Equipment control device, equipment control method, and equipment control program

Abstract

An equipment control device (100) that assists decision-making related to equipment control settings comprises an optimization calculation unit (110) and an extraction unit (140). The optimization calculation unit (110) uses an optimization technique to create candidates for a plurality of equipment control settings as elements of a creation candidate group within a range within which the equipment can be controlled. The extraction unit (140) extracts, from the creation candidate group, one or more equipment control setting candidates as elements of an extraction candidate group by using an inference model (131) that has learned the preference of an equipment manager relating to the equipment control settings.

Description

Facility control device, facility control method, and facility control program

[0001] The present disclosure relates to an equipment control device, an equipment control method, and an equipment control program.

[0002] A system is known that extracts multiple candidate equipment control settings using an optimization technique such as mathematical programming and supports decision-making regarding equipment control settings based on the extracted multiple candidate equipment control settings. Patent Document 1 discloses a method for visualizing conflicts between constraints as a method for selecting one equipment control setting from multiple equipment control settings. Patent Document 2 discloses a method for extracting some candidate equipment control settings based on conditions such as proximity to a certain value or a certain interval, and presenting them to a decision maker.

[0003] JP 2021-144569 A Patent No. 6073000 A

[0004] The method disclosed in Patent Document 1 has a problem in that the implicit decision-making criteria of the decision maker must be considered as constraints before optimization.The method disclosed in Patent Document 2 has a problem in that the decision maker's preferences cannot be sufficiently reflected, and there is a risk that equipment control settings that deviate from the decision maker's preferences will continue to be presented to the decision maker.

[0005] The present disclosure aims to support decision-making regarding equipment control settings by reflecting the preferences of a decision maker without taking into account the implicit decision-making criteria that the decision maker has in advance.

[0006] The equipment control device according to the present disclosure is an equipment control device that supports decision-making regarding equipment control settings, and includes an optimization calculation unit that uses optimization technology to create multiple equipment control setting candidates as elements of a group of candidates to be created within the equipment controllable range, and an extraction unit that uses an inference model that has learned the preferences of equipment managers regarding equipment control settings to extract one or more equipment control setting candidates from the group of candidates to be created as elements of a group of candidates to be extracted.

[0007] According to the present disclosure, the extraction unit extracts one or more candidate equipment control settings from a plurality of candidate equipment control settings created using an optimization technique, using an inference model that has learned the preferences of an equipment manager regarding equipment control settings. Therefore, according to the present disclosure, in decision-making support regarding equipment control settings, it is possible to reflect the preferences of a decision maker without taking into account the decision maker's implicit decision-making criteria in advance.

[0008] FIG. 1 is a diagram showing an example of the configuration of an equipment control system 90 according to a first embodiment. FIG. 1 is a diagram showing an example of the hardware configuration of an equipment control device 100 according to a first embodiment. FIG. 2 is a flowchart showing the operation of the equipment control device 100 according to the first embodiment during learning. FIG. 3 is a flowchart showing the operation of the equipment control device 100 according to the first embodiment during inference. It is a diagram explaining the processing of the optimization calculation unit 110 and the extraction unit 140 according to the first embodiment, where (a) is a diagram showing equipment control setting candidates created by the optimization calculation unit 110, and (b) is a diagram showing equipment control setting candidates extracted by the extraction unit 140. It is a diagram showing an example of the hardware configuration of an equipment control device 100 according to a modified example of the first embodiment. It is a diagram explaining the processing of a display unit 150 according to a second embodiment. It is a diagram explaining the processing of the display unit 150 according to a modified example of the second embodiment. It is a flowchart showing the operation of the equipment control device 100 according to a third embodiment during inference. It is a diagram explaining the processing of the extraction unit 140 according to the third embodiment. It is a flowchart showing the operation of the equipment control device 100 according to a fourth embodiment during inference. It is a diagram showing an example of the configuration of an equipment control system 90 according to a fifth embodiment. FIG. 10 is a diagram for explaining the processing of the display unit 150 according to a modified example of embodiment 5. FIG. 11 is a diagram showing an example of the configuration of an equipment control system 90 according to embodiment 6. FIG. 12 is a flowchart showing the operation of a dialogue-based learning unit 610 according to embodiment 6. FIG. 13 is a diagram showing an example of the configuration of an equipment control system 90 according to embodiment 7.

