Information processing device, information processing method, and program

Abstract

To solve the problem on difficulty in creating an appropriate scenario for making predictions for cases.SOLUTION: According to an embodiment of the present disclosure, there is provided an information processing device including: a generation unit configured to generate, based on case data including a plurality of sets of an explanatory variable and an objective variable, a plurality of scenarios each including a pair of a condition of the explanatory variable and a predicted value based on an objective variable of case data corresponding to a condition; and a determination unit configured to determine a combination of scenarios based on an evaluation value calculated according to whether the case data corresponds to the condition of the scenario to be combined and the number of scenarios to be combined.SELECTED DRAWING: Figure 11

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] Predictions based on input data are being made using machine learning models in a variety of fields. For example, in Patent Document 1, a predictive model is used to predict future time series data from multivariate time series data. Predictions using such predictive models can also be used when companies make and execute business plans, in which case scenario planning is useful. Scenario planning involves making future plans by assuming multiple future scenarios in which various uncertain factors that may affect a business change. In this case, a rule-based model consisting of conditions and results can be used as an example of a scenario. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Special Publication No. 2023-550959 Summary of the Invention [Problem to be solved by the invention]

[0004] However, when performing scenario planning, there is a problem in that it is difficult to create a small number of scenarios that can cover all possible future events. In other words, when scenario planning is performed to cover all possible future events with a high probability, the number of scenarios increases so much that humans may not be able to understand the contents of such scenarios. As a result, it is difficult to create appropriate scenarios for predicting cases.

[0005] Therefore, one of the objectives of the present disclosure is to solve the above-mentioned problem that it is difficult to create an appropriate scenario for making predictions about cases. [Means for solving the problem]

[0006] An information processing device according to an embodiment of the present disclosure includes: a generation unit that generates, based on case data including a plurality of pairs of explanatory variables and dependent variables, a plurality of scenarios each including a pair of a condition of the explanatory variables and a predicted value based on the dependent variable of the case data that satisfies the condition; a determination unit that determines a combination of the scenarios based on an evaluation value calculated depending on whether the case data satisfies the condition of the scenarios to be combined and the number of the scenarios to be combined; Equipped with The structure is as follows. Furthermore, an information processing method according to an embodiment of the present disclosure includes: generating a plurality of scenarios, each of which is a pair of a condition of the explanatory variable and a predicted value based on the objective variable of the case data that corresponds to the condition, based on the case data including a plurality of pairs of explanatory variables and objective variables; determining a combination of the scenarios based on an evaluation value calculated depending on whether the case data satisfies the condition of the scenario to be combined and the number of the scenarios to be combined; The structure is as follows. Furthermore, a program according to an embodiment of the present disclosure includes: generating a plurality of scenarios, each of which is a pair of a condition of the explanatory variable and a predicted value based on the objective variable of the case data that corresponds to the condition, based on the case data including a plurality of pairs of explanatory variables and objective variables; determining a combination of the scenarios based on an evaluation value calculated depending on whether the case data satisfies the condition of the scenario to be combined and the number of the scenarios to be combined; Have the computer perform the process, The structure is as follows. [Effects of the Invention]

[0007] With the present disclosure configured as described above, it is possible to create appropriate scenarios for making predictions about cases. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a block diagram illustrating an example of a configuration of an information processing device according to the present disclosure. [Figure 2] FIG. 1 is a diagram illustrating an example of a process performed by an information processing device according to the present disclosure. [Figure 3] FIG. 1 is a diagram illustrating an example of a process performed by an information processing device according to the present disclosure. [Figure 4] FIG. 1 is a diagram illustrating an example of a process performed by an information processing device according to the present disclosure. [Figure 5] FIG. 1 is a diagram illustrating an example of a process performed by an information processing device according to the present disclosure. [Figure 6] FIG. 1 is a diagram illustrating an example of a process performed by an information processing device according to the present disclosure. [Figure 7] 10 is a flowchart illustrating an example of a processing operation of an information processing device according to the present disclosure. [Figure 8] 10 is a flowchart illustrating an example of a processing operation of an information processing device according to the present disclosure. [Figure 9] 10 is a flowchart illustrating an example of a processing operation of an information processing device according to the present disclosure. [Figure 10] FIG. 1 is a block diagram illustrating an example of a hardware configuration of an information processing device according to the present disclosure. [Figure 11] FIG. 1 is a block diagram illustrating an example of a configuration of an information processing device according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0009] First Embodiment A first embodiment of the present disclosure will be described with reference to the drawings, which may be relevant to any embodiment.

