Learning device, presentation device, learning method and program

Abstract

A training device 1X mainly comprises a solution generation means 15X and a training means 16X. The solution generation means 15X generates a solution of an optimization problem. The training means 16X generates a plurality of combinations of solutions, and uses a combination selected from among the plurality of combinations by external input to train a parameter relating to consistency of presented solutions that are a plurality of solutions to be presented to a person who gave the external input.

Description

[Technical Field]

[0001] The present disclosure relates to the technical fields of a learning device, a presentation device, a learning method, and a storage medium that perform processing related to an optimization problem. [Background technology]

[0002] Systems for calculating solutions to optimization problems have been known for some time. For example, Patent Document 1 discloses a technology for evaluating optimization results based on multiple indicators. Furthermore, Patent Document 2 discloses an optimization system that determines (matches) a combination of sellers and buyers of goods to be traded so that their desired transaction conditions, such as transaction volume and transaction price, match, and then can change some of the transaction conditions and perform re-matching. Furthermore, Patent Document 3 discloses a system that optimizes business scheduling taking multiple indicators into consideration. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication WO2013 / 179577 [Patent Document 2] International Publication WO2021 / 001977 [Patent Document 3] International Publication WO2021 / 059506 Summary of the Invention [Problem to be solved by the invention]

[0004] When a solution to an optimization problem is obtained by optimization, a solution that satisfies the formulated constraints is obtained. On the other hand, there are cases where a user wants to compare multiple solutions and decide on the solution to be finally adopted.

[0005] In view of the above-mentioned problems, one of the objectives of the present disclosure is to provide a learning device, a learning method, a storage medium, and a presentation device that performs learning to present multiple solutions with consistency that users prefer, and that presents based on the learning results. [Means for solving the problem]

[0006] One aspect of the learning device is Solution of the optimization problem and values ​​of a plurality of items for evaluating the solution. a solution generating means for generating a solution A plurality of sets of the solutions are generated, and the set selected from the plurality of sets by an external input is selected. An index of the variation of the values ​​for each of the items Based on the above, a plurality of solutions are presented to the person who performed the external input. Determine the degree of variation of the values ​​for each of the items. a learning means for learning parameters; It is a learning device having the following.

[0007] One aspect of the learning method is: Solution of the optimization problem and values ​​of a plurality of items for evaluating the solution. Generate A plurality of sets of the solutions are generated, and the set selected from the plurality of sets by an external input is selected. An index of the variation of the values ​​for each of the items Based on the above, a plurality of solutions are presented to the person who performed the external input. Determine the degree of variation of the values ​​for each of the items. Learning the parameters, It is a learning method.

[0008] One aspect of the program is Solution of the optimization problem and values ​​of a plurality of items for evaluating the solution. Generate A plurality of sets of the solutions are generated, and the set selected from the plurality of sets by an external input is selected. An index of the variation of the values ​​for each of the items Based on the above, a plurality of solutions are presented to the person who performed the external input. Determine the degree of variation of the values ​​for each of the items. This is a program that causes a computer to execute the process of learning parameters. [Effects of the Invention]

[0009] It can learn to present multiple solutions with consistency that the user prefers. [Brief explanation of the drawings]

[0010] [Figure 1] 1 shows the configuration of an optimization system in a first embodiment. [Figure 2] 1 shows a hardware configuration of an information processing device. [Figure 3] 3 is an example of a functional block according to the first embodiment. [Figure 4] 4 is an example of a flowchart of a learning phase according to the first embodiment. [Figure 5] 10 is an example of a flowchart of a presentation phase according to the first embodiment. [Figure 6] 10 is a display example of a solution selection screen. [Figure 7] 10 is a display example of a solution presentation screen. [Figure 8] The transition of the solution based on the change of the constraints is shown. [Figure 9] 10 is an example of a solution transition history screen. [Figure 10] 10 shows the configuration of an optimization system according to a second embodiment. [Figure 11] FIG. 10 is a functional block diagram of a learning device according to a third embodiment. [Figure 12] 11 is an example of a flowchart showing a processing procedure of a learning device in the third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, embodiments of a learning device, a presentation device, a learning method, and a storage medium will be described with reference to the drawings.

