Allocation result determination device and allocation result determination method

The allocation result determination device optimizes aircraft landing orders by calculating change costs and reward values to minimize operational expenses when arrival times change, addressing increased costs in existing systems.

JP7580664B2Active Publication Date: 2024-11-11MITSUBISHI ELECTRIC CORP
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
JP2024515821
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2022-05-12
Publication Date
2024-11-11
Estimated Expiration
2042-05-12

AI Technical Summary

Technical Problem

Existing landing order determining devices for multiple aircraft incur increased operational costs when changes in scheduled arrival times require adjustments to the landing order, including fuel and pilot-related costs.

Method used

An allocation result determination device that calculates a first and second allocation result, assessing change costs and reward values using learning models to select the most cost-effective option based on predicted reward value differences and cost thresholds.

Benefits of technology

Enables the selection of a cost-effective landing order by determining whether to maintain or adjust the initial landing order, reducing operational costs and improving efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007580664000003
    Figure 0007580664000003
  • Figure 0007580664000004
    Figure 0007580664000004
  • Figure 0007580664000005
    Figure 0007580664000005
Patent Text Reader

Abstract

This allocation result determination device is configured with a changed cost calculating unit (3) that acquires, as allocation results indicating the order of allocation of a plurality of objects to be allocated, a first allocation result determined at a first time and a second allocation result determined at a second time after the first time, and calculates a changed cost that is an increase in cost when the allocation result is changed from the first allocation result to the second allocation result. The allocation result determination device further comprises an allocation result selecting unit (7) that selects the first allocation result or the second allocation result on the basis of the changed cost that is calculated by the changed cost calculating unit (3).
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present disclosure relates to an allocation result determination device and an allocation result determination method. [Background technology]

[0002] As an example of a device that determines the allocation order for a plurality of allocation objects, there is a landing order determination device that determines the landing order of a plurality of aircraft (see, for example, Patent Document 1). The landing order determination device includes a scheduler that determines the landing order of multiple aircraft based on the estimated arrival time of each aircraft at the runway and the aircraft size of each aircraft. After determining the landing order of the multiple aircraft, the scheduler redetermines the landing order of the multiple aircraft when, for example, the estimated arrival time of any aircraft changes. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Special Publication No. 2006-523874 Summary of the Invention [Problem to be solved by the invention]

[0004] When the landing order of multiple aircraft is determined and then the scheduled arrival time of any of the aircraft changes, there are cases where changing the landing order rather than maintaining the determined landing order results in lower operational costs, and cases where maintaining the landing order rather than changing the landing order results in lower operational costs. Operational costs include, for example, the cost of aircraft fuel, as well as the physical or mental burden on the pilots. The landing order determination device disclosed in Patent Document 1 had a problem in that if a scheduler determines the landing order of multiple aircraft and then the scheduled arrival time of any of the aircraft changes, the landing order of the multiple aircraft must be changed, which can result in increased operational costs.

[0005] The present disclosure has been made to solve the above-mentioned problems, and aims to provide an allocation result determination device and allocation result determination method that, when a first allocation result is determined and then a second allocation result is determined as an allocation result indicating an allocation order for multiple allocation objects, can select the first allocation result or the second allocation result based on cost. [Means for solving the problem]

[0006] An allocation result determination device according to the present disclosure includes a change cost calculation unit that obtains a first allocation result determined at a first time and a second allocation result determined at a second time that is later than the first time, as allocation results indicating an allocation order for a plurality of allocation objects, and calculates a change cost that is an increase in cost when the allocation result is changed from the first allocation result to the second allocation result; and a reward value difference prediction unit that provides each of the first allocation result and the second allocation result to a learning model for reward value prediction, and obtains from the learning model a first reward value indicating the degree of quality of the first allocation result and a second reward value indicating the degree of quality of the second allocation result, and predicts a reward value difference between the first reward value and the second reward value by subtracting the first reward value from the second reward value; If the reward value difference predicted by the reward value difference prediction unit is greater than 0 and the change cost calculated by the change cost calculation unit is equal to or less than a cost threshold, the second allocation result is selected, and if the reward value difference predicted by the reward value difference prediction unit is equal to or less than 0 or the change cost calculated by the change cost calculation unit is greater than a cost threshold, the first allocation result is selected. The reward value difference calculation unit calculates a reward value difference between the first reward value and the second reward value by providing the first allocation result to a reward function to calculate a first reward value, providing the second allocation result to the reward function to calculate a second reward value, and subtracting the first reward value from the second reward value. The reward value difference prediction unit updates the learning model so that the difference between the predicted reward value difference and the reward value difference calculated by the reward value difference calculation unit becomes smaller. do. Effect of the Invention

[0007] According to the present disclosure, when a first allocation result is determined as an allocation result indicating an allocation order for multiple allocation objects and then a second allocation result is determined, the first allocation result or the second allocation result can be selected based on cost. [Brief description of the drawings]

[0008] [Figure 1] 1 is a configuration diagram showing an allocation result determination device according to a first embodiment. [Diagram 2] 1 is a hardware configuration diagram showing hardware of an allocation result determination device according to embodiment 1. FIG. [Diagram 3] 11 is a hardware configuration diagram of a computer when the allocation result determination device is realized by software, firmware, or the like. FIG. [Figure 4] 2 is a configuration diagram showing a difference prediction processing unit 6 of the allocation result determination device according to the first embodiment. FIG. [Diagram 5] FIG. 11 is an explanatory diagram showing an example of an allocation result showing the landing allocation order of three airplanes. [Figure 6] 2 is a flowchart showing an allocation result determination method which is a processing procedure of the allocation result determination device shown in FIG. [Figure 7] FIG. 7A is an explanatory diagram showing an example of a first allocation result Xa acquired by the first allocation result acquisition unit 1 when schedule information Sa is provided to the first allocation result acquisition unit 1, and FIG. 7B is an explanatory diagram showing an example of a second allocation result Xb acquired by the second allocation result acquisition unit 2 when schedule information Sb is provided to the second allocation result acquisition unit 2. [Figure 8] FIG. 13 is an explanatory diagram illustrating an example of a change cost table. [Figure 9] FIG. 11 is an explanatory diagram showing an attenuation function g(j). [Figure 10] Figure 10A is an explanatory diagram showing difference information dab when the allocation order of aircraft j4 is changed from fourth from the beginning to the end, and Figure 10B is an explanatory diagram showing difference information dab when aircraft j8, which was not included in schedule information Sa, is included in schedule information Sb. [Figure 11] FIG. 11 is a configuration diagram showing an allocation result determination device according to the second embodiment. [Figure 12] FIG. 11 is a hardware configuration diagram showing hardware of an allocation result determination device according to a second embodiment. [Figure 13] 13 is a configuration diagram showing a reward value difference calculation unit 8 of the allocation result determination device according to the second embodiment. FIG. [Figure 14] 11 is a configuration diagram showing a difference prediction processing unit 10 of an allocation result determination device according to a second embodiment. FIG. [Figure 15] FIG. 11 is a configuration diagram showing an allocation result determination device according to embodiment 3. [Figure 16] FIG. 11 is a hardware configuration diagram showing hardware of an allocation result determination device according to embodiment 3. [Figure 17] FIG. 17A is an explanatory diagram showing allocatable times and non-allocable times, and FIG. 17B is an explanatory diagram showing a penalty table. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] In order to describe the present disclosure in more detail, embodiments of the present disclosure will be described below with reference to the accompanying drawings.

