Learning device, presentation device, learning method, and program
Patent Information
- Application Number
- JP2024510858
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2022-03-30
- Filing Date
- 2022-03-30
- Publication Date
- 2024-11-14
- Estimated Expiration
- 2042-03-30
AI Technical Summary
Users face challenges in comparing and selecting optimal solutions to optimization problems, as existing systems primarily focus on generating a single solution without providing variations or user-preferred options.
A learning device and method that generate multiple sets of solutions to an optimization problem, allowing users to select preferred solutions, and a presentation system that learns from user inputs to determine the best output based on machine learning models, such as neural networks, to present solutions with variations.
Enables users to compare and select solutions that align with their preferences, improving the decision-making process by presenting multiple solution sets and learning from user feedback to minimize errors in solution determination.
Abstract
Description
Learning device, presentation device, learning method, and storage medium
[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.
[0002] Systems for calculating solutions to optimization problems have been known for some time. For example, Patent Literature 1 discloses a technology for evaluating optimization results based on multiple indicators. Patent Literature 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. Patent Literature 3 discloses a system that optimizes business scheduling taking multiple indicators into consideration.
[0003] International Publication WO2013 / 179577 International Publication WO2021 / 001977 International Publication WO2021 / 059506
[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 variations that users prefer, and that presents solutions based on the learning results.
[0006] One aspect of the learning device is a learning device having: a solution generating means for generating a solution to an optimization problem; and a learning means for generating a plurality of sets of the solutions and learning a model for determining the set of solutions to be output based on a set selected from the plurality of sets by an external input.
[0007] One aspect of the learning method is a learning method in which a computer generates solutions to an optimization problem, generates multiple sets of the solutions, and learns a model that determines the set of solutions to be output based on a set selected from the multiple sets by an external input.
[0008] One aspect of the storage medium is a storage medium that stores a program that causes a computer to execute a process of generating solutions to an optimization problem, generating multiple sets of the solutions, and learning a model that determines the set of solutions to be output based on a set selected from the multiple sets by an external input.
[0009] It can learn to present multiple solutions with variations that the user likes.
[0010] 1 shows the configuration of an optimization system in a first embodiment; FIG. 2 shows the hardware configuration of an information processing device; FIG. 3 is an example of a functional block in the first embodiment; FIG. 4 is an example of a flowchart of the learning phase in the first embodiment; FIG. 5 is an example of a flowchart of the presentation phase in the first embodiment; FIG. 6 is a display example of a solution selection screen; FIG. 7 is a display example of a solution presentation screen; FIG. 8 is a display example of a ranking screen; FIG. 9 shows the configuration of an optimization system in a second embodiment; FIG. 10 is a functional block diagram of a learning device in a third embodiment; FIG. 11 is an example of a flowchart showing the processing procedure of the learning device in the third embodiment.
[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] 1 shows the configuration of an optimization system 100 according to the first embodiment. The optimization system 100 mainly includes 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 multiple solutions for the specified optimization problem and presents the multiple solutions (which may be transition sequences of solutions; the same applies below). In this case, when presenting the multiple solutions, the information processing device 1 performs learning so that it can present multiple solutions having variations that a user using the optimization system 100 values. Hereinafter, the stage (phase) in which learning is performed to present multiple solutions having variations 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 a combination of sellers and buyers of traded goods (and a 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 corresponds to, 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 about the problem settings) about 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 of a model (also referred to as a "presented solution determination model") that determines multiple solutions (also referred to as "presented solutions") to be presented to a user. The presented solution determination model is, for example, a learning model that is trained to output information indicating a set of multiple solutions to be used as the presented solution when multiple sets of solutions that are candidates for the presented solution are input. The presented 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 presented 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 filter 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.
[0021] 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.
[0022] 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.
[0023] (2) Hardware Configuration of Information Processing Device Fig. 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.
[0024] The processor 11 executes predetermined processes by executing programs 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.
[0025] The memory 12 is composed of various types of volatile and non-volatile memories, such as RAM (Random Access Memory) and 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 obtained from the storage device 4. The memory 12 may also function as the storage device 4. Similarly, the storage device 4 may also 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.
[0026] 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.
[0027] 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. The information processing device 1 may also be connected to or have a built-in sound output device such as a speaker.
[0028] (3) Functional Blocks Fig. 3 shows an example of functional blocks of the processor 11 in the first embodiment. Functionally, the processor 11 includes a solution generation unit 15, a learning unit 16, a presented solution determination unit 17, and a UI (User Interface) control unit 18. Note that in Fig. 3, blocks between which data is exchanged are connected by solid lines, but the combination of blocks between which data is exchanged is not limited to that shown in Fig. 3. The same applies to other functional block diagrams described later.