[0012] First Embodiment (1) System Configuration 1 shows the configuration of an optimization system 100 according to the first embodiment. The optimization system 100 mainly comprises an information processing device 1, an input device 2, a display device 3, and a storage device 4.

[0013] The information processing device 1 performs processing related to optimization of a specified optimization problem. In this embodiment, the information processing device 1 calculates and presents multiple solutions to the specified optimization problem. In this case, when presenting the multiple solutions, the information processing device 1 performs learning so that it can present multiple solutions with the consistency that a user using the optimization system 100 values. Hereinafter, the stage (phase) in which learning is performed to present multiple solutions with the consistency that a user values ​​will be referred to as the "learning phase," and the phase in which multiple solutions for a user-specified optimization problem are presented using parameters obtained through learning will also be referred to as the "presentation phase." Note that the learning phase is not a required process, and the user can select whether or not to perform it. The information processing device 1 is an example of a "learning device" and a "presentation device."

[0014] The optimization problem may be, for example, a problem of determining the combination of sellers and buyers of traded goods (and the transportation schedule for the goods), a problem of determining employee work shifts, or any other combinatorial optimization problem. The traded goods may be fuels such as LNG, steel, machinery, electronics, textiles, chemical products, medical products, food, or any other goods.

[0015] The information processing device 1 also performs data communication with the input device 2, the display device 3, and the storage device 4 via a communication network or by direct wireless or wired communication.

[0016] The input device 2 is an interface that accepts user input, which is external input, and includes, for example, a touch panel, buttons, a keyboard, a voice input device, etc. The input device 2 supplies input information “S1” generated based on the user input to the information processing device 1.

[0017] The display device 3 is, for example, a display, a projector, or the like, and performs a predetermined display based on the display information “S2” supplied from the information processing device 1.

[0018] The storage device 4 is a memory that stores various information necessary for the optimization process. For example, the storage device 4 stores condition information 40 and parameter information 41.

[0019] The condition information 40 is information (including information regarding the problem settings) regarding the conditions of the optimization problem to be solved by the information processing device 1. For example, if a problem of determining a combination of sellers and buyers of materials to be traded is set as the optimization problem to be solved by the information processing device 1, the condition information 40 includes information about the sellers of the materials to be traded (including the desired conditions of each seller regarding the delivery location, delivery period, transaction volume, price, etc.), information about the buyers of the materials to be traded (including the desired conditions of each buyer regarding the delivery location, delivery period, transaction volume, price, etc.), etc. The condition information 40 may store condition information for the optimization problem to be targeted in the learning phase and condition information for the optimization problem to be targeted in the presentation phase, respectively.

[0020] The parameter information 41 is information about parameters for determining multiple solutions (also called "presented solutions") to be presented to the user. The parameters stored in the parameter information 41 may be parameters such as weighting coefficients (also called "consistency weight parameters") that indicate the degree of importance placed on consistency for each item, or may be parameters of a model that determines the presented solution (also called "presented solution determination model").

[0021] The former consistency weight parameter may be a binary coefficient indicating whether or not each item is an important item, or may be a weight coefficient (continuous value) for each item. Note that an "item" is an index for evaluating a solution to an optimization problem, and may be an index used in the objective function or constraint formula, or may be the variable itself to be found as a solution.

[0022] The latter proposed solution determination model is a learning model that is trained to output information indicating a set of solutions to be selected as the proposed solution when multiple sets of solutions that are candidates for the proposed solution are input. In this case, the proposed solution determination model may have the architecture of any machine learning model, such as a neural network or a support vector machine. For example, if the proposed solution determination model has the architecture of a neural network, such as a convolutional neural network, the parameter information 41 includes information such as the layer structure, the neuron structure of each layer, the number and size of filters in each layer, and the weight of each element of each filter. Note that, before the learning phase is performed, information indicating predetermined initial parameters may be stored in the storage device 4 as the parameter information 41.

[0023] The storage device 4 may be an external storage device such as a hard disk connected to or built into the information processing device 1, or may be a storage medium such as a flash memory. The storage device 4 may also be a server device that performs data communication with the information processing device 1. In this case, the storage device 4 may be composed of multiple server devices.

