Allocation result determination device and allocation result determination procedure

Abstract

The allocation result determination unit comprises a change cost calculation unit (3) that acquires a first allocation result, determined at a first time point in time, and a second allocation result, determined at a second time point in time later than the first, as an allocation result that specifies an allocation sequence for a plurality of objects to be allocated, and calculates change costs, which are the amount of a cost increase when the allocation result is changed from the first allocation result to the second allocation result. The allocation result determination unit further comprises an allocation result selection unit (7) that selects the first allocation result or the second allocation result based on the change costs calculated by the change cost calculation unit (3).

Description

Allocation result determination device and allocation result determination method

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

[0002] An example of a device for determining the allocation order for multiple allocation objects is a landing order determination device that determines the landing order of multiple 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 if, for example, the estimated arrival time of any aircraft changes.

[0003] Special Publication No. 2006-523874

[0004] When a change occurs in the scheduled arrival time of one of the aircraft after the landing order of multiple aircraft has been determined, 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. Examples of operational costs include fuel costs for the aircraft, as well as costs related to the physical and mental burdens on the pilots. The landing order determination device disclosed in Patent Document 1 has a problem in that, when a change occurs in the scheduled arrival time of one of the aircraft after the scheduler has determined the landing order of multiple aircraft, changing the landing order of the multiple aircraft 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 the allocation order for multiple allocation objects, can select the first allocation result or the second allocation result based on cost.

[0006] An allocation result determination device according to the present disclosure acquires, as allocation results indicating the allocation order for a plurality of allocation objects, 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, and includes a change cost calculation unit that 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 that selects the first allocation result or the second allocation result based on the change cost calculated by the change cost calculation unit.

[0007] According to the present disclosure, when a first allocation result is determined as an allocation result indicating the 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.

[0008] FIG. 7A is a configuration diagram showing an allocation result determination device according to embodiment 1. FIG. 7B is a hardware configuration diagram showing the hardware of the allocation result determination device according to embodiment 1. FIG. 7C is a hardware configuration diagram of a computer when the allocation result determination device is realized by software, firmware, or the like. FIG. 7D is a configuration diagram showing a difference prediction processing unit 6 of the allocation result determination device according to embodiment 1. FIG. 7E is an explanatory diagram showing an example of an allocation result showing the allocation order of landing of three airplanes. FIG. 7F is a flowchart showing an allocation result determination method which is a processing procedure of the allocation result determination device shown in FIG. 1. ａ is given to the first allocation result acquisition unit 1, the first allocation result X ａ 7B is an explanatory diagram showing an example of schedule information S ｂ is given to the second allocation result acquisition unit 2, the second allocation result X ｂ FIG. 10A is an explanatory diagram showing an example of a change cost table; FIG. 10B is an explanatory diagram showing a decay function g(j); ４ The difference information d when the allocation order of ａｂ 10B is an explanatory diagram showing the schedule information S ａAircraft not included in ８ However, the schedule information S ｂ Difference information d when included in ａｂ FIG. 17A is an explanatory diagram showing an allocation result determination device according to embodiment 2. FIG. 17B is an explanatory diagram showing a penalty table. FIG. 17A is a configuration diagram showing an allocation result determination device according to embodiment 2. FIG. 17B is a hardware configuration diagram showing the hardware of the allocation result determination device according to embodiment 2. FIG. 17B is a configuration diagram showing a reward value difference calculation unit 8 of the allocation result determination device according to embodiment 2. FIG. 17C is a configuration diagram showing a difference prediction processing unit 10 of the allocation result determination device according to embodiment 2. FIG. 17A is an explanatory diagram showing allocatable times and non-allocatable times, and FIG. 17B is an explanatory diagram showing a penalty table.