[0009] In the description of the embodiments and drawings, the same elements and corresponding elements are given the same symbols. The description of elements given the same symbols is omitted or simplified as appropriate. Arrows in the drawings mainly indicate the flow of data or the flow of processing. Furthermore, "unit" may be interpreted as "circuit," "device," "equipment," "process," "step," "procedure," "processing," or "circuitry" as appropriate. The functions of each unit provided in each device may be realized by firmware, software, hardware, or a combination of these.

[0010] First Embodiment Hereinafter, the present embodiment will be described in detail with reference to the drawings.

[0011] ***Configuration*** FIG. 1 shows an example configuration of an equipment control system 90 according to the present embodiment. The equipment control system 90 includes an equipment control device 100, an equipment management device 20, a display device 30, and an input device 40. The multiple devices included in the equipment control system 90 may be integrated as appropriate. The equipment control device 100 is a device that supports decision-making regarding equipment control settings and determines the control settings for each piece of equipment according to the preferences of an equipment manager. As shown in FIG. 1 , the equipment control device 100 includes an optimization calculation unit 110, a memory unit 120, a learning unit 130, an extraction unit 140, a display unit 150, an input unit 160, a selection unit 170, and a communication unit 180. Specific examples of the equipment include lighting, air conditioners, and ventilation systems. Specific examples of the equipment include equipment installed in office buildings, commercial facilities, or factories. An equipment manager is an entity that manages each piece of equipment. The equipment manager may be a group of multiple people. The equipment management device 20 is a device that has a function of managing equipment in accordance with instructions from the equipment control device 100. The display device 30 has a function of displaying output from the equipment control device 100 to the equipment manager. The input device 40 has a function of receiving input from the equipment manager and transmitting the received input to the equipment control device 100.

[0012] The optimization calculation unit 110 uses optimization techniques to calculate multiple candidate equipment control settings that meet the preferences of the equipment manager within the equipment controllable range. The multiple candidate equipment control settings may be considered as elements of a candidate group to be created. In this case, the optimization calculation unit 110 may use data acquired from each piece of equipment and its surroundings, as well as other data related to the operation of each piece of equipment, such as data indicating date and time. The equipment control settings may indicate an operation plan for each piece of equipment.

[0013] The storage unit 120 stores each past selection result by the facility manager and each condition corresponding to each selection result. The storage unit 120 may record, as learning data, data linking a group of extraction candidates with elements selected by the facility manager from the group of extraction candidates.

[0014] The learning unit 130 learns the inference model 131 based on each past selection result by the facility manager and each condition corresponding to each selection result. The learning unit 130 may learn the inference model 131 based on learning data.

[0015] The extraction unit 140 extracts equipment control setting candidates that suit the preferences of the equipment manager from the equipment control setting candidates calculated by the optimization calculation unit 110, through inference using the inference model 131. In other words, the extraction unit 140 uses the inference model 131 to extract one or more equipment control setting candidates from the group of candidates to be created as elements of the group of candidates to be extracted.

[0016] The display unit 150 displays the equipment control setting candidates extracted by the extraction unit 140, that is, each element of the extracted candidate group, to the equipment manager.

[0017] The input unit 160 accepts input of equipment control settings selected by the equipment manager.

[0018] The selection unit 170 selects equipment control settings to be actually applied to each piece of equipment from the equipment control setting candidates extracted by the extraction unit 140 based on the input received by the input unit 160 .

[0019] The communication unit 180 transmits the equipment control settings selected by the selection unit 170 to the equipment management device 20 .

[0020] The inference model 131 will be described in detail below. The inference model 131 is a model that learns the preferences of an equipment manager regarding equipment control settings. First, the result of a single selection of an equipment control setting by the equipment manager includes, as specific examples, data indicating energy consumption, satisfaction, and the equipment control setting as each piece of feature data. Each piece of feature data is treated as a feature vector. Specific examples of energy consumption include annual power consumption [kWh], a Building Energy Index (BEI) value, and / or a percentage range of a controllable range of energy consumption. Specific examples of satisfaction include at least one of several satisfaction indices and a percentage range of a controllable satisfaction range. As the satisfaction indices, various proposed indices may be used, such as a thermal sensation index such as a predicted mean vote (PMV) or the environmental satisfaction index presented in [Reference 1]. Specific examples of equipment control settings include the dimming rate [%] of lighting for each room, the set temperature [°C] of the air conditioner for each room, and the difference [°C] between the set temperatures for each room.