[0010] The information processing device 10 in this embodiment creates scenarios that can be applied when a company performs scenario planning to create a business plan. For example, a business plan created by a company may be a plan based on a demand forecast for a product or service in response to environmental changes. For example, a production plan may be created by predicting beverage sales volume in response to environmental changes such as temperature, or an oil refining plan may be created by predicting oil demand in response to changes in crude oil prices (raw material prices). Other examples include creating a production plan by predicting product quality in response to environmental changes such as manufacturing conditions, creating a trading plan by predicting the appropriate volume of transactions in response to changes in financial transaction patterns, or creating a treatment plan by predicting a patient's condition in response to changes in the patient's physical measurements, etc.

[0011] In this embodiment, as an example, it is assumed that a company engaged in the bicycle rental business plans the number of bicycles to be deployed by predicting the number of bicycles to be rented in response to environmental changes such as temperature, and a scenario that can be applied when formulating such a business plan is created. However, the scenarios created in this disclosure may be applicable to any type of business.

[0012] The information processing device 10 is composed of one or more information processing devices each having a calculation device and a storage device. As shown in FIG. 1, the information processing device 10 includes an input unit 11, a simulation unit 12, a scenario generation unit 13, and a combination determination unit 14. The functions of the input unit 11, the simulation unit 12, the scenario generation unit 13, and the combination determination unit 14 can be realized by the calculation device executing a program for realizing each function stored in the storage device. The information processing device 10 also includes a period information storage unit 15, a virtual case storage unit 16, and a scenario storage unit 17. The period information storage unit 15, the virtual case storage unit 16, and the scenario storage unit 17 are each composed of a storage device. The functions and operations of each component will be described below.

[0013] The input unit 11 receives inputs of a "condition period" and a "result period" as period information and stores them in the period information storage unit 15 (step S11 in FIG. 7). The condition period (first period) is a period for determining whether a case satisfies the condition. The result period (second period) is a period for evaluating the outcome of a case that satisfies the condition. The condition period and result period may overlap or may be the same period. FIG. 2 shows an example of input. In this example, "July 2024" is specified as the condition period and "September 2024" is specified as the result period. Distinguishing between the condition period and the result period makes it easier to change future action plans based on observed information. For example, if a scenario is created to predict product sales (demand) for September using the July temperature as a condition, it is possible to determine which scenario applies when observing the July temperature, enabling decision-making such as changing the product production plan (supply) to meet September sales.

[0014] The simulation unit 12 generates multiple virtual cases (case data) that are multivariate time series data using sampling from the probabilistic model, and stores them in the virtual case storage unit 16 (step S12 in FIG. 7). An example of a virtual case generated by the simulation unit 12 is shown in FIG. 3. In this example, multivariate time series data consisting of a set of three explanatory variables, "temperature," "rainfall," and "number of rentals," and a target variable, "number of bicycle rentals," for each day in the time series is generated as a virtual case. "Virtual Case 1" represents the data obtained in the first trial, and "Virtual Case 2" represents the data obtained in the second trial. Although this figure shows only two virtual cases, in practice, many more virtual cases, for example, 1,000 virtual cases, are generated.

