Computer systems and methods for supporting the selection of policies

Abstract

To support the selection of measures that promote behavioral change within groups working in the field, in order to achieve predetermined objectives. [Solution] The computer system receives data containing the values ​​of multiple parameters representing the attributes of the site and the group as input, stores information of a model that outputs outcome indicators, generates initial data containing the initial values ​​of multiple parameters, repeatedly executes a process to generate analysis data by changing the initial values ​​of the parameters in the initial data, calculates the difference between the outcome indicator obtained by inputting the analysis data into the model and the outcome indicator obtained by inputting the initial data into the model for each analysis data, repeatedly executes a process to calculate an evaluation index that represents the magnitude of the influence of the parameter values ​​changed to generate the analysis data on the outcome indicator based on this difference, and selects measures based on the evaluation index.

Description

Technical Field

[0001] The present invention relates to a technology for assisting in selecting measures for promoting behavioral changes in a group.

Background Art

[0002] In order to achieve a predetermined purpose in a group operating at a site, measures for promoting behavioral changes in the group are implemented. By using a mathematical model that calculates an outcome index representing the degree of achievement of the purpose, with parameters representing the attributes of the site and the group as variables, it is possible to search for combinations of parameter values that maximize or minimize the outcome index. As a technology for optimizing combinations of parameter values, for example, the technology described in Patent Document 1 is known.

[0003] Patent Document 1 describes, "In a method of inputting data such as water quality, flow rate, temperature, etc. of a sewage treatment plant, parameters and state variables constituting a biochemical reaction model, simulating the ongoing biochemical reaction, comparing the measured value of water quality with the calculation result, and repeating the simulation by changing the parameters until the difference becomes sufficiently small to optimize the parameter values, and performing a final simulation operation based on this, in order to preferentially change parameters that have a large impact on water quality, a sensitivity analysis of the parameters is performed, and by evaluating the results of this sensitivity analysis, parameters to be preferentially changed are selected, and the selected parameter values are changed and the simulation is repeated to optimize the parameter values."

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] The combinations of parameters and values ​​to be changed by each measure differ for each measure. The technology described in Patent Document 1 is a technology that searches for combinations of parameter values ​​that maximize or minimize outcome indicators, so it is not guaranteed that the measure can be implemented using that combination. Therefore, it is difficult to select a measure even using the technology described in Patent Document 1.

[0006] The present invention aims to provide a system and method that supports the selection of policies. [Means for solving the problem]

[0007] A representative example of the invention disclosed in this application is as follows: A computer system that supports the selection of measures to promote a change in the behavior of a group working in a field in order to achieve a predetermined objective, comprising a computing device and a storage device connected to the computing device, wherein the storage device accepts data including values ​​of a plurality of parameters representing the attributes of the field and the group as input, and stores information of a model that outputs an outcome index representing the degree to which the objective is achieved, the computing device generates initial data including initial values ​​of the plurality of parameters set by the user, selects one of the parameters, repeatedly executes a process to generate first analysis data by changing the initial value of the selected parameter in the initial data, calculates the difference between the outcome index obtained by inputting the first analysis data into the model and the outcome index obtained by inputting the initial data into the model for each of the plurality of first analysis data, repeatedly executes a process to calculate a first evaluation index representing the magnitude of the influence of the parameter value changed to generate the first analysis data on the outcome index based on the difference, and selects the measures to verify the effect based on the first evaluation index. [Effects of the Invention]

[0008] According to the present invention, it is possible to support the selection of measures. Problems, configurations, and effects other than those described above will be clarified by the following description of the embodiments. [Brief explanation of the drawing]

