Rule generation device, rule generation method, and program

Abstract

A rule generation device (10) is provided with an acquisition unit (120), a feature index specifying unit (140), and a generation unit (160). The acquisition unit (120) acquires time-series data pertaining to a plurality of indexes and condition information indicating a condition related to an object index. The feature index specifying unit (140) uses the time-series data pertaining to the plurality of indexes and the condition information, thereby specifying at least one index among the plurality of indexes as a feature index for the object index. The generation unit (160) acquires a value of one or more feature indexes and generates, by using at least the acquired value, one or more rules estimated as being necessary to satisfy the condition related to the object index. Further, the rule includes at least one sub-rule related to the feature index.

Description

Technical Field

[0001] The present invention relates to a rule generation device, a determination device, a rule generation method, a determination method, and a program.

Background Art

[0002] In a field where various factors such as economy are related, when trying to achieve a certain goal, it is necessary to determine which approach is effective.

[0003] For example, Patent Document 1 discloses a system that creates a model formula using actual values of a plurality of economic indicators and executes econometric model simulation.

[0004] Also, Patent Document 2 describes predicting future macroeconomic indicators, future management indicators of individual companies, future stock prices of individual companies, etc. based on macroeconomic exogenous indicators.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0006] However, in Patent Documents 1 and 2 described above, only future predictions were made based on assumptions, and thus there was a problem that it was not possible to clarify which approach was effective for the goal to be achieved.

[0007] An example of the object of the present invention is to provide a rule generation device, a determination device, a rule generation method, a determination method, and a program that solve the above-described problems.

Means for Solving the Problem

[0008] According to one aspect of the present invention, an acquisition means for acquiring time series data of a plurality of indicators and condition information indicating conditions related to a target indicator; a feature indicator specifying means for specifying at least one of the plurality of indicators as a feature indicator for the target indicator by using the time series data of the plurality of indicators and the condition information; a generation means for acquiring values of one or more of the feature indicators and generating one or more rules estimated to be necessary for achieving the conditions related to the target indicator by using at least the values, wherein the rule includes at least one sub-rule related to the feature indicator Rule generation device is provided.

[0009] According to one aspect of the present invention, a first acquisition means for acquiring values of one or more indicators and condition information indicating conditions for a target indicator; a second acquisition means for acquiring one or more rules each including one or more sub-rules related to the indicator according to the condition information; a determination means for determining whether the acquired values of the one or more indicators satisfy at least any one of the one or more sub-rules Determination device is provided.

[0010] According to one aspect of the present invention, one or more computers acquire time series data of a plurality of indicators and condition information indicating conditions related to a target indicator, specify at least one of the plurality of indicators as a feature indicator for the target indicator by using the time series data of the plurality of indicators and the condition information, acquire values of one or more of the feature indicators and generate one or more rules estimated to be necessary for achieving the conditions related to the target indicator by using at least the values, The rule includes at least one sub-rule regarding the characteristic index Rule generation method is provided

[0011] According to one aspect of the present invention one or more computers obtain values of one or more indicators and condition information indicating conditions for a target indicator, obtain one or more rules each including one or more sub-rules regarding the indicator according to the condition information, and determine whether the obtained values of the one or more indicators satisfy at least any of the one or more sub-rules Determination method is provided

[0012] According to one aspect of the present invention a computer functions as an acquisition means for acquiring time-series data of a plurality of indicators and condition information indicating conditions for a target indicator, a characteristic index specifying means for specifying at least one of the plurality of indicators as a characteristic index for the target indicator using the time-series data of the plurality of indicators and the condition information, and an acquisition means for acquiring values of one or more of the characteristic indexes, and functions as a generation means for generating one or more rules estimated to be necessary for achieving the conditions regarding the target indicator using at least the values, The rule includes at least one sub-rule regarding the characteristic index Program is provided

[0013] According to one aspect of the present invention a computer functions as a first acquisition means for acquiring values of one or more indicators and condition information indicating conditions for a target indicator, a second acquisition means for acquiring one or more rules each including one or more sub-rules regarding the indicator according to the condition information, and Function as a determination means for determining whether the obtained value of the one or more indicators satisfies at least any one of the one or more sub-rules Program is provided

Effect of the Invention

[0014] According to one aspect of the present invention, a rule generation device, a determination device, a rule generation method, a determination method, and a program that can clarify the conditions necessary to achieve a goal are obtained

Brief Description of the Drawings

[0015]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Embodiments for Carrying Out the Invention

[0016] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all the drawings, the same reference numerals are given to the same components, and the description will be omitted as appropriate.

[0017] (First Embodiment) FIG. 1 is a diagram showing an outline of a rule generation device 10 according to the first embodiment. The rule generation device 10 according to the present embodiment includes an acquisition unit 120, a feature index specifying unit 140, and a generation unit 160. The acquisition unit 120 acquires time series data of a plurality of indices and condition information indicating conditions related to a target index. The feature index specifying unit 140 specifies at least one of the plurality of indices as a feature index for the target index using the time series data of the plurality of indices and the condition information. The generation unit 160 acquires values of one or more feature indices and generates one or more rules estimated to be necessary to achieve the conditions related to the target index using at least those values. And the rule includes at least one sub-rule related to the feature index.

[0018] According to this rule generation device 10, the conditions necessary to achieve the goal can be clarified.

[0019] Hereinafter, a detailed example of the rule generation device 10 will be described.

[0020] Each of the plurality of indicators and the target indicator is, for example, an economic indicator. There are tens of thousands of types of economic indicators, and many indicators for which time-series data can be obtained as open data exist. However, each of the plurality of indicators and the target indicator is not particularly limited, and may be an indicator indicating the social situation, an indicator indicating the physical condition, or the like. Hereinafter, an example in which the plurality of indicators and the target indicator are economic indicators will be described.