[0010] Embodiment 1 FIG. 1 is a configuration diagram showing an allocation result determination device according to the first embodiment. FIG. 2 is a hardware configuration diagram showing hardware of the allocation result determination device according to the first embodiment. The allocation result determination device shown in FIG. 1 includes a first allocation result acquisition unit 1, a second allocation result acquisition unit 2, a change cost calculation unit 3, a reward value difference prediction unit 4, and an allocation result selection unit . The allocation result determination device shown in Fig. 1 determines an allocation result indicating an allocation order for a plurality of allocation objects, for example, an allocation result indicating an allocation order for takeoffs and landings of a plurality of aircraft. However, the allocation objects are not limited to aircraft, and may be, for example, luggage or taxis. If the allocation objects are, for example, taxis, the allocation result determination device shown in Fig. 1 determines an allocation result indicating a dispatch order of taxis.

[0011] The first allocation result acquisition unit 1 is realized by, for example, a first allocation result acquisition circuit 21 shown in FIG. The first allocation result acquisition unit 1 acquires schedule information S of aircraft, which are multiple allocation targets, at a first time. a is given to the first learning model 1a, and the first assignment result X a Get the. The first allocation result acquisition unit 1 receives the first allocation result X a to the change cost calculation unit 3, the reward value difference prediction unit 4, and the allocation result selection unit 7, respectively. Schedule Information a For example, the first allocation result X includes information indicating the scheduled landing time of each aircraft or the scheduled takeoff time of each aircraft and the aircraft size of each aircraft. a is the allocation result determined at the first time instant.

[0012] During learning, the first learning model 1a is given schedule information S of multiple aircraft as input data, and is given allocation results X indicating the allocation order of takeoffs and landings of the multiple aircraft as teaching data, and learns the allocation results X. The first learning model 1a, at the time of inference, uses schedule information S of multiple aircraft. a Given schedule information S a The first allocation result X corresponding to a Output. Here, the first learning model 1a is trained by supervised learning. However, this is merely an example, and the first learning model 1a may be trained by, for example, unsupervised learning, reinforcement learning, or a mathematical optimization method.

[0013] The second allocation result acquisition unit 2 is realized by, for example, a second allocation result acquisition circuit 22 shown in FIG. The second allocation result acquisition unit 2 acquires schedule information S of aircraft, which are the objects of allocation, at a second time that is a time after the first time. b is given to the second learning model 2a, and the second assignment result X b Get the. Schedule Information b For example, the second allocation result X includes information indicating the scheduled landing time of each aircraft or the scheduled takeoff time of each aircraft and the aircraft size of each aircraft. b is the allocation result determined at the second time. The second allocation result acquisition unit 2 receives the second allocation result X b to the change cost calculation unit 3, the reward value difference prediction unit 4, and the allocation result selection unit 7, respectively.

[0014] During learning, the second learning model 2a is given schedule information S of multiple aircraft as input data, and is given allocation results X indicating the allocation order of takeoffs and landings of the multiple aircraft as teaching data, and learns the allocation results X. The second learning model 2a, at the time of inference, uses schedule information S of multiple aircraft. b Given schedule information S b The second allocation result X corresponding to b Output. Here, the second learning model 2a is trained by supervised learning. However, this is merely an example, and the second learning model 2a may be trained by, for example, unsupervised learning, reinforcement learning, or a mathematical optimization method.

[0015] The modification cost calculation unit 3 is realized by, for example, a modification cost calculation circuit 23 shown in FIG. The change cost calculation unit 3 receives the first allocation result X from the first allocation result acquisition unit 1. a and the second allocation result acquisition unit 2 outputs the second allocation result X b Get the. The change cost calculation unit 3 converts the allocation result into a first allocation result X a to the second allocation result X b The change cost C is the increase in cost when changing to ab If the object to be allocated is an aircraft, the cost for which the increase is calculated by the change cost calculation unit 3 is the operation cost. The operation cost includes, for example, the fuel cost of the aircraft, as well as the physical burden on the pilot or the burden cost related to the mental burden on the pilot. The change cost calculation unit 3 calculates the change cost C ab to the allocation result selection unit 7.

[0016] The reward value difference prediction unit 4 is realized by, for example, a reward value difference prediction circuit 24 shown in FIG. The reward value difference prediction unit 4 includes an allocation result difference detection unit 5 and a difference prediction processing unit 6 . The reward value difference prediction unit 4 No. 1 allocation result X a and the second allocation result X b Each of the above is fed to a learning model 6c for predicting reward values ​​shown in FIG. 4, and a first allocation result X a The first reward value R indicates the degree of quality of the preda and the second allocation result X b The second reward value R indicates the degree of quality of the predb and get. The reward value difference prediction unit 4 calculates the second reward value R predb to the first reward value R preda The first reward value R preda and the second reward value R predb Reward value difference ΔR pred Predict. The reward value difference prediction unit 4 calculates the reward value difference ΔR pred to the allocation result selection unit 7.

[0017] The allocation result difference detection unit 5 detects the schedule information S at the first time. a and schedule information S at the second time b Detect the difference with and generate difference information d ab to the differential prediction processing unit 6.

[0018] The difference prediction processing unit 6 Allocation result difference detection unit 5 Difference information output from ab However, if it indicates that there is a difference, No. 1 allocation result X a and the second allocation result X b Each of the above is fed to a learning model 6c for predicting a reward value, and a first reward value R preda and the second reward value R predb and get. The difference prediction processor 6 calculates a second reward value R predb to the first reward value R preda The first reward value R preda and the second reward value R predb Reward value difference ΔR pred Predict. The difference prediction processing unit 6 calculates the reward value difference ΔR pred to the allocation result selection unit 7.

[0019] The allocation result selection unit 7 is realized by, for example, an allocation result selection circuit 27 shown in FIG. The allocation result selection unit 7 selects the change cost C ab Based on the first allocation result X a , or the second allocation result X b Select . Specifically, the allocation result selection unit 7 selects the reward value difference ΔR pred is greater than 0 and the change cost C ab If is less than or equal to the cost threshold Thc, the second allocation result X b Select . The allocation result selection unit 7 calculates the reward value difference ΔR pred is 0 or less, or change cost Cab If is greater than the cost threshold Thc, the first allocation result X a Select . The cost threshold value Thc may be stored in an internal memory of the allocation result selection unit 7, or may be provided from outside the allocation result determination device.

[0020] In Fig. 1, it is assumed that each of the components of the allocation result determination device, that is, the first allocation result acquisition unit 1, the second allocation result acquisition unit 2, the change cost calculation unit 3, the reward value difference prediction unit 4, and the allocation result selection unit 7, is realized by dedicated hardware as shown in Fig. 2. That is, it is assumed that the allocation result determination device is realized by the first allocation result acquisition circuit 21, the second allocation result acquisition circuit 22, the change cost calculation circuit 23, the reward value difference prediction circuit 24, and the allocation result selection circuit 27. Each of the first allocation result acquisition circuit 21, the second allocation result acquisition circuit 22, the change cost calculation circuit 23, the reward value difference prediction circuit 24 and the allocation result selection circuit 27 corresponds to, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a combination of these.

[0021] The components of the allocation result determination device are not limited to those realized by dedicated hardware, and the allocation result determination device may be realized by software, firmware, or a combination of software and firmware. The software or firmware is stored as a program in the memory of a computer. The computer means hardware that executes the program, and includes, for example, a CPU (Central Processing Unit), a central processing unit, a processing unit, an arithmetic unit, a microprocessor, a microcomputer, a processor, or a DSP (Digital Signal Processor).

