output based on the input of g. i (t i,j ) can be expressed as a vector as in equation (8).

[0065]

number

[0066] ymax is the output data g of the decoder 213a i (t i,j) is typically set as ymax=xmax. In other words, the autoencoder 210a outputs data with the same number of dimensions as the number of dimensions of the input data. In the autoencoder 210a, the data conversion of the encoder 211a and the decoder 213a is the object of learning. i (t i,j ) and the output data g of the decoder 213a i (t i,j ) is smaller, the evaluation is higher, and thus the encoder 211a and the decoder 213a can be made to perform learning of data conversion so that the reproducibility of input data from features is increased. In this regard, the learning control unit 194 can make the encoder 211a perform learning so that the encoder 211a loses as little information contained in the input data as possible. The learning control unit 194 can control the learning, particularly in the learning of the encoder 211a, in the same manner as described above for the feature extraction unit 210.

[0067] Fig. 5 is a diagram illustrating a second example of the configuration of the feature extraction unit 210. In the configuration illustrated in Fig. 5, the graph generation unit 192 includes a GCM (Generative Contribution Mappings) 210b and a graph formation unit 220. The GCM 210b includes an encoder 211b, a relay layer 212b, a first class decoder 213b-1 to an N-th class decoder 213b-N, a first multiplier 214b-1 to an N-th multiplier 214b-N, a first average calculation unit 215b-1 to an N-th average calculation unit 215b-N, and an Argmax calculation unit 216b. Here, N is a positive integer indicating the number of classes in classification.

[0068] The first class decoder 213b-1 through the Nth class decoder 213b-N are collectively referred to as decoders 213b. The first multiplier 214b-1 through the Nth multiplier 214b-N are collectively referred to as multipliers 214b. The first average calculation unit 215b-1 through the Nth average calculation unit 215b-N are collectively referred to as average calculation unit 215b.

[0069] The GCM 210b corresponds to an example of the feature extraction unit 210. Specifically, the encoder 211b receives input data at each time and outputs a feature. The relay layer 212b outputs the feature amounts extracted by the encoder 211a from the input data for each time to each of the N decoders 213b and the graph formation unit 220.

[0070] Each of the N decoders 213b performs data conversion on the feature extracted from the input data for each time by the encoder 211b, converting the feature into data with the same number of dimensions as the number of dimensions of the input data. The multiplier 214b-i (i=1, 2, . . . , N) multiplies the data calculated by the ith class decoder 213b-i by the input data. The data output by the multiplier 214b-i can be used as information indicating how much each part of the input data contributes to the determination of the ith class.

[0071] The average calculation unit 215b-i calculates the average of all elements of the element values ​​of the data calculated by the multiplier 214b-i. That is, the average calculation unit 215b-i calculates the average of the values ​​for each dimension of the xmax-dimensional data calculated by the multiplier 214b-i. The average values ​​calculated by each average calculation unit 215b are used as evaluation values ​​(class scores) in class classification. The Argmax calculation unit 216b compares the class scores calculated for each class by the average calculation unit 215b and determines the class with the largest class score. In this way, the Argmax calculation unit 216b classifies the input data into classes.

[0072] In the GCM 210b, the encoder 211b and N decoders 213b are the targets of learning. The learning control unit 194 can control the learning, particularly in the learning of the encoder 211b, in the same manner as described above for the feature extraction unit 210.

[0073] The method by which the feature extraction unit 210 extracts features is not limited to the method using the autoencoder 210a or the method using the GCM 210b. As a method by which the feature extraction unit 210 extracts features, various methods that can convert input data into data of a desired dimension can be used.

[0074] The state information adding unit 193 adds, to a portion of the feature space (the coordinate space in which the state change graph is shown), information indicating the state of the prediction target at the time in the input time-series data of the data converted into coordinate values ​​included in that portion. For example, the state information adding unit 193 may add, to an area including a point where the feature is plotted, the name of the state indicated by that feature.

[0075] Furthermore, for example, when the learning control unit 194 controls the learning of the feature extraction unit 210 so that a specific state appears in a specific region as described above, the state information adding unit 193 may add the name of the state to that region. In the above example, the state information adding unit 193 may add the state name "healthy" to the region within a radius THr from the origin [0,0].

[0076] FIG. 6 is a diagram showing an example of a graph output by the graph generation device 100. FIG. 6 shows an example of changes in the condition of a hospitalized patient due to a certain illness. Each node in the graph in FIG. 6 represents the condition of the patient. Specifically, the coordinate values ​​of the node represent features extracted from measurement data about the patient. Point P211 represents the state when the patient's condition has improved and led to discharge from the hospital. Point P212 represents the state when the patient's condition has worsened and led to death.

[0077] An edge represents the temporal relationship between two adjacent feature amounts in the feature time-series data. In Fig. 6, the direction of the edge is indicated by an arrow only for the line L11 from point P221 to point P212, but the direction of the edges for other edges may also be as shown in the figure.

[0078] 6, the length of each edge is proportional to the time interval in the feature time-series data between the two feature amounts represented by the nodes at both ends of the edge. The closer the distance on the graph (i.e., the distance when tracing the edge) to point P211, the better the patient's condition can be determined to be. On the other hand, the closer the distance on the graph to point P212, the worse the patient's condition can be determined to be.

[0079] For example, a user such as a doctor who predicts the condition of a patient extracts feature quantities from data indicating the current condition of the patient whose condition is to be predicted using the graph generation device 100, and plots the obtained feature quantities on a graph. For example, the user can predict how the patient's condition will change and over what period by tracing the edges from the point closest to the plotted point.

[0080] FIG. 7 is a diagram showing a first example of states indicated by a state change graph. In the state change graph, one node plotted as a point in the coordinate space represents one state. In the example of FIG. 7, each of points P311, P312, P321, and P322 represents one state. In the following description, there may be cases where no distinction is made between a node and the point at which the node is plotted in the state space.

[0081] Furthermore, nodes that indicate similar states are arranged so that the distance in the coordinate space is small (i.e., close). Nodes that indicate dissimilar states are arranged so that the distance in the coordinate space is large (i.e., far away). In the example of FIG. 7, the distance d11 between points P311 and P312 is relatively small, and the distance d12 between points P321 and P322 is relatively large. From this, it can be determined that the state represented by point P311 and the state represented by point P312 are relatively similar. It can be determined that the state represented by point P321 and the state represented by point P322 are relatively different.

[0082] FIG. 8 is a diagram showing a second example of states indicated by a state change graph. The edges of the state change graph can be understood as vectors that represent changes in states over time. In the example of FIG. 8, for example, the edge from point P411 to point P412 can be understood as a vector that indicates a change from the state represented by point P411 to the state represented by point P412. Furthermore, the state change graph can be read as the length of this edge being proportional to the time it takes to change from the state represented by point P411 to the state represented by point P412.