[0021] For example, in order to achieve the goal of improving a certain target indicator, it is assumed that a certain measure is executed. However, the target indicator may not always improve as expected. The reason for this is that there are other factors for increasing the target indicator, and the fact that the factor does not satisfy the sufficient condition. Such factors are not necessarily limited to one. It is considered that the goal can be achieved by clarifying such factors and taking an appropriate approach. However, there are tens of thousands of types of economic indicators. It is necessary to identify the factors related to the target indicator among these indicators. Furthermore, by clarifying the conditions that the identified indicators should specifically satisfy, the measures for achieving the goal become clear, and the effect of the measures is enhanced.

[0022] FIG. 2 is a block diagram illustrating the functional configuration of the rule generation device 10 according to the present embodiment. In the example of this figure, the rule generation device 10 further includes an indicator storage unit 122.

[0023] <Acquisition unit 120> FIG. 3 is a diagram illustrating time-series data of a plurality of indicators acquired by the acquisition unit 120. The time-series data of the plurality of indicators (indicator 1, indicator 2, ···, indicator N) is previously held in the indicator storage unit 122. Then, the acquisition unit 120 can read and acquire the time-series data from the indicator storage unit 122. In the example of FIG. 2, the indicator storage unit 122 is provided in the rule generation device 10, but the indicator storage unit 122 may be provided outside the rule generation device 10. Further, instead of reading the time-series data from the indicator storage unit 122, the acquisition unit 120 may acquire it from another device. The number N of the plurality of indicators is not particularly limited. The number of the plurality of indicators may be 10,000 or more.

[0024] Further, the acquisition unit 120 acquires condition information. The condition information is, for example, information indicating the value or range of the target indicator. The target indicator is any one of the plurality of indicators (indicator 1, indicator 2, ···, indicator N). The condition information is input to the rule generation device 10 by the user, for example, and the acquisition unit 120 can acquire the input condition information. Alternatively, the condition information may be previously held in a storage unit accessible by the acquisition unit 120, and the acquisition unit 120 may read and acquire it, or the acquisition unit 120 may acquire the condition information from an external device.

[0025] <Characteristic Indicator Identification Unit 140> FIG. 4 is a diagram for explaining the process performed by the characteristic indicator identification unit 140. The characteristic indicator identification unit 140 extracts one or more that affect the target indicator from the plurality of indicators and the rate of change representing the transition of the plurality of indicators over time. Then, the characteristic indicator identification unit 140 identifies the characteristic indicator based on at least one of the extracted indicators and the rate of change. Specifically, the characteristic indicator identification unit 140 includes a first model 142 for extracting characteristic quantities. Then, the characteristic indicator identification unit 140 uses the first model 142 to extract one or more that affect the target indicator from the plurality of indicators and the rate of change. By thus identifying the characteristic indicator by the characteristic indicator identification unit 140, rule generation can be performed by narrowing down the indicators that contribute significantly to achieving the conditions related to the target indicator from among the plurality of indicators.

[0026] In the example of this figure, the time-series data and condition information acquired by the acquisition unit 120 are input to the feature index identification unit 140 and then input to the first model 142 in the feature index identification unit 140. Then, from the first model 142, information indicating one or more of index 1, index 2, ···, index N, the change rate of index 1, the change rate of index 2, ···, and the change rate of index N is output. What is output from the first model 142 is an index or a change rate that has a large impact on the target index among the input indices.

[0027] The feature index identification unit 140 uses the indices shown in the output data of the first model 142 as feature indices. Also, the feature index identification unit 140 uses the indices that are the basis for the change rates shown in the output data of the first model 142 as feature indices. That is, when "the change rate of index n" is shown in the output data of the first model 142, the feature index identification unit 140 uses "index n" as the feature index. Specifically, in the example of this figure, the output data of the first model 142 shows index 2, the change rate of index 15, the change rate of index 82, index 190, ···, and index 8734. And the feature index identification unit 140 uses index 2, index 15, index 82, index 190, ···, and index 8734 as feature index 1, feature index 2, feature index 3, feature index 4, ···, feature index M, respectively.

[0028] The feature index identification unit 140 does not need to identify feature indices based on all the indices and change rates extracted by the first model 142. For example, among the indices shown in the output data of the first model 142 and the indices that are the basis for the change rates shown in the output data, the remaining ones excluding the indices that are difficult to approach by measures may be used as feature indices. In such a case, it is only necessary to pre-determine a group of indices that are not used as feature indices or a group of indices that can be used as feature indices among index 1, index 2, ···, index N. Then, the feature index identification unit 140 can identify feature indices according to the determined group of indices.

[0029] The number M of characteristic indicators specified by the characteristic indicator specifying unit 140 is not particularly limited. However, the number M of characteristic indicators is smaller than the number N of a plurality of indicators input to the first model 142. M may be, for example, 1 / 10 or less of N, or may be 1 / 100 or less. M is, for example, 100 or less. M may be, for example, 10 or more, or may be 20 or more.

[0030] For example, the characteristic indicator specifying unit 140 may specify a predetermined number Mp of characteristic indicators based on the extraction result by the first model 142. In that case, the extraction result of the first model 142 is ranked to indicate the strength of the correlation with the condition information, and the characteristic indicator specifying unit 140 can determine the characteristic indicators based on Mp indicators or change rates with strong correlations.

[0031] The first model 142 can be realized using existing technologies. The first model 142 is a trained model by machine learning. This machine learning can be performed using time series data of a combination of the value of the target indicator, other indicator values, and correct / incorrect flags as training data. The correct / incorrect flag can be assigned based on a predetermined condition for the target indicator. Here, the predetermined condition may be the same as the condition shown in the condition information, or may not be the same.