[0009] [Figure 1] This is a flowchart illustrating an example of the processing performed by the computer in Example 1. [Figure 2] This figure shows an example of the computer configuration in Example 1. [Figure 3] This figure shows an example of a setting range DB for Example 1. [Figure 4] This figure shows an example of the policy database for Example 1. [Figure 5] This figure shows an example of the data stored in the parameter DB of Example 1. [Figure 6] This figure shows an example of the screen displayed by the computer in Example 1. [Figure 7] This figure shows an example of the impact analysis dataset from Example 1. [Figure 8] This figure shows an example of the impact analysis results database for Example 1. [Figure 9] This figure shows an example of the screen displayed by the computer in Example 1. [Figure 10] This figure shows an example of a dataset for analyzing the effectiveness of the measures taken in Example 1. [Figure 11] This figure shows an example of the screen displayed by the computer in Example 1. [Figure 12] This figure shows an example of the screen displayed by the computer in Example 1. [Figure 13] This figure shows an example of the computer configuration in Example 2. [Figure 14] This figure shows an example of the condition database for Example 2. [Figure 15] This figure shows an example of a dataset for analyzing the effectiveness of the measures taken in Example 2. [Modes for carrying out the invention]

[0010] Hereinafter, embodiments of the present invention will be described with reference to the drawings. However, the present invention is not to be construed as being limited to the description of the embodiments shown below. It will be readily understood by those skilled in the art that the specific configuration can be changed without departing from the spirit or gist of the present invention.

[0011] In the configuration of the invention described below, the same or similar configurations or functions are denoted by the same reference numerals, and redundant descriptions are omitted.

[0012] The notations such as "first", "second", "third", etc. in this specification and the like are attached to identify components, and do not necessarily limit the number or order.

[0013] In the drawings and the like, the positions, sizes, shapes, and ranges of each configuration shown may not represent the actual positions, sizes, shapes, and ranges in order to facilitate understanding of the invention. Therefore, in the present invention, it is not limited to the positions, sizes, shapes, and ranges disclosed in the drawings and the like.

Embodiment

[0014] First, the hardware configuration and software configuration of a computer for realizing the present invention will be described. FIG. 2 is a diagram showing an example of the configuration of the computer of Embodiment 1.

[0015] The computer 200 has, as a hardware configuration, an arithmetic unit 201, a memory 202, a storage device 203, a communication device 204, an input device 205, and an output device 206. Each hardware element is connected via a bus.

[0016] The arithmetic unit 201 is a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), etc., and executes a program stored in the memory 202. By the arithmetic unit 201 executing processing according to the program, it operates as a functional unit (module) that realizes a specific function. In the following description, when the processing is described with the program as the subject, it indicates that the arithmetic unit 201 is executing the program.

[0017] Memory 202 is a DRAM (Dynamic Random Access Memory) or similar, and stores the program executed by the arithmetic unit 201 and the information used by the program. Memory 202 is also used as a work area.

[0018] The storage device 203 is a large-capacity storage device such as an HDD (Hard Disk Drive), SSD (Solid State Drive), and flash memory. The storage device 203 stores the parameter setting program 211, the impact analysis program 212, and the policy effect analysis program 213. The storage device 203 also stores the setting guide DB 221, the setting range DB 222, the policy DB 223, the parameter DB 224, the impact analysis dataset 225, the policy effect analysis dataset 226, the prediction model DB 227, the impact analysis results DB 228, and the policy effect analysis results DB 229.

[0019] The arithmetic unit 201 reads the program and data stored in the database from the storage device 203 and loads them into the memory 202.

[0020] Communication device 204 is a LAN adapter, etc., and connects to a network such as a LAN (Local Area Network). Input device 205 is a keyboard, mouse, touch panel, etc. Output device 206 is a display, printer, etc.

[0021] Furthermore, the functions implemented by the program may be implemented using a virtual computer, a computer system, or dedicated circuits such as FPGAs (Field-Programmable Gate Arrays) and ASICs (Application Specific Integrated Circuits).

[0022] Computer 200 assists in selecting measures to promote behavioral change within groups working in the field, in order to achieve predetermined objectives.

[0023] A group at a site is represented using parameter values ​​that indicate the attributes of the site and the group. A policy is represented as an operation that transforms a certain parameter into a specific value. Various policies can be set by changing the combination of parameters and values. However, depending on the characteristics of the site or group, it may not be possible to change the parameter to a predetermined value, potentially preventing the implementation of the policy.