[0029] 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.
[0030] 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 treats 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, Gurobii Optimizer, SCIP). A method of formulating the integer programming problem to determine sellers, buyers, ships to be used, and the voyage period of the ships is disclosed, for example, in Patent Document 2.
[0031] The learning unit 16 updates the parameter information 41 during the learning phase. In this case, the learning unit 16 generates multiple sets of solutions (i.e., generates multiple candidate presented solutions) based on the calculation results of the solution generation unit 15 and presents them to the user in a selectable manner. In this case, the learning unit 16 generates multiple sets of solutions, for example, by randomly sampling from the solutions calculated by the solution generation unit 15. The learning unit 16 then considers a set of solutions selected by user input from the presented sets of solutions as a correct solution (i.e., a set of solutions having variations preferred by the user). As a result, the learning unit 16 generates training data for a presented solution determination model using the multiple sets of solutions presented to the user as options as input data and the set of solutions selected by user input as correct answer data. In training the presented solution determination model using the above-described training data, the learning unit 16 determines parameters of the presented solution determination model so as to minimize the error (loss) between the data output by the presented solution determination model when input data is input and the correct answer data corresponding to the input data. The algorithm for determining the above parameters so as to minimize the loss may be any learning algorithm used in machine learning, such as gradient descent or backpropagation.
[0032] The presented solution determination unit 17 determines presented solutions, which are N (N is an integer equal to or greater than 2) 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 a presented solution determination model to which parameters indicated by the parameter information 41 are applied. In this case, for example, the presented solution determination unit 17 generates multiple sets of presented solution candidates and determines the presented solutions based on information output by the presented solution determination model when these are input into 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."
[0033] 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."
[0034] The components of the solution generation unit 15, the learning unit 16, the presented solution determination 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 on any non-volatile storage medium and installed as needed to realize each component. At least some of these 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 these 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 above components. Furthermore, at least a portion of each component may be configured by an ASSP (Application Specific Standard Product), an ASIC (Application Specific Integrated Circuit), or a quantum processor (quantum computer control chip). In this way, each component may be realized by various hardware. The same applies to other embodiments described below. Furthermore, each of these components may be realized by the cooperation of multiple computers, for example, using cloud computing technology.
[0035] (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.
[0036] 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 multiple sets of multiple 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 multiple sets based on any method.
[0037] 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 variation that is preferred by 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.
[0038] Next, the learning unit 16 updates the parameter information 41 based on the result of the selection received in step S13 (step S14). In this case, for example, the learning unit 16 regards the selected set of multiple solutions as correct data for the presented solution, and determines parameters of the presented solution determination model that minimize the error between the output result of the presented solution determination model and the correct data.
[0039] The learning unit 16 then determines whether or not to terminate 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 terminated (step S15; Yes), the processing of the flowchart ends. On the other hand, if the learning unit 16 determines that the learning should not be terminated (step S15; No), the processing returns to step S11. Note that the learning unit 16 may return to step S12 instead of returning 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.
[0040] FIG. 5 is an example of a flowchart executed by the information processing device 1 in the presentation phase according to the first embodiment.
[0041] 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 to the optimization problem (step S21). In this case, the predetermined number is set to a value greater than N.
[0042] Next, the presented solution determination unit 17 determines a presented solution based on the learned parameters indicated by the parameter information 41 (step S22). In this case, the presented solution determination unit 17 determines a presented solution based on information output from a presented solution determination model configured based on the learned parameters when multiple sets of solutions that are candidates for the presented solution are input to the presented solution determination model.
[0043] Then, the UI control unit 18 causes the display device 3 to display information about the presented solutions determined by the presented solution determination unit 17 (step S23). In this case, the UI control unit 18 may highlight differences between the multiple solutions or display a ranking of the solutions for each item, which is an index for evaluating the solutions. Examples of this display will be described later.
[0044] 6 shows a display example of a solution selection screen that the UI control unit 18 displays on the display device 3 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.
[0045] The solution selection screen has candidate display fields 50 (50A-50C) that display information about multiple candidate solutions (here, candidate A-candidate C) that the user can select from. Here, each candidate shows a set of three solutions, and each candidate display field 50 has a solution display field 51 corresponding to the respective solution. Each solution has an identification name (solution 1, solution 2, ...) that is a serial number assigned in descending order of the value of the objective function used to optimize the optimization problem (objective function value). Here, as an example, it is assumed that the larger the objective function value, the more preferable it is.