[0032] In this figure, an example is shown in which the first model 142 extracts one or more that affect the target indicator from a plurality of indicators and the change rate representing the transition of the plurality of indicators over time. As shown in this figure, it is preferable for the first model 142 to extract at least one change rate of the indicator. By performing extraction from candidates including not only the indicator itself but also the change rate of the indicator, analysis considering the transition of each indicator over time becomes possible. Therefore, the rule generation device 10 can generate more accurate rules. In this case as well, the acquisition unit 120 does not necessarily need to acquire the time series data of the change rate of the indicator separately from the time series data of the indicator. However, the first model 142 may extract one or more that affect the target indicator from only a plurality of indicators without considering the change rate.

[0033] FIG. 5 is a diagram showing a specific example of information output from the first model 142. The numbers at the beginning of each row in this figure are identification codes for each index. In addition to the index and information indicating the change rate of the index, the output data of the first model 142 may show a situation that is highly correlated with the situation that satisfies the condition information input to the first model 142 as shown in this figure. Even in that case, it is useful that more specific rules are generated by the processing of the generation unit 160 described later.

[0034] <generation unit 160> As described above, the generation unit 160 acquires the values of one or more characteristic indexes and generates one or more rules that are estimated to be necessary to achieve the conditions regarding the target index using at least those values.

[0035] FIG. 6 is a diagram illustrating the values of one or more characteristic indexes acquired by the generation unit 160. The values acquired by the generation unit 160 may be, for example, the values of the indexes corresponding to each characteristic index among the time-series data of a plurality of indexes acquired by the acquisition unit 120. Also, the values acquired by the generation unit 160 may be, for example, the values indicating the latest situation among the time-series data. In addition, the generation unit 160 may separately accept input of the values of the characteristic indexes by the user, apart from the time-series data acquired by the acquisition unit 120.

[0036] The number of values of the characteristic indexes acquired by the generation unit 160 is not particularly limited, and may be, for example, 100 or less, or may be 50 or less. The number of values of the characteristic indexes acquired by the generation unit 160 may be, for example, 10 or more, or may be 20 or more.

[0037] The generation unit 160 includes a second model 162 by ensemble machine learning. The second model 162 is, for example, a trained model by Ensemble Machine Learning (EML) with high interpretability. This machine learning can use time-series data of the combination of the value of the target index, other index values, and the correct / incorrect flag as training data. The correct / incorrect flag can be assigned based on a predetermined condition for the target index. Here, the predetermined condition may or may not be the same as the condition shown in the condition information.

[0038] FIG. 7 is a diagram illustrating the configuration of the output data of the second model 162. In the generation unit 160, the value of the feature index and the condition information are input to the second model 162. As the value of the feature index, one value may be input for each feature index. Also, the number of feature indexes for which values are input to the second model 162 is not particularly limited. Then, a plurality of rules are output from the second model 162. Each rule includes one or more sub-rules. Each sub-rule indicates a condition related to any one of the feature indexes. Here, the sub-rules output from the second model 162 may include the conditions satisfied by the values of the feature indexes input to the second model 162 and the conditions not satisfied.

[0039] The number of sub-rules included in each rule can be preset in the second model 162. When a plurality of rules are generated from the second model 162, the number of sub-rules included in the rules may be different from each other or the same.

[0040] FIG. 8 is a diagram showing a specific example of an output rule output from the generation unit 160. In this figure, the numbers at the beginning of each sub-rule are identification codes of each index. When there is a rule including a plurality of sub-rules in the rule output from the second model 162, the generation unit 160 connects those sub-rules with "AND". That is, in each rule, the fulfillment of that rule means that all the sub-rules included in that rule are fulfilled. Also, when a plurality of rules are output from the second model 162, the generation unit 160 connects those rules with "AND" or "OR". In this way, the generation unit 160 outputs one generated rule or two or more rules connected to each other as an output rule. The output rule output from the generation unit 160 may be displayed on a display, for example, or may be held in a storage device accessible from the generation unit 160. The user can recognize the output rule output from the generation unit 160 as a condition necessary to satisfy the condition regarding the target index shown in the condition information.

[0041] In the example of this figure, the generation unit 160 outputs, as the final output rule, a rule obtained by connecting Rule 1 and Rule 2 with "AND". In Rule 1 and Rule 2, the sub-rules included in each rule are connected to each other with "AND".

[0042] FIG. 9 is a diagram showing an example of the configuration of an output rule output from the generation unit 160. One or more rules generated by the second model 162 in the generation unit 160 may include two or more rules that are replaceable with each other. In the example of this figure, Rule 2-1 and Rule 2-2 are connected to each other with "OR". That is, Rule 2-1 and Rule 2-2 are replaceable with each other, and at least one of them may be satisfied. By generating alternative rules in this way, even if it is difficult to satisfy any one of the rules, an alternative measure can be executed.

[0043] FIG. 10 and FIG. 11 are diagrams each showing an example of the configuration of the output rules output from the generation unit 160. The number of rules output from the second model 162 is not particularly limited and can be set in advance in the second model 162. Further, the generation unit 160 can generate output rules having a predetermined structure using the output data of the second model 162. For example, in the example of FIG. 10, in the output rules, the rule 2-2-1 and the rule 2-2-2 combined by "AND" and the rule 2-1 are replaceable with each other. In the example of FIG. 11, in the output rules, three or more rules are connected to each other by "AND". Note that the configurations of the output rules shown in FIGS. 8 to 11 are examples and are not limited thereto.