[0009] In order to explain 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 embodiment 1. Fig. 2 is a hardware configuration diagram showing hardware of the allocation result determination device according to embodiment 1. 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 7. The allocation result determination device shown in Fig. 1 determines an allocation result indicating, for example, the allocation order of takeoffs and landings of multiple aircraft as an allocation result indicating the allocation order for multiple allocation objects. 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 the 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. 2. The first allocation result acquisition unit 1 acquires schedule information S ａ is given to the first learning model 1a, and the first assignment result X ａThe first allocation result acquisition unit 1 acquires 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. ａ The first allocation result X 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. 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 a plurality of aircraft as input data, and is given allocation results X indicating the allocation order of takeoffs and landings of a plurality of aircraft as training data, and learns the allocation results X. During inference, the first learning model 1a is given schedule information S of a plurality of aircraft as input data, and learns the allocation results X. ａ When the schedule information S ａ The first allocation result X corresponding to ａ Here, the first learning model 1a is learned by supervised learning. However, this is merely an example, and the first learning model 1a may be learned by unsupervised learning, reinforcement learning, or a mathematical optimization method, for example.

[0013] The second allocation result acquisition unit 2 is realized by, for example, a second allocation result acquisition circuit 22 shown in Fig. 2. The second allocation result acquisition unit 2 acquires schedule information S of aircraft, which are multiple allocation targets, at a second time that is a time later than the first time. ｂ is given to the second learning model 2a, and the second learning model 2a outputs the second assignment result X ｂ Schedule information S ｂ The second allocation result X 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. ｂ is the allocation result determined at the second time. The second allocation result acquisition unit 2 acquires 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 a plurality of aircraft as input data, and is given allocation results X indicating the allocation order of takeoffs and landings of a plurality of aircraft as training data, and learns the allocation results X. During inference, the second learning model 2a is given schedule information S of a plurality of aircraft as input data, and learns the allocation results X. ｂ When the schedule information S ｂ The second allocation result X corresponding to ｂ 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 change cost calculation unit 3 is realized by, for example, the change cost calculation circuit 23 shown in Fig. 2. The change cost calculation unit 3 receives the first allocation result X from the first allocation result acquisition unit 1. ａ and obtains the second allocation result X from the second allocation result obtaining unit 2. ｂ The change cost calculation unit 3 obtains the allocation result as the 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 change cost calculation unit 3 calculates an increase 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, the reward value difference prediction circuit 24 shown in FIG. 2. 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 calculates an allocation result X ａ and the second allocation result X ｂ are given to the learning model 6c for predicting reward values ​​shown in FIG. 4, and the first allocation result X ａA first reward value R indicating the degree of quality of the ｐｒｅｄａ and the second allocation result X ｂ A second reward value R indicating the degree of quality of the ｐｒｅｄｂ The reward value difference prediction unit 4 obtains the second reward value R ｐｒｅｄｂ to the first reward value R ｐｒｅｄａ The first reward value R ｐｒｅｄａ and a second reward value R ｐｒｅｄｂ The reward value difference ΔR ｐｒｅｄ The reward value difference prediction unit 4 predicts 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 and a difference information d indicating the difference. ａｂ is output to the differential prediction processing unit 6.

[0018] The difference prediction processing unit 6 calculates the difference information d ａｂ indicates that there is a difference, the allocation result X ａ and the second allocation result X ｂ are given to a learning model 6c for predicting a reward value, and a first reward value R ｐｒｅｄａ and a second reward value R ｐｒｅｄｂ The difference prediction processing unit 6 obtains the second reward value R ｐｒｅｄｂ to the first reward value R ｐｒｅｄａ The first reward value R ｐｒｅｄａ and a second reward value R ｐｒｅｄｂ The reward value difference ΔR ｐｒｅｄ The difference prediction processing unit 6 predicts 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, the allocation result selection circuit 27 shown in FIG. ａｂ Based on this, the first allocation result X ａ , or the second allocation result X ｂSpecifically, 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 the cost threshold Thc is less than or equal to the second allocation result X ｂ The allocation result selection unit 7 selects the reward value difference ΔR ｐｒｅｄ is 0 or less, or the change cost C ａｂ is greater than the cost threshold Thc, the first allocation result X ａ The cost threshold 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, namely, first allocation result acquisition unit 1, second allocation result acquisition unit 2, change cost calculation unit 3, reward value difference prediction unit 4, and allocation result selection unit 7, is realized by dedicated hardware as shown in Fig. 2. In other words, it is assumed that the allocation result determination device is realized by first allocation result acquisition circuit 21, second allocation result acquisition circuit 22, change cost calculation circuit 23, reward value difference prediction circuit 24, and 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 is, 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 thereof.