[0046] Each solution display field 51 displays the identification name of the corresponding solution, the objective function value, and the values of each item. Each solution display field 51 also has a details button for displaying detailed information about the corresponding solution. Here, the items (item a, item b, ...) are indices in the optimization problem, and may be indices used in the objective function or constraint formula, or may be the variables themselves to be found as a solution.
[0047] Each of the candidate display fields 50 (50A to 50C) is selectable based on user input, and the UI control unit 18 prompts the user to select the candidate display field 50 corresponding to the set of solutions having the most desirable variation for the user. When one candidate display field 50 is selected based on a click operation, touch operation, or the like on the solution selection screen, the UI control unit 18 receives input information S1 indicating the selected candidate display field 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 accepts the selection of a set of multiple solutions having the most desirable variation for the user.
[0048] Generally, what is emphasized varies from user to user, with some users prioritizing diversity and others prioritizing that a particular item is within a predetermined value range. Taking this into consideration, the information processing device 1 accepts the selection of a set of multiple solutions with variations preferred by the user on the solution selection screen. This allows the information processing device 1 to suitably obtain data for learning the user's tendency to prioritize.
[0049] 7 is a display example of a solution presentation screen that the UI control unit 18 displays on the display device 3 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.
[0050] The UI control unit 18 displays a proposed solution table 53 on the solution presentation screen, which shows details of each item of the proposed solutions (solution X, solution Y, solution Z, ...) determined in step S22. The proposed solution table 53 has a record for each solution, and each record has a details button 54 for checking detailed information about the corresponding solution.
[0051] Furthermore, the UI control unit 18 highlights items in the presented solution table 53 that show significant differences. Here, the UI control unit 18 highlights the top two items (item a and item c) with the largest variance (i.e., variation) in the presented solutions using a border effect. Specifically, the UI control unit 18 surrounds item a, which has the largest variance in the presented solutions, with a thick frame, and surrounds item c, which has the second largest variance in the presented solutions, with a thin frame. Note that the UI control unit 18 may determine the number of items to highlight, the highlighting style (including the thickness of the frame, whether or not to change the background color, etc.), and the like, based on setting information generated based on user input.
[0052] The proposed solutions displayed in the proposed solution table 53 are combinations that take into consideration the tendency of the sets of solutions selected by the user in the learning phase (i.e., the tendency of the variations 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.
[0053] Furthermore, the UI control unit 18 displays an item-by-item ranking display button 55 on the solution presentation screen, and when it detects that the item-by-item ranking display button 55 has been selected, it causes a screen (also referred to as a "ranking screen") displaying the ranking of the presented solutions for each item to be displayed on the display device 3. In this case, preferably, each item in the presented solution table 53 is selectable, and the UI control unit 18 may generate a ranking screen showing a ranking of the items that were selected on the presented solution table 53 at the time the item-by-item ranking display button 55 was selected.
[0054] 8 shows an example of the display of the ranking screen. For example, when the UI control unit 18 detects that the item-by-item ranking display button 55 has been selected on the solution presentation screen, the UI control unit 18 transmits display information S2 to the display device 3 via the interface 13, thereby causing the display device 3 to display the ranking screen.
[0055] The UI control unit 18 displays a ranking table 56 on the ranking screen, which shows the ranking of the presented solutions for each item. For example, the ranking for item a is in the order of solution X, solution Y, and solution Z. Here, the ranking for each item may be determined based on whether the target item is close to a predetermined optimal value (which may be within a range; the same applies below), or may be determined by further considering the objective function value of the solution in addition to the closeness to the optimal value. In the latter case, the weighting values for the closeness to the optimal value and the objective function value can be specified by, for example, the user, and the setting value specified by the user input is stored in advance in the storage device 4, etc.
[0056] In this way, the UI control unit 18 displays the ranking screen, allowing the user to easily grasp the preferred solution for each item.
[0057] Second Embodiment Fig. 9 shows the configuration of an optimization system 100A in the second embodiment. As shown in Fig. 9, 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.
[0058] 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.
[0059] 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 accepted 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.
[0060] 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 .
[0061] 10 is a functional block diagram of a learning device 1X according to a third embodiment. The learning device 1X mainly includes a solution generating unit 15X and a learning unit 16X. The learning device 1X may be composed of multiple devices.
[0062] 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.
[0063] The learning means 16X generates a plurality of sets of solutions and learns a model that determines a set of solutions to be output 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.