[0015] The simulation unit 12 generates virtual cases using a pre-created probabilistic model. The probabilistic model used by the simulation unit 12 may be any model that can generate multivariate time series data probabilistically by machine learning learning data consisting of pre-prepared explanatory variables and target variables. For example, a vector autoregressive model (VAR model) can be used as the probabilistic model. A VAR model of order p can be expressed as the following equation (1).

number

[0016] The above VAR model does not take seasonality into account, but by using an improved VAR model that takes seasonality into account, it is possible to perform a more realistic simulation.

[0017] The parameters of the probability model used by the simulation unit 12 can be adjusted by machine learning based on past data actually observed. In the example of Figure 3, "Number of Rentals" represents the number of bicycles rented. From past data, trends such as the number of rentals decreasing when the temperature is too high or too low or when there is too much rain, and the number of rentals increasing when the temperature is neither too high nor too low and there is little rain, are learned by machine learning in the probability model, making it possible to generate realistic virtual cases.

[0018] The simulation unit 12 generates a hypothetical case so as to include data for at least the condition period and the result period. In the example of FIG. 3, data for three months from July to September is generated. Note that the hypothetical case does not necessarily have to be generated by the simulation unit 12, but may be input as a hypothetical case generated in advance and stored in the hypothetical case storage unit 16. The hypothetical case may also be data measured from an actual case.

[0019] The scenario generation unit 13 (generation unit) aggregates the generated hypothetical cases in units used for scenario generation. This process is optional and may be omitted. For example, the scenario generation unit 13 may aggregate the hypothetical cases generated daily as described above into monthly units. This makes it possible to precisely simulate the hypothetical cases described above in daily units, while explaining the scenarios shown to humans in more understandable monthly units. Note that when the scenario generation unit 13 aggregates the hypothetical cases, it may perform special aggregations or conversions other than averaging or summing to improve interpretability.

[0020] FIG. 4 shows an example of a hypothetical case after being compiled by the scenario generation unit 13. In this example, the hypothetical case generated by the simulation unit 12 on a daily basis is compiled on a monthly basis. At this time, the scenario generation unit 13 converts the temperature into a monthly average temperature and compiles it, specifically, by subtracting the average temperature for a normal year from the monthly average temperature. This makes it easy to see whether the temperature is higher or lower than normal. In addition, the scenario generation unit 13 counts the number of days with rainfall greater than 0, and compiles and converts the rainfall into the number of rainy days per month. Note that the scenario generation unit 13 may compile the hypothetical case using any method.

[0021] The scenario generation unit 13 generates multiple scenarios consisting of pairs of "conditions" in the condition period and "predicted values" calculated from the values ​​that virtual cases that meet those conditions take in the result period, and stores them in the scenario memory unit 17 (step S14 in Figure 7).

[0022] When the scenario generation unit 13 generates a scenario, it distinguishes between explanatory variables and objective variables of the hypothetical case. Explanatory variables are variables used to generate conditions, and objective variables are variables used to calculate predictions. Here, as shown in FIG. 4, the "average monthly temperature" and "number of rainy days" calculated from the hypothetical cases are used as explanatory variables, and the "number of rentals" is used as the objective variable. However, when the scenario generation unit 13 generates a scenario, which variables are used as explanatory variables and which as objective variables may be fixed, or may be externally specified by the user.

[0023] Figure 5 shows an example of a scenario generated by the scenario generation unit 13. In this example, 100 scenarios are generated. The "Candidate Scenario ID" column is a serial number assigned to each scenario. The "Condition" column indicates the condition in the condition period for determining whether a certain case applies to that scenario. "Occurrence Probability" indicates the proportion of virtual cases generated that apply the condition in the condition period. "Average Number of Rentals," "Number of Rentals 1Q," and "Number of Rentals 3Q" are predicted values ​​for the objective variable. The predicted values ​​are the aggregate values ​​of the objective variable in the result period for virtual cases that apply the condition in the condition period. 1Q and 3Q are the first and third quartiles, respectively.