[0024] The configuration of the optimization system 100 shown in FIG. 1 is an example, and various modifications may be made to the configuration. For example, the input device 2 and the display device 3 may be configured as an integrated device. In this case, the input device 2 and the display device 3 may be configured as a tablet terminal integrated with the information processing device 1. The information processing device 1 may also be configured as a plurality of devices. In this case, the plurality of devices that make up the information processing device 1 exchange information required to execute pre-assigned processing between these plurality of devices.

[0025] (2) Hardware configuration of information processing device 2 shows the hardware configuration of the information processing device 1. The information processing device 1 includes, as hardware, a processor 11, a memory 12, and an interface 13. The processor 11, the memory 12, and the interface 13 are connected via a data bus 19.

[0026] The processor 11 executes a predetermined process by executing a program stored in the memory 12. The processor 11 is a processor such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or a TPU (Tensor Processing Unit). The processor 11 may be composed of multiple processors. The processor 11 is an example of a computer.

[0027] The memory 12 is composed of various types of volatile and non-volatile memories, such as a RAM (Random Access Memory) and a ROM (Read Only Memory). The memory 12 also stores programs for the information processing device 1 to execute various processes. The memory 12 is also used as a working memory, and temporarily stores information acquired from the storage device 4. The memory 12 may function as the storage device 4. Similarly, the storage device 4 may function as the memory 12 of the information processing device 1. The programs executed by the information processing device 1 may be stored in a storage medium other than the memory 12.

[0028] The interface 13 is an interface for electrically connecting the information processing device 1 to other devices. These interfaces may be wireless interfaces such as network adapters for wirelessly transmitting and receiving data to and from other devices, or may be hardware interfaces for connecting to other devices via cables or the like.

[0029] The hardware configuration of the information processing device 1 is not limited to the configuration shown in Fig. 2. For example, the information processing device 1 may include at least one of an input device 2 or a display device 3. Furthermore, the information processing device 1 may be connected to or have a built-in sound output device such as a speaker.

[0030] (3) Functional Blocks Fig. 3 shows an example of functional blocks of the processor 11 in the first embodiment. Functionally, the processor 11 has a solution generating unit 15, a learning unit 16, a presented solution determining unit 17, and a UI (User Interface) control unit 18. Note that in Fig. 3, blocks that exchange data are connected by solid lines, but the combination of blocks that exchange data is not limited to that shown in Fig. 3. The same applies to other functional block diagrams described later.

[0031] The solution generation unit 15 determines a solution to the optimization problem. In this case, the solution generation unit 15 calculates multiple solutions to the optimization problem based on the condition information 40 of the optimization problem stored in the storage device 4. In this case, the solution generation unit 15 calculates a predetermined number of solutions that is greater than the number of solutions to be presented as presented solutions, for example. In order to obtain the predetermined number of solutions, the solution generation unit 15 may relax the constraint conditions stored in the condition information 40 and find an optimal solution for each relaxed constraint condition. In this case, the degree of relaxation of the constraint conditions may be determined based on user input.

[0032] The solution generating unit 15 may determine a solution to an optimization problem based on any optimization method (optimization solver). For example, when solving a problem of determining a combination of sellers and buyers of goods to be traded, the solution generating unit 15 regards the problem as a single combinatorial optimization problem and formulates it as an integer programming problem. The solution generating unit 15 then obtains a solution to the formulated integer programming problem by performing processing equivalent to that of a general application program (e.g., IBM ILOG CPLEX, Gurobi Optimizer, SCIP). A method of formulating the integer programming problem and determining sellers, buyers, ships to be used, and the voyage period of the ships is disclosed, for example, in Patent Document 2.

[0033] The learning unit 16 updates the parameter information 41 in the learning phase. In this case, the learning unit 16 generates multiple sets of solutions (i.e., generates multiple candidates for the presented solution) based on the calculation results of the solution generation unit 15, and presents these to the user in a selectable manner. In this case, the learning unit 16 generates multiple sets of solutions by, for example, randomly sampling from the solutions calculated by the solution generation unit 15. Then, the learning unit 16 considers a set of solutions selected by user input from the presented multiple sets of solutions to be multiple solutions that represent the correct answer (i.e., have the consistency preferred by the user).