[0022] FIG. 3 is a hardware configuration diagram of a computer when the allocation result determination device is realized by software, firmware, or the like. When the allocation result determination device is realized by software, firmware, or the like, a program for causing a computer to execute the respective processing procedures in the first allocation result acquisition unit 1, the second allocation result acquisition unit 2, the change cost calculation unit 3, the reward value difference prediction unit 4, and the allocation result selection unit 7 is stored in the memory 41. Then, the processor 42 of the computer executes the program stored in the memory 41.

[0023] 2 shows an example in which each of the components of the allocation result determination device is realized by dedicated hardware, and FIG. 3 shows an example in which the allocation result determination device is realized by software or firmware, etc. However, this is merely an example, and some of the components in the allocation result determination device may be realized by dedicated hardware, and the remaining components may be realized by software or firmware, etc.

[0024] FIG. 4 is a configuration diagram showing the difference prediction processing unit 6 of the allocation result determination device according to the first embodiment. The difference prediction processing unit 6 shown in FIG. 4 includes a first prediction processing unit 6a, a second prediction processing unit 6b, a learning model 6c for reward value prediction, and a difference calculation processing unit 6d.

[0025] The first prediction processing unit 6a uses the difference information d output from the allocation result difference detection unit 5. ab indicates that there is a difference, the first allocation result X output from the first allocation result acquisition unit 1 is a is given to a learning model 6c for predicting a reward value, and a first reward value R preda Get the. The first prediction processor 6a calculates a first reward value R preda to the difference calculation processing unit 6d.

[0026] The second prediction processing unit 6b uses the difference information d output from the allocation result difference detection unit 5. abindicates that there is a difference, the second allocation result X output from the second allocation result acquisition unit 2 is b is fed to a learning model 6c for predicting a reward value, and a second reward value R predb Get the. The second prediction processor 6b calculates a second reward value R predb to the difference calculation processing unit 6d.

[0027] In the learning model 6c for predicting reward values, the allocation result X is given as input data during learning, and the reward value R is given as training data. pred is given, and the reward value R pred The reward value R pred For example, if the cost when allocation result X is selected is high, then θ is a small value, and if the cost when allocation result X is selected is low, then θ is a large value. During inference, the learning model 6c uses the first assignment result X a , or the second allocation result X b Given the first allocation result X a The first reward value R preda , or the second allocation result X b The second reward value R predb Output. Here, the learning model 6c is trained by supervised learning. However, this is merely an example, and the learning model 6c may be trained by, for example, unsupervised learning, reinforcement learning, or a mathematical optimization method.

[0028] The difference calculation processing unit 6d calculates the second reward value R predb to the first reward value R preda The first reward value R preda and the second reward value R predb Reward value difference ΔR pred Calculate. The difference calculation processing unit 6d calculates the reward value difference ΔR pred to the allocation result selection unit 7.

[0029] FIG. 5 is an explanatory diagram showing an example of an allocation result showing the landing allocation order of three airplanes. In the example of FIG. 5, the three airplanes are a small airplane, a medium airplane, and a large airplane. In the example of Figure 5, the no-landing time after a small aircraft lands is 60 [sec], the no-landing time after a medium-sized aircraft lands is 180 [sec], and the no-landing time after a large aircraft lands is 240 [sec]. If medium-sized planes, large planes, and small planes are allowed to land in that order, as shown in Figure 5, the shortest time it takes for all three planes to land is 420 (=180 + 240) [sec]. If medium-sized planes, small planes, and large planes are allowed to land in that order, the shortest time it takes for all three planes to land is 240 (=180 + 60) [sec], as shown in Figure 5. Therefore, if medium-sized planes, small planes, and large planes are allowed to land in this order, the shortest time it will take for all planes to land will be 180 (=420-240) seconds shorter than if medium-sized planes, large planes, and small planes were allowed to land in this order.

[0030] Next, the operation of the allocation result determination device shown in FIG. 1 will be described. FIG. 6 is a flowchart showing an allocation result determination method which is a processing procedure of the allocation result determination device shown in FIG. The first allocation result acquisition unit 1 acquires schedule information S of a plurality of aircraft at a first time. a Get the. Schedule Information a includes, for example, information indicating the scheduled landing time of each aircraft or the scheduled takeoff time of each aircraft, and the aircraft size of each aircraft. The first allocation result acquisition unit 1 receives schedule information S a is given to the first learning model 1a, and the first assignment result X a (Step ST1 in FIG. 6). The first allocation result acquisition unit 1 receives the first allocation result X ato the change cost calculation unit 3, the reward value difference prediction unit 4, and the allocation result selection unit 7, respectively.

[0031] FIG. 7A shows schedule information S a is provided to the first allocation result acquisition unit 1, the first allocation result X a FIG. In FIG. 7A, t 1 ,t 2 ,t 8 is the time, and j 1 ,j 2 ,j 5 is an ID (IDentification) that identifies an aircraft. A "0" indicates that no aircraft takeoff or landing can be allocated, and a "1" indicates that an aircraft takeoff or landing can be allocated. In the example of FIG. 7A, aircraft j 3 ,aircraft j 5 ,aircraft j 1 ,aircraft j 2 ,aircraft j 4 The first allocation result X that allows takeoff and landing in the order a has been obtained.

[0032] The second allocation result acquisition unit 2 acquires schedule information S of a plurality of aircraft at a second time that is a time after the first time. b Get the. Schedule Information b includes, for example, information indicating the scheduled landing time of each aircraft or the scheduled takeoff time of each aircraft, and the aircraft size of each aircraft. The second allocation result acquisition unit 2 receives the schedule information S b is given to the second learning model 2a, and the second assignment result X b (Step ST2 in FIG. 6). The second allocation result acquisition unit 2 receives the second allocation result X b to the change cost calculation unit 3, the reward value difference prediction unit 4, and the allocation result selection unit 7, respectively.

[0033] FIG. 7B shows schedule information S b When the second allocation result acquisition unit 2 is provided with the second allocation result X b FIG. In FIG. 7B, t 1 ,t 2 ,t 8 is the time, and j 1 ,j 2 ,j 5 is an ID that identifies the aircraft. A "0" indicates that no aircraft takeoff or landing can be allocated, and a "1" indicates that an aircraft takeoff or landing can be allocated. In the example of FIG. 7B, aircraft j 3 ,aircraft j 1 ,aircraft j 5 ,aircraft j 2 ,aircraft j 4 The second allocation result X allows takeoff and landing in the order b has been obtained.

[0034] The change cost calculation unit 3 receives the first allocation result X from the first allocation result acquisition unit 1. a and the second allocation result acquisition unit 2 outputs the second allocation result X b Get the. The change cost calculation unit 3 refers to a change cost table as shown in FIG. 8, for example, and calculates the allocation result as a first allocation result X a to the second allocation result X b The change cost C is the increase in cost when changing to ab (Step ST3 in FIG. 6). The change cost calculation unit 3 calculates the change cost C ab to the allocation result selection unit 7.

[0035] FIG. 8 is an explanatory diagram illustrating an example of the change cost table. In Figure 8, j 1 ,j 2 ,j 5 is the identification code for the aircraft. The numbers in the table indicate the cost of the change. For example, if the first allocation result is X a =[j 3 ,j 5 ,j 1 ,j 2 ,j 4 ] and the second allocation result is X b =[j 3 ,j 1 ,j 5 ,j 2 ,j 4 ], then aircraft j 5 and aircraft 1 The order of the two has been swapped. Therefore, the change cost C ab is "100". For example, if the first allocation result is X a =[j 3 ,j 5 ,j 1 ,j 2 ,j 4 ] and the second allocation result is X b =[j 3 ,j 2 ,j 5 ,j 1 ,j 4 ], then aircraft j 5 and aircraft 2 The order of the aircraft was changed, and the aircraft j 5 and aircraft 1 The order of the two has been swapped. Therefore, the change cost C ab is “180” (=80+100).