[0083] Also, a certain node may be the starting point in a graph. In the example of Fig. 8, point P411 is the starting node in the graph of Fig. 8. The starting node is associated with the first data (data at the oldest time) in the input time series data, and it can be considered that there is no measurement data at a time earlier than that.

[0084] Also, a certain node may be the end point in the graph. In the example of Fig. 8, point P414 is the end point node in the graph of Fig. 8. The start point node is associated with the last data (data at the most recent time) in the input time series data, and it can be considered that there is no measurement data at a time more recent than that.

[0085] Also, a certain node may be an intermediate node in the graph. An intermediate node represents a state resulting from a change from another state, and can be understood as a change to yet another state. In the example of FIG. 8, the state represented by point P412 is a state resulting from a change from the state represented by point P411. Also, the state represented by point P412 has changed to the state represented by point P413.

[0086] FIG. 9 is a diagram showing a third example of the state indicated by the state change graph. When multiple feature quantities are plotted at the same position in the feature quantity space and represented by one node, multiple edges may emerge from one node. In the example of Fig. 9, point P511 is considered to represent the most recent feature quantity of the feature quantity represented by point P512 on the feature quantity time-series data, and the most recent feature quantity of the feature quantity represented by point P514 on the feature quantity time-series data. For this reason, an edge from point P511 to point P512 and an edge from point P511 to point P514 are established.

[0087] Furthermore, when multiple feature quantities are plotted at the same position in the feature quantity space and represented by a single node, multiple edges may reach a single node. In the example of Fig. 9, point P514 is considered to represent the feature quantity in the near future of the feature quantity represented by point P513 on the feature quantity time-series data and the feature quantity in the near future of the feature quantity represented by point P511 on the feature quantity time-series data. For this reason, an edge from point P513 to point P514 and an edge from point P511 to point P514 are established.

[0088] Furthermore, there may be multiple paths from a node to another node. In this case, the state change graph can be interpreted by assuming that the sum of the lengths of the edges included in each path is proportional to the time required for a state change when following that path. In the example of Figure 9, the sum of the lengths of the edges in the path from point P511 to point P514 via points P12 and P513 is 3. On the other hand, the path from point P511 directly to point P514 has one edge, and its length is 2. From this, it can be interpreted that the time required for a state change from the state indicated by point P511 to the state indicated by point P514 via the states indicated by points P512 and P513 is 1.5 times the time required for a state change from the state indicated by point P511 to the state indicated by point P514 directly.

[0089] FIG. 10 is a diagram showing a fourth example of the state indicated by the state change graph. In the example of Figure 10, an edge is established from point P611 to point P612 and an edge is established to point P613. The probability of passing through the edge from point P611 to point P612 is indicated as 70%. The probability of passing through the edge from point P611 to point P613 is indicated as 30%. In this way, when multiple edges extend from one node, the probability of a state change occurring through that edge may be indicated for each edge.

[0090] In this case, the probability may indicate the percentage of times that, in all feature time series data, the feature associated with the node that is the starting point of the edge is the most recent feature associated with each node that is the destination of the edge. In the example of Figure 10, when counting the feature values ​​in the immediate future of the feature value linked to point P611 for all feature time-series data, the feature value linked to point P612 may appear seven times, and the feature value linked to point P613 may appear three times.

[0091] FIG. 11 is a diagram showing a fifth example of a state indicated by a state change graph. In the example of Figure 11, there are two routes from point P711 to point P714, and the route from point P711 to point P714 via point P712 has a probability of 70%, while the route from point P711 directly to point P714 has a probability of 30%. Furthermore, there is only one path from point P713 to P714, which is a path that goes directly from point P713 to P714, and this path is shown to have a probability of 100%.

[0092] In this way, for each path from one node to another, the probability of passing through that path may be indicated. In this case, the probability may indicate the probability of the number of times a state change occurs from the state represented by the node at the start of the path to the state represented by the node at the end of the path, and the number of times each path is taken. In the example of Figure 11, the number of times that the state indicated by point P711 has progressed to the state indicated by point P714 via the state indicated by point P712 is seven, and the number of times that the state indicated by point P711 has progressed directly to the state indicated by point P714 is three.

[0093] FIG. 12 is a diagram showing an example of a state change graph in which the display area of ​​an edge is determined according to the direction of the edge. The condition change graph in the example of Figure 12 shows changes in the condition of a patient with a certain disease. The feature space of this condition change graph is formed as a two-dimensional space (i.e., a plane) defined by the z1 axis and the z2 axis.

[0094] Furthermore, the lower left region of the feature space, within a specified distance from the origin, is set as a region indicating a state in which the patient's condition has improved and led to discharge from the hospital. The upper right region of the feature space, within a specified distance from the maximum value of z1 and z2, is set as a region indicating a state in which the patient's condition has worsened and led to death. In this condition change graph, the edge from the lower left (towards the origin) to the upper right (towards the maximum values ​​of z1 and z2) is considered to indicate a worsening of the condition. The edge from the upper right (towards the maximum values ​​of z1 and z2) to the lower left (towards the origin) is considered to indicate an improvement of the condition.

[0095] In this case, the graph generation unit 192 may generate a state change graph in which edges indicating a worsening of the state and edges indicating an improvement of the state are shown in separate regions. In the example of Fig. 12, edges indicating a worsening of the state are shown on the upper left side of the figure, and edges indicating an improvement of the state are shown on the lower right side, with line L21, which is a diagonal line connecting the origin and the maximum points of z1 and z2, as the boundary.

[0096] For this purpose, the learning control unit 194 may control the learning of the graph generating unit 192 using an evaluation function that gives a higher evaluation as the value of equation (9) becomes smaller.

[0097]

number

[0098] eval is the feature f(t i,j+1 ) to f(t i,j ) indicates a worsening of the condition, and outputs a value of -1 if the change indicates an improvement. For example, the positive direction of the z1 axis is the reference (0 degrees), and the vector f(t i,j+1 )-f(t i,j ) may be such that the value of eval is 1 when 0≦θ<135° and 315°≦θ<360°, and the value of eval is −1 when 135°≦θ<315°. Step indicates a step function, which is expressed as in equation (10).

[0099]

number

[0100] "step(z1(i,t i,j )-z2(i,t i,j ))" value is z1(i,t i,j ) ≧ z2(i,t i,j )) and z1(i,t i,j) <z2(i,t i,j )) becomes 0. Therefore, "step(z1(i,t i,j )-z2(i,t i,j ))" is the value of the feature f i (t i,j )=[z1(i,t i,j ),z2(i,t i,j )] is 1 when it is located to the lower right of line L21, and 0 when it is located to the upper left of line L21.