[0034] Here, for example, if the parameter information 41 indicates a consistency weight parameter, the learning unit 16 considers an item that is consistent among multiple solutions representing the correct answer (e.g., an item whose variance index is equal to or less than a predetermined value) as an item for which the user places importance on consistency, and changes the consistency weight parameter so that the consistency of the item is emphasized. The variance index is any index that represents variance, the difference between the maximum value and the minimum value, or the like. On the other hand, if the parameter information 41 indicates parameters of a presented solution determination model, the learning unit 16 generates training data for the presented solution determination model using multiple sets of solutions presented to the user as options as input data and a set of solutions selected by user input as correct answer data. Then, in training the presented solution determination model using the above-mentioned training data, the learning unit 16 determines parameters of the presented solution determination model so as to minimize the error (loss) between data output by the presented solution determination model when input data is input and the correct answer data corresponding to the input data. Note that the algorithm for determining the above-mentioned parameters so as to minimize the loss may be any learning algorithm used in machine learning, such as gradient descent or backpropagation.

[0035] The presented solution determination unit 17 determines presented solutions, which are N (N is an integer equal to or greater than 1) solutions to be presented to the user in the presentation phase. In this case, the presented solution determination unit 17 determines the presented solutions based on the solutions calculated by the solution generation unit 15 and the parameter information 41. For example, if the parameter information 41 indicates a consistency weight parameter, the presented solution determination unit 17 selects N presented solutions from the multiple solutions calculated by the solution generation unit 15 based on the consistency weight parameter. In this case, for example, the presented solution determination unit 17 selects N presented solutions such that the index value of variation (e.g., variance) for an item having a larger consistency weight parameter becomes smaller. As another example, if the parameter information 41 indicates parameters of a presented solution determination model, the presented solution determination unit 17 generates multiple sets of presented solution candidates and determines a presented solution based on information output by the presented solution determination model when these are input to the presented solution determination model. Note that the number N may be stored in advance in the storage device 4 or the like, or may be determined based on user input. The presented solution determination unit 17 is an example of a "determination means."

[0036] The UI control unit 18 controls the acceptance of user input and the display of information to be viewed by the user in the learning phase and presentation phase of the learning unit 16 and the presentation solution determination unit 17, respectively. In this case, the UI control unit 18 accepts user input based on input information S1 supplied from the input device 2, and controls the display of the display device 3 by supplying display information S2 to the display device 3. Specific processing by the UI control unit 18 will be described later with reference to display examples. The UI control unit 18 is an example of a "control means" and a "presentation means."

[0037] The components of the solution generating unit 15, the learning unit 16, the presented solution determining unit 17, and the UI control unit 18 described in FIG. 3 can be realized, for example, by the processor 11 executing a program. Alternatively, the necessary programs may be recorded in any nonvolatile storage medium and installed as needed to realize the components. At least some of the components may not necessarily be realized by software programs, but may be realized by any combination of hardware, firmware, and software. At least some of the components may be realized using a user-programmable integrated circuit, such as an FPGA (Field-Programmable Gate Array) or a microcontroller. In this case, the integrated circuit may be used to realize a program consisting of the components. At least some of the components may be configured using an ASSP (Application Specific Standard Produce), an ASIC (Application Specific Integrated Circuit), or a quantum processor (quantum computer control chip). In this way, the components may be realized by various hardware. The same applies to other embodiments described later. Furthermore, the components may be realized by the cooperation of multiple computers, for example, using cloud computing technology.

[0038] (4) Processing Flow FIG. 4 is an example of a flowchart executed by the information processing device 1 in the learning phase of the first embodiment.

[0039] First, the solution generating unit 15 generates a predetermined number of solutions for the optimization problem specified by the condition information 40 (step S11). In this case, the predetermined number is set to a value greater than N. Next, the learning unit 16 determines a plurality of sets of solutions (step S12). In this case, for example, the learning unit 16 generates a predetermined number of sets each consisting of N solutions. In this case, the learning unit 16 may generate a plurality of sets based on any method.

[0040] Next, the UI control unit 18 displays the sets of solutions determined in step S12 on the display device 3 and accepts an input to select a set of solutions having a consistency that is preferable to the user from the sets of solutions (step S13). Then, when the UI control unit 18 receives input information S1 indicating the user's selection result from the input device 2, it notifies the learning unit 16 of the user's selection result.

[0041] Next, the learning unit 16 updates the parameter information 41 based on the result of the selection received in step S13 (step S14).

