Information processing device, control system, information processing method, and recording medium

Abstract

This information processing device comprises a generation means for generating training data for a learning model for solving a combinatorial optimization problem, said training data having a graph structure which includes nodes and edges.

Description

Information processing device, control system, information processing method, and recording medium

[0001] This disclosure relates to an information processing device, a control system, an information processing method, and a recording medium.

[0002] Numerous combinatorial optimization problems are known, such as the traveling salesperson problem and the knapsack problem. Combinatorial optimization problems are often solved using solvers. However, this method tends to have a huge processing load, especially when the problem is large. In contrast, Patent Document 1 discloses a method for calculating the predicted cost between two nodes selected from a plurality of nodes, based on graph information relating to a connected graph consisting of a plurality of nodes corresponding to points on a map, edges connecting the nodes, and costs attached to each edge. This method involves obtaining the actual cost between two points on the map corresponding to the two selected nodes, generating a learning model that learns the relationship between the predicted cost and the actual cost, and calculating the cost between any two points on the map based on the generated learning model. Furthermore, Patent Document 1 discloses a method for reducing the processing load by using this learning model to determine the travel cost between two points in the traveling salesperson problem.

[0003] By the way, building a learning model using machine learning or deep learning requires a large amount of training data (a set of problems and solutions), but collecting the kind of training data needed for combinatorial optimization problems incurs human, economic, and time costs. For example, the training data for the Traveling Salesperson Problem requires maps, traffic information, delivery records, and so on.

[0004] Japanese Patent Publication No. 2020-046894

[0005] One of the objectives of this disclosure is to provide a method for generating training data necessary for constructing a learning model to solve combinatorial optimization problems.

[0006] According to one aspect of this disclosure, the information processing apparatus comprises a generation means for generating training data for a learning model to solve a combinatorial optimization problem, the training data having a graph structure including nodes and edges.

[0007] According to one aspect of the present disclosure, the above-mentioned information processing device further comprises: learning means for learning the learning data using a deep learning model and constructing the learning model which serves as a solver for solving the combinatorial optimization problem; and a control system comprising: planning means for planning the patrol route of a mobile body based on the learning model; and means for controlling the mobile body based on the planned route.

[0008] According to one aspect of this disclosure, the computer generates training data for a learning model to solve a combinatorial optimization problem, the training data having a graph structure including nodes and edges.

[0009] According to one aspect of the present disclosure, the present invention relates to a recording medium that stores a program causing a computer to perform a process to generate training data for a learning model for solving a combinatorial optimization problem, the training data having a graph structure including nodes and edges.

[0010] According to this disclosure, it is possible to generate training data necessary for constructing a learning model for solving combinatorial optimization problems.

[0011] This is a block diagram showing an example of a solver creation device according to the first embodiment. This is a flowchart showing an example of a method for constructing a learning model according to the first embodiment. This is a diagram showing an example of a combinatorial optimization problem to which the first embodiment can be applied. This is a diagram showing an overview of the learning model construction process according to the first embodiment. This is a diagram illustrating an example of application to a delivery control system according to the first embodiment. This is a block diagram showing an example of an information processing device according to the second embodiment. This is a flowchart showing an example of an information processing method according to the second embodiment. This is a diagram showing an example of the hardware configuration of the device according to each embodiment.

[0012] The training data generation method and training model construction method of this disclosure will be described below with reference to the drawings. In the drawings used in the following description, components of parts not related to this disclosure may be omitted from the description and may not be shown. In all drawings, the same reference numerals are used for identical or equivalent components, and common descriptions may be omitted.

[0013] <First Embodiment> (Configuration) Figure 1 is a block diagram showing an example of a solver creation device according to the first embodiment. The solver creation device 10 generates training data necessary for constructing a learning model for solving combinatorial optimization problems, and uses a deep learning model to learn the generated training data and construct a learning model (solver) that can solve combinatorial optimization problems. In this disclosure, this learning model is also referred to as a neural solver. Examples of combinatorial optimization problems include TSP (traveling salesman problem), VRP (Vehicle Routing Problem), FSSP (flow shop scheduling problem), JSSP (Job shop Scheduling Problem), and FairDivision. The functions of the solver creation device 10 will be explained below using the case of TSP as an example.

[0014] The solver creation device 10 comprises a learning data generation unit 11, a learning unit 12, and an output unit 13.