[0024] Next, we will describe the database maintained by computer 200.

[0025] The Configuration Guide DB221 is a database for managing the configuration guides for the values ​​of each parameter.

[0026] The setting range DB222 is a database for managing the setting range of each parameter's value. Figure 3 shows an example of the setting range DB222 in Example 1.

[0027] The setting range DB222 shown in Figure 3 is a matrix data structure where rows represent range IDs and columns represent the parameter groups for the field and the parameter groups for the group. Each cell stores a value corresponding to the parameter's range ID. In Figure 3, there are 70 field parameters and 30 group parameters. Note that the parameter types are just examples and are not limited to these.

[0028] In this example, the values ​​are set to take up to five values. Cells for parameters with fewer than five values ​​are left blank. For example, the field parameter "f1" can take three values: "a", "b", and "c". Also, the group parameter "g1" can take five values: "18", "25", "35", "45", and "60".

[0029] In this embodiment, the parameters are assumed to take discrete values, but the range of the parameters may also be continuous.

[0030] Policy DB223 is a database for managing policies. Figure 4 shows an example of Policy DB223 in Example 1.

[0031] The policy DB223 shown in Figure 4 is a table-format data structure that stores records containing policy ID 401, name 402, and setting details 403. There is one record for each policy.

[0032] Policy ID 401 is a field that stores the policy ID. Name 402 is a field that stores the policy name. Setting Details 403 is a field that stores the policy details, that is, the combination of parameters and values ​​that will be changed by the implementation of the policy.

[0033] Parameter DB224 is a database for managing the parameter values ​​of the target group. Figure 5 shows an example of the data stored in Parameter DB224 in Example 1. Parameter DB224 stores, for example, data 500 as shown in Figure 5. Data 500 includes a data ID and the values ​​of the field parameter group and the group parameter group. The data 500 shown in Figure 5 is user-initialized data, with the data ID set to "base". In the following description, user-initialized data will be referred to as initial data.

[0034] The prediction model DB227 is a database for managing prediction models. A prediction model is a model that accepts values ​​for each parameter as input and outputs an outcome indicator that represents the degree to which the objective has been achieved. A prediction model is, for example, a machine learning model such as a neural network. An outcome indicator is, for example, the cooperation rate of the entire group. In this embodiment, a larger outcome indicator indicates a greater degree of goal achievement.

[0035] The Impact Analysis Dataset 225 is used to analyze the magnitude of change (impact) in outcome indicators when the parameters of the initial data are changed from their initial values ​​to specific values. Details of the Impact Analysis Dataset 225 are explained using Figure 7.

[0036] The Policy Effectiveness Analysis Dataset 226 is a dataset used to analyze the effectiveness of policies. Details of the Policy Effectiveness Analysis Dataset 226 are explained using Figure 10. The effectiveness of a policy is the magnitude of the change in an outcome indicator when the value of a parameter in the initial data is changed based on the content of the policy.

[0037] The Impact Analysis Results DB228 is a database for managing the results of impact analyses. Details of the Impact Analysis Results DB228 are explained using Figure 8.

[0038] The Policy Effectiveness Analysis Results DB229 is a database for managing the results of policy effectiveness analysis. Details of the Policy Effectiveness Analysis Results DB229 are explained using Figure D.

[0039] Next, we will describe the processes performed by the computer 200. Figure 1 is a flowchart illustrating an example of the processes performed by the computer 200 in Example 1. Figures 6, 9, 11, and 12 are examples of screens displayed by the computer 200 in Example 1. Figure 7 is an example of the impact analysis dataset in Example 1. Figure 8 is an example of the impact analysis results DB228 in Example 1. Figure 10 is an example of the policy effect analysis dataset 226 in Example 1.

[0040] When computer 200 receives a request from the user, it starts processing (step S101).

[0041] The computer 200 displays a screen 600 as shown in Figure 6 and waits for user input. The screen 600 includes buttons 601, 602, 603, 604, a selection field 605, and setting areas 606, 607.