[0042] The learning unit 16 then determines whether or not to end the learning (step S15). For example, the learning unit 16 may make the above-mentioned determination based on whether or not step S14 has been executed a preset number of times, or may make the above-mentioned determination based on user input. If the learning unit 16 determines that the learning should be ended (step S15; Yes), it ends the processing of the flowchart. On the other hand, if the learning unit 16 determines that the learning should not be ended (step S15; No), it returns the processing to step S11. Note that the learning unit 16 may return the processing to step S12 instead of returning the processing to step S11. In this case, the learning unit 16 executes step S12 based on the solution generated in step S11 that has already been executed.

[0043] FIG. 5 is an example of a flowchart executed by the information processing device 1 in the presentation phase according to the first embodiment.

[0044] First, when an optimization problem to be solved is specified based on a user input or the like, the solution generating unit 15 generates a predetermined number of solutions for the optimization problem (step S21). In this case, the predetermined number is set to a value greater than N.

[0045] Next, the presented solution determination unit 17 determines a presented solution based on the learned parameters indicated by the parameter information 41 (step S22). For example, if the parameter information 41 indicates a consistency weight parameter, the presented solution determination unit 17 selects N presented solutions from the multiple solutions calculated by the solution generation unit 15 based on the consistency weight parameter. On the other hand, if the parameter information 41 indicates parameters of a presented solution determination model, the presented solution determination unit 17 determines a presented solution based on information output by the presented solution determination model when multiple sets of multiple solutions that are candidates for the presented solution are input to the presented solution determination model configured based on the learned parameters.

[0046] Then, the UI control unit 18 causes the display device 3 to display information about the presented solution determined by the presented solution determination unit 17 (step S23). An example of this display will be described later.

[0047] (5) Display example 6 is a display example of a solution selection screen that is a screen that the UI control unit 18 causes the display device 3 to display in step S13 of Fig. 4, which is the learning phase. The UI control unit 18 generates display information S2 for displaying the solution selection screen based on the processing results of steps S11 and S12, and transmits the generated display information S2 to the display device 3 via the interface 13, thereby causing the display device 3 to display the solution selection screen.

[0048] The solution selection screen has a candidate display table 50 (50A, 50B) that displays information about multiple candidate solutions (here, candidate A and candidate B) that are options that the user can select from. Here, each candidate indicates a set of two solutions, and each candidate display table 50 indicates the value of each solution for each item. Note that, instead of the example in FIG. 6, each candidate may indicate a set of three or more solutions, and the number of candidates may be three or more.

[0049] Furthermore, the UI control unit 18 highlights, by using a border effect, items with small variations between solutions (i.e., items with consistency) on the candidate display table 50. For example, in the case of the candidate display table 50A, the difference in value between the item a and the item b between solutions 1 and 2 is each equal to or less than a predetermined value (e.g., 10), so the UI control unit 18 surrounds the record of item a with a frame F1 and the record of item b with a frame F2. Similarly, in the case of the candidate display table 50B, the difference in value between the item b and the item c between solutions 1 and 3 is each equal to or less than a predetermined value, so the UI control unit 18 surrounds the record of item b with a frame F3 and the record of item c with a frame F4.

[0050] The candidate display tables 50 (50A, 50B) can each be selected based on a user input, and the UI control unit 18 prompts the user to select the candidate display table 50 corresponding to the set of solutions having the most consistent value for the user. When one candidate display table 50 is selected based on a click operation, a touch operation, or the like on the solution selection screen, the UI control unit 18 receives input information S1 indicating the selected candidate display table 50 from the input device 2 and supplies the selection result indicated by the input information S1 to the learning unit 16. Thereafter, if the learning phase is to be continued, the UI control unit 18 causes the display device 3 to display a solution selection screen showing new multiple solution candidates, and again accepts the selection of a set of multiple solutions having the consistency preferred by the user.

[0051] Generally, the degree to which consistency of each item is emphasized varies from user to user. Taking the above into consideration, the information processing device 1 accepts the selection of a set of multiple solutions that have a consistency preferred by the user on the solution selection screen. This allows the information processing device 1 to preferably obtain data for learning the tendency that the user values.