[0015] The learning data generation unit 11 generates learning data. The learning data for TSP consists of the coordinates of each point and the travel cost between points (distance and time required for travel). Travel costs have properties such as being symmetric or asymmetric, and satisfying (metric) or not satisfying (non-metric) the triangle inequality. The travel costs between point A and point B are symmetric if the travel cost when moving from point A to point B is equal to the travel cost when moving from point B to point A, and asymmetric if these travel costs do not match. Metric means that, considering points A to C, the sum of the travel cost from point A to point B and the travel cost from point B to point C is greater than the travel cost from point A to point C, and non-metric means that this relationship does not hold. In the real world, travel costs between points are generally asymmetric and metric. In order to generate training data (coordinates and travel costs) that are asymmetric and satisfy the properties of a metric, it is often done by "randomly generating coordinates and travel costs between multiple points and modifying the travel costs to satisfy the properties of asymmetry and a metric." However, in this method, if the number of points is n, the computational complexity required is n cubed, and as the number of points n increases, it becomes impractical to generate training data in this way. In contrast, in this embodiment, training data (coordinates and travel costs) is generated in the following steps 1 to 5.

[0016] [Method for generating training data] (Step 1) Generate symmetric and metric travel costs. For example, determine the coordinates of multiple points by generating random numbers, and calculate the distance between any two of the multiple points. The travel cost between point i and point j is S. ｉｊ Then, normalize the data so that the maximum value of the movement cost is 1.

[0017] (Step 2) Determine an arbitrary value for γ from the range 0 < γ ≤ 1 / 2.

[0018] (Step 3) For each movement cost, a value is randomly selected from the range of the uniform distribution U[γ, 2γ] and designated as the asymmetric component. The asymmetric component between point i and point j is A. ｉｊ Let's assume that we obtain an asymmetric component for each movement cost.

[0019] (Step 4) Add the components of (Step 1) and (Step 3) for each movement cost. For example, let the movement cost from point i to point j be S ｉｊ + A ｉｊ . For the movement cost from point j to point i, it may be S ｉｊ , or another asymmetric component A ｊｉ may be calculated in Step 3, and it may be S ｉｊ + A ｊｉ .

[0020] (Step 5) Normalize each movement cost. For example, let the movement cost from point i to point j be (S ｉｊ + A ｉｊ ) ÷ (1 + 2γ).

[0021] By repeating Steps 1 to 5 as necessary, learning data can be efficiently generated with a computational complexity of about the square of the number of points n. Specifically, for each of the n points, only the process of calculating the movement costs between one point and the other n - 1 points needs to be performed, and an asymmetric and metric movement cost can be generated without checking and correcting whether each movement cost is a metric. Although omitted in this disclosure, it has been proven by the inventor that the movement costs generated by the method of Steps 1 to 5 are metrics.

[0022] The learning unit 12 learns from the learning data generation unit 11 and constructs a learning model (neural solver) capable of solving combinatorial optimization problems (e.g., TSP). A deep learning model such as a transformer can be used for learning. A transformer is a neural network architecture used in LLMs (Large-Scale Language Models). By providing the transformer with learning data and instructing it to learn a route (a way to traverse n locations) that minimizes the objective function, for example, the travel cost when visiting all locations once, the transformer constructs a learning model that searches for such a route, that is, a learning model (neural solver) capable of solving TSP. By using a transformer, there is no need to include ground truth data in the learning data; the Transformer itself searches for the correct route by simply providing location information (locations and travel costs). This eliminates the need to prepare ground truth data (paths with the minimum cost) as learning data, and furthermore, since location information can be generated using the methods described in steps 1 to 5 above, the processing load required for generating learning data can be reduced. It is already known that a learning model for finding solutions can be obtained by applying a transformer to a TSP or similar. The learning unit 12 stores the constructed learning model.

[0023] The output unit 13 outputs the learning model constructed by the learning unit 12 to other devices. The learning model, constructed by learning artificially generated learning data by the learning data generation unit 11, can be used in a general-purpose manner. For example, if domestic map information is provided to a learning model constructed for TSP and any point is specified, the learning model will output the route that visits the specified point at the lowest cost.

[0024] (Operation) Figure 2 is a flowchart illustrating an example of a method for constructing a learning model according to the first embodiment. The learning data generation unit 11 generates learning data (coordinates of multiple locations and travel costs between each location) by executing the processes of steps 1 to 5 described above (step S11). The learning data generation unit 11 outputs the generated learning data to the learning unit 12. Next, the learning unit 12 constructs a learning model (neural solver) (step S12). The user sets the objective function to the learning unit 12 and instructs it to learn the learning data and construct a learning model that optimizes the objective function. The learning unit 12 constructs a learning model that uses a transformer to find the lowest cost route to visit each location. Next, the output unit 13 outputs the learning model constructed in step S12 to another device (step S13). Other devices include, for example, a device that performs delivery planning.