[0036] In the allocation result determination device shown in FIG. 1, the change cost calculation unit 3 refers to a change cost table as shown in FIG. ab However, this is merely an example, and the change cost calculation unit 3 may calculate the change cost C ab may be calculated. First, the change cost calculation unit 3 calculates the second allocation result X b ' to the first allocation result X a The allocation difference ΔX is calculated by subtracting b ' is the second allocation result X bThe time of the first allocation result X a For example, the first allocation result X a The time of t 1 ,t 2 ,t 8 and the second allocation result X b The time of t 3 ,t 4 ,t 10 If so, the second allocation result X b At time t 3 t 1 , time t 4 t 2 , time t 10 t 8 It is assumed that. ΔX=X b '-X a (1)

[0037] Next, the change cost calculation unit 3 substitutes the allocation difference ΔX into the following formula (2) to calculate the change cost C associated with the change in order. 0 Calculate. In addition, the change cost calculation unit 3 substitutes the allocation difference ΔX into the following formula (3) to calculate the change cost C associated with the time change. t Calculate.

[0038] TIFF0007580664000001.tif31166g(j) is the decay function shown in Figure 9, for example, g(j)=e (-j / T) where j is an ID for identifying an aircraft, and T is a time constant. d ab is the difference information d output from the allocation result difference detection unit 5 to the change cost calculation unit 3 ab In FIG. 1, the arrow from the allocation result difference detection unit 5 to the change cost calculation unit 3 is omitted. a and schedule information b If there is no difference with d ab = 0, and the schedule information S a and schedule information b If there is a difference with d ab =1. Gamma 0 ,γ t Each of these is a coefficient.

[0039] The change cost calculation unit 3 calculates the change cost C associated with the change in order, for example, as shown in the following formula (4): 0 and the change cost C associated with the time change t The change cost C ab Calculate. C ab =C 0 +w·C t (4) In equation (4), w is a weighting coefficient.

[0040] The reward value difference prediction unit 4 calculates the reward value difference ΔR pred (Step ST4 in FIG. 6). Hereinafter, the reward value difference ΔR pred The prediction process will now be described in detail. The allocation result difference detection unit 5 of the reward value difference prediction unit 4 calculates the schedule information S at the first time. a and schedule information S at the second time b and get. As shown in FIG. 10, the allocation result difference detection unit 5 detects the schedule information S a and schedule information b Detect the difference with and generate difference information d ab The change cost calculation unit 3 outputs the change cost C ab When calculating the difference in allocation result, the allocation result difference detection unit 5 uses the difference information d ab is also output to the modification cost calculation unit 3. FIG. 10A shows the aircraft j 4 The difference information d when the allocation order of is changed from the fourth to the last. ab FIG. FIG. 10B shows schedule information S a Aircraft not included in 8 However, schedule information b Difference information d when included inab FIG. 10A and 10B, the numbers in the circles are IDs that identify aircraft, with the j symbol omitted. Schedule Information a and schedule information b If there is no difference with d ab = 0, and the schedule information S a and schedule information b If there is a difference with d ab =1.

[0041] The first prediction processing unit 6a of the difference prediction processing unit 6 receives the first allocation result X from the first allocation result acquisition unit 1. a and obtains the difference information d from the allocation result difference detection unit 5. ab Get the. The first prediction processing unit 6a calculates the difference information d ab If is "1", the first allocation result X a is given to a learning model 6c for predicting a reward value, and a first reward value R preda Get the. The first prediction processor 6a calculates a first reward value R preda to the difference calculation processing unit 6d.

[0042] The second prediction processing unit 6b of the difference prediction processing unit 6 receives the second allocation result X from the second allocation result acquisition unit 2. b and obtains the difference information d from the allocation result difference detection unit 5. ab Get the. The second prediction processing unit 6b calculates the difference information d ab If is "1", the second allocation result X b is fed to a learning model 6c for predicting a reward value, and a second reward value R predb Get the. The second prediction processor 6b calculates a second reward value R predb to the difference calculation processing unit 6d.

[0043] The difference calculation processing unit 6d calculates the first reward value R predaand the second prediction processor 6b outputs a second reward value R predb Get the. The difference calculation processing unit 6d calculates the second reward value R predb to the first reward value R preda The first reward value R preda and the second reward value R predb Reward value difference ΔR pred Calculate the reward value difference ΔR pred If is a negative value, the second allocation result X b The cost of selecting the first allocation result X a The reward difference ΔR pred If is a positive value, the second allocation result X b The cost of selecting the first allocation result X a If you choose the cost is lower. ΔR pred =R predb -R preda (5) The difference calculation processing unit 6d calculates the reward value difference ΔR pred to the allocation result selection unit 7.

[0044] The allocation result selection unit 7 receives the first allocation result X from the first allocation result acquisition unit 1. a and the second allocation result acquisition unit 2 outputs the second allocation result X b Get the. The allocation result selection unit 7 selects the change cost C ab and the reward value difference ΔR predicted by the reward value difference prediction unit 4 pred Based on the first allocation result X a , or the second allocation result X b (Step ST5 in FIG. 6). That is, the allocation result selection unit 7 selects the reward value difference ΔR predicted by the reward value difference prediction unit 4. pred is greater than 0 and the change cost C ab If is less than or equal to the cost threshold Thc, the second allocation result X b Select . The allocation result selection unit 7 calculates the reward value difference ΔRpred is 0 or less, or change cost C ab If is greater than the cost threshold Thc, the first allocation result X a Select .

[0045] In the allocation result determination device shown in FIG. 1, the allocation result selection unit 7 determines the change cost C ab and the reward value difference ΔR pred Based on the first allocation result X a , or the second allocation result X b However, this is merely an example, and the allocation result selection unit 7 selects the change cost C ab Based only on the first allocation result X a , or the second allocation result X b The allocation result selection unit 7 may select the change cost C ab Based only on the first allocation result X a , or the second allocation result X b In the case where the above-mentioned is selected, the allocation result determination device does not need to include the reward value difference prediction unit 4. In addition, the allocation result selection unit 7 calculates the reward value difference ΔR pred Based only on the first allocation result X a , or the second allocation result X b The allocation result selection unit 7 may select the reward value difference ΔR pred Based only on the first allocation result X a , or the second allocation result X b In the case where the above-mentioned is selected, the allocation result determination device does not need to include the change cost calculation unit 3.

[0046] In the above-described first embodiment, the allocation result determination device is configured to include a change cost calculation unit 3 that acquires a first allocation result determined at a first time and a second allocation result determined at a second time that is a time later than the first time as an allocation result indicating an allocation order for a plurality of allocation objects, and calculates a change cost that is an increase in cost when the allocation result is changed from the first allocation result to the second allocation result. The allocation result determination device also includes an allocation result selection unit 7 that selects the first allocation result or the second allocation result based on the change cost calculated by the change cost calculation unit 3. Therefore, the allocation result determination device can select the first allocation result or the second allocation result based on the cost when the second allocation result is determined after the first allocation result is determined as an allocation result indicating an allocation order for a plurality of allocation objects.

[0047] Embodiment 2 In the second embodiment, an allocation result determination device including a reward value difference prediction unit 9 that updates a learning model 10c will be described.

[0048] Fig. 11 is a configuration diagram showing an allocation result determination device according to embodiment 2. In Fig. 11, the same reference numerals as in Fig. 1 indicate the same or corresponding parts, and therefore description thereof will be omitted. Fig. 12 is a hardware configuration diagram showing hardware of an allocation result determination device according to embodiment 2. In Fig. 12, the same reference numerals as in Fig. 2 denote the same or corresponding parts, and therefore description thereof will be omitted. The allocation result determination device shown in Figure 11 includes a first allocation result acquisition unit 1, a second allocation result acquisition unit 2, a change cost calculation unit 3, a reward value difference prediction unit 9, an allocation result selection unit 7, and a reward value difference calculation unit 8.

