Information processing method and information processing program

Abstract

This information processing device receives an input of a gain table indicating the extent to which a cooperation task consisting of a combination of actions is performed, such input received for each of the combination patterns of the actions that can be taken by each performer in the cooperation task. Thereafter, the information processing device excludes, from the input gain table, an action that has no possibility of improving the performance of the cooperation task (first exclusion step). Next, the information processing device excludes, from the gain table resulting from the execution of the first exclusion step, patterns in which there is only one combination of the actions that improves the performance of the cooperation task (second exclusion step). Subsequently, if there are patterns with similar combinations of the actions in the gain table resulting from the execution of the second exclusion step, the information processing device excludes one of the patterns among the patterns with similar combinations of the actions (third exclusion step). Consequently, the information processing device outputs the combinations of actions remaining in the gain table after the execution of the third exclusion step.

Description

Information processing method and information processing program

[0001] The present invention relates to an information processing method and an information processing program.

[0002] In the past, when it came to tasks performed collaboratively by multiple people (collaborative tasks), in order to predict the level of performance on the task or to practice it, it was necessary to actually perform the task, even if it was complex.

[0003] Mizrahi, D., Laufer, I., Zuckerman, I.: Modeling and predicting individual tacit coordination ability. Brain informatics 9(1), 4 (2022)

[0004] Therefore, for example, when machine learning is performed on the behavior of each participant in a collaborative task to predict the level of performance in the collaborative task, there is a problem that a large amount of data is required for machine learning. Also, when practicing to improve performance in a collaborative task, there is a problem that random practice takes a long time.

[0005] However, no technology has been considered for creating tasks (simple tasks) that are narrowed down to only those situations that are effective in predicting high performance in collaborative tasks or improving performance.

[0006] Therefore, the present invention aims to solve the above-mentioned problems and create tasks (simple tasks) that are narrowed down to only those situations that are effective in predicting high performance in cooperative tasks and improving performance.

[0007] In order to solve the above-mentioned problems, the present invention is an information processing method executed by an information processing device, characterized in that it includes the steps of: receiving input of a payoff table showing, for each pattern of combinations of actions that each participant can take in a collaborative task, the level of performance in the collaborative task resulting from the combination of actions; a first elimination step of excluding, from the input payoff table, actions that are unlikely to improve performance in the collaborative task; a second elimination step of excluding, from the payoff table after the first elimination step, patterns in which there is only one combination of actions that improves performance in the collaborative task; a third elimination step of excluding, if there are patterns in which the combinations of actions are similar to each other in the payoff table after the second elimination step, any of the patterns in which the combinations of actions are similar to each other; and a step of outputting the combinations of actions remaining in the payoff table after the third elimination step.

[0008] According to the present invention, it is possible to create a task (simple task) that narrows down only to situations that are effective for predicting the level of performance in a cooperative task and for improving performance.

[0009] FIG. 1 is a diagram for explaining an overview of an information processing device. FIG. 2 is a diagram showing an example of a cooperative task. FIG. 3 is a diagram showing an example of a payoff table for the cooperative task shown in FIG. 2. FIG. 4 is a diagram showing an example of eliminating and simplifying options in a payoff table. FIG. 5 is a diagram showing an example of eliminating obvious patterns in a payoff table. FIG. 6 is a diagram showing an example of similar patterns in a payoff table. FIG. 7 is a diagram showing an example of the configuration of an information processing device. FIG. 8 is a diagram showing an example of a processing procedure executed by the information processing device. FIG. 9 is a diagram showing an example of calculating the success probability when the cooperative task is fly catching. FIG. 10 is a diagram showing an example of a payoff table for a cooperative task derived from the success probability shown in FIG. 9. FIG. 11 is a diagram showing an example of a computer that executes an information processing program.

[0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, a description will be given of an embodiment of the present invention with reference to the drawings, but the present invention is not limited to the embodiment.

[0011] [Overview] An overview of the information processing device of this embodiment will be described with reference to Fig. 1. The information processing device creates a task (simple cooperative task) from a cooperative task by narrowing down the tasks to those that are effective for predicting the performance of the cooperative task and improving performance.

[0012] A cooperative task (cooperative work) as referred to here is, for example, a task in which, when a situation (information) is given, each member of a group (also referred to as a "performer") performing the cooperative work selects a strategy and performs the work (action). A cooperative work is, for example, a repetitive task in which the next action of the other member is unpredictable. Examples of cooperative work include baseball fielding, badminton or tennis doubles, and work division. Note that the above is merely an example, and cooperative work can be any work performed by multiple people in cooperation (cooperation) with a common goal, such as a work performed by three or more people as a team.