[0101] "step(z1(i,t i,j+1 )-z2(i,t i,j+1 ))" value is z1(i,t i,j+1 ) ≧ z2(i,t i,j+1 )) becomes 1 when z1(i,t i,j+1 ) <z2(i,t i,j+1 )) becomes 0. Therefore, "step(z1(i,t i,j+1 )-z2(i,t i,j+1 ))" is the value of the feature f i (t i,j+1 )=[z1(i,t i,j+1 ),z2(i,t i,j+1 )] is 1 when it is located to the lower right of line L21, and 0 when it is located to the upper left of line L21.

[0102] Therefore, "step(z1(i,t i,j+1 )-z2(i,t i,j+1 ))+step(z1(i,t i,j+1 )-z2(i,t i,j+1 ))-1" is the value of the feature f i (t i,j ) and f i (t i,j+1 ) is 1 when both are located to the right and down from line L21, 0 when only one is located to the right and down from line L21, and -1 when both are located to the left and up from line L21.

[0103] Feature f(t i,j+1 ) to f(t i,j ) indicates a worsening of the condition, the value of eval is 1, and the feature fi (t i,j ) and f i (t i,j+1 ) are both located above the left of line L21, the value of formula (9) becomes the minimum value 0. Feature amount f(t i,j+1 ) to f(t i,j ) indicates that the state is improving, the value of eval is -1, and the feature amount f i (t i,j ) and f i (t i,j+1 ) are both located below the right of line L21, the value of formula (9) becomes the minimum value 0.

[0104] Thus, in the upper left side (region where z1 < z2) of the feature amount space, an edge indicating deterioration of the state is shown, and in the lower right side (region where z1 ≥ z2), an edge indicating improvement of the state is expected to be shown.

[0105] FIG. 13 is a diagram showing an example when a state change graph is shown in a three-dimensional feature amount space. In the example of FIG. 13, the feature amount space is constituted by three coordinate axes of the z1 axis, the z2 axis, and the z3 axis, and the state change graph is shown three-dimensionally in the feature amount space. Thus, by showing the state change graph three-dimensionally, it is expected that the difference in states is shown more clearly than when the state change graph is shown two-dimensionally. For example, feature amounts shown close in a two-dimensional feature amount space may be shown relatively far apart in a three-dimensional feature amount space.

[0106] FIG. 14 is a flowchart showing an example of a procedure of a process in which the graph generation device 100 performs learning of the graph generation unit 192. In the process of FIG. 14, the data acquisition unit 191 acquires learning data (step S111). The data acquisition unit 191 acquires, as learning data, one or more input time series data and information indicating the state of the graph generation target at that time, which is associated with one or more input data for each time of the input time series data. The information indicating the state of the graph generation target is used as the correct answer (teacher data) for classifying the state of the graph generation target.

[0107] Next, the graph generation unit 192 calculates feature amounts and output data (step S112). Specifically, the graph generation unit 192 extracts feature amounts for each piece of input data for each time in the input time series data. The feature amounts indicate coordinate values ​​in a feature amount space and can be treated as nodes in a state change graph. Then, the graph generation unit 192 draws edges between the feature amounts as nodes according to the order in which the input data appear in the input time series data. The graph generating unit 192 performs the process of step S112 on all input time series data provided as learning data or on input time series data selected by the learning control unit 194, and generates a state change graph.

[0108] Next, the learning control unit 194 determines whether a learning termination condition is met (step S113). The termination condition here is not limited to a specific one. For example, the termination condition here may be a condition that the evaluation value of the state change graph or a part of it generated in step S112 is equal to or greater than a predetermined threshold. Alternatively, the termination condition here may be a condition that the loop of steps S112, S113, and S114 has been repeated a predetermined number of times or more.

[0109] If the learning control unit 194 determines that the termination condition is not satisfied (step S113: NO), the graph generation unit 192 updates the learning model parameter values ​​under the control of the learning control unit 194 (step S114). A known method may be used to update the learning model parameter values ​​here. For example, if the feature extraction unit 210 is configured using a neural network, the feature extraction unit 210 may update the parameter values ​​of the neural network based on backpropagation under the control of the learning control unit 194. After step S114, the process returns to step S112. On the other hand, if the learning control unit 194 determines in step S113 that the termination condition is met (step S113: YES), the graph generation device 100 terminates the processing of FIG.

[0110] The state information adding unit 193 may add information indicating the state of the graph generation target to the state change graph finally obtained during learning, to create a state change graph to be used for state prediction. Alternatively, a state change graph may be generated using the graph generation device 100 after learning is completed. In this case, the graph generation unit 192 may generate a state change graph by performing the same process as in step S112, and the state information addition unit 193 may add information indicating the state of the graph generation target to the obtained state change graph.

[0111] As described above, the graph generation unit 192 converts each piece of data (input data for each time) included in the time series of data (input time series data) related to the prediction target (graph generation target) into coordinate values ​​in a coordinate space set so that the length of time in the time series is proportional to the distance in the coordinate space, and generates a graph in the coordinate space (state change graph). The state information addition unit 193 adds, to a portion of the coordinate space, information indicating the state of the prediction target at the time in the time series (input time series data) of the data (input data for each time) converted into the coordinate values ​​included in that portion.

[0112] The graph generation device 100 can visualize the predicted state changes and show the relative length of time it takes for the state changes to occur. Specifically, the graph generation device 100 generates a state change graph that shows how the state of the graph generation target changes and includes information indicating the state, such as the name of the state. A person or a state prediction device can plot the current state of the prediction target on the state change graph to predict the future state. In this case, since the state change graph is generated so that the distance in the coordinate space of the state change graph is proportional to the time interval in the input time series data, it is expected that a person or a state prediction device will be able to predict the time required for a state change with relatively high accuracy.

[0113] The data acquisition unit 191 acquires input time series data. The coordinate space of the state change graph can be regarded as a feature space. The graph generation unit 192 converts each piece of data included in the time series into a feature using a feature extraction method obtained by learning using an evaluation index in which the closer the distance in the feature space between two feature amounts obtained by extracting feature amounts from each of two pieces of data (input data for each time point) included in the same time series (input time series data) is to a value obtained by multiplying the time interval in the time series of the two pieces of data by a predetermined proportional coefficient, the higher the evaluation. In the graph generation device 100, the process of calculating the coordinate values ​​of nodes in a state change graph can be performed as feature extraction processing. In this respect, the graph generation device 100 allows a feature extraction method to be used to calculate the coordinate values ​​of nodes in a state change graph. A known feature extraction method may also be used to calculate the coordinate values ​​of nodes in a state change graph.