[0024] As a specific example, we will explain the case where scenario z is created from the hypothetical case in Figure 4. For example, in "hypothetical case 1," if the explanatory variables "monthly average temperature (-2.5)" and "number of rainy days (8)" for the condition period "July" meet the "conditions" of "scenario z," then the "number of rentals (1600)" for the result period "September" in "hypothetical case 1" is used to calculate the "prediction value" of "scenario z."

[0025] 8 shows a flowchart of scenario generation by the scenario generation unit 13. Here, the number of scenarios to be generated is n, and the number of inequalities included in one condition is m.

[0026] First, the scenario generation unit 13 starts a loop to generate n scenarios (step S21 in FIG. 8). Then, the scenario generation unit 13 starts a loop to generate m inequalities (step S22 in FIG. 8).

[0027] Next, the scenario generation unit 13 generates an inequality by randomly selecting an explanatory variable, an inequality sign, and a threshold (step S23 in FIG. 8). For example, one explanatory variable is randomly selected from "monthly average temperature" and "number of rainy days." An inequality sign is also randomly selected from "<=" and ">". A threshold is then randomly selected. The threshold may be uniformly randomly selected, for example, from between the maximum and minimum values ​​of the explanatory variables included in the hypothetical case. This allows the generation of an inequality such as "monthly average temperature > + 3.5". The scenario generation unit 13 then ends the inequality generation loop (step S24 in FIG. 8). The end of the loop results in m inequalities. While the explanatory variables, inequality signs, and thresholds are randomly selected in the above example, inequalities may also be generated by selecting them according to a predetermined rule.

[0028] Next, the scenario generation unit 13 obtains "conditions" by combining the generated m inequalities with "AND" (step S25 in FIG. 8). For example, a "condition" such as "average monthly temperature > + 3.5 AND number of rainy days <= 5" can be obtained. If combining all inequalities with AND results in no applicable hypothetical cases, some of the inequalities may be excluded.

[0029] Next, the scenario generation unit 13 calculates the "occurrence probability" by counting the number of virtual cases that meet the "condition" during the condition period (step S26 in FIG. 8). For example, if 350 virtual cases out of 1000 meet the condition, the occurrence probability is 35%.

[0030] Next, the scenario generation unit 13 calculates a "predicted value" by aggregating the values ​​that the objective variable takes in the result period for the hypothetical cases that meet the "condition" in the condition period (step S27 in FIG. 8). For example, the average value or quartile of the objective variable in the result period for all hypothetical cases that meet the "condition" can be used as the predicted value.

[0031] The scenario generation unit 13 ends the loop for generating scenarios (step S28 in FIG. 8). When the loop ends, n scenarios are obtained. Then, the scenario generation unit 13 outputs the n generated scenarios to the combination determination unit 14 (step S29 in FIG. 8). As an example, the scenario generation unit 13 generates 100 scenarios. However, the number of scenarios to be generated is not limited to the number mentioned above.

[0032] The combination determination unit 14 (determination unit) determines a combination of multiple scenarios from the scenarios generated as described above (step S15 in FIG. 7). At this time, the combination determination unit 14 determines the combination of scenarios based on an evaluation value calculated depending on whether or not the hypothetical cases meet the conditions of the scenarios to be combined, and the number of scenarios to be combined. Specifically, the combination determination unit 14 calculates a value corresponding to the proportion of hypothetical cases that meet the conditions of the scenarios as the above-mentioned evaluation value, determines a combination of scenarios such that this proportion is high and the number of scenarios included in the combination is small, and outputs the combination as a scenario set.

[0033] 6 shows an example of a scenario set output by the combination determination unit 14. In this example, the combination determination unit 14 selects only some of the 100 scenarios generated by the scenario generation unit 13, such as candidate scenario IDs = 3, 18, ..., 73, and outputs a scenario set consisting of combinations of these scenarios.

[0034] The determination of a combination of scenarios by the combination determination unit 14 can be formulated as a combinatorial optimization problem. Below, two examples of objective functions that can be used as objective functions for combinatorial optimization problems are given.