[0052] 7 is a display example of a solution presentation screen that the UI control unit 18 causes the display device 3 to display in step S23 of Fig. 5, which is the presentation phase. The UI control unit 18 generates display information S2 for displaying the solution presentation screen based on the processing results of steps S21 and S22, and transmits the generated display information S2 to the display device 3 via the interface 13, thereby causing the display device 3 to display the solution presentation screen.

[0053] The UI control unit 18 displays a proposed solution table 53 showing details of each item of the proposed solutions (solution X, solution Y, solution Z, . . . ) determined in step S22 on the solution presentation screen.

[0054] Furthermore, the UI control unit 18 highlights items for which consistency is emphasized using a border effect on the presented solution table 53. Here, the UI control unit 18 surrounds items b and d, for which the variability index in the presented solution is equal to or less than a predetermined value, with frames F5 and F6, respectively. Note that the UI control unit 18 may determine the above-mentioned predetermined value, the number of items to be highlighted, the highlighting mode (including the thickness of the frame, whether or not to change the background color, etc.), etc., based on setting information generated based on user input.

[0055] The proposed solutions displayed in the proposed solution table 53 are combinations that take into consideration the tendency of the set of solutions selected by the user in the learning phase (i.e., the tendency of consistency that the user values). Therefore, the UI control unit 18 can prevent a cumbersome display of a large number of solutions and effectively display solutions that are important to the user.

[0056] (6) Variations The information processing device 1 may accept a user input specifying a change in the constraint conditions, and display a transition history of the solution to the optimization problem based on the changed constraint conditions (also referred to as a "solution transition history").

[0057] In this modification, the UI control unit 18 accepts the selection of an arbitrary solution based on user input on a solution presentation screen or the like, and causes the display device 3 to display a screen for changing the constraint conditions of the selected solution (also referred to as a "constraint condition change screen"). In this case, for example, the UI control unit 18 refers to the condition information 40 and displays a list of changeable constraint conditions on the constraint condition change screen. For example, in the above-mentioned list, the current setting contents (e.g., ranges, numerical values, etc.) of the corresponding constraint conditions are displayed in any format such as gauges, pull-down menus, text entry fields, check boxes, etc., and the setting contents can be changed based on user input.

[0058] Then, when the UI control unit 18 detects that input on the constraint condition change screen has been completed by pressing a predetermined button or the like, it supplies input information S1 indicating the constraint condition settings on the constraint condition change screen to the solution generation unit 15, and the solution generation unit 15 calculates a solution based on the constraint condition indicated by the input information S1. Then, the UI control unit 18 stores the constraint condition settings indicated by the input information S1 and the solution calculated by the solution generation unit 15 in the storage device 4 or the like as a solution transition history based on the changed constraint condition.

[0059] Fig. 8 shows the transition of a solution based on a change in a constraint condition. Fig. 9 shows an example of a solution transition history screen displayed based on the solution transition history generated by the change in a constraint condition shown in Fig. 8.

[0060] As shown in Fig. 8, first, the UI control unit 18 detects a first user input instructing a change to the constraint conditions used in calculating solution A, and the solution generation unit 15 calculates solution B using the constraint conditions changed based on the first user input. Furthermore, the UI control unit 18 detects a second user input instructing a change to the constraint conditions used in calculating solution B, and the solution generation unit 15 calculates solution C using the constraint conditions changed based on the second user input. Then, the UI control unit 18 detects a user input instructing a display of the solution transition history, and displays the solution transition history screen shown in Fig. 9 on the display device 3. In this case, the UI control unit 18 generates display information S2 for displaying the solution transition history screen, and transmits the generated display information S2 to the display device 3 via the interface 13, thereby causing the display device 3 to display the solution transition history screen.

[0061] The UI control unit 18 provides a solution transition table 60, a constraint change button 61, a bar graph display button 62, and a line graph display button 63 on the solution transition history screen. The UI control unit 18 displays, on the solution transition table 60, the values ​​of each item of each solution calculated in response to a constraint change based on the solution transition history, arranged in the chronological order in which each solution was calculated. Furthermore, in the solution transition table 60, arrows are used to associate the date and time when a constraint change occurred, the solution before the change, and the solution after the change. When an arrow is selected, the UI control unit 18 may display the change details of the constraint corresponding to the arrow.