[0021] [Reference 1] K. Fukuhara et al. , “Digital Twin Based Evolutionary Building Facility Control Optimization,”2022 IEEE Congress on Evolutionary Computation (CEC), 2022, pp. 1-8

[0022] The learning unit 130 trains the inference model 131 by modeling the preferences (profile) of the equipment manager using feature data based on multiple selection results by the equipment manager. The inference model 131 may utilize a recommendation method, such as cosine similarity or a naive Bayes classifier, employed in content-based filtering of recommendations on electronic commerce (EC) sites, as a specific example, or other methods. When the inference model 131 utilizes cosine similarity, the closeness of each equipment control setting candidate to the equipment manager's profile is obtained. Therefore, in this case, a predetermined number of candidates may be extracted and output from the equipment control setting candidates in order of corresponding closeness. The similarity may be calculated after mapping multidimensional features to two dimensions using a self-organization map (SOM) or a variational autoencoder (VAE). When a classifier is used in the inference model 131, it is determined whether each candidate equipment control setting matches the equipment manager profile. Therefore, in this case, only equipment control settings that match the equipment manager profile may be extracted and output. Furthermore, if the results of equipment control setting selections by equipment managers in other buildings can also be used, a method employed in collaborative filtering may be used in addition to content-based methods. Furthermore, when selecting an equipment control setting, it is easier to select from candidates with significantly different energy consumption, satisfaction, etc. Therefore, the candidate equipment control settings may be divided into several clusters in advance, an inference model 131 may be constructed for each cluster, and a set of equipment control settings recommended by the inference model 131 corresponding to each cluster may be output as extracted candidates. As a specific example, with regard to the clusters, ranges corresponding to each cluster may be defined in advance by dividing the range of energy consumption in increments of N units, and each cluster may be constructed consisting of candidate equipment control settings corresponding to each range.The target of range segmentation may be satisfaction or equipment control settings instead of energy consumption, or a combination of these. Clusters may also be constructed by grouping data according to the proximity of corresponding features using a k-means method or the like. Features may also be mapped to two dimensions using a SOM or VAE, and then range segmentation or k-means classification may be performed.

[0023] 2 shows an example of the hardware configuration of the equipment control device 100 according to this embodiment. The equipment control device 100 is made up of a computer. The equipment control device 100 may be made up of multiple computers.

[0024] As shown in the figure, the equipment control device 100 is a computer that includes hardware such as a processor 11, a memory 12, an auxiliary storage device 13, an input / output interface (IF) 14, and a communication device 15. These pieces of hardware are connected as appropriate via signal lines 19.

[0025] The processor 11 is an integrated circuit (IC) that performs arithmetic processing and controls the hardware of a computer. Specific examples of the processor 11 include a central processing unit (CPU), a digital signal processor (DSP), or a graphics processing unit (GPU). The equipment control device 100 may include multiple processors that replace the processor 11. The multiple processors share the role of the processor 11.

[0026] The memory 12 is typically a volatile storage device, specifically a random access memory (RAM). The memory 12 is also called a primary storage device or a main memory. Data stored in the memory 12 is saved in the secondary storage device 13 as needed.

[0027] The auxiliary storage device 13 is typically a non-volatile storage device, and specific examples thereof include a ROM (Read Only Memory), an HDD (Hard Disk Drive), or a flash memory. Data stored in the auxiliary storage device 13 is loaded into the memory 12 as needed. The memory 12 and the auxiliary storage device 13 may be configured integrally.

[0028] The input / output IF 14 is a port to which an input device and an output device are connected. Specific examples of the input / output IF 14 include a USB (Universal Serial Bus) terminal. Specific examples of the input device include a keyboard and a mouse. Specific examples of the output device include a display.

[0029] The communication device 15 is a receiver and a transmitter, and is specifically a communication chip or a NIC (Network Interface Card).

[0030] Each unit of the equipment control device 100 may use the input / output IF 14 and the communication device 15 as appropriate when communicating with other devices.