[0114] Second Embodiment When generating a state change graph after learning is completed (during operation), the configuration for learning may be removed from the configuration of the graph generation device 100. This point will be described in the second embodiment. Fig. 15 is a diagram showing an example of the configuration of a graph generation device according to the second embodiment, showing an example of the configuration of the graph generation device when generating a state change graph after learning is completed. 15, graph generation device 100b includes a communication unit 110, a display unit 120, an operation input unit 130, a storage unit 180, and a control unit 190. Control unit 190b includes a data acquisition unit 191, a graph generation unit 192, and a state information addition unit 193.

[0115] 15, parts having similar functions to those in FIG. 1 are given the same reference numerals (110, 120, 130, 180, 191, 193), and detailed description thereof will be omitted here. Graph generation device 100b differs from control unit 190 of graph generation device 100 in that control unit 190b does not include learning control unit 194. In other respects, graph generation device 100b is similar to graph generation device 100. When generating a state change graph, the graph generation device 100 may be used in the same way as during learning. Alternatively, a graph generation device 100b may be prepared separately from the graph generation device 100, and the parameter values ​​of the learning model of the graph generation unit 192 obtained by the graph generation device 100 may be set in the graph generation unit 192 of the graph generation device 100b.

[0116] Fig. 16 is a diagram showing a third example of the configuration of the feature extraction unit 210. Fig. 16 shows an example of the configuration of the feature extraction unit 210 when generating a state change graph in a case where the feature extraction unit 210 is configured using an autoencoder during learning. 16, the graph generation unit 192 includes a feature extraction unit 210 and a graph formation unit 220. The feature extraction unit 210 includes an encoder 211 and a relay layer 212.

[0117] 16, parts having similar functions to those of the parts in FIG. 4 are given the same reference numerals (211a, 212a, 220), and detailed description thereof will be omitted here. The configuration of the feature extraction unit 210 in FIG. 15 is the same as the configuration of the autoencoder 210a in FIG. 4, except that the decoder 213a is removed. In this way, if a configuration for learning is added to the feature extraction unit 210 during learning, that configuration is not necessary when generating a state change graph.

[0118] When the graph generation device 100 is used to generate a state change graph, the feature extraction unit 210 may also use the autoencoder 210a in Fig. 4, as in the case of learning. Alternatively, when a graph generation device 100b is prepared separately from the graph generation device 100, the feature extraction unit 210 may have the configuration shown in Fig. 16. In this case, the parameter values ​​of the learning model of the encoder 211a obtained during learning may be set in the encoder 211a used to generate a state change graph.

[0119] Third Embodiment In the third embodiment, a state prediction using a state change graph will be described. FIG. 17 is a diagram illustrating an example of the configuration of a state prediction system according to the third embodiment. In the configuration shown in FIG. 17, the state prediction system 1 includes a graph generation device 100 and a state prediction device 300.

[0120] The graph generation device 100 in the first embodiment can be used as the graph generation device 100. Alternatively, instead of the graph generation device 100, the graph generation device 100b in the second embodiment or the graph generation device 400 in the fourth embodiment described later may be used. The state prediction device 300 predicts the state of the prediction target using the state change graph generated by the graph generation device 100. The state prediction device 300 may be configured using a computer such as a workstation or a personal computer.

[0121] FIG. 18 is a diagram illustrating an example of the configuration of the state prediction device 300. 18, the state prediction device 300 includes a communication unit 310, a display unit 320, an operation input unit 330, a storage unit 380, and a control unit 390. The control unit 390 includes a data acquisition unit 391 and a prediction unit 392.

[0122] The communication unit 310 communicates with other devices. For example, the communication unit 310 may communicate with the graph generation device 100 to receive a state change graph. Alternatively, the communication unit 310 may communicate with the graph generation device 100 to acquire information indicating learning model parameter values ​​obtained by learning by the graph generation device 100. Alternatively, the communication unit 310 may communicate with a measurement device that measures data related to the prediction target to acquire the latest measurement data related to the prediction target.

[0123] The display unit 320 has a display screen such as a liquid crystal panel or an LED panel, and displays various images. For example, the display unit 320 may display a state change graph and a state prediction result of a prediction target using the state change graph. The operation input unit 330 includes input devices such as a keyboard and a mouse, and receives user operations. For example, the operation input unit 330 may receive a user operation to instruct the start of state prediction and a user operation to instruct a source for obtaining data related to the prediction target.

[0124] The storage unit 380 stores various data. For example, the storage unit 380 stores the state change graph obtained from the graph generation device 100. The storage unit 380 is configured using a storage device included in the state prediction device 300. The control unit 390 performs various processes by controlling each unit of the state prediction device 300. The functions of the control unit 390 are performed, for example, by a CPU included in the state prediction device 300 reading out a program from the storage unit 380 and executing it.

[0125] The data acquisition unit 391 acquires various data for predicting the state of the prediction target by the state prediction device 300. In particular, the data acquisition unit 391 acquires a state change graph and data related to the state of the prediction target. When the communication unit 310 receives a state change graph from the graph generation device 100, the data acquisition unit 391 may read out the state change graph from the data received by the communication unit 310. Alternatively, when the storage unit 380 stores the state change graph in advance, the data acquisition unit 391 may read out the state change graph from the storage unit 380. Furthermore, when the communication unit 310 receives data related to the state of the prediction target from another device, the data acquisition unit 391 may read out the data related to the state of the prediction target from the data received by the communication unit 310. It is preferable that the data acquisition unit 391 acquires data of items similar to the items of input data for each time in the input time-series data when the graph generation device 100 creates a state change graph.

[0126] The prediction unit 392 predicts the state of the prediction target using the state change graph. Specifically, feature quantities are extracted from data related to the state of the prediction target. In particular, the prediction unit 392 extracts feature quantities using the same feature quantity extraction method as that used by the feature quantity extraction unit 210 of the graph generation device 100. As a result, the feature quantities extracted by the prediction unit 392 indicate coordinate values ​​in a feature quantity space, which is the coordinate space of the state change graph. Therefore, the feature quantities extracted by the prediction unit 392 can be treated as plotting the feature quantities on the state change graph. Then, the prediction unit 392 determines which node of the state change graph to refer to based on the extracted feature amount, and predicts the state of the prediction target based on the edge going out from the determined node. Hereinafter, the feature extracted by the prediction unit 392 will be referred to as a feature to be predicted.

[0127] Fig. 19 is a diagram showing an example of nodes in a state change graph that are referenced by the state prediction device 300. In the example of Fig. 19, points P811 and P821 each indicate an example of displaying a feature quantity to be predicted in the state change graph. Point P811 shows an example in which the prediction unit 392 selects one node from the nodes of the state change graph. When there is one or more nodes that are within a predetermined first distance threshold from the feature to be predicted, the prediction unit 392 may select one of these nodes that is closest to the feature to be predicted. Area A11 corresponds to an example of an area within the first distance threshold from the feature to be predicted. Furthermore, point P812 corresponds to an example of a node selected by the prediction unit 392.