[0062] Furthermore, when the UI control unit 18 detects that the constraint change button 61 has been selected, it causes the display device 3 to display a constraint change screen for displaying and changing the setting contents of the constraints of the latest solution (here, solution C). Furthermore, when the UI control unit 18 detects that the bar graph display button 62 has been selected, it causes the display device 3 to display a screen that displays the contents of the solution transition table 60 as a bar graph. Furthermore, when the UI control unit 18 detects that the line graph display button 63 has been selected, it causes the display device 3 to display a screen that displays the contents of the solution transition table 60 as a line graph.

[0063] In this way, the information processing device 1 according to this modification can accept changes to the constraint conditions and can suitably present to the user the transition of the solution based on the changed constraint conditions.

[0064] Second Embodiment Fig. 10 shows the configuration of an optimization system 100A in the second embodiment. As shown in Fig. 10, the optimization system 100A mainly includes an information processing device 1A, a storage device 4, and a terminal device 5. The information processing device 1A and the terminal device 5 perform data communication via a network 6.

[0065] The information processing device 1A performs processing related to optimization. In this case, the information processing device 1A receives input information S1, which the information processing device 1 receives from the input device 2 in the first embodiment, from the terminal device 5 via the network 6. The information processing device 1A also transmits display information S2, which the information processing device 1 transmitted to the display device 3 in the first embodiment, to the terminal device 5 via the network 6. In this way, the information processing device 1A according to the second embodiment functions as a server device.

[0066] The terminal device 5 is a terminal having an input function, a display function, and a communication function, and functions as the input device 2 and the display device 3 in the first embodiment. The terminal device 5 may be, for example, a personal computer, a tablet terminal, a PDA (Personal Digital Assistant), or the like. The terminal device 5 transmits input information S1 generated based on a received user input to the information processing device 1A via the network 6. Furthermore, when the terminal device 5 receives display information S2 from the information processing device 1A, it displays various screens based on the display information S2.

[0067] The information processing device 1A according to the second embodiment can preferably execute the input process and display process executed by the information processing device 1 in the first embodiment for the user of the terminal device 5.

[0068] <Third embodiment> 11 is a functional block diagram of a learning device 1X in the third embodiment. The learning device 1X mainly includes a solution generating means 15X and a learning means 16X. The learning device 1X may be made up of multiple devices.

[0069] The solution generating means 15X generates a solution to the optimization problem. The solution generating means 15X can be, for example, the solution generating unit 15 in the first or second embodiment.

[0070] The learning means 16X generates a plurality of sets of solutions, and learns parameters related to consistency among the presented solutions, which are a plurality of solutions to be presented to the person who made the external input, based on a set selected from the plurality of sets by an external input. The learning means 16X can be, for example, the learning unit 16 in the first or second embodiment.

[0071] 12 is an example of a flowchart executed by the learning device 1X in the third embodiment. First, the solution generating means 15X generates a solution to the optimization problem (step S31). The learning means 16X generates a plurality of sets of solutions (step S32). Then, based on a set selected from the plurality of sets by external input, the learning means 16X learns parameters related to consistency among the presented solutions, which are a plurality of solutions to be presented to the person who made the external input (step S33).

[0072] The learning device 1X according to the third embodiment can suitably learn parameters for determining presented solutions that have consistency that is preferred by the user.

[0073] In addition, part or all of the above-described embodiments (including modified examples, the same applies below) can be described as, but are not limited to, the following supplementary notes.