[0042] Button 601 is used to set the initial values ​​of each parameter. When the user operates button 601, the computer 200 displays the parameters in setting areas 606 and 607 and enables the operation of setting areas 606 and 607.

[0043] The setting area 606 is for setting the initial values ​​of field parameters. Multiple input fields for entering the initial values ​​of parameters are displayed in the setting area 606. When the user selects any of the input fields, a setting guide for that parameter's value is displayed in the display area 611.

[0044] The setting area 607 is for setting the initial values ​​of the group's parameters. Multiple input fields for entering the initial values ​​of the parameters are displayed in the setting area 607. When the user selects any of the input fields, a guide for setting the value of that parameter is displayed in the display area 611.

[0045] Button 602 is an operation button to instruct the execution of an impact analysis. Button 603 is an operation button to instruct the execution of a policy effect analysis. Button 604 is a button to change the content of a policy. Selection field 605 is a field for selecting the policy whose content will be changed.

[0046] The user presses button 601, enters information into setting areas 606 and 607, and then presses button 602.

[0047] When button 602 is operated, the parameter setting program 211 generates initial data and stores it in the parameter DB 224 (step S102), and the impact analysis program 212 performs the impact analysis (step S103). Specifically, the following processes are performed.

[0048] (S103-1) The impact analysis program 212 selects a parameter, changes the value of the selected parameter within the range, and sets the initial data values ​​for the other parameters to generate first analysis data, which is then registered in the impact analysis dataset 225. Figure 7 shows an example of the impact analysis dataset 225. The bold border indicates the changed value. f1sn (where n is an integer from 1 to 5) is the first analysis data generated by changing the value of parameter f1. As shown in Figure 3, since parameter f1 has three values, three first analysis data sets are generated.

[0049] (S103-2) The impact analysis program 212 determines whether or not it has generated first analysis data for all parameters. If it has not generated first analysis data for all parameters, the impact analysis program 212 returns to S103-1.

[0050] (S103-3) Once the first analysis data has been generated for all parameters, the impact analysis program 212 calculates the outcome indicator (base indicator) by inputting the initial data into the prediction model.

[0051] (S103-4) The impact analysis program 212 selects one parameter (target parameter).

[0052] (S103-5) The impact analysis program 212 selects the first analysis data generated by changing the value of the target parameter within a specified range.

[0053] (S103-6) The impact analysis program 212 calculates an outcome index by inputting the selected first analysis data into the prediction model. The impact analysis program 212 calculates the difference between the outcome index and the base index. In this embodiment, this difference is used as the first evaluation index, which represents the magnitude of the impact on the outcome index when the initial value of the target parameter of the initial data is changed to the value of the target parameter of the first analysis data. Alternatively, the first evaluation index may be calculated using a formula that uses the difference as a parameter. The impact analysis program 212 registers the ID of the first analysis data, the value of the target parameter of the first analysis data, and the first evaluation index as analysis results in the impact analysis results DB 228.

[0054] Figure 8 shows an example of the impact analysis results DB228. For example, if the first analysis data with data ID "f1s1" is selected, the calculated outcome indicator will be stored in the cell where the range ID is "s1" and the parameter is "f1". Cells where there is no first analysis data corresponding to the range ID will be left blank.

[0055] (S103-7) The impact analysis program 212 determines whether it has processed all of the first analysis data for the selected parameters. If it has not processed all of the first analysis data for the selected parameters, the impact analysis program 212 returns to S103-5.

[0056] (S103-8) If all the first analysis data for the selected parameters has been processed, the impact analysis program 212 determines whether all parameters have been processed. If not all parameters have been processed, the impact analysis program 212 returns to S103-4.

[0057] (S103-9) Once all parameters have been processed, the impact analysis program 212 presents the analysis results to the user and terminates the impact analysis. For example, the impact analysis program 212 transitions screen 600 to screen 900 as shown in Figure 9. Screen 900 includes display fields 901, 902, 903 and a button 904.