[0031] The auxiliary storage device 13 stores an equipment control program. The equipment control program is a program that causes a computer to realize the functions of each unit included in the equipment control device 100. The equipment control program is loaded into the memory 12 and executed by the processor 11.

[0032] Data used when executing the equipment control program and data obtained by executing the equipment control program are stored in a storage device as appropriate. Each part of the equipment control device 100 uses a storage device as appropriate. Specific examples of the storage device include at least one of the memory 12, the auxiliary storage device 13, a register in the processor 11, and a cache memory in the processor 11. Note that the terms "data" and "information" may have the same meaning. The storage device may be independent of the computer. The functions of the memory 12 and the auxiliary storage device 13 may be realized by other storage devices.

[0033] The equipment control program may be recorded on a computer-readable non-volatile recording medium. Specific examples of the non-volatile recording medium include an optical disk and a flash memory. The equipment control program may be provided as a program product.

[0034] ***Description of Operation*** The operation procedure of the equipment control device 100 corresponds to an equipment control method. Also, the program that realizes the operation of the equipment control device 100 corresponds to an equipment control program.

[0035] 3 is a flowchart showing an example of the operation of the equipment control device 100 during learning. This operation will be described with reference to FIG.

[0036] (Step S101) The optimization calculation unit 110 creates a plurality of candidates for equipment control settings.

[0037] (Step S102) Before the inference model 131 is trained, the extraction unit 140 does not extract candidates, but presents all of the created equipment control setting candidates to the equipment manager via the display unit 150.

[0038] (Step S103) The equipment manager selects one equipment control setting from the equipment control setting candidates displayed on the display device 30, and inputs the selected equipment control setting from the input device 40. The input unit 160 accepts the input from the input device 40. When an equipment control setting is selected, the equipment control device 100 transitions to step S104.

[0039] (Step S104) The selection unit 170 selects one equipment control setting from the candidate equipment control settings based on the input received by the input unit 160, and transmits the selected equipment control setting to the equipment management device 20 via the communication unit 180.

[0040] (Step S105) The selection unit 170 records, in the storage unit 120, a list of candidate equipment control settings and the equipment control setting selected from the list of candidate equipment control settings as the current selection result.

[0041] (Step S106) If the number of selection results recorded in the storage unit 120 reaches or exceeds a certain number, the equipment control device 100 proceeds to step S107. Otherwise, the equipment control device 100 ends the processing of this flowchart.

[0042] (Step S107 ) The learning unit 130 learns an inference model 131 that infers the preferences of the facility manager based on the selection results recorded in the storage unit 120 .

[0043] 4 is a flowchart showing an example of the operation of the equipment control device 100 during inference. This operation will be explained using FIG.

[0044] (Step S111) The optimization calculation unit 110 creates a plurality of candidates for equipment control settings.

[0045] (Step S112) The extraction unit 140 extracts equipment control settings that match the preferences of the equipment manager from among multiple equipment control setting candidates using the inference model 131. Here, the inference model 131 is a model that has learned the preferences of the equipment manager.

[0046] Fig. 5 is a diagram illustrating the processing of the optimization calculation unit 110 and the extraction unit 140. Fig. 5(a) shows an example of a plurality of equipment control setting candidates created by the optimization calculation unit 110. Fig. 5(a) shows each equipment control setting candidate created by the optimization calculation unit 110 within the equipment controllable range, taking satisfaction level and energy consumption into consideration. Fig. 5(b) is a diagram corresponding to Fig. 5(a) and shows an example of equipment control setting candidates extracted by the extraction unit 140.

[0047] (Step S113) The display unit 150 displays only the equipment control settings extracted by the extraction unit 140 to the equipment manager.

[0048] (Step S114) The equipment manager selects one equipment control setting from the equipment control setting candidates displayed on the display device 30, and inputs the selected equipment control setting from the input device 40. The input unit 160 accepts the input from the input device 40. When an equipment control setting is selected, the equipment control device 100 transitions to step S115.

[0049] (Step S115) The selection unit 170 selects one equipment control setting from the candidate equipment control settings based on the input received by the input unit 160, and transmits the selected equipment control setting to the equipment management device 20 via the communication unit 180.