[0128] In this case, when the position of the feature to be predicted is close to the position of the node selected by the prediction unit 392, there is a relatively high possibility that the state of the target to be predicted will change in a manner similar to the state change indicated by the edge from the node selected by the prediction unit 392. Therefore, the prediction unit 392 may trace edges going out from the selected node, and if the node reached has information indicating a state attached thereto, predict that state as the future state of the prediction target. Alternatively, the prediction unit 392 may multiply the length of the traced edge by a predetermined proportionality coefficient to calculate a predicted value of the time required for the state change. In this case, the proportionality coefficient may be the reciprocal (1 / a) of the proportionality coefficient "a" in equation (5). The prediction unit 392 may repeat tracing edges from the destination node to predict a further future state of the prediction target.

[0129] On the other hand, point P821 shows an example in which the prediction unit 392 selects one or more nodes from the nodes of the state change graph. If there is no node within a predetermined first distance threshold from the feature to be predicted, the prediction unit 392 may select all nodes within a second distance threshold that is longer than the first distance threshold. Area A21 corresponds to an example of an area within the second distance threshold from the feature to be predicted. Furthermore, points P822, P823, and P824 correspond to examples of nodes selected by the prediction unit 392.

[0130] In this case, the prediction unit 392 may calculate an intermediate edge among the edges going out from the selected node and treat it as a prediction of the state change to be predicted. For example, the prediction unit 392 may treat edges as vectors in feature space and calculate a weighted average of the vectors according to the distance from the feature to be predicted to the node (starting point of the vector).The prediction unit 392 may then treat the position advanced by the vector calculated from the feature to be predicted as a prediction of the future state of the prediction target.In this case, the prediction unit 392 may also multiply the length of the calculated vector by a predetermined proportional coefficient to calculate a prediction value of the time required for the state change. The prediction unit 392 may also predict a further future state of the prediction target.

[0131] FIG. 20 is a flowchart showing an example of processing by the state prediction device 300 to predict the state of the prediction target. 20, the data acquiring unit 391 acquires data for predicting the state of the prediction target (step S201). For example, the data acquiring unit 391 acquires a state change graph and data related to the state of the prediction target. The data acquiring unit 391 acquires data of items similar to the items of input data for each time in the input time-series data when the graph generation device 100 creates a state change graph.

[0132] Next, the prediction unit 392 extracts features of data related to the state of the prediction target (step S202). The prediction unit 392 extracts features using the same feature extraction method as in the case of the feature extraction unit 210 of the graph generation device 100. Next, the prediction unit 392 selects a node in the state change graph (step S203). As described with reference to Fig. 19, the prediction unit 392 may select one node that is closest to the feature to be predicted, or may select one or more nodes within a predetermined distance from the feature to be predicted.

[0133] Next, the prediction unit 392 predicts the state of the prediction target based on the edges outgoing from the selected node (step S204). As described with reference to Fig. 19, the prediction unit 392 may treat the node reached by tracing an edge outgoing from one node selected in step S203 as a prediction of the future state of the prediction target. Alternatively, the prediction unit 392 may treat the edges outgoing from one or more nodes selected in step S203 as a vector, perform a weighted average, and treat the position advanced from the feature quantity of the prediction target by the amount of the obtained vector as a prediction of the future state of the prediction target. The prediction unit 392 may repeat the processes of steps S203 and S204 to predict a further future state of the prediction target. After step S204, the state prediction device 300 ends the processing of FIG.

[0134] As described above, the prediction unit 392 predicts the state of the object to be predicted using a graph in which the time series of data related to the object to be predicted is shown in a coordinate space set so that the length of time in the time series is proportional to the distance in the coordinate space. According to the state prediction device 300, it is possible to calculate a predicted value of the time required for a state change by a relatively simple calculation, for example, multiplying the length of an edge in the state change graph by a predetermined proportional coefficient.

[0135] Furthermore, the prediction unit 392 detects data (nodes of the state change graph) at which the distance in the coordinate space between the point at which the state of the prediction target before the state change indicated as the state prediction target is plotted in the coordinate space of the state change graph is smallest, and predicts the state of the prediction target after the state change based on the edges of the state change graph from the detected data to other data. In this case, the prediction unit 392 can select only one node in the state change graph. In this respect, the prediction unit 392 can perform state prediction with a relatively simple process, for example, by treating a node reached by tracing an edge from the selected node as a future state prediction of the prediction target.

[0136] Furthermore, the prediction unit 392 detects data (nodes of the state change graph) located within a predetermined distance in the coordinate space from the point at which the state of the prediction target before the state change, which is indicated as the state prediction target, is plotted in the coordinate space of the state change graph, and predicts the state of the prediction target after the state change based on edges in the state change graph from the detected data to other data. This allows the prediction unit 392 to predict the state of the prediction target. In particular, by selecting multiple nodes, the prediction unit 392 can perform state prediction with relatively high accuracy, for example, by calculating a weighted average of the edges coming out from the multiple nodes.

[0137] <Fourth embodiment> In the fourth embodiment, a case will be described in which a graph generation device generates a state change graph by converting an already generated graph. FIG. 21 is a diagram illustrating an example of the configuration of a graph generation device according to the fourth embodiment. 21 , graph generation device 400 includes a communication unit 410, a display unit 420, an operation input unit 430, a storage unit 480, and a control unit 490. Control unit 490 includes a data acquisition unit 491, a graph generation unit 492, and a state information addition unit 493.

[0138] The graph generation device 400 converts graphs. In particular, the graph generation device 400 converts graphs in which the ratio between the length of an edge of the graph and the time in the time-series data varies depending on the position in the coordinate space, so that the ratio between the length of an edge of the graph and the time in the time-series data becomes constant. Through this conversion, the graph generation device 400 generates a state change graph. The graph generating device 400 may be configured using a computer such as a workstation or a personal computer.

[0139] The communication unit 410 communicates with other devices. For example, the communication unit 410 may communicate with the device that generated the graph to receive the graph. The display unit 420 has a display screen such as a liquid crystal panel or an LED panel, and displays various images. For example, the display unit 420 may display a graph before conversion and a graph after conversion. The operation input unit 430 includes input devices such as a keyboard and a mouse, and receives user operations. For example, the operation input unit may receive a user operation to instruct conversion of a graph and a user operation to instruct a source from which to obtain a graph.

[0140] The storage unit 480 stores various data. For example, the storage unit 480 may store a graph before conversion and a graph after conversion. The control unit 490 performs various processes by controlling each unit of the graph generation device 400. The functions of the control unit 490 are performed, for example, by the CPU included in the graph generation device 400 reading and executing a program from the storage unit 480.