[0035] A first example of the objective function will be explained. Let X be the set of virtual cases, S0 be the set of scenarios generated by the scenario generation unit 13, and S be the set of scenarios determined by the combination determination unit 14. In this case, the first example of the objective function can be written as in the following formula 2.

number

[0036] Here is a second example of an objective function for optimization. This second example differs in that it also takes into account prediction error. As a preliminary step, let us define the set of scenarios Sub(x,S) that are included in the scenario set S and that correspond to the hypothetical case x, as shown in Equation 3 below.

number

number

[0037] Using the above definitions, a second example of the objective function is defined as shown in the following equation 5.

number

[0038] The second example of the objective function is the same as the first example in that the fewer the number of scenarios included in the combination and the higher the proportion of hypothetical cases that meet the conditions of the scenarios included in the combination, the higher the objective function value. However, the second example differs in that it also takes into account prediction error. This makes it more likely that when selecting a combination of scenarios, not only will hypothetical cases meet the conditions, but scenarios whose predictions are closer will be selected. This increases the likelihood that the combination will include scenarios that closely predict future events.

[0039] The combination determination unit 14 finds a scenario set S that maximizes the objective function. In the simplest case, a subset S of S0 is randomly selected, the objective function is calculated, and this process is repeated multiple times to output the set S with the highest objective function.

[0040] Here, Fig. 9 shows an example of a flowchart of the combination determination process. The combination determination unit 14 repeats t times the process of generating a subset S of scenarios by adding a scenario included in S0 with a probability p (steps S31 to S37 in Fig. 9). At this time, the combination determination unit 14 evaluates the value of the objective function of the subset S of scenarios (step S36 in Fig. 9). Then, the combination determination unit 14 outputs the subset S of scenarios with the highest value of the objective function (step S38 in Fig. 9). At this time, t and p are pre-set hyperparameters.

[0041] The combination determination unit 14 may maximize the objective function using an optimization method different from the above-described method. For example, the objective function may be formulated as a mathematical optimization problem such as an integer programming problem or a maximum satisfiability problem (Max-SAT), and a mathematical optimization solver may be used to determine a combination that maximizes the objective function.

[0042] The number of scenarios included in the combination does not have to be explicitly included in the objective function. That is, Equation 2 and Equation 5 do not have to include the term -λ|S|. In this case, instead of being explicitly included in the objective function, the number of scenarios included in the combination may be given as a constraint when searching for a solution. For example, if the number of scenarios included in the combination is fixed at 10, the combination determination unit 14 may output the combination that has the highest objective function value among candidate combinations that result in 10 scenarios. Candidate combinations that result in 10 scenarios can be obtained, for example, by randomly sampling 10 scenarios from S0 without replacement. The number of scenarios included in the combination set as a constraint is not limited to the fixed value described above, and may be an upper limit or a value within a predetermined range. In this case, the combination determination unit 14 may determine a combination of scenarios whose number does not exceed the upper limit or range.

[0043] <Second embodiment> Next, a second embodiment of the present disclosure will be described with reference to the drawings. In this embodiment, an outline of the information processing device and the like described in the above-mentioned embodiment is shown. Note that the drawings may be relevant to any of the embodiments.

[0044] First, a description will be given of the hardware configuration of the information processing device 100 in the present disclosure. The information processing device 100 is configured as a general information processing device, and is equipped with the following hardware configuration, as an example, as shown in FIG. ·CPU(Central Processing Unit)101(Arithmetic unit) ROM (Read Only Memory) 102 (storage device) RAM (Random Access Memory) 103 (storage device) ·Programs 104 loaded into RAM 103 A storage device 105 for storing a group of programs 104 A drive device 106 that reads and writes from a storage medium 110 external to the information processing device A communication interface 107 that connects to a communication network 111 outside the information processing device Input / output interface 108 for inputting and outputting data Bus 109 connecting each component

[0045] 10 shows an example of the hardware configuration of the information processing device 100, and the hardware configuration of the information processing device is not limited to the above-described case. For example, the information processing device may be configured with a part of the above-described configuration, such as not including the drive device 106. Furthermore, the information processing device may use a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), an MPU (Micro Processing Unit), an FPU (Floating point number Processing Unit), a PPU (Physics Processing Unit), a TPU (Tensor Processing Unit), a quantum processor, a microcontroller, or a combination thereof, instead of the above-described CPU.