[0058] Display field 901 displays the analysis results sorted in descending order of the first evaluation metric. Alternatively, the analysis results may be displayed sorted based on the absolute value of the first evaluation metric. When the user selects an analysis result in display field 901, the changes to the parameters relative to the initial data are displayed in display field 902, and a setting guide for the changed parameters is displayed in display field 903. Button 904 is a button to transition to screen 600.

[0059] The user presses button 904 to transition to screen 600, and then operates button 603.

[0060] If button 603 is pressed, the policy effectiveness analysis program 213 selects the policy to be examined (step S104).

[0061] Specifically, the policy effectiveness analysis program 213 selects the top n analysis results based on the magnitude of the first evaluation indicator. The policy effectiveness analysis program 213 then selects a policy that includes the parameter values ​​changed from the initial data in order to generate the first analysis data corresponding to the selected analysis results. For example, if the first analysis data was generated by changing f5 to "c", then the policy that changes f5 to "c" will be selected.

[0062] The policy effectiveness analysis program 213 performs the policy effectiveness analysis (step S105). Specifically, the following processes are executed.

[0063] (S105-1) The policy effectiveness analysis program 213 calculates outcome indicators (base indicators) by inputting data 500 into a predictive model.

[0064] (S105-2) The policy effectiveness analysis program 213 generates second analysis data for each policy by changing the parameter values ​​of the initial data based on the policy settings 403, and registers it in the policy effectiveness analysis dataset 226. Figure 10 shows an example of the policy effectiveness analysis dataset 226. The bold border indicates the changed values.

[0065] (S105-3) The policy effectiveness analysis program 213 selects one policy from the policies selected in step S104 and obtains second analysis data corresponding to the selected policy from the policy effectiveness analysis dataset 226.

[0066] (S105-4) The policy effectiveness analysis program 213 calculates an outcome indicator by inputting the acquired second analysis data into a predictive model. The policy effectiveness analysis program 213 calculates the difference between the outcome indicator and the base indicator. In this embodiment, this difference is used as the second evaluation indicator, which represents the magnitude of the policy's effect. Alternatively, the second evaluation indicator may be calculated using a formula that uses the difference as a parameter. The policy effectiveness analysis program 213 registers the policy ID and the second evaluation indicator as analysis results in the policy effectiveness analysis results DB 229.

[0067] (S105-5) The policy effectiveness analysis program 213 determines whether processing has been completed for all policies selected in step S104. If processing has not been completed for all policies selected in step S104, the policy effectiveness analysis program 213 returns to S105-3.

[0068] (S105-6) When processing is complete for all measures selected in step S104, the measure effectiveness analysis program 213 presents the analysis results to the user and terminates the measure effectiveness analysis. For example, the measure effectiveness analysis program 213 transitions screen 600 to screen 1100 as shown in Figure 11. Screen 1100 includes display fields 1101, 1102, 1103, 1104 and a button 1105.

[0069] Display field 1101 displays analysis results sorted in descending order of effectiveness. When a user selects an analysis result in display field 1101, the name and effect of the measure are displayed in display field 1102, and the changes to the parameters from the initial data are displayed in display field 1103. In addition, the results of the parameter impact analysis are displayed in display field 1104. Button 1105 is a button to transition to screen 600.

[0070] By displaying the details of the policy, i.e., the combination of parameters and values, in display field 1104, it is possible to support the decision-making process regarding changes to the policy's content.

[0071] If the content of a measure needs to be changed, the user sets the target measure in the selection field 605 and operates button 604. If at least one of the field or group needs to be changed, the user presses button 601, enters information in the setting areas 606 and 607, and then presses button 602.

[0072] The computer 200 waits for user input. When it receives user input, it determines whether or not it has received an instruction to change the settings of the policy (step S106). Specifically, the computer 200 determines whether or not button 604 has been pressed.

[0073] When the computer 200 receives an instruction to change the settings of a policy, it transitions to a mode for changing the policy parameters and updates the policy content based on the user's operation (step S107). After that, the computer 200 returns to step S103. Specifically, the parameter setting program 211 displays a screen 600 as shown in Figure 12, showing the parameters to be changed.