[0049] The reward value difference calculation unit 8 is realized by, for example, a reward value difference calculation circuit 28 shown in FIG. The reward value difference calculation unit 8 calculates the first allocation result X a is fed to the reward function to obtain the first reward value R a Calculate the second allocation result X b to the reward function to obtain the second reward value Rb Calculate. The reward value difference calculation unit 8 calculates the second reward value R b to the first reward value R a The first reward value R a and the second reward value R b The reward value difference ΔR between the The reward value difference calculation unit 8 outputs the reward value difference ΔR to the reward value difference prediction unit 9.

[0050] The reward value difference prediction unit 9 is realized by, for example, a reward value difference prediction circuit 29 shown in FIG. The reward value difference prediction unit 9 includes an allocation result difference detection unit 5 and a difference prediction processing unit 10. The reward value difference prediction unit 9 No. 1 allocation result X a and the second allocation result X b Each of the above is fed to a learning model 10c for predicting reward values ​​shown in FIG. 14, and a first allocation result X a The first reward value R indicates the degree of quality of the preda and the second allocation result X b The second reward value R indicates the degree of quality of the predb and get. The reward value difference prediction unit 9 calculates the second reward value R predb to the first reward value R preda The first reward value R preda and the second reward value R predb Reward value difference ΔR pred Predict. The reward value difference prediction unit 9 calculates the reward value difference ΔR pred to the allocation result selection unit 7. In addition, the reward value difference prediction unit 9 predicts the predicted reward value difference ΔR pred The learning model 10c is updated so that the difference between the reward value difference ΔR calculated by the reward value difference calculation unit 8 and the reward value difference ΔR becomes smaller.

[0051] In Fig. 11, it is assumed that each of the components of the allocation result determination device, that is, the first allocation result acquisition unit 1, the second allocation result acquisition unit 2, the change cost calculation unit 3, the reward value difference prediction unit 9, the allocation result selection unit 7, and the reward value difference calculation unit 8, is realized by dedicated hardware as shown in Fig. 12. That is, it is assumed that the allocation result determination device is realized by the first allocation result acquisition circuit 21, the second allocation result acquisition circuit 22, the change cost calculation circuit 23, the reward value difference prediction circuit 29, the allocation result selection circuit 27, and the reward value difference calculation circuit 28. Each of the first allocation result acquisition circuit 21, the second allocation result acquisition circuit 22, the change cost calculation circuit 23, the reward value difference prediction circuit 29, the allocation result selection circuit 27 and the reward value difference calculation circuit 28 corresponds to, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination of these.

[0052] The components of the allocation result determination device are not limited to those realized by dedicated hardware, and the allocation result determination device may be realized by software, firmware, or a combination of software and firmware. When the allocation result determination device is realized by software, firmware, or the like, a program for causing a computer to execute the respective processing procedures in the first allocation result acquisition unit 1, the second allocation result acquisition unit 2, the change cost calculation unit 3, the reward value difference prediction unit 9, the allocation result selection unit 7, and the reward value difference calculation unit 8 is stored in the memory 41 shown in Fig. 3. Then, the processor 42 shown in Fig. 3 executes the program stored in the memory 41.

[0053] Also, Fig. 12 shows an example in which each of the components of the allocation result determination device is realized by dedicated hardware, and Fig. 3 shows an example in which the allocation result determination device is realized by software or firmware, etc. However, this is merely an example, and some of the components in the allocation result determination device may be realized by dedicated hardware, and the remaining components may be realized by software or firmware, etc.

[0054] FIG. 13 is a configuration diagram showing the reward value difference calculation unit 8 of the allocation result determination device according to the second embodiment. The reward value difference calculation unit 8 shown in FIG. 13 includes a first reward value calculation unit 8a, a second reward value calculation unit 8b, and a difference calculation processing unit 8c. The first reward value calculation unit 8a receives the first allocation result X from the first allocation result acquisition unit 1. a Get the. The first reward value calculation unit 8a calculates the first allocation result X a is fed to the reward function to obtain the first reward value R a Calculate the first reward value R a to the difference calculation processing unit 8c.

[0055] The second reward value calculation unit 8b receives the second allocation result X from the second allocation result acquisition unit 2. b Get the. The second reward value calculation unit 8b calculates the second allocation result X b to the reward function to obtain the second reward value R b Calculate the second reward value R b to the difference calculation processing unit 8c. The difference calculation processing unit 8c calculates the first reward value R a and the second allocation result acquisition unit 2 outputs the second reward value R b Get the. The difference calculation processing unit 8c calculates the second reward value R b to the first reward value R a The first reward value R a and the second reward value R b The reward value difference ΔR between the The difference calculation processing unit 8c outputs the reward value difference ΔR to the reward value difference prediction unit 9.

[0056] FIG. 14 is a configuration diagram showing a difference prediction processing unit 10 of the allocation result determination device according to the second embodiment. The difference prediction processing unit 10 shown in FIG. 14 includes a first prediction processing unit 10a, a second prediction processing unit 10b, a learning model 10c for reward value prediction, and a difference calculation processing unit 10d.

[0057] The first prediction processing unit 10a uses the difference information d output from the allocation result difference detection unit 5. ab indicates that there is a difference, the first allocation result X output from the first allocation result acquisition unit 1 is a is given to a learning model 10c for predicting a reward value, and a first reward value R preda Get the. The first prediction processor 10a calculates a first reward value R preda to the difference calculation processing unit 10d.

[0058] The second prediction processing unit 10b uses the difference information d output from the allocation result difference detection unit 5. ab indicates that there is a difference, the second allocation result X output from the second allocation result acquisition unit 2 is b is fed to a learning model 10c for predicting a reward value, and a second reward value R predb Get the. The second prediction processor 10b calculates a second reward value R predb to the difference calculation processing unit 10d.

[0059] In the learning model 10c for predicting reward values, the allocation result X is given as input data during learning, and the reward value R is given as training data. pred is given, and the reward value R pred are learning. During inference, the learning model 10c uses the first assignment result X a , or the second allocation result X b Given the first allocation result X a The first reward value R preda , or the second allocation result X b The second reward value R predb Output. Here, the learning model 10c is trained by supervised learning, but this is merely an example, and the learning model 10c may be trained by, for example, unsupervised learning, reinforcement learning, or a mathematical optimization method.

[0060] The difference calculation processing unit 10d calculates the second reward value R predb to the first reward value R preda The first reward value R preda and the second reward value R predb Reward value difference ΔR pred Calculate.

[0061] Next, the operation of the allocation result determination device shown in Fig. 11 will be described. However, other than the reward value difference calculation unit 8 and the reward value difference prediction unit 9, it is the same as the allocation result determination device shown in Fig. 1. Therefore, here, only the operation of the reward value difference calculation unit 8 and the reward value difference prediction unit 9 will be described.

[0062] The first reward value calculation unit 8a of the reward value difference calculation unit 8 receives the first allocation result X from the first allocation result acquisition unit 1. a Get the. The first reward value calculation unit 8a calculates the first allocation result X a is fed to the reward function shown in the following equation (6) to obtain the first reward value R a Calculate. R a =R assigna +α·R separationa (6) In formula (6), R assigna is an evaluation value for evaluating whether the assigned time of each aircraft is appropriate or not. R assigna is the first allocation result X a The earlier the allocation time of each aircraft is within the range of allocatable times, the larger the value becomes. R separationa is the evaluation value for the allocation interval of multiple aircraft. R separationa is the first allocation result X a If the allocation interval is larger than the minimum allocatable interval, the smaller the allocation interval, the larger the value. α is a weighting coefficient. The first reward value calculation unit 8a calculates the first reward value R a to the difference calculation processing unit 8c.