[0046] The information processing device 100 can be equipped with the generation unit 121 and the determination unit 122 shown in Fig. 11 by having the CPU 101 acquire and execute the program group 104. The program group 104 is stored in advance in, for example, the storage device 105 or the ROM 102, and is loaded into the RAM 103 and executed by the CPU 101 as needed. The program group 104 may be supplied to the CPU 101 via the communication network 111, or may be stored in advance in the storage medium 110, and the drive device 106 may read out the programs and supply them to the CPU 101. However, the generation unit 121 and the determination unit 122 described above may be constructed using dedicated electronic circuits for realizing such means.

[0047] The generation unit 121 generates, based on case data including a plurality of pairs of explanatory variables and objective variables, a plurality of scenarios each consisting of a pair of a condition of the explanatory variables and a predicted value based on the objective variable of the case data that satisfies the condition. The determination unit 122 determines the combination of scenarios based on an evaluation value calculated depending on whether the case data satisfies the condition of the scenario to be combined, and the number of scenarios to be combined.

[0048] By configuring the present disclosure as described above, it is possible to cover a large amount of case data, determine a small number of scenario combinations, and create appropriate scenarios for making predictions about cases.

[0049] At least one of the functions of the generation unit 121 and the determination unit 122 described above may be executed by an information processing device installed and connected anywhere on the network, that is, may be executed by so-called cloud computing.

[0050] The above-described program can be stored and supplied to a computer using various types of non-transitory computer-readable media. Non-transitory computer-readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)). The program can also be supplied to a computer by various types of transitory computer-readable media. Examples of transitory computer-readable media include electrical signals, optical signals, and electromagnetic waves. The transitory computer-readable media can supply the program to a computer via a wired communication path such as an electric wire or optical fiber, or via a wireless communication path.

[0051] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each of the above-described embodiments can be combined with other embodiments as appropriate.