[0074] If the received operation is not an instruction to change the settings of a policy, the computer 200 determines whether or not an instruction to set initial data has been received (step S108).

[0075] If the instruction to set initial data is received, the computer 200 returns to step S102. If the instruction to terminate is received, the computer 200 terminates the series of processes.

[0076] The screens used for data entry and processing instructions are examples only and are not limited to those shown. Voice-controlled interfaces are also acceptable.

[0077] According to Example 1, the computer 200 can narrow down the measures to be tested based on the magnitude of the impact on outcome indicators associated with changes in parameter values ​​and the settings of the measures. This allows the computer 200 to efficiently and quickly verify the effectiveness of the measures.

[0078] When the implementation of a policy, i.e., changing parameter values, is difficult due to the characteristics of the field or group, the user can set parameter values ​​that are highly feasible and have a high improvement effect on the outcome indicator, based on their knowledge of the parameters and the first evaluation indicator. When there are multiple parameters, it is difficult to determine which parameter to change and its value. However, by referring to the presentation of this embodiment, it is possible to easily determine which parameter to change and its value. [Examples]

[0079] In Example 2, the processing method for analyzing the effectiveness of the measures differs in some respects. Below, we will explain Example 2, focusing on the differences from Example 1.

[0080] Figure 13 shows an example of the configuration of the computer 200 in Example 2.

[0081] The hardware configuration of the computer 200 in Example 2 is the same as that of Example 1. The software configuration of the computer 200 in Example 2 differs in part from that of Example 1. Specifically, the computer 200 in Example 2 maintains the condition DB1301.

[0082] Condition DB1301 is a database for managing the conditions for the recommended parameter values ​​in a policy.

[0083] Figure 14 shows an example of the conditions DB1301 in Example 2.

[0084] The condition DB1301 shown in Figure 14 is a table-style data structure that stores records containing policy ID 1401, name 1402, and recommended conditions 1403. There is one record for each policy.

[0085] Policy ID 1401 is a field that stores the policy ID. Name 1402 is a field that stores the policy name. Recommendation Condition 1403 is a field that stores the recommended parameter values ​​for the policy. Specifically, it contains one or more combinations of parameters and values.

[0086] The processing flow executed by the computer 200 in Example 2 is the same as in Example 1. However, the processing in step S104 and step S105 are slightly different.

[0087] In step S104, the policy effectiveness analysis program 213 selects the top n analysis results based on the magnitude of the second evaluation indicator. The policy effectiveness analysis program 213 selects policies in which the values ​​of the parameters changed from the initial data to generate the first analysis data corresponding to the selected analysis results match the values ​​of the changed parameters. Furthermore, the policy effectiveness analysis program 213 determines whether each selected policy satisfies the recommendation conditions. The policy effectiveness analysis program 213 assigns a first selection flag to policies that satisfy the recommendation conditions and a second selection flag to policies that do not satisfy the recommendation conditions. In Example 2, a policy effectiveness analysis dataset 226 is generated as shown in Figure 15. The first selection flag is indicated by a circle symbol, and the second selection flag is indicated by a triangle symbol.

[0088] In step S105, the policy effectiveness analysis program 213 selects the policies that have been assigned the first selection flag and the second selection flag as the policies to be examined. Furthermore, if a policy has been assigned the second selection flag, the policy effectiveness analysis program 213 stores the policy ID, the second evaluation indicator, and the alert as analysis results in the policy effectiveness analysis results DB 229. Note that only policies assigned the first selection flag may be selected.

[0089] When the policy effectiveness analysis program 213 displays the analysis results, it will show information indicating that policies for which alerts have been set are unlikely to be implemented.

[0090] By providing alerts, we can help users select feasible measures.

[0091] It should be noted that the present invention is not limited to the embodiments described above, and various modifications are included. Furthermore, for example, the embodiments described above are detailed explanations of the configuration in order to clearly illustrate the present invention, and are not necessarily limited to those having all the configurations described. In addition, some of the configurations in each embodiment can be added to, deleted from, or replaced with other configurations.