[0044] Further, the output rules output from the generation unit 160 may include all of the rules output from the second model 162, or may include only a part thereof. Further, in the output rules output from the generation unit 160, sub-rules for all feature indicators may exist, or sub-rules may exist only for some feature indicators.

[0045] The hardware configuration of the rule generation device 10 will be described below. Each functional component of the rule generation device 10 is realized by a combination of hardware and software (for example, a combination of an electronic circuit and a program for controlling the same). This will be further described below.

[0046] FIG. 12 is a diagram illustrating a computer 1000 for realizing the rule generation device 10. The rule generation device 10 may be realized by one computer 1000, or may be realized by the cooperation of a plurality of computers 1000. The computer 1000 is an arbitrary computer. For example, the computer 1000 is a System On Chip (SoC), a Personal Computer (PC), a server machine, a tablet terminal, or a smartphone. The computer 1000 may be a dedicated computer designed to realize the rule generation device 10, or may be a general-purpose computer.

[0047] The computer 1000 has a bus 1020, a processor 1040, a memory 1060, a storage device 1080, an input / output interface 1100, and a network interface 1120. The bus 1020 is a data transmission path for the processor 1040, the memory 1060, the storage device 1080, the input / output interface 1100, and the network interface 1120 to transmit and receive data to and from each other. However, the method of connecting the processor 1040 and the like to each other is not limited to bus connection. The processor 1040 is various processors such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or an FPGA (Field-Programmable Gate Array). The memory 1060 is a main storage device realized using a RAM (Random Access Memory) or the like. The storage device 1080 is an auxiliary storage device realized using a hard disk, an SSD (Solid State Drive), a memory card, or a ROM (Read Only Memory).

[0048] The input / output interface 1100 is an interface for connecting the computer 1000 and an input / output device. For example, an input device such as a keyboard and an output device such as a display are connected to the input / output interface 1100.

[0049] The network interface 1120 is an interface for connecting the computer 1000 to a network. This communication network is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network). The method by which the network interface 1120 connects to the network may be a wireless connection or a wired connection.

[0050] The storage device 1080 stores program modules that implement each functional component of the rule generation device 10. The processor 1040 reads out and executes these program modules in the memory 1060, thereby implementing the functions corresponding to the respective program modules.

[0051] Also, when the index storage unit 122 is provided inside the rule generation device 10, for example, the index storage unit 122 is implemented using the storage device 1080.

[0052] FIG. 13 is a flowchart illustrating the flow of the rule generation method according to the present embodiment. The rule generation method according to the embodiment is executed by one or more computers. The rule generation method according to the present embodiment includes step S110, step S120, and step S130. In step S110, time series data of a plurality of indices and condition information indicating conditions related to the target index are acquired. In step S120, using the time series data of the plurality of indices and the condition information, at least one of the plurality of indices is specified as a characteristic index for the target index. In step S130, values of one or more characteristic indices are acquired, and one or more rules that are estimated to be necessary to achieve the conditions related to the target index are generated using at least those values. The rule includes at least one sub-rule related to the characteristic index.

[0053] The rule generation method according to this embodiment can be executed by the above-described rule generation apparatus 10. First, when receiving an instruction to execute rule generation, the rule generation apparatus 10 acquires time series data of a plurality of indices (index 1 to N) and condition information in step S110. Then, in step S120, the time series data and the condition information are input to the first model 142 of the feature index specifying unit 140. Then, information indicating one or more of index 1, index 2, ···, index N, the change rate of index 1, the change rate of index 2, ···, and the change rate of index N is output from the first model 142. The feature index specifying unit 140 specifies one or more feature indices (feature indices 1 to M) based on the output of the first model 142. Next, in step S130, the values of one or more feature indices and the condition information are input to the second model 162 of the generation unit 160. One or more rules are output from the second model 162. The generation unit 160 generates an output rule using one or more rules output from the second model 162 and outputs the output rule.

[0054] As described above, according to this embodiment, the generation unit 160 acquires the values of one or more feature indices and generates one or more rules that are estimated to be necessary to achieve the conditions regarding the target index using at least those values. Therefore, it is possible to clarify the conditions necessary to achieve the target.

[0055] (Second Embodiment) FIG. 14 is a diagram showing an overview of the determination apparatus 20 according to the second embodiment. The determination apparatus 20 according to this embodiment includes a first acquisition unit 220, a second acquisition unit 240, and a determination unit 260. The first acquisition unit 220 acquires the values of one or more indices and condition information indicating the conditions for the target index. The second acquisition unit 240 acquires one or more rules according to the condition information. Each of the one or more rules includes one or more sub-rules regarding the index. The determination unit 260 determines whether the acquired values of the one or more indices satisfy at least any one of the one or more sub-rules.

[0056] According to this determination apparatus 20, it is possible to clarify the conditions necessary to achieve the target.

[0057] FIG. 15 is a diagram illustrating the functional configuration of the determination device 20 according to the present embodiment. In the example of this figure, the determination device 20 further includes a rule storage unit 242 and an output unit 280. In the present embodiment, one or more rules are held in the rule storage unit 242 in advance. Then, the second acquisition unit 240 reads and acquires one or more rules from the rule storage unit 242. In this figure, an example in which the rule storage unit 242 is included in the determination device 20 is shown, but the rule storage unit 242 may be provided outside the determination device 20.

[0058] The rules held in the rule storage unit 242 can be generated using the rule generation device 10 according to the first embodiment.