[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. Software or firmware is stored in the memory of a computer as a program. A computer refers to hardware that executes a program, and includes, for example, a CPU (Central Processing Unit), central processing unit, processing unit, arithmetic unit, microprocessor, microcomputer, processor, or DSP (Digital Signal Processor).

[0022] 3 is a hardware configuration diagram of a computer when the allocation result determination device is realized by software, firmware, etc. When the allocation result determination device is realized by software, firmware, etc., a program for causing a computer to execute the processing procedures of 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 memory 41. Then, a processor 42 of the computer executes the program stored in 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, 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, firmware, etc.

[0024] Fig. 4 is a configuration diagram showing the difference prediction processing unit 6 of the allocation result determination device according to embodiment 1. 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 calculates 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 ａ is given to the learning model 6c for predicting the reward value, and the first reward value R ｐｒｅｄａ The first prediction processing unit 6a obtains the first reward value R ｐｒｅｄａ is output to the difference calculation processing unit 6d.

[0026] The second prediction processing unit 6b calculates 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 ｂ is given to the learning model 6c for predicting the reward value, and the second reward value R ｐｒｅｄｂ The second prediction processing unit 6b obtains the second reward value R ｐｒｅｄｂ is output to the difference calculation processing unit 6d.

[0027] The learning model 6c for predicting reward values ​​is given the allocation result X as input data during learning, and the reward value R ｐｒｅｄ is given, and the reward value R ｐｒｅｄ The reward value R ｐｒｅｄ For example, if the cost of selecting the allocation result X is high, then ρ is a small value, and if the cost of selecting the allocation result X is low, then ρ is a large value. ａ , or the second allocation result X ｂ Given the first allocation result X ａ A first reward value R corresponding to ｐｒｅｄａ , or the second allocation result X ｂ A second reward value R corresponding to ｐｒｅｄｂ 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 unsupervised learning, reinforcement learning, or a mathematical optimization method, for example.

[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 Rｐｒｅｄａ and a second reward value R ｐｒｅｄｂ The reward value difference ΔR ｐｒｅｄ 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 indicating the allocation order of landings 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 FIG. 5, the no-landing time after the small airplane lands is 60 [sec], the no-landing time after the medium airplane lands is 180 [sec], and the no-landing time after the large airplane lands is 240 [sec]. If the landings of the medium airplane, the large airplane, and the small airplane are permitted in this order, as shown in FIG. 5, the shortest time until all three airplanes land is 420 (= 180 + 240) [sec]. If the landings of the medium airplane, the small airplane, and the large airplane are permitted in this order, as shown in FIG. 5, the shortest time until all three airplanes land is 240 (= 180 + 60) [sec]. Therefore, if the landing permission is given to medium-sized planes, then small planes, then large planes, the shortest time until all planes land will be 180 (= 420 - 240) seconds shorter than if the landing permission is given to medium-sized planes, then large planes, then small planes.

[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. 1. The first allocation result acquisition unit 1 acquires schedule information S of a plurality of aircraft at a first time. ａ Schedule information S ａ The schedule information S 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. 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 acquires 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 the schedule information S ａ is given to the first allocation result acquisition unit 1, the first allocation result X ａ 7A is an explanatory diagram showing an example of t １ , t ２ , ..., t ８ is the time, and j １ , j ２ , ..., j ５ is an ID (IDentification) that identifies an aircraft. "0" indicates that the aircraft cannot be assigned a takeoff or landing, and "1" indicates that the aircraft can be assigned a takeoff or landing. In the example of FIG. 7A, ３ , aircraft j ５ , aircraft j １ , aircraft j ２ , aircraft j ４ The first allocation result X 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 later than the first time. ｂ Schedule information S ｂ The schedule information S includes, for example, information indicating the scheduled landing time of each aircraft or the scheduled takeoff time of each aircraft and the size of each aircraft. ｂ is given to the second learning model 2a, and the second learning model 2a outputs the second assignment result X ｂ (Step ST2 in FIG. 6). The second allocation result acquisition unit 2 acquires 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 the schedule information S ｂ is given to the second allocation result acquisition unit 2, the second allocation result Xｂ 7B is an explanatory diagram showing an example of t １ , t ２ , ..., t ８ is the time, and j １ , j ２ , ..., j ５ is an ID for identifying an aircraft. "0" indicates that the aircraft cannot be assigned a takeoff or landing, and "1" indicates that the aircraft can be assigned a takeoff or landing. 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 that 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 obtains the second allocation result X from the second allocation result obtaining unit 2. ｂ The change cost calculation unit 3 obtains the allocation result as a first allocation result X by referring to a change cost table such as that shown in FIG. 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 showing an example of a change cost table. １ , j ２ , ..., j ５ is an identification code indicating the aircraft. The numbers in the table indicate the change cost. 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 Therefore, the order of the change cost C ａｂ 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 is reversed, and ５ and aircraft １ Therefore, the order of 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 the change cost table shown in FIG. 8 to calculate the change cost C ａｂ However, this is merely an example, and the change cost calculation unit 3 may calculate the change cost C as follows, for example: ａｂ First, the change cost calculation unit 3 calculates the second allocation result X as shown in the following formula (1). ｂ ' to the first allocation result X ａ The allocation difference ΔX is calculated by subtracting X. ｂ ' is the second allocation result X ｂ The time is set as 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 t３ Gat １ , time t ４ Gat ２ , time t １０ Gat ８ Assume that ΔX = X ｂ '-X ａ　　　　 (1)