[0063] The second reward value calculation unit 8b receives the second allocation result X from the second allocation result acquisition unit 2. b Get the. The second reward value calculation unit 8b calculates the second allocation result X b is fed to the reward function shown in the following equation (7) to obtain the second reward value R b Calculate. R b =R assignb +β·R separationb (7) In formula (7), R assignb is an evaluation value for evaluating whether the assigned time of each aircraft is appropriate or not. R assignb is the second allocation result X b The earlier the allocation time of each aircraft is within the range of allocatable times, the larger the value becomes. R separationb is the evaluation value for the allocation interval of multiple aircraft. R separationb is the second allocation result X b If the allocation interval is larger than the minimum allocatable interval, the smaller the allocation interval, the larger the value. β is a weighting coefficient. The second reward value calculation unit 8b calculates the second reward value R b to the difference calculation processing unit 8c.

[0064] The difference calculation processing unit 8c calculates the first reward value R a and the second allocation result acquisition unit 2 outputs the second reward value R b Get the. The difference calculation processing unit 8c calculates the second reward value R b to the first reward value R a The first reward value R a and the second reward value R b The reward value difference ΔR between the ΔR pred =R b -R a (8) The difference calculation processing unit 8c outputs the reward value difference ΔR to a difference prediction processing unit 10 of the reward value difference prediction unit 9.

[0065] The first prediction processing unit 10a of the difference prediction processing unit 10 receives the first allocation result X from the first allocation result acquisition unit 1. a and obtains the difference information d from the allocation result difference detection unit 5. ab Get the. The first prediction processing unit 10a calculates the difference information d ab If is "1", the first allocation result X a is given to a learning model 10c for predicting a reward value, and a first reward value R preda Get the. The first prediction processor 10a calculates a first reward value R preda to the difference calculation processing unit 10d.

[0066] The second prediction processing unit 10b receives the second allocation result X from the second allocation result acquisition unit 2. b and obtains the difference information d from the allocation result difference detection unit 5. ab Get the. The second prediction processing unit 10b calculates the difference information d ab If is "1", the second allocation result X b is fed to a learning model 10c for predicting a reward value, and a second reward value R predb Get the. The second prediction processor 10b calculates a second reward value R predb to the difference calculation processing unit 10d.

[0067] The difference calculation processing unit 10d calculates the first reward value R preda and the second prediction processing unit 10b outputs a second reward value R predb Get the. The difference calculation processing unit 10d calculates the second reward value R predb to the first reward value R preda The first reward value R preda and the second reward value R predb Reward value difference ΔR pred Calculate. The difference calculation processing unit 10d calculates the reward value difference ΔR pred to the allocation result selection unit 7.

[0068] Each of the first prediction processing unit 10a and the second prediction processing unit 10b calculates the reward value difference ΔR pred The learning model 10c is updated so that the difference between the reward value difference ΔR calculated by the difference calculation processing unit 8c of the reward value difference calculation unit 8 and the reward value difference ΔR becomes smaller. Specifically, each of the first prediction processing unit 10a and the second prediction processing unit 10b calculates (ΔR-ΔR pred ) 2 The weights of the learning model 10c are updated so that is minimized.

[0069] In the above-described second embodiment, the allocation result determination device shown in FIG. 11 is configured to include a reward value difference calculation unit 8 that calculates a reward value difference between the first reward value and the second reward value by providing the first allocation result to the reward function to calculate a first reward value, providing the second allocation result to the reward function to calculate a second reward value, and subtracting the first reward value from the second reward value. In addition, the allocation result determination device shown in FIG. 11 updates the learning model 10c so that the difference between the reward value difference predicted by the reward value difference prediction unit 9 and the reward value difference calculated by the reward value difference calculation unit 8 becomes smaller. Therefore, the allocation result determination device shown in FIG. 11 can improve the selection accuracy of the allocation result more than the allocation result determination device shown in FIG. 1.

[0070] Embodiment 3 In the third embodiment, an allocation result determination device including a penalty value calculation unit 11 will be described.

[0071] Fig. 15 is a configuration diagram showing an allocation result determination device according to embodiment 3. In Fig. 15, the same reference numerals as in Fig. 1 indicate the same or corresponding parts, and therefore description thereof will be omitted. Fig. 16 is a hardware configuration diagram showing hardware of an allocation result determination device according to embodiment 3. In Fig. 16, the same reference numerals as in Fig. 2 denote the same or corresponding parts, and therefore description thereof will be omitted. The allocation result determination device shown in Figure 15 includes a first allocation result acquisition unit 1, a second allocation result acquisition unit 15, a change cost calculation unit 3, a reward value difference prediction unit 4, an allocation result selection unit 7, and a penalty value calculation unit 11.

[0072] The penalty value calculation unit 11 is realized by, for example, a penalty value calculation circuit 31 shown in FIG. The penalty value calculation section 11 includes a penalty value calculation processing section 12, an objective function value calculation section 13, and a function value addition section . If there is an allocation violation in the allocation result selected by the allocation result selection unit 7, the penalty value calculation unit 11 calculates a penalty value for the allocation violation. The penalty value calculation unit 11 outputs the penalty value to the second allocation result acquisition unit 15.

[0073] If there is an allocation violation in the allocation result selected by the allocation result selection unit 7, the penalty value calculation unit 12 calculates a penalty value for the allocation violation. The penalty value calculation unit 12 outputs the penalty value to the function value addition unit 14 . The objective function value calculation unit 13 provides the allocation result selected by the allocation result selection unit 7 to the objective function, and calculates an objective function value that is the value of the objective function. The objective function value calculation unit 13 outputs the objective function value to the function value addition unit 14 . The function value adding unit 14 adds the objective function value calculated by the objective function value calculating unit 13 to the penalty value calculated by the penalty value calculating unit 12 . The function value adding unit 14 outputs the penalty value after the addition of the objective function value to the second allocation result acquiring unit 15.

[0074] In the allocation result determination device shown in Fig. 15, the penalty value calculation unit 11 includes a penalty value calculation processing unit 12, an objective function value calculation unit 13, and a function value addition unit 14. However, this is merely an example, and the penalty value calculation unit 11 may include only either the penalty value calculation processing unit 12 or the objective function value calculation unit 13. When the penalty value calculation unit 11 includes only the penalty value calculation processing unit 12, the penalty value calculated by the penalty value calculation processing unit 12 is output to the second allocation result acquisition unit 15. When the penalty value calculation unit 11 includes only the objective function value calculation unit 13, the objective function value is output to the second allocation result acquisition unit 15 as a penalty value.

[0075] The second allocation result acquisition unit 15 is realized by, for example, a second allocation result acquisition circuit 35 shown in FIG. The second allocation result acquisition unit 15 acquires the schedule information S at the second time. b is given to the second learning model 15a, and a second allocation result X b Get the. The second allocation result acquisition unit 15 receives the second allocation result X b to the change cost calculation unit 3, the reward value difference prediction unit 4, and the allocation result selection unit 7, respectively. Furthermore, the second allocation result acquisition unit 15 updates the second learning model 15a so that the penalty value calculated by the penalty value calculation unit 11 becomes smaller.