[0059] Similar to the rule generation device 10 according to the first embodiment, the determination device 20 according to the present embodiment can be realized using the computer 1000 having the configuration illustrated in FIG. 12. The storage device 1080 stores program modules that realize the respective functional configuration parts of the determination device 20. The processor 1040 reads these program modules into the memory 1060 and executes them, thereby realizing the functions corresponding to the respective program modules. The determination device 20 may be realized by one computer 1000 or may be realized by the cooperation of a plurality of computers 1000. Further, when the rule storage unit 242 is provided inside the determination device 20, for example, the rule storage unit 242 can be realized using the storage device 1080.

[0060] <First acquisition unit 220> The first acquisition unit 220 acquires the values of one or more indicators, for example, by receiving an input from a user. Alternatively, the first acquisition unit 220 may read and acquire the values of one or more indicators from a storage device (for example, the storage device 1080) accessible from the first acquisition unit 220, or may acquire them from another external device. The values of the indicators acquired by the first acquisition unit 220 may correspond to, for example, the characteristic indicator values acquired by the generation unit 160 in the first embodiment, but are not limited thereto.

[0061] The first acquisition unit 220 only needs to acquire one value for each index. Also, the number of indices for which the first acquisition unit 220 acquires values is not particularly limited, and for example, it may be 100 or less, or may be 50 or less. The number of indices for which the first acquisition unit 220 acquires values may be, for example, 10 or more, or may be 20 or more.

[0062] Also, the first acquisition unit 220 acquires condition information. The condition information is, for example, information indicating the value or range of the target index. The target index may be any one of the indices for which the first acquisition unit 220 acquires values, or may be an index different from the indices for which the first acquisition unit 220 acquires values.

[0063] The condition information is input to the determination device 20 by the user, for example, and the first acquisition unit 220 can acquire the input condition information. For example, options for the target index are displayed on the display of the determination device 20, and the user can input information indicating the target index to the determination device 20 by performing an operation of selecting any one of the options. Also, for example, options indicating the value or range of the target index are displayed on the display of the determination device 20, and the user can input information indicating the value or range of the target index to the determination device 20 by performing an operation of selecting any one of the options.

[0064] Note that the condition information may be held in advance in a storage device (for example, the storage device 1080) accessible by the first acquisition unit 220, and the first acquisition unit 220 may read and acquire it, or the first acquisition unit 220 may acquire the condition information from an external device.

[0065] Also, for example, the first acquisition unit 220 may first acquire the condition information, and depending on the condition information, it may be determined which index values should be acquired. In that case, for each target index, which index values should be acquired is determined in advance. Then, when the first acquisition unit 220 acquires the condition information, it causes the input index corresponding to the target index indicated by the condition information to be displayed on the display of the determination device 20. Then, the user inputs a value for the displayed index.

[0066] <Second acquisition unit 240> The second acquisition unit 240 acquires one or more rules according to the condition information acquired by the first acquisition unit 220. The one or more rules acquired by the second acquisition unit 240 may be independent of each other as in the example shown in FIG. 7, or may be combined with each other by "AND" or "OR" as shown in FIGS. 8 to 11. Hereinafter, the one or more rules acquired by the second acquisition unit 240 are collectively referred to as a rule set. For example, FIGS. 7 to 11 each show one rule set.

[0067] The rule storage unit 242 holds a plurality of rule sets. The rule storage unit 242 also holds rule set reference information in advance. In the rule set reference information, each rule set is associated with a combination of what the target index is and the value or range of the target index.

[0068] FIG. 16 is a diagram illustrating the rule set reference information. Using such rule set reference information, the second acquisition unit 240 can identify which rule set should be used based on the condition information. For example, the second acquisition unit 240 identifies a rule set corresponding to the target index shown in the condition information and the range to which the value of the target index belongs. Then, the second acquisition unit 240 reads out and acquires the identified rule set from the rule storage unit 242. In this figure, an example in which the range of the target index is associated with the rule set is shown, but the value of the target index may be associated with the rule set. When the first acquisition unit 220 acquires the condition information via the option as described above, it is preferable that the range or value of the target index in the rule set reference information corresponds to the option.

[0069] <Determination unit 260> The determination unit 260 performs determination on at least the sub - rules included in the rule set acquired by the second acquisition unit 240. Specifically, the determination unit 260 determines whether the value of the index acquired by the first acquisition unit 220 satisfies each of the sub - rules acquired by the second acquisition unit 240. Each sub - rule indicates a condition regarding any one of the indexes acquired by the first acquisition unit 220. Further, the determination unit 260 may further determine whether at least any one of the rules is satisfied based on the determination results of the sub - rules. Specifically, for a certain rule, if all the sub - rules included in that rule are satisfied, it is determined that the rule is satisfied. On the other hand, a rule that includes even one unsatisfied sub - rule is determined to be unsatisfied. The determination unit 260 may perform determination on only some of the sub - rules included in the rule set, but it is preferable to perform determination on all the sub - rules.

[0070] Note that in the rule set acquired by the second acquisition unit 240, there may be sub - rules for all the indexes whose values are acquired by the first acquisition unit 220, or there may be sub - rules only for some of the indexes.

[0071] <Output unit 280> The output unit 280 outputs one or more sub - rules determined by the determination unit 260 as not being satisfied by the value of the index acquired by the first acquisition unit 220. By doing so, the user of the determination device 20 can grasp the conditions that need to be satisfied, consider countermeasures, or take appropriate measures. The output unit 280 preferably outputs all the sub - rules determined as not being satisfied by the value of the index acquired by the first acquisition unit 220. Also, the output unit 280 may further output the sub - rules determined as being satisfied by the value of the index acquired by the first acquisition unit 220. The output method of the output unit 280 is not particularly limited, and for example, it can be display on a display or output to an external device or a storage device.