[0074] [Appendix 1] a solution generating means for generating a solution to an optimization problem; a learning means for generating a plurality of sets of solutions, and learning a parameter relating to consistency among presented solutions, which are a plurality of solutions to be presented to a person who has made the external input, based on the set selected from the plurality of sets by an external input; A learning device having the above configuration. [Appendix 2] The solution is associated with an item for evaluating the solution; 2. The learning device according to claim 1, wherein the parameter is information that determines the degree of consistency of the presented solution for each item. [Appendix 3] 3. The learning device according to claim 1, further comprising a control means for displaying the plurality of sets on a display device and receiving the external input for selecting an arbitrary set from the plurality of sets. [Appendix 4] The learning device described in Appendix 3, wherein the control means displays the solution value for each item in each of the multiple sets, and determines the item to emphasize based on the variation in the solution value for each item. [Appendix 5] a solution generating means for generating a solution to an optimization problem; A determination means for determining a solution to be presented from the plurality of solutions based on the plurality of solutions generated by the solution generating means and parameters learned by the learning device described in any one of Supplementary Notes 1 to 4; a presentation means for presenting the proposed solution; A presentation device having the [Appendix 6] The presentation device according to claim 5, wherein the presentation means presents the value of the presented solution for each item and determines the item to be emphasized based on the variation in the value of the presented solution for each item. [Appendix 7] the solution generating means, when receiving a change in a constraint condition specifying any of the presented solutions, generates the solution based on the changed constraint condition; 7. The presentation device according to claim 5, wherein the presentation means presents a transition of the solution generated by the solution generating means based on a change in the constraint condition. [Appendix 8] The computer Generate solutions to optimization problems, generating a plurality of sets of solutions, and learning a parameter related to consistency among presented solutions, which are a plurality of solutions to be presented to the person who provided the external input, based on the set selected from the plurality of sets by an external input; How to learn. [Appendix 9] Generate solutions to optimization problems, A storage medium storing a program that causes a computer to execute a process of generating multiple sets of solutions and, based on a set selected from the multiple sets by external input, learning parameters related to consistency among the presented solutions, which are multiple solutions to be presented to the person who made the external input.

[0075] In each of the above-described embodiments, the program can be stored using various types of non-transitory computer-readable media and supplied to a computer processor or the like. Non-transitory computer-readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic storage media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical storage 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 may 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 medium 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.

[0076] Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above embodiments. Various modifications within the scope of the present invention that would be understood by those skilled in the art can be made to the configuration and details of the present invention. In other words, the present invention naturally includes various modifications and alterations that would be possible for those skilled in the art based on the entire disclosure, including the claims, and the technical ideas. Furthermore, the disclosures of the above-cited patent documents and other documents are incorporated herein by reference. [Explanation of symbols]

[0077] 1, 1A Information processing equipment 1X Learning Device 2 Input devices 3 Display device 4 Storage device 5 Terminal Devices 100, 100A Optimized System

Claims

1. a solution generating means for generating a solution to an optimization problem and values ​​of a plurality of items for evaluating said solution; a learning means for generating a plurality of sets of solutions, and for learning a parameter that determines the degree of variation in the value for each of the items in presented solutions, which are a plurality of solutions to be presented to a person who performed the external input, based on an index of variation in the value for each of the items in the set selected from the plurality of sets by an external input; A learning device having the above configuration.

2. 2. The learning device according to claim 1, further comprising control means for displaying the plurality of sets on a display device and receiving the external input for selecting an arbitrary set from the plurality of sets.

3. 3. The learning device according to claim 2, wherein the control means displays the value for each item in each of the plurality of sets, and determines the item to be emphasized based on a variation in the value for each item.

4. a solution generating means for generating a solution to an optimization problem; a determination means for determining a solution to be presented from the plurality of solutions based on the plurality of solutions generated by the solution generation means and parameters learned by the learning device according to any one of claims 1 to 3; a presentation means for presenting the proposed solution; A presentation device having the

5. The presentation device according to claim 4 , wherein the presentation means presents a value for evaluating the presented solution for each item, and determines the item to be emphasized based on a variation in the value for each item.

6. the solution generating means, when receiving a change in a constraint condition specifying any of the presented solutions, generates the solution based on the changed constraint condition; The presentation device according to claim 4 , wherein the presentation means presents a transition of the solution generated by the solution generating means based on a change in the constraint condition.

7. The computer generating a solution to the optimization problem and values ​​of a plurality of terms for evaluating said solution; generating a plurality of sets of solutions, and based on an index of variation in the values ​​for each of the items in the set selected from the plurality of sets by external input, learning a parameter that determines the degree of variation in the values ​​for each of the items in presented solutions, which are a plurality of solutions to be presented to the person who performed the external input; How to learn.

8. generating a solution to the optimization problem and values ​​of a plurality of terms for evaluating said solution; A program that causes a computer to execute a process of generating multiple sets of solutions, and based on an index of the variation in values ​​for each item of a set selected from the multiple sets by external input, learning a parameter that determines the degree of variation in values ​​for each item in presented solutions, which are multiple solutions that are presented to a person who made the external input.

Images