[0052] <Additional Notes> Some or all of the above embodiments may be described as follows: The following provides an overview of the configurations of an information processing device, an information processing method, and a program according to the present disclosure. However, the present disclosure is not limited to the configurations described in the following supplementary notes. Note that the configurations described in Supplements 2 to 8, which are dependent on Supplementary Note 1 below, and some or all of the functions of the configurations, may also be dependent on other Supplements 9 and 16 in the same dependent relationship as Supplements 2 to 8. Furthermore, not limited to Supplements 1, 9, and 16, but also within the scope of the above-described embodiments, similar hardware, software, various recording means for recording software, or systems may be similarly made to be dependent on the configurations described as Supplements and some or all of the functions of the configurations. (Appendix 1) a generation unit that generates, based on case data including a plurality of pairs of explanatory variables and dependent variables, a plurality of scenarios each including a pair of a condition of the explanatory variables and a predicted value based on the dependent variable of the case data that satisfies the condition; a determination unit that determines a combination of the scenarios based on an evaluation value calculated depending on whether the case data satisfies the condition of the scenarios to be combined and the number of the scenarios to be combined; An information processing device comprising: (Appendix 2) 10. The information processing device according to claim 1, the determination unit calculates, as the evaluation value, a proportion of the case data that meets the conditions of the scenarios to be combined, and determines the combination of scenarios based on the proportion and the number of the scenarios to be combined. Information processing device. (Appendix 3) 10. The information processing device according to claim 2, the determination unit determines the combination of scenarios such that the ratio of the case data that meets the conditions of the scenarios to be combined is high and the number of scenarios to be combined is small. Information processing device. (Appendix 4) 10. The information processing device according to claim 1, the determination unit calculates, as the evaluation value, an error between a value of the objective variable of predetermined case data and a comparison value based on the objective variable of the case data, the comparison value being calculated depending on whether the predetermined case data satisfies the condition of the scenario to be combined, and determines the combination of scenarios based on the error and the number of scenarios to be combined. Information processing device. (Appendix 5) 5. The information processing device according to claim 4, the determination unit calculates the error for the predetermined case data that does not satisfy the condition of the scenario to be combined so that the error is larger than when the condition is satisfied, and determines the combination of scenarios so that the error is small and the number of scenarios is small. Information processing device. (Appendix 6) 5. The information processing device according to claim 4, the determination unit calculates the error by setting, as the comparison value, the predicted value of the scenario that satisfies the condition of the scenario to be combined, for the predetermined case data that does not satisfy the condition of the scenario to be combined, and sets, as the comparison value, values ​​based on the objective variables of all of the case data, and determines the combination of scenarios such that the error is small and the number of scenarios is small. Information processing device. (Appendix 7) 10. The information processing device according to claim 1, the generation unit generates the scenario including a pair of the condition of the explanatory variable in a predetermined first period of the case data that is time-series data and the predicted value based on the objective variable in a predetermined second period of the case data that corresponds to the condition; Information processing device. (Appendix 8) 8. The information processing device according to claim 7, The second period is a period that is later in time series than the first period. Information processing device. (Appendix 9) generating a plurality of scenarios, each of which is a pair of a condition of the explanatory variable and a predicted value based on the objective variable of the case data that corresponds to the condition, based on the case data including a plurality of pairs of explanatory variables and objective variables; determining a combination of the scenarios based on an evaluation value calculated depending on whether the case data satisfies the condition of the scenario to be combined and the number of the scenarios to be combined; Information processing methods. (Appendix 10) 10. The information processing method according to claim 9, calculating, as the evaluation value, a proportion of the case data that meets the conditions of the scenarios to be combined, and determining the combination of scenarios based on the proportion and the number of the scenarios to be combined; Information processing methods. (Appendix 11) 11. The information processing method according to claim 10, further comprising: determining a combination of the scenarios so that the ratio of the case data that meets the conditions of the scenarios to be combined is high and the number of the scenarios to be combined is small; Information processing methods. (Appendix 12) 10. The information processing method according to claim 9, calculating, as the evaluation value, an error between the value of the objective variable of predetermined case data and a comparison value based on the objective variable of the case data, the comparison value being calculated depending on whether or not the predetermined case data satisfies the condition of the scenario to be combined, and determining the combination of scenarios based on the error and the number of scenarios to be combined; Information processing methods. (Appendix 13) 13. The information processing method according to claim 12, further comprising: For the predetermined case data that does not meet the conditions of the scenarios to be combined, the error is calculated so that it is a larger value than when the conditions meet, and the combination of scenarios is determined so that the error is small and the number of scenarios is small. Information processing methods. (Appendix 14) 13. The information processing method according to claim 12, further comprising: For the predetermined case data that meets the conditions of the scenarios to be combined, the predicted value of the corresponding scenario is used as the comparison value, and for the predetermined case data that does not meet the conditions of the scenarios to be combined, values ​​based on the objective variables of all the case data are used as the comparison value, and the error is calculated, and a combination of scenarios is determined so that the error is small and the number of scenarios is small. Information processing methods. (Appendix 15) 10. The information processing method according to claim 9, generating the scenario consisting of a pair of the condition of the explanatory variable in a first period set in advance of the case data which is time-series data and the predicted value based on the objective variable in a second period set in advance of the case data which corresponds to the condition; Information processing methods. (Appendix 16) generating a plurality of scenarios, each of which is a pair of a condition of the explanatory variable and a predicted value based on the objective variable of the case data that corresponds to the condition, based on the case data including a plurality of pairs of explanatory variables and objective variables; determining a combination of the scenarios based on an evaluation value calculated depending on whether the case data satisfies the condition of the scenario to be combined and the number of the scenarios to be combined; A program that causes a computer to perform a process. [Explanation of symbols]