[0013] Here, an example will be described in which the cooperative task to be processed by the information processing device is a task in which two people simultaneously repeat the action of selecting one card, and if they select the same card, it is a success (see FIG. 4).

[0014] First, the information processing device receives input of the above-mentioned cooperative task payoff table (Fig. 3) prepared in advance. The cooperative task payoff table is information that indicates the level of cooperative task performance resulting from each combination of actions that each participant can take in the cooperative task. Fig. 3 is an example of a payoff table in which the objective function (level of performance) of the cooperative task is defined as (probability of success - cost of two participants). Note that all selection costs are set to 0.

[0015] As shown in FIG. 1, first, the information processing device eliminates options other than those that can be solutions to the cooperative task from the behaviors (options) of each pattern shown in the payoff table (elimination and simplification of options).

[0016] For example, as shown in Figure 4, the information processing device excludes from the options for each pattern all options other than those that could be solutions to the cooperative task (for example, in pattern A, your hand = 1, 6, your opponent's hand = 1, 6; in pattern B, your hand = 3, your opponent's hand = 3).

[0017] Returning to the explanation of Figure 1, the information processing device then eliminates patterns with only one solution from the payoff table after the above-mentioned options have been eliminated and simplified (eliminating patterns with obvious solutions). For example, of patterns A and B shown in Figure 4, pattern B only has the option of player's hand = 3 and opponent's hand = 3. Therefore, the information processing device eliminates pattern B (see Figure 5).

[0018] Returning to the explanation of Figure 1, the information processing device then eliminates patterns with similar options from the payoff table from which patterns with obvious solutions have been eliminated (elimination of similar patterns). For example, both pattern A and pattern C shown in Figure 6 have the same options (your hand = 1, 6, your opponent's hand = 1, 6). Therefore, the information processing device eliminates either pattern A or pattern C.

[0019] This allows the information processing device to obtain a payoff table (payoff table for simple cooperative tasks) that excludes unnecessary patterns and unnecessary options for performing the cooperative task.The information processing device can then create a simple cooperative task by extracting combinations of options (actions) for each user listed in the payoff table for the simple cooperative task.

[0020] This simplified cooperative task can be considered a task that extracts only the situations from the cooperative task that require the participant to use their own heuristics. Therefore, by using the simplified cooperative task instead of the cooperative task, the amount of data required for machine learning to predict the level of performance on the cooperative task can be reduced. Furthermore, the amount of practice required to improve performance on the cooperative task can be reduced.

[0021] [Configuration Example] Next, a configuration example of the information processing device 10 will be described with reference to Fig. 7. The information processing device 10 is realized by a general-purpose computer such as a personal computer, and has a communication unit 110, a storage unit 120, and a control unit 130.

[0022] In addition, the information processing device 10 may have an input device (e.g., a keyboard, a mouse, etc.) that accepts various operations from a user of the information processing device 10, an output device such as a display device (e.g., an LCD display, etc.) for displaying information, and an audio output device (e.g., a speaker, etc.) for outputting information audibly.

[0023] The communication unit 110 is realized by, for example, a network interface card (NIC). The communication unit 110 is connected to a predetermined network such as the Internet via a wired or wireless connection, and transmits and receives information to and from an external device. For example, the communication unit 110 receives a payoff table for a cooperative task.

[0024] The storage unit 120 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 stores data and programs used when the control unit 130 executes various processes. For example, the storage unit 120 stores a payoff table (see FIG. 3) for cooperative tasks.

[0025] The control unit 130 is responsible for overall control of the information processing device 10. The functions of the control unit 130 are realized, for example, by a central processing unit (CPU) executing a program stored in the storage unit 120.

[0026] The control unit 130 includes an input unit 131 , a first excluding unit 132 , a second excluding unit 133 , a third excluding unit 134 , and an output unit 135 .

[0027] The input unit 131 receives an input of a payoff table for a cooperative task (see FIG. 3 ). The first elimination unit 132 eliminates, from the input payoff table, combinations of actions that have no possibility of improving performance in the cooperative task. For example, the first elimination unit 132 eliminates options other than options that can be solutions for the cooperative task from the behaviors (options) of each pattern shown in the payoff table, and outputs the results (see FIG. 4 ).

[0028] The second elimination unit 133 excludes patterns that have only one combination of actions that improves the performance of the cooperative task from the payoff table output from the first elimination unit 132. For example, the second elimination unit 133 excludes patterns that have only one solution from the payoff table output from the first elimination unit 132 and outputs the result (see FIG. 5 ).