[0072] FIG. 17 is a flowchart exemplifying the flow of the determination method according to the present embodiment. The determination method according to the embodiment is executed by one or more computers. The determination method according to the present embodiment includes step S210, step S220, and step S230. In step S210, the values of one or more indicators and condition information indicating conditions for the target indicator are acquired. In step S220, one or more rules are acquired according to the condition information. Each of the one or more rules includes one or more sub-rules regarding the indicator. In step S230, it is determined whether the acquired values of the one or more indicators satisfy at least any one of the one or more sub-rules.

[0073] The determination method according to the present embodiment can be executed by the determination device 20 described above. For example, when the values of the indicators and the condition information are input to the determination device 20 by the user, the first acquisition unit 220 acquires them (step S210). Then, in step S220, the second acquisition unit 240 acquires one or more rules (rule set) based on the condition information. Then, in step S230, the determination unit 260 determines whether the sub-rules included in the rule set are satisfied by the values of the indicators acquired by the first acquisition unit 220.

[0074] Next, the operations and effects of the present embodiment will be described. In the present embodiment, the same operations and effects as those of the first embodiment can be obtained. In addition, according to the present embodiment, the determination device 20 determines whether the acquired values of the one or more indicators satisfy at least any one of the one or more sub-rules. Therefore, it is possible to more clearly grasp the indicators and conditions that require countermeasures.

[0075] (Third Embodiment) FIG. 18 is a block diagram illustrating the functional configuration of the determination device 20 according to the third embodiment. The determination device 20 according to the present embodiment is the same as the determination device 20 according to the second embodiment, except that it further includes a rule generation unit 250 that generates one or more rules. In the present embodiment, the second acquisition unit 240 acquires the one or more rules generated by the rule generation unit 250. In the present embodiment, the determination device 20 does not necessarily include the rule storage unit 242. This will be described in detail below.

[0076] In the example of this figure, the rule generation unit 250 includes a feature index specifying unit 251 and a generation unit 252. The feature index specifying unit 251 is the same as the feature index specifying unit 140 described in the first embodiment, and the generation unit 252 is the same as the generation unit 160 described in the first embodiment. However, the rule generation unit 250 may not include the feature index specifying unit 251 and may include the generation unit 252. The feature index specifying unit 251 includes a first model 253, and the generation unit 252 includes a second model 254. The first model 253 is the same as the first model 142 described in the first embodiment, and the second model 254 is the same as the second model 162 described in the first embodiment.

[0077] When the rule generation unit 250 does not include the feature index specifying unit 251 and includes the generation unit 252, the rule generation unit 250 generates rules as follows. The generation unit 252 acquires the values of the one or more indicators acquired by the first acquisition unit 220, and uses at least those values to generate one or more rules that are estimated to be necessary to achieve the conditions regarding the target indicator indicated by the condition information. Specifically, the values of the one or more indicators acquired by the first acquisition unit 220 and the condition information are input to the second model 254 of the generation unit 252. Then, a plurality of rules are output from the second model 254. And the generation unit 252 generates output rules in the same manner as the generation unit 160. The second acquisition unit 240 acquires the output rules generated by the generation unit 252.

[0078] When the rule generation unit 250 includes a feature index identification unit 251 and a generation unit 252, the first acquisition unit 220 acquires time-series data of a plurality of indices in the same manner as the acquisition unit 120 in the first embodiment. Then, the feature index identification unit 251 identifies feature indices in the same manner as the feature index identification unit 140 described in the first embodiment. Then, the generation unit 252 acquires values of one or more feature indices in the same manner as the generation unit 160 described in the first embodiment, and generates one or more rules that are estimated to be necessary to achieve the conditions regarding the target index using at least those values. In this case, the determination device 20 may include the rule generation device 10 described in the first embodiment.

[0079] Next, the operations and effects of this embodiment will be described. In this embodiment, the same operations and effects as those of the first embodiment can be obtained. In addition, the determination device 20 according to this embodiment further includes a rule generation unit 250 that generates one or more rules. Therefore, it is not necessary to generate and store many rules in advance, and rule generation according to condition information can be performed each time.

[0080] (Fourth Embodiment) FIG. 19 is a diagram for explaining the determination device 20 according to the fourth embodiment. This figure is displayed on, for example, the display of the determination device 20. The determination device 20 according to this embodiment is the same as the determination device 20 according to the second or third embodiment except for the points described below.

[0081] In the determination device 20 according to this embodiment, the output unit 280 outputs one or more insufficient sub-rules. An insufficient sub-rule is a sub-rule determined by the determination unit 260 when the values of one or more indices acquired by the first acquisition unit 220 are not satisfied. Then, the first acquisition unit 220 accepts a selection of at least any one of the output one or more insufficient sub-rules. Further, the first acquisition unit 220 uses the selected insufficient sub-rule as condition information.

[0082] According to such a determination device 20, for example, when non-compliance sub-rules are indicators or conditions that are difficult to directly approach by measures or the like, the user can grasp alternative rules to be satisfied instead of the non-compliance sub-rules.

[0083] That is, the first acquisition unit 220 uses the non-compliance sub-rule as condition information and newly performs the flow from steps S210 to S230. In that flow, the second acquisition unit 240 acquires an alternative rule instead of the non-compliance sub-rule, and a determination is made for that alternative rule. As a result, the user can grasp the rules to be satisfied instead of the non-compliance sub-rules, and the rules that are not satisfied among them. Such an alternative to the non-compliance sub-rule may be repeated. Therefore, the user can find indicators and conditions that are more approachable by measures.