[0037] Next, the change cost calculation unit 3 substitutes the allocation difference ΔX into the following equation (2) to calculate the change cost C associated with the change in order: ０ Furthermore, the change cost calculation unit 3 calculates the change cost C associated with the time change by substituting the allocation difference ΔX into the following equation (3): ｔ Calculate.

[0038] g(j) is a decay function as shown in FIG. 9, for example, g(j)=e （－ｊ／Ｔ） j is an ID that identifies the aircraft, and T is a time constant. 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 S ｂ If there is no difference with ａｂ =0, and the schedule information S ａ and schedule information S ｂ If there is a difference with d ａｂ = 1. 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 of order, for example, as shown in the following formula (4): ０ and the change cost C associated with the time change ｔ By weighting and adding these, 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 ΔRｐｒｅｄ (Step ST4 in FIG. 6). Hereinafter, the reward value difference ΔR ｐｒｅｄ The allocation result difference detection unit 5 of the reward value difference prediction unit 4 calculates the schedule information S ａ and schedule information S at the second time ｂ As shown in FIG. 10, the allocation result difference detection unit 5 acquires the schedule information S ａ and schedule information S ｂ and a difference information d indicating the difference. ａｂ to the difference prediction processing unit 6. The change cost calculation unit 3 calculates the change cost C ａｂ When calculating the difference information d ａｂ is also output to the change cost calculation unit 3. ４ The difference information d when the allocation order of ａｂ FIG. 10B is an explanatory diagram showing the schedule information S ａ Aircraft not included in ８ However, the schedule information S ｂ Difference information d when included in ａｂ 10A and 10B, the numbers in the circles are IDs that identify aircraft. However, the symbol j is omitted. ａ and schedule information S ｂ If there is no difference with ａｂ =0, and the schedule information S ａ and schedule information S ｂ If there is a difference with d ａｂ =1.

[0041] The first prediction processing unit 6a of the differential 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 The first prediction processing unit 6a obtains the difference information d ａｂ If is "1", the first allocation result X ａis given to the learning model 6c for predicting the reward value, and the first reward value R ｐｒｅｄａ The first prediction processing unit 6a obtains the first reward value R ｐｒｅｄａ is output 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 The second prediction processing unit 6b obtains the difference information d ａｂ If "1", the second allocation result X ｂ is given to the learning model 6c for predicting the reward value, and the second reward value R ｐｒｅｄｂ The second prediction processing unit 6b obtains the second reward value R ｐｒｅｄｂ is output to the difference calculation processing unit 6d.