[0076] During learning, the second learning model 15a is given schedule information S of multiple aircraft as input data, and is given allocation results X indicating the allocation order of takeoffs and landings of the multiple aircraft as teaching data, and learns the allocation results X. The second learning model 15a, during inference, uses schedule information S of multiple aircraft. b Given schedule information S b The second allocation result X corresponding to b Output. Here, the second learning model 15a is trained by supervised learning. However, this is merely an example, and the second learning model 15a may be trained by, for example, unsupervised learning, reinforcement learning, or a mathematical optimization method.

[0077] In the allocation result determination device shown in Fig. 15, the second allocation result acquisition unit 15 and the penalty value calculation unit 11 are each applied to the allocation result determination device shown in Fig. 1. However, this is merely an example, and the second allocation result acquisition unit 15 and the penalty value calculation unit 11 may each be applied to the allocation result determination device shown in Fig. 11.

[0078] In Fig. 15, it is assumed that each of the first allocation result acquisition unit 1, the second allocation result acquisition unit 15, the change cost calculation unit 3, the reward value difference prediction unit 4, the allocation result selection unit 7, and the penalty value calculation unit 11, which are components of the allocation result determination device, is realized by dedicated hardware as shown in Fig. 16. That is, it is assumed that the allocation result determination device is realized by the first allocation result acquisition circuit 21, the second allocation result acquisition circuit 35, the change cost calculation circuit 23, the reward value difference prediction circuit 24, the allocation result selection circuit 27, and the penalty value calculation circuit 31. Each of the first allocation result acquisition circuit 21, the second allocation result acquisition circuit 35, the change cost calculation circuit 23, the reward value difference prediction circuit 24, the allocation result selection circuit 27 and the penalty value calculation circuit 31 corresponds to, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination of these.

[0079] The components of the allocation result determination device are not limited to those realized by dedicated hardware, and the allocation result determination device may be realized by software, firmware, or a combination of software and firmware. When the allocation result determination device is realized by software, firmware, or the like, a program for causing a computer to execute the respective processing procedures in the first allocation result acquisition unit 1, the second allocation result acquisition unit 15, the change cost calculation unit 3, the reward value difference prediction unit 4, the allocation result selection unit 7, and the penalty value calculation unit 11 is stored in the memory 41 shown in Fig. 3. Then, the processor 42 shown in Fig. 3 executes the program stored in the memory 41.

[0080] Also, Fig. 16 shows an example in which each of the components of the allocation result determination device is realized by dedicated hardware, and Fig. 3 shows an example in which the allocation result determination device is realized by software or firmware, etc. However, this is only one example, and some of the components in the allocation result determination device may be realized by dedicated hardware, and the remaining components may be realized by software or firmware, etc.

[0081] Next, the operation of the allocation result determination device shown in Fig. 15 will be described. However, other than the penalty value calculation unit 11 and the second allocation result acquisition unit 15, the allocation result determination device is the same as that shown in Fig. 1. Therefore, here, only the operations of the penalty value calculation unit 11 and the second allocation result acquisition unit 15 will be described.

[0082] The penalty value calculation processing unit 12 of the penalty value calculation unit 11 calculates the allocation result X selected by the allocation result selection unit 7. sel The first allocation result X a , or the second allocation result X b Get the. The penalty value calculation processing unit 12 calculates the allocation result X sel It is determined whether the allocation time of each aircraft indicated by is an allocable time. FIG. 17A is an explanatory diagram showing allocatable times and non-allocable times. In FIG. 17A, t 1 ,t 2 ,t 8 is the time, and j 1 ,j 2 ,j5 is an ID that identifies the aircraft. "0" indicates a time that is not available for allocation, and "1" indicates a time that is available for allocation. Allocation result X sel If the assigned time of each aircraft indicated by is assigned to an assignable time, there is no assignment violation in the assignment result, and if it is assigned to an unassignable time, there is an assignment violation in the assignment result.

[0083] FIG. 17B is an explanatory diagram showing the penalty table. The penalty table shown in FIG. 17B indicates the penalty value when an assignment is made at an allocable time and the penalty value when an assignment is made at an unallocable time. In the example of FIG. 17B, the penalty value when an assignment is made at an allocable time is "0", and the penalty value when an assignment is made at an unallocable time is a negative value. For example, the penalty value when an allocation is made earlier than the allocatable time has a larger absolute value as the allocation is made earlier than the allocatable time. If there is an allocation violation, the penalty value calculation processing unit 12 refers to the penalty table shown in FIG. 17B and calculates a penalty value p. For example, aircraft j 2 is time t 2 and the violation of the quota assigned to aircraft j 3 is time t 5 If there is an allocation violation assigned to , the penalty value p becomes -510 (=-500-10). For example, aircraft j 5 is time t 6 If there are only quota violations assigned to , then the penalty value p will be -5. The penalty value calculation unit 12 outputs the penalty value p to the function value addition unit 14 .

[0084] Here, the penalty value calculation processing unit 12 calculates the penalty value by referring to the penalty table shown in FIG. 17B. However, this is merely an example. For example, the penalty value calculation processing unit 12 calculates the penalty value by referring to the penalty table shown in FIG. selis expressed as a penalty function p(X sel ) and the penalty function p(X sel ) may be calculated as a penalty value p.

[0085] TIFF0007580664000002.tif19166 In equation (9), the penalty function p(X sel ) is a decay function, which is 0 if there is no quota violation. Gamma j is the coefficient, j=j 1 ,j 2 ,····,J.

[0086] The objective function value calculation unit 13 calculates the allocation result X selected by the allocation result selection unit 7. sel The first allocation result X a , or the second allocation result X b Get the. The objective function value calculation unit 13 calculates the allocation result X sel The objective function f(X sel ) to obtain the objective function f(X sel ) is calculated as the objective function value f. f(X sel )=f assign +ε f separation (10) In equation (10), f assign is the allocation result X sel The value is determined by f assign is the allocation result X sel If the allocation time of each aircraft indicated by is within the range of the available allocation time, the earlier the allocation time is within the range of the available allocation time, the larger the value will be. sel If the assigned time of each aircraft indicated by is unavailable, then f assign will be a small value such as -1000. f separation is the allocation result X sel The value is determined by f separationIf the allocation interval is larger than the minimum allocatable interval, the smaller the allocation interval, the larger the value of f separation will be a small value such as -1000. ε is a weighting coefficient. The objective function value calculation unit 13 outputs the objective function value f to the function value addition unit 14 .

[0087] The function value addition unit 14 obtains the penalty value p from the penalty value calculation unit 12 and obtains the objective function value f from the objective function value calculation unit 13 . The function value adding unit 14 performs weighted addition of the penalty function p and the objective function value f as shown in the following equation (11). p'=p+δ·f (11) In equation (11), δ is a weighting coefficient. The function value adding unit 14 outputs the penalty value p′ after the addition of the objective function value to the second allocation result acquiring unit 15.

[0088] When the second allocation result acquisition unit 15 is given the penalty value p' by the penalty value calculation unit 11, the second allocation result acquisition unit 15 updates the second learning model 15a so that the penalty value p' becomes smaller. The second allocation result acquisition unit 15 acquires the schedule information S at the second time. b Given the schedule information S b is given to the second learning model 15a, and a second allocation result X b Get the. The second allocation result acquisition unit 15 receives the second allocation result X b to the change cost calculation unit 3, the reward value difference prediction unit 4, and the allocation result selection unit 7, respectively.

[0089] In the above-described third embodiment, the allocation result determination device shown in FIG. 15 is configured to include a penalty value calculation unit 11 that calculates a penalty value for an allocation violation if there is an allocation violation in the allocation result selected by the allocation result selection unit 7. Furthermore, in the allocation result determination device shown in FIG. 15, the second allocation result acquisition unit 15 updates the second learning model 15a so that the penalty value calculated by the penalty value calculation unit 11 becomes smaller. Therefore, the allocation result determination device shown in FIG. 15 can improve the selection accuracy of the allocation result compared to the allocation result determination device shown in FIG. 1.