[0084] This figure illustrates an image displayed on the display as an output by the output unit 280. For example, in the image, the compliance sub-rules and the non-compliance sub-rules are displayed in different colors. Note that the compliance sub-rule is a sub-rule determined by the determination unit 260 when the values of one or more indicators acquired by the first acquisition unit 220 are satisfied. In this figure, the compliance sub-rules are displayed in white characters with black backgrounds, and the non-compliance sub-rules are displayed in black characters with white backgrounds. And, next to the non-compliance sub-rule, a button 300 (a "generate alternative rule" button) for requesting generation of an alternative rule is displayed. By clicking this button 300 by the user, the first acquisition unit 220 accepts the selection of this non-compliance sub-rule and acquires the selected non-compliance sub-rule as condition information.

[0085] When the output unit 280 outputs a plurality of non-compliance sub-rules, the user may select only one of them, or may select two or more of them. When two or more non-compliance sub-rules are selected, the determination device 20 performs processing for generating and determining an alternative rule for each non-compliance sub-rule. In generating the alternative rule, the values of the indicators already acquired may be used, or one or more indicator values may be newly acquired by the first acquisition unit 220.

[0086] Next, the operations and effects of this embodiment will be described. In this embodiment, the same operations and effects as those of the first embodiment can be obtained. In addition, according to the determination device 20 according to this embodiment, the first acquisition unit 220 accepts a selection of at least any one of one or more insufficient sub-rules, and uses the selected insufficient sub-rule as condition information. Therefore, for example, when the insufficient sub-rule is an index or condition that is difficult to directly approach by measures or the like, the user can grasp an alternative rule to be satisfied instead of the insufficient sub-rule.

[0087] As described above, the embodiments of the present invention have been described with reference to the drawings. These are examples of the present invention, and various configurations other than the above can also be adopted.

[0088] Also, in the plurality of flowcharts used in the above description, a plurality of steps (processes) are described in order. However, the execution order of the steps executed in each embodiment is not limited to the order of the description. In each embodiment, the order of the steps shown can be changed within a range that does not substantially affect the content. In addition, the above-described embodiments can be combined within a range where the contents do not conflict.

[0089] Some or all of the above embodiments can be described as follows in the appended claims, but are not limited thereto. 1. An acquisition means for acquiring time-series data of a plurality of indicators and condition information indicating conditions related to a target indicator, A feature index specifying means for specifying at least one of the plurality of indicators as a feature index for the target indicator by using the time-series data of the plurality of indicators and the condition information, An acquisition means for acquiring values of one or more of the feature indices, and a generation means for generating one or more rules estimated to be necessary for achieving the conditions related to the target indicator by using at least the values, The rule includes at least one sub-rule related to the feature index Rule generation device. 2. In the rule generation device according to 1., The characteristic index specifying means extracts one or more that affect the target index from among the plurality of indexes and the change rates representing the transitions of the plurality of indexes over time, and specifies the characteristic index based on at least one of the extracted index and the change rate Rule generation device. 3. In the rule generation device according to 2., The characteristic index specifying means includes a first model for extracting feature quantities, and extracts one or more that affect the target index from among the plurality of indexes and the change rate using the first model Rule generation device. 4. In the rule generation device according to any one of 1. to 3., The generation means includes a second model by ensemble machine learning Rule generation device. 5. In the rule generation device according to any one of 1. to 4., The one or more generated rules include two or more rules that can be replaced with each other Rule generation device. 6. In the rule generation device according to any one of 1. to 5., The index is an economic index Rule generation device. 7. First acquisition means for acquiring values of one or more indexes and condition information indicating conditions for a target index, Second acquisition means for acquiring one or more rules each including one or more sub - rules related to the index according to the condition information, and determination means for determining whether the acquired values of the one or more indexes satisfy at least any of the one or more sub - rules Determination device. 8. In the determination device according to 7., The one or more rules are pre - held in a storage means, The second acquisition means reads and acquires the one or more rules from the storage means. Determination device. 9. In the determination device according to 7., further comprising rule generation means for generating the one or more rules, the second acquisition means acquires the one or more rules generated by the rule generation means. Determination device. 10. In the determination device according to any one of 7. to 9., further comprising output means for outputting one or more insufficient sub - rules, which are the sub - rules for which it is determined by the determination means that the values of the one or more indicators are not satisfied. Determination device. 11. In the determination device according to 10., the first acquisition means, receives a selection of at least any one of the one or more output insufficient sub - rules, and uses the selected insufficient sub - rule as the condition information. Determination device. 12. One or more computers acquire time - series data of a plurality of indicators and condition information indicating conditions regarding a target indicator, use the time - series data of the plurality of indicators and the condition information to identify at least one of the plurality of indicators as a characteristic indicator for the target indicator, acquire values of one or more of the characteristic indicators, and generate one or more rules that are estimated to be necessary to achieve the conditions regarding the target indicator using at least the values, wherein the rule includes at least one sub - rule regarding the characteristic indicator. Rule generation method. 13. In the rule generation method according to 12., the one or more computers extract one or more of the plurality of indicators and the rate of change representing the transition of the plurality of indicators with respect to time that affect the target indicator, Identify the characteristic index based on at least one of the extracted index and the change rate Rule generation method 14. In the rule generation method according to 13., The one or more computers extract one or more that affect the target index among the plurality of indexes and the change rate using a first model for extracting feature amounts Rule generation method 15. In the rule generation method according to any one of 12. to 14., The one or more computers generate the one or more rules using a second model based on ensemble machine learning Rule generation method 16. In the rule generation method according to any one of 12. to 15., The one or more generated rules include two or more rules that can be replaced with each other Rule generation method 17. In the rule generation method according to any one of 12. to 16., The index is an economic index Rule generation method 18. One or more computers Obtain values of one or more indexes and condition information indicating conditions for a target index Obtain one or more rules each including one or more sub - rules regarding the index according to the condition information Determine whether the obtained values of the one or more indexes satisfy at least any of the one or more sub - rules Determination method 19. In the determination method according to 18., The one or more rules are stored in a storage means in advance The one or more computers read and obtain the one or more rules from the storage means Determination method 20. In the determination method according to 18., The one or more computers Generate the above one or more rules, Obtain the above one or more generated rules Determination method. 21. In the determination method according to any one of 18. to 20., The above one or more computers output one or more insufficient sub-rules, which are the sub-rules determined that the values of the above one or more indicators are not satisfied Determination method. 22. In the determination method according to 21., The above one or more computers Accept at least one selection among the one or more output insufficient sub-rules, Use the selected insufficient sub-rule as the above condition information Determination method. 23. A computer, An acquisition means for acquiring time series data of a plurality of indicators and condition information indicating conditions related to a target indicator, Using the time series data of the plurality of indicators and the condition information, a feature indicator specifying means for specifying at least one of the plurality of indicators as a feature indicator for the target indicator, and Function as a generation means for obtaining values of one or more of the above feature indicators and generating one or more rules estimated to be necessary to achieve the conditions related to the target indicator using at least the values, The rule includes at least one sub-rule related to the feature indicator Program. 24. In the program according to 23., The feature indicator specifying means Extract one or more that affect the target indicator from the plurality of indicators and the rate of change representing the transition of the plurality of indicators with respect to time, Specify the feature indicator based on at least one of the extracted indicator and the rate of change Program. 25. In the program according to 24., The feature indicator specifying means including a first model for extracting feature quantities, using the first model, extracting one or more that affect the target index among the plurality of indices and the rate of change Program. 26. In the program according to any one of 23. to 25., the generation means includes a second model by ensemble machine learning Program. 27. In the program according to any one of 23. to 26., the one or more generated rules include two or more rules that can be replaced with each other Program. 28. In the program according to any one of 23. to 27., the index is an economic index Program. 29. A computer is made to function as a first acquisition means for acquiring values of one or more indices and condition information indicating conditions for a target index, a second acquisition means for acquiring one or more rules each including one or more sub - rules regarding the index according to the condition information, and a determination means for determining whether the acquired values of the one or more indices satisfy at least any one of the one or more sub - rules Program. 30. In the program according to 29., the one or more rules are pre - held in a storage means, and the second acquisition means reads and acquires the one or more rules from the storage means Program. 31. In the program according to 29., the computer is further made to function as a rule generation means for generating the one or more rules, and the second acquisition means acquires the one or more rules generated by the rule generation means Program. 32. In the program according to any one of 29. to 31., further cause the computer to function as output means for outputting one or more insufficient sub - rules, which are the sub - rules determined by the determination means not to satisfy the values of the one or more indicators. Program. 33. In the program according to 32., the first acquisition means receives a selection of at least any one of the one or more output insufficient sub - rules, and sets the selected insufficient sub - rule as the condition information. Program.