[0029] If there is a pattern in which the combinations of options are similar to each other in the payoff table output from the second elimination unit 133, the third elimination unit 134 excludes one of the patterns in which the combinations of options are similar to each other and outputs it.

[0030] For example, if there are multiple patterns in which the same options remain in the payoff table output from the second elimination unit 133, the third elimination unit 134 keeps one of the patterns and excludes the remaining patterns. For example, from patterns A and C shown in FIG. 6 , pattern C is excluded. Alternatively, if there are patterns in which the remaining combinations of options are similar to each other in the pattern group output from the second elimination unit 133, the third elimination unit 134 keeps one of the patterns and excludes the remaining patterns. Note that patterns in which the remaining combinations of options are similar are identified using, for example, k-means++ or the like.

[0031] The output unit 135 outputs the options (actions) of each implementer remaining in the payoff table output from the third exclusion unit 134 (the payoff table processed by the first exclusion unit 132, the second exclusion unit 133, and the third exclusion unit 134) as a simple collaborative task.

[0032] By outputting the simple cooperative task described above, the information processing device 10 can reduce, for example, the amount of data required for machine learning to predict the level of performance in the cooperative task, and can also reduce the amount of practice required to improve performance in the cooperative task.

[0033] [Example of Processing Procedure] Next, an example of processing procedure executed by the information processing device 10 will be described with reference to Fig. 8. First, the input unit 131 of the information processing device 10 receives input of a payoff table for a target cooperative task (S1). In Fig. 8, the number of game patterns in the payoff table is P, the number of choices of the user (the person who performs the cooperative task) in pattern i is c(i), and the user's choices in pattern i are A. choice (i)=(a i1 ,a i2 ,…,a ic(i) ) Also, let S(i) be the environmental factor for pattern i, and f(a,S) be the Boolean function that determines whether it is the best performance or not.

[0034] Next, the first elimination unit 132 eliminates and simplifies the options of the payoff table received in S1 (S2). For example, the first elimination unit 132 eliminates and simplifies the options of f(a i* ,S(i)) = false i* As a result, as shown in Figure 8, c(i) → c'(i) (∀i c(i) ≥ c'(i)), A choice (i)=(a i1 ,a i2 ,…,a ic´(i) )

[0035] Thereafter, the second elimination unit 133 eliminates patterns having obvious solutions from the payoff table processed in S2 (S3). For example, the second elimination unit 133 eliminates i for which c'(i) = 1. As a result, P → P1 (P ≥ P1) is obtained as shown in FIG. 3.

[0036] Next, the third elimination unit 134 eliminates similar patterns from the payoff table processed in S3 (S4). For example, the third elimination unit 134 choice (i)=A choice(j) is removed. As a result, as shown in FIG. 8, P1 → P2 (P1 ≧ P2) is obtained. In this way, the third excluding unit 134 can obtain a payoff table for the simple cooperative task (S5). Thereafter, the output unit 135 outputs the options (actions) of each participant shown in the payoff table as the simple cooperative task.

[0037] By performing the above process, the information processing device 10 can create a simple cooperative task from the payoff table of the cooperative task.

[0038] [Application Example] An application example will be described in which the cooperative task to be processed by the information processing device 10 is "fly catching." Here, as shown in FIG. 9, a case where person A or person B catches a fly will be described as an example. Note that, when person A's position x a =0, ball landing point x ball = 4, B's position x b = 10. The options for actions taken by A and B are "catch (the fly)," "leave (it to the other person)," and "follow (the other person)." The success probability of catching the fly in this case is as shown in Figure 9.

[0039] Here, if the objective function is defined as "probability of success - cost of two players," the cost of catching a fly ball = distance / 10, the cost of leaving it to the other player = 0, and the cost of following the other player = distance / 20, then if we create a payoff table for the above objective function from the success probability shown in Figure 9, we get the result shown in Figure 10.

[0040] If the above-described payoff table can be created, the information processing device 10 can create a simplified cooperative task by reducing the number of cooperative task options and patterns, using the same procedure as described above.

[0041] The simple cooperative task created by the information processing device 10 extracts only the behaviors of participants in situations where it is necessary to use their heuristics in the cooperative task. Therefore, the simple cooperative task can be considered to contain high-quality information for better reproducing the participants' behavior in the cooperative task. Therefore, the simple cooperative task can also be used to improve the quality of data used to reproduce the behavior of each participant in the cooperative task and to understand the preferences of each participant.