[0043] The difference calculation processing unit 6d receives the first reward value R ｐｒｅｄａ and the second prediction processing unit 6b obtains a second reward value R ｐｒｅｄｂ The difference calculation processing unit 6d calculates the second reward value R as shown in the following equation (5): ｐｒｅｄｂ to the first reward value R ｐｒｅｄａ The first reward value R ｐｒｅｄａ and a second reward value R ｐｒｅｄｂ The reward value difference ΔR ｐｒｅｄ The reward value difference ΔR is calculated. ｐｒｅｄ is a negative value, the second allocation result X ｂ The cost when selecting the first allocation result X ａ The reward value difference ΔR ｐｒｅｄ If is a positive value, the second allocation result X ｂ The cost when selecting the first allocation result X ａ This is lower than the cost of selecting 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 obtains the second allocation result X from the second allocation result obtaining unit 2. ｂ The allocation result selection unit 7 obtains the change cost C calculated by the change cost calculation unit 3. ａｂ and the reward value difference ΔR predicted by the reward value difference prediction unit 4 ｐｒｅｄ Based on this, 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 the cost threshold Thc is less than or equal to the second allocation result X ｂ The allocation result selection unit 7 selects the reward value difference ΔR ｐｒｅｄ is 0 or less, or the change cost C ａｂ 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 this, the first allocation result X ａ , or the second allocation result X ｂ However, this is only 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 this case, the allocation result determination device does not need to include the reward value difference prediction unit 4. Furthermore, the allocation result selection unit 7 does not need to include 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 ｐｒｅｄBased only on the first allocation result X ａ , or the second allocation result X ｂ When the above-mentioned selection is made, the allocation result determination device does not need to include the change cost calculation unit 3.

[0046] In the first embodiment described above, the allocation result determination device is configured to include a change cost calculation unit 3 that acquires, as allocation results indicating the allocation order for a plurality of allocation objects, 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, 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, when a second allocation result is determined after a first allocation result is determined as an allocation result indicating the allocation order for a plurality of allocation objects, the allocation result determination device can select the first allocation result or the second allocation result based on the cost.

[0047] Second Embodiment In a 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] Figure 11 is a configuration diagram showing an allocation result determination device according to embodiment 2. In Figure 11, the same reference numerals as in Figure 1 indicate the same or corresponding parts, and therefore explanations will be omitted. Figure 12 is a hardware configuration diagram showing the hardware of the allocation result determination device according to embodiment 2. In Figure 12, the same reference numerals as in Figure 2 indicate the same or corresponding parts, and therefore explanations will be omitted. The allocation result determination device shown in Figure 11 comprises 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, the reward value difference calculation circuit 28 shown in FIG. 12. The reward value difference calculation unit 8 calculates the first allocation result X ａ is given to the reward function to obtain the first reward value R ａand calculate the second allocation result X ｂ is given to the reward function to obtain the second reward value R ｂ 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 a second reward value R ｂ 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. 12. 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 calculates an allocation result X ａ and the second allocation result X ｂ are given to the learning model 10c for predicting reward values ​​shown in FIG. 14, and the first allocation result X ａ A first reward value R indicating the degree of quality of the ｐｒｅｄａ and the second allocation result X ｂ A second reward value R indicating the degree of quality of the ｐｒｅｄｂ The reward value difference prediction unit 9 obtains the second reward value R ｐｒｅｄｂ to the first reward value R ｐｒｅｄａ The first reward value R ｐｒｅｄａ and a second reward value R ｐｒｅｄｂ The reward value difference ΔR ｐｒｅｄ The reward value difference prediction unit 9 predicts the reward value difference ΔR ｐｒｅｄ to the allocation result selection unit 7. The reward value difference prediction unit 9 outputs 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 estimated reward value difference ΔR becomes smaller.

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

[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 processing procedures of 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 memory 41 shown in Figure 3. Then, a processor 42 shown in Figure 3 executes the program stored in memory 41.

[0053] 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, 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, firmware, etc.

[0054] 13 is a block diagram showing a reward value difference calculation unit 8 of the allocation result determination device according to embodiment 2. 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 The first reward value calculation unit 8a obtains the first allocation result X ａ is given to the reward function to obtain the first reward value R ａ and calculates the first reward value R ａ is output 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 The second reward value calculation unit 8b obtains the second allocation result X ｂ is given to the reward function to obtain the second reward value R ｂ and calculates the second reward value R ｂ The difference calculation processing unit 8c receives the first reward value R from the first reward value calculation unit 8a. ａ and obtains the second reward value R ｂ The difference calculation processing unit 8c obtains the second reward value R ｂ to the first reward value R ａ The first reward value R ａ and a second reward value R ｂ 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 embodiment 2. 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 calculates 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 ａis given to a learning model 10c for predicting a reward value, and a first reward value R ｐｒｅｄａ The first prediction processing unit 10a obtains the first reward value R ｐｒｅｄａ is output to the difference calculation processing unit 10d.