[0025] Figure 3 shows an example of a combinatorial optimization problem to which the data generation method and learning model construction method according to this embodiment can be applied. Item 1 in the table in Figure 3 is TSP and VRP. This is as explained using Figures 1 and 2. A large amount of asymmetric metric data is generated, with the points to be visited as nodes and the edges between nodes as travel costs, to generate learning data in a graph structure. Then, the transformer is instructed to learn this learning data and search for a path that minimizes the travel cost, thereby constructing a learning model capable of solving TSP and VRP. In the case of using multiple vehicles in VRP, the travel cost when multiple vehicles divide the task of visiting each point is set as the objective function, and by learning a route that minimizes this objective function, a learning model that can handle the case of multiple vehicles can be constructed.

[0026] Item 2 in the table in Figure 3 is FSSP. When multiple jobs are completed, each processed by multiple machines, for example, the goal is to find the machine operation schedule (the order in which each machine processes its work) that minimizes the operating time of each machine. In this case, training data is generated in the form of a graph structure where the processing time for each job and each machine is a node, the difference in processing time with the previous job in the flow order is an edge between nodes, and the total processing time of the last job is an edge. The transformer is instructed to learn from this training data and search for the order in which jobs are assigned to each machine (flow order) that minimizes the total processing time, thereby constructing a learning model capable of solving FSSP.

[0027] Item 3 in the table in Figure 3 is FairDivision. FairDivision refers to problems such as fairly distributing property to heirs, fairly distributing relief supplies and services to disaster victims, or equally allocating work to employees. In this case, a learning model capable of solving the FairDivision problem is constructed by generating training data in a graph structure where the utility of each player (a unit of property, relief supplies, work) is represented by nodes, and the utility of each player is represented by edges (if good a is a node, the edges connected to the node of good a represent the utility when player A obtains good a, the utility when player B obtains good a, etc.). The transformer is instructed to learn from this training data to maximize the utility (nodes) obtained by each player and to search for a distribution method that does not create a sense of unfairness even when exchanged with the utility obtained by other players, thereby constructing a learning model capable of solving the FairDivision problem.

[0028] What these methods have in common is that they generate training data in the form of a graph structure (only the problem, no correct answer is needed), and then train the transformer to learn how to traverse nodes and how to distribute nodes (how to partition the graph) in that graph structure that satisfies a certain objective function. As shown in Figure 4, a solver (neural solver) for the combinatorial optimization problem is obtained by generating training data in the form of a graph structure (the training data corresponds to the "problem" of the combinatorial optimization problem), and creating a learning model that can efficiently learn and solve the problem using the transformer. At this time, the focus is on generating training data for creating a learning model that can solve the combinatorial optimization problem. In the case of TSP and VRP, the training data for creating a learning model that can solve the problem is training data in which the movement cost is asymmetric and has the property of a metric. By devising the process of generating the training data, for example, as in steps 1 to 5 above, a large amount of training data can be generated by a relatively simple process with little computational load. In this embodiment, for each combinatorial optimization problem, the type of training data needed to create a solvable learning model is analyzed, and a method (for example, steps 1 to 5) is developed and devised to obtain training data suitable for that optimization problem. Then, data is generated using the developed and devised method, and this is used as training data in the form of a graph structure with nodes and edges. If training data in the form of a graph structure can be generated, a learning model for solving can be created by having the transformer learn how to traverse and distribute nodes to achieve the objective. In other words, if a method for generating training data suitable for combinatorial optimization problems can be developed, it is expected that solvers for any combinatorial optimization problem can be created. That is, the method for generating training data and constructing a learning model according to this embodiment is a systematic methodology for solving combinatorial optimization problems.