[0042] [System Configuration, etc.] The components of each unit shown in the figure are conceptual functional units and do not necessarily have to be physically configured as shown. In other words, the specific form of distribution and integration of each device is not limited to that shown, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc. Furthermore, all or any part of the processing functions performed by each device can be realized by a CPU and a program executed by the CPU, or can be realized as hardware using wired logic.

[0043] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using a known method.In addition, the information including the processing procedures, control procedures, specific names, various data and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified.

[0044] [Program] The information processing device 10 can be implemented by installing a program (information processing program) as package software or online software on a desired computer. For example, by executing the program on an information processing device, the information processing device can function as the information processing device 10. The information processing device referred to here includes mobile communication terminals such as smartphones, mobile phones, and PHS (Personal Handyphone Systems), as well as terminals such as PDAs (Personal Digital Assistants).

[0045] 11 is a diagram showing an example of a computer that executes an information processing program. The computer 1000 includes, for example, a memory 1010 and a CPU 1020. The computer 1000 also includes a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.

[0046] The memory 1010 includes a read-only memory (ROM) 1011 and a random access memory (RAM) 1012. The ROM 1011 stores a boot program such as a basic input / output system (BIOS). The hard disk drive interface 1030 is connected to a hard disk drive 1090. The disk drive interface 1040 is connected to a disk drive 1100. A removable storage medium such as a magnetic disk or optical disk is inserted into the disk drive 1100. The serial port interface 1050 is connected to a mouse 1110 and a keyboard 1120, for example. The video adapter 1060 is connected to a display 1130, for example.

[0047] The hard disk drive 1090 stores, for example, an OS 1091, an application program 1092, a program module 1093, and program data 1094. That is, the programs that define the processes executed by the information processing device 10 are implemented as program modules 1093 in which computer-executable code is written. The program modules 1093 are stored, for example, in the hard disk drive 1090. For example, the program modules 1093 for executing processes similar to those of the functional configuration of the information processing device 10 are stored in the hard disk drive 1090. Note that the hard disk drive 1090 may be replaced with an SSD (Solid State Drive).

[0048] Data used in the processing of the above-described embodiment is stored as program data 1094, for example, in the memory 1010 or the hard disk drive 1090. The CPU 1020 then reads the program module 1093 or the program data 1094 stored in the memory 1010 or the hard disk drive 1090 into the RAM 1012 as necessary and executes them.

[0049] The program module 1093 and program data 1094 may not necessarily be stored in the hard disk drive 1090, but may also be stored in a removable storage medium and read by the CPU 1020 via the disk drive 1100 or the like. Alternatively, the program module 1093 and program data 1094 may be stored in another computer connected via a network (such as a local area network (LAN) or a wide area network (WAN)). The program module 1093 and program data 1094 may then be read by the CPU 1020 from the other computer via the network interface 1070.

[0050] REFERENCE SIGNS LIST 10 Information processing device 110 Communication unit 120 Storage unit 130 Control unit 131 Input unit 132 First exclusion unit 133 Second exclusion unit 134 Third exclusion unit 135 Output unit

Claims

1. An information processing method executed by an information processing device, comprising: a step of receiving input of a payoff table showing, for each pattern of combinations of actions that each participant can take in a collaborative task, the level of performance in the collaborative task resulting from the combination of actions; a first elimination step of excluding, from the input payoff table, actions that are unlikely to improve performance in the collaborative task; a second elimination step of excluding, from the payoff table after the first elimination step, patterns in which there is only one combination of actions that improves performance in the collaborative task; a third elimination step of excluding, if the payoff table after the second elimination step contains patterns in which the combinations of actions are similar to each other, any of the patterns in which the combinations of actions are similar to each other; and a step of outputting the combinations of actions remaining in the payoff table after the third elimination step.

2. The information processing method described in claim 1, characterized in that the level of performance of the cooperative task shown in the payoff table is a value obtained by subtracting the cost required for the implementer to select the action from the probability of success of the cooperative task using the combination of actions.

3. An information processing program for causing a computer to execute the following steps: a step of receiving input of a payoff table showing, for each pattern of combinations of actions that each participant can take in a cooperative task, the level of performance in the cooperative task resulting from said combinations of actions; a first elimination step of excluding, from the input payoff table, actions that are unlikely to improve performance in the cooperative task; a second elimination step of excluding, from the payoff table after the first elimination step, patterns in which there is only one combination of actions that improves performance in the cooperative task; a third elimination step of excluding, if the payoff table after the second elimination step contains patterns in which the combinations of actions are similar to each other, one of the patterns in which the combinations of actions are similar to each other; and a step of outputting the combinations of actions remaining in the payoff table after the third elimination step.

Images