[0058] The second prediction processing unit 10b calculates 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 ｂ is given to the learning model 10c for predicting the reward value, and the second reward value R ｐｒｅｄｂ The second prediction processing unit 10b obtains the second reward value R ｐｒｅｄｂ is output to the difference calculation processing unit 10d.

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

[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 a second reward value R ｐｒｅｄｂ The 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, the allocation result determination device is the same as that shown in Fig. 1. Therefore, only the operation of the reward value difference calculation unit 8 and the reward value difference prediction unit 9 will be described here.

[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 The first reward value calculation unit 8a obtains the first allocation result X ａ is given 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. ａｓｓｉｇｎａ is the first allocation result X ａ The earlier the allocation time of each aircraft is within the range of allocable times, the larger the value becomes. ｓｅｐａｒａｔｉｏｎａ is an evaluation value regarding the allocation interval of multiple aircraft. 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 becomes. α is a weighting coefficient. The first reward value calculation unit 8a calculates the first reward value R ａ is output 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 The second reward value calculation unit 8b obtains the second allocation result X ｂ is given 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. ａｓｓｉｇｎｂis the second allocation result X ｂ The earlier the allocation time of each aircraft is within the range of allocable times, the larger the value becomes. ｓｅｐａｒａｔｉｏｎｂ is an evaluation value regarding the allocation interval of multiple aircraft. 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 becomes. β is a weighting coefficient. The second reward value calculation unit 8b calculates the second reward value R ｂ is output to the difference calculation processing unit 8c.

[0064] The difference calculation processing unit 8c receives the first reward value R from the first reward value calculation unit 8a. ａ and obtains the second reward value R ｂ The difference calculation processing unit 8c calculates the second reward value R as shown in the following equation (8). ｂ to the first reward value R ａ The first reward value R ａ and a second reward value R ｂ Calculate the reward value difference ΔR between ｐｒｅｄ =R ｂ -R ａ　 (8) The difference calculation processing unit 8 c outputs the reward value difference ΔR to the difference prediction processing unit 10 of the reward value difference prediction unit 9 .

[0065] The first prediction processing unit 10a of the differential 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 The first prediction processing unit 10a obtains 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 The first prediction processing unit 10a obtains the first reward value R ｐｒｅｄａ is output 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. ｂand obtains the difference information d from the allocation result difference detection unit 5. ａｂ The second prediction processing unit 10b obtains the difference information d ａｂ If "1", the second allocation result X ｂ is given to the learning model 10c for predicting the reward value, and the second reward value R ｐｒｅｄｂ The second prediction processing unit 10b obtains the second reward value R ｐｒｅｄｂ is output to the difference calculation processing unit 10d.

[0067] The difference calculation processing unit 10d receives the first reward value R ｐｒｅｄａ and obtains a second reward value R ｐｒｅｄｂ The difference calculation processing unit 10d obtains the second reward value R as shown in the above formula (5). ｐｒｅｄｂ to the first reward value R ｐｒｅｄａ The first reward value R ｐｒｅｄａ and a second reward value R ｐｒｅｄｂ The reward value difference ΔR ｐｒｅｄ 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 and the reward value difference ΔR calculated by the difference calculation processing unit 8c of the reward value difference calculation unit 8. Specifically, each of the first prediction processing unit 10a and the second prediction processing unit 10b updates the learning model 10c so as to reduce the difference between (ΔR - ΔR ｐｒｅｄ ) ２ The weights of the learning model 10c are updated so that the following is minimized:

[0069] In the second embodiment described above, 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 a first allocation result to a reward function to calculate a first reward value, providing a second allocation result to the reward function to calculate a second reward value, and subtracting the first reward value from the second reward value. Furthermore, the allocation result determination device shown in FIG. 11 updates the learning model 10c so that the reward value difference prediction unit 9 reduces 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. Therefore, the allocation result determination device shown in FIG. 11 can improve the accuracy of allocation result selection more than the allocation result determination device shown in FIG. 1.