[0090] In addition, the present disclosure allows free combination of the respective embodiments, modification of any of the components of each embodiment, or omission of any of the components of each embodiment. [Industrial Applicability]

[0091] The present disclosure is suitable for an allocation result determination device and an allocation result determination method. [Explanation of symbols]

[0092] 1 First allocation result acquisition unit, 1a First learning model, 2 Second allocation result acquisition unit, 2a Second learning model, 3 Change cost calculation unit, 4 Reward value difference prediction unit, 5 Allocation result difference detection unit, 6 Difference prediction processing unit, 6a First prediction processing unit, 6b Second prediction processing unit, 6c Learning model, 6d Difference calculation processing unit, 7 Allocation result selection unit, 8 Reward value difference calculation unit, 8a First reward value calculation unit, 8b Second reward value calculation unit, 8c Difference calculation processing unit, 9 Reward value difference prediction unit, 10 Difference prediction processing unit, 10a First prediction processing unit, 10b Second prediction processing unit, 10c Learning model, 10d Difference calculation processing unit, 11 Penalty value calculation unit, 12 Penalty value calculation processing unit, 13 Objective function value calculation unit, 14 Function value addition unit, 15 Second allocation result acquisition unit, 15a Second learning model, 21 First allocation result acquisition circuit, 22 second allocation result acquisition circuit, 23 change cost calculation circuit, 24 reward value difference prediction circuit, 27 allocation result selection circuit, 28 reward value difference calculation circuit, 29 reward value difference prediction circuit, 31 penalty value calculation circuit, 35 second allocation result acquisition circuit, 41 memory, 42 processor.

Claims

1. a change cost calculation unit that acquires a first allocation result determined at a first time and a second allocation result determined at a second time that is later than the first time as an allocation result indicating an allocation order for a plurality of allocation objects, and calculates a change cost that is an increase in cost when the allocation result is changed from the first allocation result to the second allocation result; a reward value difference prediction unit that predicts a reward value difference between the first reward value and the second reward value by providing each of the first allocation result and the second allocation result to a learning model for predicting a reward value, obtaining from the learning model a first reward value indicating a degree of quality of the first allocation result and a second reward value indicating a degree of quality of the second allocation result, and subtracting the first reward value from the second reward value; an allocation result selection unit that selects the second allocation result if the reward value difference predicted by the reward value difference prediction unit is greater than 0 and the change cost calculated by the change cost calculation unit is equal to or less than a cost threshold, and selects the first allocation result if the reward value difference predicted by the reward value difference prediction unit is equal to or less than 0 or the change cost calculated by the change cost calculation unit is greater than the cost threshold; a reward value difference calculation unit that calculates the first reward value by providing the first allocation result to a reward function, calculates the second reward value by providing the second allocation result to the reward function, and calculates a reward value difference between the first reward value and the second reward value by subtracting the first reward value from the second reward value, The reward value difference prediction unit updates the learning model so that a difference between the predicted reward value difference and the reward value difference calculated by the reward value difference calculation unit becomes small. Allocation result determination device.

2. a first allocation result acquisition unit that provides schedule information of the plurality of allocation objects at a first time to a first learning model as an allocation result indicating an allocation order for the plurality of allocation objects, and acquires a first allocation result from the first learning model; a second allocation result acquisition unit that provides schedule information of the plurality of allocation objects at a second time that is a time later than the first time to a second learning model as an allocation result indicating an allocation order for the plurality of allocation objects, and acquires a second allocation result from the second learning model; a change cost calculation unit that acquires the first allocation result output from the first allocation result acquisition unit and the second allocation result output from the second allocation result acquisition unit, and calculates a change cost that is an increase in cost when the allocation result is changed from the first allocation result to the second allocation result; an allocation result selection unit that selects the first allocation result or the second allocation result based on the change cost calculated by the change cost calculation unit; a penalty value calculation unit that calculates a penalty value for an allocation violation if the allocation result selected by the allocation result selection unit includes the allocation violation, the penalty value calculation unit provides the allocation result selected by the allocation result selection unit to an objective function to calculate a value of the objective function, and adds an objective function value, which is the value of the objective function, to the penalty value; the second allocation result acquisition unit updates the second learning model so that a penalty value to which the objective function value is added becomes smaller. Allocation result determination device.

3. a change cost calculation unit that acquires a first allocation result determined at a first time and a second allocation result determined at a second time that is later than the first time as an allocation result indicating an allocation order for a plurality of allocation objects, and calculates a change cost that is an increase in cost when the allocation result is changed from the first allocation result to the second allocation result; a reward value difference prediction unit that predicts a reward value difference between the first reward value and the second reward value by providing each of the first allocation result and the second allocation result to a learning model for predicting a reward value, obtaining from the learning model a first reward value indicating a degree of quality of the first allocation result and a second reward value indicating a degree of quality of the second allocation result, and subtracting the first reward value from the second reward value; an allocation result selection unit that selects the second allocation result if the reward value difference predicted by the reward value difference prediction unit is greater than 0 and the change cost calculated by the change cost calculation unit is equal to or less than a cost threshold, and selects the first allocation result if the reward value difference predicted by the reward value difference prediction unit is equal to or less than 0 or the change cost calculated by the change cost calculation unit is greater than the cost threshold; an allocation result determination method of an allocation result determination device including: a reward value difference calculation unit that calculates the first reward value by providing the first allocation result to a reward function, calculates the second reward value by providing the second allocation result to the reward function, and calculates a reward value difference between the first reward value and the second reward value by subtracting the first reward value from the second reward value, the reward value difference prediction unit updates the learning model so that a difference between the predicted reward value difference and the reward value difference calculated by the reward value difference calculation unit becomes small. How allocation results are determined.

4. a first allocation result acquisition unit that provides schedule information of the plurality of allocation objects at a first time to a first learning model as an allocation result indicating an allocation order for the plurality of allocation objects, and acquires a first allocation result from the first learning model; a second allocation result acquisition unit that provides schedule information of the plurality of allocation objects at a second time that is a time later than the first time to a second learning model as an allocation result indicating an allocation order for the plurality of allocation objects, and acquires a second allocation result from the second learning model; a change cost calculation unit that acquires the first allocation result output from the first allocation result acquisition unit and the second allocation result output from the second allocation result acquisition unit, and calculates a change cost that is an increase in cost when the allocation result is changed from the first allocation result to the second allocation result; an allocation result selection unit that selects the first allocation result or the second allocation result based on the change cost calculated by the change cost calculation unit; an allocation result determination method for an allocation result determination device including: a penalty value calculation unit that calculates a penalty value for an allocation violation if the allocation result selected by the allocation result selection unit includes: the penalty value calculation unit provides the allocation result selected by the allocation result selection unit to an objective function to calculate a value of the objective function, and adds an objective function value, which is the value of the objective function, to the penalty value; the second allocation result acquisition unit updates the second learning model so that a penalty value to which the objective function value is added becomes smaller. How allocation results are determined.

Citation Information

Patent Citations

  • A Method for Ordering Landing Aircraft

    JP2006523874A

  • Scheduling device and scheduling method

    JP2017199193A

  • Vehicle allocation device, vehicle allocation method and program

    JP2020184094A

  • SYSTEM AND METHOD FOR PRIORITIZING OBJECT PREDICTIONS FOR AUTONOMOUS VEHICLES - Patent application

    JP2020531993A