[0050] ***Explanation of Effects of First Embodiment*** When performing optimization calculations that explicitly consider the preferences implicitly held by an equipment manager, it is necessary to explicitly consider the preferences, for example, by formulating the preferences and incorporating them into the optimization calculations as objective functions and constraints. On the other hand, in this embodiment, the preferences of the equipment manager are learned based on the selection results of the equipment manager. Therefore, according to this embodiment, it is possible to select equipment control settings that reflect the preferences without explicitly considering the preferences.

[0051] Furthermore, when selecting equipment control settings, methods that extract settings based on predetermined conditions may result in the extraction conditions not matching the preferences of the equipment manager, making it impossible to present a reasonable solution and requiring the extraction to be started over again. In contrast, in this embodiment, the preferences of the equipment manager are learned based on the selection results of the equipment manager, and equipment control settings are extracted based on the learning results. Therefore, according to this embodiment, it is possible to extract and select settings that match the preferences of the equipment manager relatively efficiently. Furthermore, by utilizing this embodiment, the equipment manager can make satisfactory decisions with relatively little effort.

[0052] ***Other Configurations*** <Modification 1> Fig. 6 shows an example of the hardware configuration of the equipment control device 100 according to this modification. The equipment control device 100 includes a processing circuit 18 instead of the processor 11, the processor 11 and memory 12, the processor 11 and auxiliary storage device 13, or the processor 11, memory 12, and auxiliary storage device 13. The processing circuit 18 is hardware that realizes at least a portion of the components included in the equipment control device 100. The processing circuit 18 may be dedicated hardware, or may be a processor that executes a program stored in the memory 12.

[0053] When the processing circuitry 18 is dedicated hardware, the processing circuitry 18 may be, 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. The equipment control device 100 may be provided with multiple processing circuits that replace the processing circuitry 18. The multiple processing circuits share the role of the processing circuitry 18.

[0054] In the equipment control device 100, some functions may be realized by dedicated hardware, and the remaining functions may be realized by software or firmware.

[0055] The processing circuitry 18 is realized by, for example, hardware, software, firmware, or a combination of these. The processor 11, memory 12, auxiliary storage device 13, and processing circuitry 18 are collectively referred to as the "processing circuitry." In other words, the functions of the functional components of the equipment control device 100 are realized by the processing circuitry. Equipment control devices 100 according to other embodiments may also have a configuration similar to this modification.

[0056] Second Embodiment The following mainly describes the differences from the above-described embodiment with reference to the drawings.

[0057] *** Description of Configuration *** The configuration of the equipment control system 90 according to this embodiment is the same as the configuration of the equipment control system 90 according to the first embodiment. The display unit 150 according to this embodiment displays each element of the creation candidate group to the equipment manager, and displays each element of the extraction candidate group as a recommended solution to the equipment manager. Specifically, in order to facilitate comparison and selection by the equipment manager, the display unit 150 does not display only the solution extracted by the extraction unit 140, but displays the solution extracted by the extraction unit 140 from among other possible solutions as a recommended solution. The solution may be an optimal equipment control setting, or an equipment control setting that is expected to be optimal. There may be multiple recommended solutions.

[0058] ***Explanation of Operation*** The following describes the differences between the operation during inference of the equipment control device 100 according to this embodiment and the operation during inference of the equipment control device 100 according to the first embodiment.

[0059] (Step S113) This step is basically the same as step S113 according to the first embodiment. However, the display unit 150 displays all of the equipment control setting candidates created by the optimization calculation unit 110 from among the extracted equipment control settings. The display unit 150 also displays each of the equipment control setting candidates extracted by the extraction unit 140 from among the created equipment control setting candidates as a recommended solution. Figure 7 is a diagram illustrating the processing of the display unit 150. In Figure 7, each equipment control setting candidate created by the optimization calculation unit 110 and each recommended solution are displayed.

[0060] ***Explanation of Effects of Embodiment 2*** In this embodiment, each equipment control setting candidate created by the optimization calculation unit 110 and each recommended solution are displayed. Therefore, according to this embodiment, the equipment manager can infer the reason why each recommended solution was extracted by comparing each recommended solution with other equipment control settings. Therefore, by utilizing this embodiment, the equipment manager can select equipment control settings with greater satisfaction and can make decisions more easily.