[0070] Third Embodiment In a 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 the hardware of an allocation result determination device according to embodiment 3. In Fig. 16, the same reference numerals as in Fig. 2 indicate the same or corresponding parts, and therefore description thereof will be omitted. The allocation result determination device shown in Fig. 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. 16 . 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. 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 processing unit 12 calculates a penalty value for the allocation violation. The penalty value calculation processing 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 an objective function to calculate an objective function value, which 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 addition unit 14 adds the objective function value calculated by the objective function value calculation unit 13 to the penalty value calculated by the penalty value calculation processing unit 12. The function value addition unit 14 outputs the penalty value after the addition of the objective function value to the second allocation result acquisition unit 15.

[0074] 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, it outputs the penalty value calculated by the penalty value calculation processing unit 12 to the second allocation result acquisition unit 15. When the penalty value calculation unit 11 includes only the objective function value calculation unit 13, it outputs the objective function value as the penalty value to the second allocation result acquisition unit 15.

[0075] The second allocation result acquisition unit 15 is realized by, for example, a second allocation result acquisition circuit 35 shown in FIG. 16. The second allocation result acquisition unit 15 acquires schedule information S ｂ is given to the second learning model 15a, and the second learning model 15a outputs a second assignment result X ｂ The second allocation result acquisition unit 15 acquires 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. In addition, 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 a plurality of aircraft as input data, and is given allocation results X indicating the allocation order of takeoffs and landings of a plurality of aircraft as training data, and learns the allocation results X. During inference, the second learning model 15a is given schedule information S of a plurality of aircraft as input data, and learns the allocation results X. ｂ When the schedule information S ｂ The second allocation result X corresponding to ｂ Here, the second learning model 15a is learned by supervised learning. However, this is merely an example, and the second learning model 15a may be learned by unsupervised learning, reinforcement learning, or a mathematical optimization method, for example.

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

[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 processing procedures 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 is stored in memory 41 shown in Fig. 3. Then, a processor 42 shown in Fig. 3 executes the program stored in memory 41.

[0080] 16 shows an example in which each of the components of the allocation result determination device is realized by dedicated hardware, while Fig. 3 shows an example in which the allocation result determination device is realized by software, 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, 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, only the operations of the penalty value calculation unit 11 and the second allocation result acquisition unit 15 will be described here.

[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 The penalty value calculation processing unit 12 obtains the allocation result X ｓｅｌ 17A is an explanatory diagram showing allocatable times and non-allocable times. １ , t ２ , ..., t ８is the time, and j １ , j ２ , ..., j ５ is an ID that identifies the aircraft. "0" indicates an unavailable time, and "1" indicates an available time. 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 a penalty table. The penalty table shown in FIG. 17B shows the penalty value when an assignment is made at an assignable time and the penalty value when an assignment is made at an unassignable time. In the example of FIG. 17B, the penalty value when an assignment is made at an assignable time is "0", and the penalty value when an assignment is made at an unassignable time is a negative value. For example, the absolute value of the penalty value when an assignment is made at an earlier time than the assignable time is larger the earlier the assignment is made at the assignable time. If there is an assignment violation, the penalty value calculation processing unit 12 refers to the penalty table shown in FIG. 17B and calculates the penalty value p. For example, for aircraft j ２ is time t ２ and the allocation violations assigned to aircraft j ３ is time t ５ If there is an allocation violation and aircraft j is assigned to aircraft j, the penalty value p is −510 (=−500−10). ５ is time t ６ If there is only an allocation violation assigned to , the penalty value p will be −5. The penalty value calculation processing unit 12 outputs the penalty value p to the function value addition unit .

[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 only an example. For example, the penalty value calculation processing unit 12 may calculate the penalty value by referring to the allocation result X ｓｅｌ is expressed as a penalty function p(X ｓｅｌ ) and the penalty function p(X ｓｅｌ) may be calculated as a penalty value p.