[0092] Furthermore, each of the above-mentioned configurations, functions, processing units, processing means, etc., may be implemented in hardware, in whole or in part, for example, by designing them as integrated circuits. The present invention can also be implemented by software program code that realizes the functions of the embodiment. In this case, a storage medium on which the program code is recorded is provided to a computer, and the processor of that computer reads the program code stored in the storage medium. In this case, the program code read from the storage medium itself realizes the functions of the embodiment described above, and the program code itself and the storage medium on which it is stored constitute the present invention. Examples of storage media used to supply such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs (Solid State Drives), optical disks, magneto-optical disks, CD-Rs, magnetic tapes, non-volatile memory cards, ROMs, and the like.

[0093] Furthermore, the program code that implements the functions described in this embodiment can be implemented in a wide range of programming or scripting languages, such as assembler, C / C++, Perl, Shell, PHP, Python, and Java (registered trademark).

[0094] Furthermore, the program code for the software that implements the functions of the embodiment may be distributed via a network and stored in a storage means such as a computer's hard disk or memory, or in a storage medium such as a CD-RW or CD-R, and the computer's processor may read and execute the program code stored in the storage means or storage medium.

[0095] In the above-described embodiment, the control lines and information lines shown are those deemed necessary for explanation and do not necessarily represent all control lines and information lines in the actual product. All components may be interconnected. [Explanation of Symbols]

[0096] 200 calculator 201 Arithmetic equipment 202 memory 203 Storage device 204 Communication equipment 205 Input device 206 Output device 211 Parameter setting program 212 Impact Analysis Program 213 Policy Effectiveness Analysis Program 221 Configuration Guide DB 222 Setting Range DB 223 Measures DB 224 Parameter DB 225 Impact Analysis Datasets 226 Policy Effectiveness Analysis Dataset 227 Predictive Model Database 228 Impact analysis results DB 229 Policy Effectiveness Analysis Results Database 600, 900, 1100 screens 1301 Condition DB

Claims

1. A computer system that supports the selection of measures to promote behavioral change in a group working in the field in order to achieve a predetermined objective, The system comprises a computing device and a storage device connected to the computing device, The storage device receives data as input, which includes values ​​for multiple parameters representing the attributes of the site and the group, and stores information for a model that outputs an outcome index representing the degree to which the objective has been achieved. The aforementioned computing device is Initial data is generated that includes the initial values ​​of the multiple parameters set by the user. The process of generating first analysis data by selecting one of the parameters and changing the initial value of the selected parameter in the initial data is repeatedly executed. For each of the multiple sets of first analysis data, the process of calculating the difference between the outcome index obtained by inputting the first analysis data into the model and the outcome index obtained by inputting the initial data into the model, and calculating a first evaluation index that represents the magnitude of the influence of the parameter values ​​changed to generate the first analysis data on the outcome index based on this difference, is repeatedly performed. A computer system characterized by selecting the measures to verify the effectiveness of based on the first evaluation indicator.

2. A computer system according to claim 1, The storage device stores a policy database for managing policy data, which includes identification information of the policy and the content of the policy. The content of the aforementioned measures is a combination of the parameters and the values ​​of the parameters that are changed by the implementation of the aforementioned measures, The aforementioned computing device is Based on the first evaluation index, select the value of the parameter that has a significant impact on the outcome index. A computer system characterized by selecting a measure, wherein the content of the measure includes the value of the selected parameter.

3. A computer system according to claim 2, The aforementioned computing device is The process of selecting one measure from among the measures selected based on the magnitude of the first evaluation index, and generating second analysis data by changing the initial values ​​of the parameters of the initial data based on the content of the selected measure, is repeatedly executed. For each of the multiple sets of second analysis data, the difference between the outcome indicator obtained by inputting the second analysis data into the model and the outcome indicator obtained by inputting the initial data into the model is calculated, and a second evaluation indicator representing the magnitude of the effect of the measure is calculated based on this difference. A computer system characterized by outputting analysis results including the measures selected based on the magnitude of the first evaluation indicator and the second evaluation indicator.