Explanation of Signs

[0090] 10 Rule generation device 20 Determination device 120 Acquisition unit 122 Index storage unit 140 Feature index specifying unit 142 First model 160 Generation unit 162 Second model 220 First acquisition unit 240 Second acquisition unit 242 Rule storage unit 250 Rule generation unit 251 Feature index specifying unit 252 Generation unit 253 First model 254 Second model 260 Determination unit 280 Output unit 1000 Computer

Claims

1. An acquisition means for acquiring time series data of a plurality of indicators and condition information indicating conditions related to a target indicator; A feature indicator specifying means for specifying at least one of the plurality of indicators as a feature indicator for the target indicator by using the time series data of the plurality of indicators and the condition information; A generation means for obtaining values of one or more of the feature indicators and generating one or more rules estimated to be necessary for achieving conditions related to the target indicator by using at least the values; The rule includes at least one sub-rule related to the feature indicator Rule generation device.

2. In the rule generation device according to claim 1, The feature indicator specifying means, Extracts one or more that affect the target indicator among the plurality of indicators and the rate of change representing the transition of the plurality of indicators with respect to time, Specifies the feature indicator based on at least one of the extracted indicator and the rate of change Rule generation device.

3. In the rule generation device according to claim 2, The feature indicator specifying means, Includes a first model for extracting feature quantities, Using the first model, extracts one or more that affect the target indicator among the plurality of indicators and the rate of change Rule generation device.

4. In the rule generation device according to any one of claims 1 to 3, The generation means includes a second model based on ensemble machine learning Rule generation device.

5. In the rule generation device according to any one of claims 1 to 4, The one or more generated rules include two or more rules that are mutually replaceable Rule generation device.

6. In the rule generation device according to any one of claims 1 to 5, The indicator is an economic indicator Rule generation device.

7. One or more computers, Acquire time series data of a plurality of indicators and condition information indicating conditions related to a target indicator, Using the time series data of the plurality of indicators and the condition information, specify at least one of the plurality of indicators as a feature indicator for the target indicator, Obtain values of one or more of the feature indicators and generate one or more rules estimated to be necessary for achieving conditions related to the target indicator by using at least the values, The rule includes at least one sub-rule related to the feature indicator Rule generation method.

8. A computer, An acquisition means for acquiring time-series data of a plurality of indicators and condition information indicating conditions related to a target indicator, A feature indicator specifying means for specifying at least one of the plurality of indicators as a feature indicator for the target indicator by using the time-series data of the plurality of indicators and the condition information, and Function as a generation means for obtaining values of one or more of the feature indicators and generating one or more rules estimated to be necessary for achieving the conditions related to the target indicator by using at least the values, The rule includes at least one sub-rule related to the feature indicator Program.

Images