[0064] 11 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, the learning means 16X learns a model that determines a set of solutions to be output based on a set selected from the plurality of sets by an external input (step S33).
[0065] When learning a model that determines a set of solutions, the learning device 1X according to the third embodiment can learn the model so as to determine a set of solutions that matches the preferences of the user.
[0066] 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.
[0067] [Supplementary Note 1] A learning device comprising: solution generation means for generating a solution to an optimization problem; and learning means for generating a plurality of sets of solutions and learning a model for determining the set of solutions to be output based on a set selected from the plurality of sets by an external input. [Supplementary Note 2] The learning device according to Supplementary Note 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. [Supplementary Note 3] The learning device according to Supplementary Note 1 or 2, wherein the learning means repeatedly generates the plurality of sets and selects from the plurality of sets, and updates parameters of the model based on each of the sets obtained by the selection. [Supplementary Note 4] The learning device according to any one of Supplements 1 to 3, wherein the model is a learning model that is trained to output information indicating a set of solutions to be presented from the plurality of sets when a plurality of sets of solutions are input. [Supplementary Note 5] The learning device according to any one of Supplements 1 to 4, wherein the set of solutions is presented to a person who provided the external input. [Supplementary Note 6] A presentation device comprising: solution generation means for generating a solution to an optimization problem; determination means for determining a set of solutions based on a plurality of solutions generated by the solution generation means and a model trained by the learning device described in any one of Supplements 1 to 5; and presentation means for presenting the set of solutions. [Supplementary Note 7] The presentation device described in Supplementary Note 6, wherein the presentation means presents a table showing values of each solution in the set of solutions for each item. [Supplementary Note 8] The presentation device described in Supplementary Note 7, wherein the presentation means determines an item to be highlighted in the table based on a variation in the value of each solution for each item. [Supplementary Note 9] The presentation device described in any one of Supplements 6 to 8, wherein the presentation means presents a ranking of the set of solutions for each item. [Supplementary Note 10] A learning method, wherein a computer: generates a solution to an optimization problem; generates a plurality of sets of solutions; and learns a model that determines the set of solutions to be output based on a set selected from the plurality of sets by external input. [Supplementary Note 11] A storage medium storing a program that causes a computer to execute a process of generating solutions to an optimization problem, generating a plurality of sets of the solutions, and learning a model that determines the set of solutions to be output based on a set selected from the plurality of sets by an external input.
[0068] 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, etc. 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, semiconductor memories (e.g., mask ROMs, programmable ROMs (PROMs), erasable PROMs (EPROMs), flash ROMs, and random access memories (RAMs). The program may also be supplied to a computer by various types of transient computer-readable media. Examples of transient computer-readable media include electric signals, optical signals, and electromagnetic waves. The transient 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.
[0069] 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.
[0070] 1, 1A Information processing device 1X Learning device 2 Input device 3 Display device 4 Storage device 5 Terminal device 100, 100A Optimization system
Claims
1. A solution generating means for generating a solution to an optimization problem; a learning means for generating a plurality of sets of the solutions and learning a model for determining the set of the solutions to be output based on 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 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.
3. 3 . The learning device according to claim 1 , wherein the learning means repeatedly generates the plurality of sets and selects from the plurality of sets, and updates parameters of the model based on each of the sets obtained by the selection.
4. The learning device according to any one of claims 1 to 3, wherein the model is a learning model that is trained to output information indicating a solution set to be presented from the multiple solution sets when multiple solution sets are input.
5. 5. The learning device according to claim 1, wherein the set of solutions is presented to a person who has performed the external input.
6. A solution generating means for generating a solution to an optimization problem; A determination means for determining the set of solutions based on a plurality of solutions generated by the solution generating means and a model trained by the learning device according to any one of claims 1 to 5; a presentation means for presenting the set of solutions; A presentation device having the above configuration.
7. The presentation device according to claim 6 , wherein the presentation means presents a table showing values of each solution of the set of solutions for each item.
8. The presentation device according to claim 7 , wherein the presentation means determines which items to highlight in the table based on a variance in the values of the solutions for each of the items.
9. The computer Generate a solution to the optimization problem, generating a plurality of sets of said solutions; learning a model that determines the set of solutions to be output based on the set selected from the plurality of sets by an external input; How to learn.
10. Generate a solution to the optimization problem, generating a plurality of sets of said solutions; A program that causes a computer to execute a process of learning a model that determines the set of solutions to be output based on the set selected from the plurality of sets by an external input.