[0029] (Example of Use) Next, an example of planning a delivery plan and controlling a delivery plan based on a learning model for VRP constructed using the method of this embodiment will be described with reference to Figure 5. The delivery control system 100 includes a solver creation device 10, a delivery planning device 20, a vehicle control device 30, and vehicles 40a, 40b, ... The solver creation device 10 generates learning data using the method of steps 1 to 5, learns the learning data using transformer, and constructs a learning model for VRP that enables multiple vehicles 40a, 40b to divide the work and deliver goods at the lowest cost. The solver creation device 10 outputs the constructed learning model to the delivery planning device 20. The delivery planning device 20 applies a real-world delivery planning problem to the learning model obtained from the solver creation device 10 and solves it. For example, the delivery planning device 20 is given map information including the route to the delivery destination and the number of vehicles that can be used for delivery as calculation conditions, and has a learning model solve a delivery planning problem (VRP) that determines how to deliver goods to multiple destinations using multiple vehicles 40a, 40b, ... in a way that minimizes travel costs. By solving the VRP, a solution is obtained in which vehicle 40a visits point 1, point 2, point 3, ..., vehicle 40b visits point 4, point 5, point 6, ..., ... and so on. The delivery planning device 20 outputs the obtained solution to the vehicle control device 30. Vehicles 40a, 40b, ... are vehicles capable of autonomous or remote driving, and the vehicle control device 30 can control vehicles 40a, 40b, .... The vehicle control device 30 controls vehicles 40a, 40b, ... based on the information of the delivery destinations that each vehicle should visit, obtained from the delivery planning device 20. For example, the vehicle control device 30 sets points 1, 2, 3, etc. as delivery destinations for vehicle 40a and instructs vehicle 40a to automatically travel in the order of points 1, 2, 3, etc. Similarly, the vehicle control device 30 sets points 4, 5, 6, etc. as delivery destinations for vehicle 40b and instructs vehicle 40a to automatically travel in the order of points 4, 5, 6, etc. Following these instructions, vehicle 40a travels to points 1, 2, 3, etc. and delivers the goods, and vehicle 40b travels to points 4, 5, 6, etc. and delivers the goods.The learning model created by this embodiment can be used in actual control applications.

[0030] <Second Embodiment> Figure 6 is a block diagram showing an example of an information processing device according to the second embodiment. The information processing device 800 includes a generation means 801 that generates training data for a learning model for solving combinatorial optimization problems, the training data having a graph structure including nodes and edges. The training data generation unit 11 of the solver creation device 10 is an example of the generation means 801.

[0031] Figure 7 is a flowchart showing an example of an information processing method according to the second embodiment. The computer generates training data for a learning model to solve a combinatorial optimization problem, the training data having a graph structure including nodes and edges (step S801).

[0032] Figure 8 shows an example of the hardware configuration of the apparatus according to each embodiment. The computer 900 includes a CPU 901, main memory 902, auxiliary storage 903, input / output interface 904, and communication interface 905. The solver creation device 10 and information processing device 800 described above are implemented in the computer 900. The functions described above are stored in the auxiliary storage 903 in the form of a program. The CPU 901 reads the program from the auxiliary storage 903, expands it in the main memory 92, and executes the above processing according to the program. The CPU 901 also allocates a storage area in the main memory 902 according to the program. The CPU 901 also allocates a storage area in the auxiliary storage 903 to store the data being processed according to the program.

[0033] A program for realizing all or part of the functions of the solver creation device 10 and the information processing device 800 may be recorded on a computer-readable recording medium, and the program recorded on this recording medium may be loaded into a computer system and executed to perform processing by each functional unit. Here, "computer system" includes hardware such as the OS and peripheral devices. Furthermore, if a WWW system is used, "computer system" also includes the homepage provisioning environment (or display environment). Furthermore, "computer-readable recording medium" refers to portable media such as CDs, DVDs, USBs, and storage devices such as hard disks built into the computer system. Furthermore, if this program is distributed to the computer 900 via a communication line, the computer 900 that receives the distribution may load the program into the main memory 902 and execute the above processing. Furthermore, the above program may be for realizing only a part of the functions described above, and may also be for realizing the above functions in combination with programs already recorded in the computer system.

[0034] Although one embodiment of this disclosure has been described in detail above with reference to the drawings, the specific configuration is not limited to that described above, and various design changes can be made without departing from the spirit of this invention. Furthermore, one aspect of this disclosure can be modified in various ways within the scope of the claims, and embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of this disclosure. In addition, configurations in which elements described in each of the above embodiments and modifications that produce similar effects are substituted for each other are also included. Moreover, each embodiment can be appropriately combined with other embodiments.

[0035] Some or all of the above embodiments may be described as follows, but are not limited to the following:

[0036] (Note 1) An information processing apparatus comprising: a generation means for generating training data for a learning model for solving a combinatorial optimization problem, the training data having a graph structure including nodes and edges.