[0053] 10. Information processing equipment 11 Input section 12 Simulation Section 13 Scenario Generation Unit 14 Combination determination unit 15 Period information storage unit 16 Virtual Case Memory 17 Scenario Memory Section 100 Information processing device 101 CPU 102 ROM 103 RAM 104 Programs 105 Storage device 106 Drive device 107 Communication Interface 108 Input / Output Interface 109 Bus 110 Storage medium 111 Communication Network 121 Generation part 122 Decision Section

Claims

1. a generation unit that generates, based on case data including a plurality of pairs of explanatory variables and dependent variables, a plurality of scenarios each including a pair of a condition of the explanatory variables and a predicted value based on the dependent variable of the case data that satisfies the condition; a determination unit that determines a combination of the scenarios based on an evaluation value calculated depending on whether the case data satisfies the condition of the scenarios to be combined and the number of the scenarios to be combined; An information processing device comprising:

2. 2. The information processing device according to claim 1, the determination unit calculates, as the evaluation value, a proportion of the case data that meets the conditions of the scenarios to be combined, and determines the combination of scenarios based on the proportion and the number of the scenarios to be combined. Information processing device.

3. 3. The information processing device according to claim 2, the determination unit determines the combination of scenarios such that the ratio of the case data that meets the conditions of the scenarios to be combined is high and the number of scenarios to be combined is small. Information processing device.

4. 2. The information processing device according to claim 1, the determination unit calculates, as the evaluation value, an error between a value of the objective variable of predetermined case data and a comparison value based on the objective variable of the case data, the comparison value being calculated depending on whether the predetermined case data satisfies the condition of the scenario to be combined, and determines the combination of scenarios based on the error and the number of scenarios to be combined. Information processing device.

5. 5. The information processing device according to claim 4, the determination unit calculates the error for the predetermined case data that does not satisfy the condition of the scenario to be combined so that the error is larger than when the condition is satisfied, and determines the combination of scenarios so that the error is small and the number of scenarios is small. Information processing device.

6. 5. The information processing device according to claim 4, the determination unit calculates the error by setting, as the comparison value, the predicted value of the scenario that satisfies the condition of the scenario to be combined, for the predetermined case data that does not satisfy the condition of the scenario to be combined, and sets, as the comparison value, values ​​based on the objective variables of all of the case data, and determines the combination of scenarios such that the error is small and the number of scenarios is small. Information processing device.

7. 2. The information processing device according to claim 1, the generation unit generates the scenario including a pair of the condition of the explanatory variable in a first period set in advance of the case data that is time-series data and the predicted value based on the objective variable in a second period set in advance of the case data that corresponds to the condition; Information processing device.

8. 8. The information processing device according to claim 7, The second period is a period that is later in time series than the first period. Information processing device.

9. generating a plurality of scenarios, each of which is a pair of a condition of the explanatory variable and a predicted value based on the objective variable of the case data that corresponds to the condition, based on the case data including a plurality of pairs of explanatory variables and objective variables; determining a combination of the scenarios based on an evaluation value calculated depending on whether the case data satisfies the condition of the scenario to be combined and the number of the scenarios to be combined; Information processing methods.

10. generating a plurality of scenarios, each of which is a pair of a condition of the explanatory variable and a predicted value based on the objective variable of the case data that corresponds to the condition, based on the case data including a plurality of pairs of explanatory variables and objective variables; determining a combination of the scenarios based on an evaluation value calculated depending on whether the case data satisfies the condition of the scenario to be combined and the number of the scenarios to be combined; A program that causes a computer to perform a process.

Images