[0085] In equation (9), the penalty function p(X ｓｅｌ ) is a decay function, which is 0 if there is no allocation violation. ｊ is a coefficient, and 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 The objective function value calculation unit 13 obtains the allocation result X ｓｅｌ is expressed as the objective function f(X ｓｅｌ ) and the objective function f(X ｓｅｌ ) is calculated as the objective function value f(X ｓｅｌ ) = f ａｓｓｉｇｎ +ε·fseparation (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 allocatable times, the earlier the allocation time is within the range of allocatable times, the larger the value. ｓｅｌ If the assigned time of each aircraft indicated by is an unavailable time, ａｓｓｉｇｎ fseparation is a small value such as -1000. ｓｅｌ fseparation is a value determined by the following equation. If the allocation interval is larger than the minimum allocatable interval, fseparation becomes a larger value as the allocation interval becomes smaller. If the allocation interval is smaller than the minimum allocatable interval, fseparation becomes 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 adder 14 obtains the penalty value p from the penalty value calculation processor 12 and obtains the objective function value f from the objective function value calculator 13. The function value adder 14 performs a 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 adder 14 outputs the penalty value p' after the addition of the objective function value to the second allocation result acquirer 15.

[0088] When the penalty value p′ is given to the second allocation result acquisition unit 15 from 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. ｂ Given the schedule information S ｂ is given to the second learning model 15a, and the second learning model 15a outputs a second assignment result X ｂ The second allocation result acquisition unit 15 acquires 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 the allocation result selected by the allocation result selection unit 7 contains an allocation violation. 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 as to reduce the penalty value calculated by the penalty value calculation unit 11. Therefore, the allocation result determination device shown in Fig. 15 can improve the accuracy of allocation result selection compared to the allocation result determination device shown in Fig. 1.

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

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

[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. An allocation result determination device comprising: a change cost calculation unit that acquires, as allocation results indicating the allocation order for a plurality of allocation objects, 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, and calculates a change cost that is the increase in cost when the allocation result is changed from the first allocation result to the second allocation result; and 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.

2. The allocation result determination device described in claim 1 further comprises a reward value difference prediction unit that predicts the 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 reward values, obtaining from the learning model a first reward value indicating the degree of goodness or badness of the first allocation result and a second reward value indicating the degree of goodness or badness of the second allocation result, and subtracting the first reward value from the second reward value, wherein the allocation result selection unit selects the first allocation result or the second allocation result based on the change cost calculated by the change cost calculation unit and the reward value difference predicted by the reward value difference prediction unit.

3. An allocation result determination device as described in claim 2, characterized in that instead of having the change cost calculation unit, it has the reward value difference prediction unit, and the allocation result selection unit selects the first allocation result or the second allocation result based on the reward value difference predicted by the reward value difference prediction unit.

4. The allocation result determination device described in claim 2, further comprising a reward value difference calculation unit that calculates the 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 the first reward value, providing the second allocation result to the reward function to calculate the second reward value, and subtracting the first reward value from the second reward value, wherein 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.

5. The allocation result determination device according to claim 1, characterized in that it comprises: a first allocation result acquisition unit that provides schedule information of the plurality of allocation objects at the first time to a first learning model, acquires the first allocation result from the first learning model, and outputs the first allocation result to the change cost calculation unit; and a second allocation result acquisition unit that provides schedule information of the plurality of allocation objects at the second time to a second learning model, acquires the second allocation result from the second learning model, and outputs the second allocation result to the change cost calculation unit.

6. The allocation result determination device described in claim 5, further comprising a penalty value calculation unit that calculates a penalty value for the allocation violation if there is an allocation violation in the allocation result selected by the allocation result selection unit, and the second allocation result acquisition unit updates the second learning model so that the penalty value calculated by the penalty value calculation unit becomes smaller.

7. The allocation result determination device described in claim 6, characterized in that the penalty value calculation unit provides the allocation result selected by the allocation result selection unit to an objective function to calculate the value of the objective function and adds the objective function value, which is the value of the objective function, to the penalty value, and the second allocation result acquisition unit updates the second learning model so that the penalty value after adding the objective function value becomes smaller.

8. An allocation result determination method in which a change cost calculation unit obtains, as allocation results indicating the allocation order for multiple allocation objects, 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, and calculates a change cost which is the increase in cost when the allocation result is changed from the first allocation result to the second allocation result; and an allocation result selection unit selects the first allocation result or the second allocation result based on the change cost calculated by the change cost calculation unit.

Images