[0037] (Appendix 2) The generation means normalizes the distance between two predetermined points, determines an arbitrary value γ from a range greater than 0 and less than or equal to 1 / 2, selects an arbitrary value from a range greater than or equal to γ and less than or equal to γ×2, adds the selected value to the normalized distance, and normalizes the added value to calculate the movement cost between the two points, and generates the learning data with the two points as the nodes and the movement cost as the edges, the information processing apparatus according to Appendix 1.

[0038] (Appendix 3) For the two predetermined points, the generation means generates the coordinates of each point, and calculates the distance between the two points based on the generated coordinates, the information processing apparatus according to Appendix 2.

[0039] (Appendix 4) The generation means randomly generates the coordinates of a plurality of points, selects two from the generated plurality of points, calculates the distance between the selected two points, and normalizes the calculated distance, the information processing apparatus according to Appendix 2 or Appendix 3.

[0040] (Appendix 5) Learning means for learning the learning data by a deep learning model and constructing the learning model that becomes a solver for solving the combinatorial optimization problem, the information processing apparatus according to Appendices 1 to 4.

[0041] (Appendix 6) The deep learning model is a transformer, the information processing apparatus according to Appendix 5.

[0042] (Appendix 7) The learning means constructs the learning model that becomes a solver for the traveling salesman problem or the vehicle routing problem by learning, based on the learning data, a path that minimizes the cost when traversing the nodes included in the graph structure, the information processing apparatus according to Appendix 5 or Appendix 6.

[0043] (Appendix 8) A control system comprising: an information processing apparatus according to any one of Appendices 3 to 7; planning means for planning a tour route of a mobile body based on the learning model; and means for controlling the mobile body based on the planned plan.

[0044] (Appendix 9) An information processing method in which a computer generates learning data for a learning model for solving a combinatorial optimization problem, the learning data having a graph structure including nodes and edges.

[0045] (Appendix 10) A recording medium storing a program that causes a computer to execute a process of generating learning data for a learning model for solving a combinatorial optimization problem, the learning data having a graph structure including nodes and edges.

[0046] This application claims priority based on Japanese Patent Application No. 2025-006859 filed on January 17, 2025, and incorporates the entire disclosure thereof herein.

[0047] The present disclosure may be applied to an information processing apparatus, a control system, an information processing method, and a recording medium.

[0048] 10... Solver creation device 11... Learning data generation unit 12... Learning unit 13... Output unit 20... Delivery planning device 30... Vehicle control device 40a, 40b... Vehicles 100... Delivery control system 800... Information processing apparatus 801... Generation means 900... Computer 901... CPU 902... Main storage device 903... Auxiliary storage device 904... Input / output interface 905... Communication interface

Claims

1. An information processing device comprising: a generation means for generating training data for a learning model for solving a combinatorial optimization problem, the training data having a graph structure including nodes and edges.

2. The information processing apparatus according to claim 1, wherein the generation means normalizes the distance between two predetermined points, determines an arbitrary value γ from a range greater than 0 and less than or equal to 1 / 2, selects an arbitrary value from a range greater than or equal to γ ​​and less than or equal to γ ​​× 2, adds the selected value to the normalized distance, calculates the movement cost between the two points by normalizing the added value, and generates the learning data in which the two points are the nodes and the movement cost is the edge.

3. The information processing apparatus according to claim 2, wherein the generation means generates coordinates for two predetermined points and calculates the distance between the two points based on the generated coordinates.

4. The information processing apparatus according to claim 2, wherein the generation means randomly generates coordinates of a plurality of points, selects two of the generated plurality of points, calculates the distance between the two selected points, and normalizes the calculated distance.

5. The information processing apparatus according to claim 1 or 2, further comprising: a learning means for learning the learning data using a deep learning model and constructing the learning model which serves as a solver for solving the combinatorial optimization problem.

6. The information processing apparatus according to claim 5, wherein the deep learning model is a transformer.

7. The information processing apparatus according to claim 5, wherein the learning means constructs a learning model that serves as a solver for the traveling salesman problem or the vehicle routing problem by learning a path that minimizes the cost of visiting the nodes included in the graph structure based on the learning data.

8. A control system comprising: an information processing device according to claim 7; planning means for planning a mobile body's patrol route based on the learning model; and means for controlling the mobile body based on the planned route.

9. An information processing method in which a computer generates training data for a learning model to solve a combinatorial optimization problem, the training data having a graph structure including nodes and edges.

10. A recording medium storing a program that causes a computer to perform a process of generating training data for a learning model to solve a combinatorial optimization problem, the training data having a graph structure including nodes and edges.

Images