[0141] The data acquisition unit 491 acquires, as the graph before conversion, a graph in which the ratio between the length of the edge of the graph and the time in the time-series data varies depending on the position in the coordinate space. For example, when the communication unit 410 receives a graph from another device, the data acquisition unit 491 may read the graph from the signal received by the communication unit 410.

[0142] The graph generation unit 492 converts the graph. As described above for the graph generation device 400, the graph generation unit 492 converts a graph in which the ratio between the length of an edge of the graph and the time in the time-series data varies depending on the position in the coordinate space, so that the ratio between the length of an edge of the graph and the time in the time-series data becomes constant.

[0143] The state information adding unit 493 adds information indicating the state of the prediction target at the time in the input time-series data of the data converted into coordinate values ​​included in a portion of the coordinate space of the graph generated by the graph generating unit 492. The state information adding unit 493 may detect information added to the graph acquired by the data acquiring unit 491, and add the detected information to an area of ​​the converted graph corresponding to the area to which the detected information is added.

[0144] FIG. 22 is a diagram showing an example of a graph before conversion. In the example of FIG. 22, each node of the graph represents a feature of data obtained by repeatedly measuring the graph generation target at regular time intervals. Meanwhile, in the graph shown in FIG. 22, the length of the edges varies depending on the position in the coordinate space. Therefore, in the graph shown in FIG. 22, the ratio of the length of the graph edges to the time in the time-series data varies depending on the position in the coordinate space. Time series data f represented by the graph before conversion m ts i can be expressed as in equation (11).

[0145]

number

[0146] As in the case of equation (3), in equation (11), tmax_i represents the number of data for each time included in the i-th time series data. In the example of Figure 22, the number of time series data is k (k is a positive integer), and f m ts1, f m ts2···, f m ts k It is expressed as follows. Time series data f m ts i Data f for each time m (t i,j ) is expressed as in equation (12).

[0147]

number

[0148] [z m 1(t i,j ),z m 2(t i,j )] is z m 1 coordinate axis and z m The coordinate values ​​of the graph nodes in the two-dimensional coordinate space formed by two coordinate axes are shown below. m i (t i,j ) is the node represented by node f m i (t i,j ) is also written as Fig. 23 is a diagram showing an example of a graph after conversion. Fig. 23 shows an example of a graph obtained by converting the graph of Fig. 22. In the graph of FIG. 22, the lengths of the edges of the graph vary depending on the position in the coordinate space, whereas in the graph of FIG. 23, the lengths of the edges are approximately constant.

[0149] When the graph generation unit 492 converts a graph, if an area associated with a specific state category such as "health" is set in the original graph, it is preferable to set an area corresponding to that area in the converted graph as well. To achieve this, it is possible to reflect the distance between nodes in the original graph in addition to the time interval in the time-series data in the distance between nodes in the converted graph so that two nodes that are close to each other in the original graph are also close to each other in the converted graph.

[0150] For example, graph generating unit 492 may set the distance D between nodes in the converted graph as follows, and repeat the conversion of the graph. For two nodes connected by an edge, graph generation unit 492 calculates and sets the distance between the nodes based on equation (13).

[0151]

number

[0152] Node f in Figure 22 m 2(t 2,2 ) and f m 2(t 2,3 ), node f m i (t i,j ) and node f m i (t i,j+1 ) are nodes whose data are adjacent in time on the timeline, and these two nodes are connected by an edge. f represents the coordinate value of the node m i (t i,j ) and f m i (t i,j+1 ) is the value before this conversion. For example, in the first conversion, f m i (t i,j ) and f m i (t i,j+1 ) is used as the value in the graph acquired by data acquisition unit 491. In the second and subsequent conversions, the value in the graph obtained in the immediately preceding conversion is used. "||f m i (t i,j+1 )-f m i (t i,j )||2" is the edge between two nodes f m i (t i,j ) and f m i (t i,j+1 ) in the coordinate space before the transformation (L2 norm).

[0153] "t i,j+1 -t i,j " is the node f i m (t i,j ) and f i m (t i,j+1 ) represents the time interval in time series data. Each of α and β is a positive real constant. Alternatively, the value of α and / or β may be changed, such as by halving the value of α after a predetermined number of iterations of the transformation.

[0154] In this way, by reflecting the distance before the current change and the time interval in the time series data in the distance between nodes, the distance between nodes in the graph acquired by the data acquisition unit 491 can be reflected, and as the conversion is repeated, the distance between nodes can gradually approach a distance proportional to the time interval in the time series data.

[0155] For two nodes that are not connected by an edge, graph generation unit 492 calculates and sets the distance D between the nodes based on equation (14).

[0156]

number

[0157] Node f in Figure 22 m 2(t 2,2 ) and f m k (t k,1 ), node f m i (t i,j ) and node f m i’ (t i’,j’ ) are not connected by an edge. γ and K are real constants, or the values ​​of γ and / or K may be varied. In equation (14), the two nodes are not connected by an edge, and the concept of time for state change does not apply between these two nodes. Therefore, "β × (t i,j+1 -t i,j On the other hand, in equation (14), the term for the distance in the graph before transformation, "γ×||f m i (t i,j )-f mi’ (t i’,j’ )||2)" is provided.

[0158] The method by which the graph generation unit 492 generates a converted graph so that the distance setting is reflected is not limited to a specific method. For example, the graph generation unit 492 may set any one node as a reference node, and determine the position of each node in order from the reference node, reflecting the set distance. If graph generation fails, the graph generation unit 492 may reset the reference node to another node, and redo the process of determining the node positions in order. When the graph generation unit 492 converts the graph, a constraint or an evaluation function may be set to minimize the movement distance of the nodes before and after the conversion so as to maintain the positional relationship of the nodes on the graph acquired by the data acquisition unit 491 as much as possible.

[0159] Alternatively, the set distance does not necessarily have to be accurately reflected for all pairs of two nodes for which a distance is set. For example, a constraint may be set such that the closer the set distance (the smaller the distance value), the closer the distance in the transformed graph will be, and an error between the set distance under the set constraint and the distance in the transformed graph may be allowed.

[0160] The graph acquired by the data acquisition unit 491 corresponds to an example of a first graph in which the time series of data related to the prediction target is shown in a first coordinate space. m ts i is an example of a time series of data related to the target of prediction. The distance D calculated by equation (13) is an example of a distance index that is a weighted sum of the distance in the first coordinate space between two pieces of data included in the time series shown in the first coordinate space and the time interval in the time series of these two pieces of data.

[0161] The conversion performed by graph generation unit 492 is an example of a coordinate conversion from first coordinates to second coordinates such that the smaller the value of the distance index, the closer the distance between two pieces of data in the second coordinate space. The graph generated by the graph generating unit 492 through the conversion corresponds to an example of a second graph in which the time series of data is shown in a second coordinate space.