[0061] ***Other Configurations*** <Variation 2> In this variation, the display unit 150 displays to the equipment manager not only each recommended solution, but also the basis for the extraction of each recommended solution, i.e., each element of the extraction candidate group. Specific examples of the basis include the reason why the solution was extracted, whether a predetermined criterion is satisfied, or whether each index value is relatively high. Here, the inference model 131 may output the basis, or the extraction unit 140 may generate the basis based on the output of the inference model 131. FIG. 8 is a diagram illustrating the processing of the display unit 150. FIG. 8 shows the basis for the extraction of a recommended solution. Each basis may be displayed by hovering the mouse over it.

[0062] In this modification, the basis for extracting the equipment control setting candidates is clearly indicated, so that the equipment manager can select the equipment control settings while checking that the selected settings match his or her preferences, making decision-making easier.

[0063] Third Embodiment Hereinafter, differences from the above-described embodiments will be mainly described with reference to the drawings.

[0064] ***Description of Configuration*** The configuration of the equipment control system 90 according to this embodiment is the same as the configuration of the equipment control system 90 according to the first embodiment.

[0065] After the equipment manager selects an element from the extraction candidate group, the extraction unit 140 according to this embodiment extracts one or more equipment control setting candidates as elements of a re-extraction candidate group around the selected element within the equipment controllable range. That is, the extraction unit 140 re-extracts solutions similar to the one solution selected by the equipment manager from the multiple solutions initially extracted. In this case, as a specific example, the extraction unit 140 extracts a predetermined number of equipment control settings at equal intervals within a predetermined range around the one solution selected within the equipment controllable range.

[0066] The display unit 150 according to this embodiment displays each newly extracted solution, that is, each element of the re-extracted candidate group, to the facility manager.

[0067] ***Explanation of Operation*** Fig. 9 is a flowchart showing an example of the operation during inference of the equipment control device 100. This operation will be described using Fig. 9.

[0068] (Step S114) This step is basically the same as step S114 according to embodiment 1. However, the equipment control device 100 transitions to step S311 instead of step S115.

[0069] (Step S311) If the display unit 150 is displaying the initially extracted solution, the equipment control device 100 transitions to step S312. Otherwise, the equipment control device 100 transitions to step S115. Note that the equipment control device 100 may transition to step S312 not only after the initial selection but also when the equipment manager wants to fine-tune the equipment control settings.

[0070] (Step S312) The extracting unit 140 extracts solutions similar to one solution selected by the facility manager.

[0071] Fig. 10 is a diagram illustrating the processing of the extraction unit 140. Fig. 10 shows equipment control setting candidates initially extracted by the extraction unit 140 and equipment control setting candidates newly extracted by the extraction unit 140.

[0072] ***Explanation of Effects of Embodiment 3*** In this embodiment, candidates that are close to a specific equipment control setting candidate and that were not initially extracted are newly extracted and displayed. Therefore, according to this embodiment, the equipment manager can select from the newly displayed candidates, thereby fine-tuning the equipment control settings to a range that is close to the equipment manager's preferences. Here, the fine-tuned equipment control settings can be used in the operation of the equipment.

[0073] Fourth Embodiment Hereinafter, differences from the above-described embodiments will be mainly described with reference to the drawings.

[0074] *** Description of Configuration *** The configuration of the equipment control system 90 according to this embodiment is the same as the configuration of the equipment control system 90 according to the first embodiment. When the equipment manager does not select any element of the extraction candidate group, the display unit 150 according to this embodiment displays each equipment control setting candidate that is not included in the extraction candidate group to the equipment manager. That is, when the solution extracted by the extraction unit 140 does not match the preference of the equipment manager, the display unit 150 also displays solutions other than the extracted solution. When the equipment manager selects a solution other than the extracted solution, the selection result by the equipment manager is stored in the memory unit 120 and is used when re-learning the inference model 131.

[0075] ***Explanation of Operation*** Fig. 11 is a flowchart showing an example of the operation during inference of the equipment control device 100. This operation will be described using Fig. 11.

[0076] (Step S114) This step is basically the same as step S114 according to embodiment 1. However, the equipment control device 100 transitions to step S414 when equipment control setting is selected.

[0077] (Step S411) The equipment control device 100 ends the processing of this flowchart if the equipment manager makes a selection from the candidates extracted by the extraction unit 140. Otherwise, the equipment control device 100 proceeds to step S412.