4. A computer system according to claim 3, The storage device stores a condition database for managing condition data, which includes identification information of the measure and recommended conditions for the parameter values ​​recommended in the implementation of the measure. The aforementioned computing device is Based on the magnitude of the first evaluation indicator, it is determined whether the content of the measures selected satisfies the recommendation conditions. A computer system characterized in that, in the analysis results of a measure whose content does not meet the recommended conditions, information indicating that the content of the measure does not meet the recommended conditions is included.

5. A computer system according to claim 3, The computing system is characterized in that the calculation device includes in the analysis results the changes in the parameter values ​​from the initial data, and the first evaluation index related to the parameter whose initial value in the initial data is changed.

6. A computer system provides a method for supporting the selection of measures to promote behavioral changes in a group working in the field in order to achieve a predetermined objective, The aforementioned computer system has an arithmetic unit and a storage device connected to the arithmetic unit. The storage device receives data as input, which includes values ​​for multiple parameters representing the attributes of the site and the group, and stores information for a model that outputs an outcome index representing the degree to which the objective has been achieved. The aforementioned method for supporting the selection of measures is: The first step is for the calculation device to generate initial data including initial values ​​for the plurality of parameters set by the user, The second step involves the arithmetic unit repeatedly executing a process to generate first analysis data by selecting one of the parameters and changing the initial value of the selected parameter in the initial data. A third step in which the calculation device repeatedly performs a process to calculate, for each of the plurality of first analysis data, the difference between the outcome index obtained by inputting the first analysis data into the model and the outcome index obtained by inputting the initial data into the model, and calculate a first evaluation index that represents the magnitude of the influence of the parameter values ​​changed to generate the first analysis data on the outcome index based on the difference, The calculation device performs a fourth step of selecting the measures to verify the effectiveness of based on the first evaluation indicator, A method for supporting the selection of policies, characterized by including the following:

7. A method for supporting the selection of measures according to claim 6, The storage device stores a policy database for managing policy data, which includes identification information of the policy and the content of the policy. The content of the aforementioned measures is a combination of the parameters and the values ​​of the parameters that are changed by the implementation of the aforementioned measures, The fourth step described above is: The calculation device selects a value for the parameter that has a significant impact on the outcome indicator based on the first evaluation indicator, A method for supporting the selection of a policy, characterized in that the calculation device includes the step of selecting a policy, which includes the value of the parameter selected for the content of the policy.

8. A method for supporting the selection of measures according to claim 7, A fifth step in which the calculation device repeatedly performs a process to generate second analysis data by selecting one of the measures selected based on the magnitude of the first evaluation index, and changing the initial values ​​of the parameters of the initial data based on the content of the measure, A sixth step in which the computing device calculates the difference between the outcome index obtained by inputting the second analysis data into the model and the outcome index obtained by inputting the initial data into the model, for each of the plurality of second analysis data, and calculates a second evaluation index representing the magnitude of the effect of the measure based on the difference. A seventh step in which the calculation device outputs an analysis result including the measures selected based on the magnitude of the first evaluation indicator and the second evaluation indicator, A method for supporting the selection of policies, characterized by including the following:

9. A method for supporting the selection of measures according to claim 8, The storage device stores a condition database for managing condition data, which includes identification information of the measure and recommended conditions for the parameter values ​​recommended in the implementation of the measure. The fourth step includes the calculation device determining whether the content of the measures selected based on the magnitude of the first evaluation index satisfies the recommendation conditions, The seventh step is a method for supporting the selection of measures, characterized in that the computing device includes in the analysis results of measures in which the content of the measures does not satisfy the recommended conditions information indicating that the content of the measures does not satisfy the recommended conditions.

10. A method for supporting the selection of measures according to claim 8, The seventh step is a method for supporting the selection of measures, characterized in that the computing device includes in the analysis results the changes made to the parameter values ​​from the initial data, and the first evaluation index related to the parameter whose initial value in the initial data is changed.

Images