[0162] The data acquisition unit 491 may acquire a graph (the above-mentioned first graph) to be converted by the graph generation unit 492 based on tidal flow diagram data, which is data indicating a state change speed vector at each position in a coordinate space.

[0163] FIG. 24 is a diagram showing a first example in which graph generation device 400 generates a graph from a power flow diagram of state change speed vectors. 24, the data acquisition unit 491 sets sampling points at regular intervals within a coordinate space in which the state change speed vector is indicated. The data acquisition unit 491 sets one of the set sampling points as a starting point, sets a sampling point at a position a predetermined time ahead from the starting point according to the state change speed vector, and sets a directed edge from the starting point to the newly set sampling point.

[0164] Furthermore, the data acquisition unit 491 sets the newly set sampling point as the starting point, sets a sampling point at a position a predetermined time ahead from the starting point according to the state change speed vector, and sets a directed edge from the starting point to the newly set sampling point. The data acquisition unit 491 repeats the setting of new sampling points and directed edges by advancing in accordance with the state change speed vector, for example, a predetermined number of times, or until the advancing destination goes outside the domain of the coordinate space.

[0165] The data acquisition unit 491 repeats the setting of new sampling points and directed edges by proceeding from each of the sampling points set at regular intervals in accordance with the state change speed vector, thereby acquiring a graph.

[0166] FIG. 25 is a diagram showing a second example in which graph generation device 400 generates a graph from a power flow diagram of state change speed vectors. 25, the data acquisition unit 491 randomly sets sampling points that serve as starting points of time-series data within the coordinate space indicated by the state change speed vector. The data acquisition unit 491 sets the randomly set sampling points as the starting point. As in the case of FIG. 24, the data acquisition unit 491 repeatedly sets new sampling points and directed edges by moving from the starting point along the state change speed vector. For example, the data acquisition unit 491 repeats the setting of random sampling points a predetermined number of times to acquire a graph based on a predetermined number of pieces of time-series data.

[0167] As described above, the data acquisition unit 491 acquires the time series data f m ts i The graph generating unit 492 obtains a first graph in which the time series data f is shown in the first coordinate space. m ts i The distance in the first coordinate space between the two data contained in m ts i The coordinate transformation from the first coordinate to the second coordinate is performed using a distance index obtained by weighting the sum of the time intervals in the time series data f and the time intervals in the time series data f, so that the smaller the value of the distance index, the closer the distance between the two data in the second coordinate space. * ts i generates a second graph shown in a second coordinate space.

[0168] The graph generating device 400 can visualize the predicted state changes and show the relative length of time it takes for the state changes to occur. Specifically, the graph generation device 400 generates a state change graph that shows how the state of the graph generation target changes and includes information indicating the state, such as the name of the state. A person or a state prediction device can plot the current state of the prediction target on the state change graph to predict the future state. In this case, since the state change graph is generated so that the distance in the coordinate space of the state change graph is proportional to the time interval in the input time series data, it is expected that a person or a state prediction device will be able to predict the time required for a state change with relatively high accuracy.

[0169] In addition, the data acquisition unit 491 acquires tidal flow chart data, which is data indicating state change speed vectors at each point in the first coordinate space, and plots state time series data in the first coordinate space based on the state change speed vectors to generate a first graph. The graph generating unit 492 can convert the first graph acquired by the data acquiring unit 491 to generate a state change graph in which the relative lengths of time taken for state changes are shown in the diagram.

[0170] 26 is a schematic block diagram illustrating an example of a computer configuration according to at least one embodiment. In the configuration shown in FIG. 26, a computer 700 includes a CPU 710, a main memory device 720, an auxiliary memory device 730, and an interface 740.

[0171] Any one or more of the graph generation device 100, graph generation device 100b, state prediction device 300, and graph generation device 400 may be implemented in a computer 700. In this case, the operation of each of the above-mentioned processing units is stored in the auxiliary storage device 730 in the form of a program. The CPU 710 reads the program from the auxiliary storage device 730, loads it into the main storage device 720, and executes the above-mentioned processing in accordance with the program. The CPU 710 also allocates storage areas in the main storage device 720 corresponding to each of the above-mentioned storage units in accordance with the program.

[0172] When the graph generation device 100 is implemented in a computer 700, the operations of the control unit 190 and each of the units are stored in the form of a program in an auxiliary storage device 730. The CPU 710 reads the program from the auxiliary storage device 730, loads it into the main storage device 720, and executes the above-described processing in accordance with the program.

[0173] Furthermore, the CPU 710 allocates a storage area corresponding to the storage unit 180 in the main storage device 720 in accordance with the program. Communication with other devices via the communication unit 110 is performed by the interface 740 having a communication function and performing communication under the control of the CPU 710. The display unit 120 displays various images in accordance with the control of the CPU 710, using a display device provided in the interface 740. The operation input unit 130 receives a user operation by using an interface 740 having input devices such as a keyboard and a mouse to receive the user operation, and outputting information indicating the received user operation to the CPU 710.

[0174] When graph generation device 100b is implemented in computer 700, the operations of control unit 190b and each of its components are stored in the form of a program in auxiliary storage device 730. CPU 710 reads the program from auxiliary storage device 730, loads it into main storage device 720, and executes the above-described processing in accordance with the program.

[0175] Furthermore, the CPU 710 allocates a storage area corresponding to the storage unit 180 in the main storage device 720 in accordance with the program. Communication with other devices via the communication unit 110 is performed by the interface 740 having a communication function and performing communication under the control of the CPU 710. The display unit 120 displays various images in accordance with the control of the CPU 710, using a display device provided in the interface 740. The operation input unit 130 receives a user operation by using an interface 740 having input devices such as a keyboard and a mouse to receive the user operation, and outputting information indicating the received user operation to the CPU 710.

[0176] When the state prediction device 300 is implemented in a computer 700, the operations of the control unit 390 and each of its components are stored in the form of a program in an auxiliary storage device 730. The CPU 710 reads the program from the auxiliary storage device 730, loads it into the main storage device 720, and executes the above-described processing in accordance with the program.

[0177] Furthermore, the CPU 710 allocates a storage area corresponding to the storage unit 380 in the main storage device 720 in accordance with the program. Communication with other devices via the communication unit 310 is performed by the interface 740 having a communication function and performing communication under the control of the CPU 710. The display unit 320 displays various images by having an interface 740 with a display device and displaying various images under the control of the CPU 710 . The operation input unit 330 receives a user operation by an interface 740 having input devices such as a keyboard and a mouse, and outputs information indicating the received user operation to the CPU 710.

[0178] When the graph generation device 400 is implemented in a computer 700, the operations of the control unit 490 and each of the units are stored in the form of a program in an auxiliary storage device 730. The CPU 710 reads the program from the auxiliary storage device 730, loads it into the main storage device 720, and executes the above-described processing in accordance with the program.

[0179] Furthermore, the CPU 710 allocates a storage area corresponding to the storage unit 480 in the main storage device 720 in accordance with the program. Communication with other devices via the communication unit 410 is performed by the interface 740 having a communication function and performing communication under the control of the CPU 710. The display unit 420 displays various images by having the interface 740 have a display device and displaying various images under the control of the CPU 710 . The operation input unit 430 receives a user operation by an interface 740 having input devices such as a keyboard and a mouse, and outputs information indicating the received user operation to the CPU 710.

[0180] Note that a program for realizing all or part of the functions of the graph generation device 100, the graph generation device 100b, the state prediction device 300, and the graph generation device 400 may be recorded on a computer-readable recording medium, and the program recorded on this recording medium may be read into a computer system and executed to perform processing of each part. Note that the term "computer system" here includes hardware such as an OS (Operating System) and peripheral devices. Furthermore, "computer-readable recording media" refers to portable media such as flexible disks, optical magnetic disks, ROMs (Read Only Memory), and CD-ROMs (Compact Disc Read Only Memory), as well as storage devices such as hard disks built into computer systems. The program may be one that realizes part of the aforementioned functions, or may be one that can realize the aforementioned functions in combination with a program already stored in the computer system.

[0181] Although an embodiment of the present invention has been described in detail above with reference to the drawings, the specific configuration is not limited to this embodiment, and design changes and the like are also included within the scope that does not deviate from the gist of the present invention. [Explanation of symbols]

[0182] 1. State Prediction System 100, 100b, 400 graph generator 110, 310, 410 Communications Department 120, 320, 420 display 130, 330, 430 Operation input section 180, 380, 480 storage section 190, 190b, 390, 490 control section 191, 391, 491 Data acquisition section 192, 492 Graph generation unit 193, 493 Status information addition section 194 Learning control unit 210 Feature Extraction Unit 210a Autoencoder 210b GCM 211a, 211b Encoders 212a, 212b relay layer 213a, 213b decoder 214b multiplier 215b Average calculation section 216b Argmax operation section 220 Graph Formation Section 300 State Prediction Device 392 Prediction Department

Claims

1. A data acquisition unit that acquires time series data related to a prediction target; a graph generating unit that converts each of the data included in the time series into a feature using a feature extraction method obtained by learning using an evaluation index in which an evaluation is higher the closer the distance in a feature space between two feature amounts obtained by extracting feature amounts from each of the two data included in the same time series is to a value obtained by multiplying a time interval in the time series of the two data by a predetermined proportionality coefficient; and a state information adding unit that adds, to a portion of the coordinate space, information indicating a state of the prediction target at a time in the time series of the data that is converted into a coordinate value included in the portion; A graph generating device comprising:

2. A data acquisition unit that acquires a first graph in which a time series of data related to a prediction target is shown in a first coordinate space; a graph generating unit that generates a second graph in which the time series is displayed in the second coordinate space by performing coordinate transformation from the first coordinates to second coordinates using a distance index that is a weighted sum of a distance in the first coordinate space between two pieces of data included in the time series displayed in the first coordinate space and a time interval in the time series between the two pieces of data, such that the smaller the value of the distance index, the closer the distance between the two pieces of data in the second coordinate space; a state information adding unit that adds, to a portion of the coordinate space, information indicating a state of the prediction target at a time in the time series of the data that is converted into a coordinate value included in the portion; A graph generating device comprising:

3. the data acquisition unit acquires tidal flow chart data which is data indicating a state change speed vector at each point in the first coordinate space, and plots time-series data of the state in the first coordinate space based on the state change speed vector to generate the first graph; The graph generating device according to claim 2 .

4. a prediction unit that performs state prediction of the prediction target using a graph in which the feature space is a coordinate space obtained by converting each of the data included in the time series into the feature using a feature extraction method obtained by learning using an evaluation index in which an evaluation is higher the closer the distance in a feature space between two feature amounts obtained by extracting feature amounts from each of two data included in the same time series among time series of data related to the prediction target is to a value obtained by multiplying a predetermined proportional coefficient by the time interval in the time series of the two data A state prediction device comprising:

5. The prediction unit detects the data at which the distance in the coordinate space is smallest between the point at which the state of the prediction target before a state change indicated as a state prediction target is plotted in the coordinate space, and predicts the state of the prediction target after a state change based on an edge of the graph from the detected data to another data. The state prediction device according to claim 4 .

6. The prediction unit detects the data located within a predetermined distance in the coordinate space from a point at which a state of the prediction target before a state change indicated as a state prediction target is plotted in the coordinate space, and predicts the state of the prediction target after a state change based on an edge of the graph from the detected data to another data. The state prediction device according to claim 4 .

7. The computer Obtaining a time series of data relating to a target for prediction; converting each of the data included in the time series into the feature using a feature extraction method obtained by learning using an evaluation index in which the closer the distance in a feature space between two feature amounts obtained by performing feature extraction on each of the two data included in the same time series is to a value obtained by multiplying a predetermined proportionality coefficient by the time interval in the time series of the two data, the higher the evaluation; and generating a graph in which the feature space is a coordinate space; adding information to a portion of the coordinate space that indicates a state of the prediction target at a time in the time series of the data that is converted into a coordinate value included in the portion; A graph generation method including:

8. The computer A feature extraction method is used to perform learning using an evaluation index in which the closer the distance in a feature space between two feature amounts obtained by extracting feature amounts from two pieces of data included in the same time series of data related to a prediction target is to a value obtained by multiplying the time interval in the time series of the two pieces of data by a predetermined proportional coefficient, the higher the evaluation, and the state of the prediction target is predicted using a graph in which the feature space is a coordinate space obtained by converting each piece of data included in the time series into the feature amount. A state prediction method including:

9. On the computer, Obtaining a time series of data relating to a target for prediction; converting each of the data included in the time series into the feature using a feature extraction method obtained by learning using an evaluation index in which the closer the distance in a feature space between two feature amounts obtained by performing feature extraction on each of the two data included in the same time series is to a value obtained by multiplying a predetermined proportionality coefficient by the time interval in the time series of the two data, the higher the evaluation; and generating a graph in which the feature space is a coordinate space; adding information to a portion of the coordinate space that indicates a state of the prediction target at a time in the time series of the data that is converted into a coordinate value included in the portion; A program to execute.

10. On the computer, A feature extraction method is used to perform learning using an evaluation index in which the closer the distance in a feature space between two feature amounts obtained by extracting feature amounts from two pieces of data included in the same time series of data related to a prediction target is to a value obtained by multiplying the time interval in the time series of the two pieces of data by a predetermined proportional coefficient, the higher the evaluation, and the state of the prediction target is predicted using a graph in which the feature space is a coordinate space obtained by converting each piece of data included in the time series into the feature amount. A program to execute.

Images