[0078] (Step S412) The selection unit 170 records the selection result by the facility manager in the storage unit 120.

[0079] (Step S413) The learning unit 130 re-learns the inference model 131. This step is similar to step S107.

[0080] (Step S414) If there are selectable candidates for equipment control settings, the equipment control device 100 proceeds to step S114. Otherwise, the equipment control device 100 proceeds to step S415.

[0081] (Step S415) The display unit 150 presents all of the equipment control setting candidates.

[0082] ***Explanation of the Effects of Embodiment 4*** In this embodiment, when the learning of the inference model 131 is insufficient or when an inappropriate candidate is extracted by the extraction unit 140, the inference model 131 is re-trained using a selection result that fully reflects the preferences of the facility manager. Therefore, according to this embodiment, the accuracy of the inference model 131 can be improved as needed.

[0083] Fifth Embodiment Hereinafter, differences from the above-described embodiments will be mainly described with reference to the drawings.

[0084] ***Description of Configuration*** Fig. 12 shows an example of the configuration of an equipment control system 90 according to this embodiment. The equipment control device 100 according to this embodiment further includes a condition collection unit 510.

[0085] The input unit 160 according to the present embodiment accepts not only the selection results related to the operation plan but also the input of selection conditions. The selection conditions are conditions that the equipment manager considers when selecting equipment control settings. Specific examples of the selection conditions include reducing energy consumption by 1% compared to the previous year, keeping costs below a certain value, keeping annual energy reserves above a certain value, a long-term forecast of a cool summer or warm winter, a predicted value of the building utilization rate, or a maintenance plan for the building.

[0086] The storage unit 120 according to the present embodiment further stores selection conditions. As a specific example, the storage unit 120 records, as learning data, data linking a group of extraction candidates, elements selected from the group of extraction candidates by an equipment manager, and the selection conditions.

[0087] The learning unit 130 according to this embodiment learns the inference model 131 based on the selection conditions and selection results recorded in the memory unit 120. That is, the learning unit 130 may further learn the inference model 131 based on the selection conditions.

[0088] The condition collection unit 510 accepts conditions input by the equipment manager during inference and inputs the accepted conditions into the inference model 131.

[0089] The extraction unit 140 according to this embodiment extracts candidate equipment control settings that reflect the preferences of the equipment manager under the conditions input to the inference model 131.

[0090] ***Explanation of Operation*** The following describes the differences between the operation of the equipment control device 100 according to the present embodiment during learning and the operation of the equipment control device 100 according to the first embodiment during learning.

[0091] (Step S107) This step is basically the same as step S107 in embodiment 1. However, the learning unit 130 learns the inference model 131 based on the selection results and selection conditions recorded in the memory unit 120.

[0092] The following describes the differences between the operation of the equipment control device 100 according to this embodiment during inference and the operation of the equipment control device 100 according to the first embodiment during inference.

[0093] (Step S112) This step is basically the same as step S112 in embodiment 1. However, during inference, the condition collection unit 510 accepts conditions input by the facility manager and inputs the accepted conditions into the inference model 131.

[0094] ***Explanation of Effects of Embodiment 5*** In this embodiment, selection conditions are further taken into consideration during learning. Furthermore, conditions input by the equipment manager are used during inference. Therefore, according to this embodiment, compared to when learning and inference are performed based only on the selection results of the equipment manager, it is possible to take the preferences of the equipment manager into greater consideration and perform inference with higher accuracy. Here, inference refers to the extraction of candidates for equipment control settings.

[0095] ***Other Configurations*** <Variation 3> When displaying the extraction results, the display unit 150 according to this variation also displays to the equipment manager information indicating the basis for the extraction of each equipment control setting candidate, i.e., information indicating the conditions corresponding to the basis for the extraction of each element of the extracted candidate group. The basis may be each condition satisfied by each extracted equipment control setting candidate, or the reason corresponding to each condition. Here, the inference model 131 may output the basis, or the extraction unit 140 may generate the basis based on the output of the inference model 131. FIG. 13 is a diagram illustrating the processing of the display unit 150. FIG. 13 shows an example of the basis for the extraction of equipment control setting candidates.

[0096] In this modification, the basis for extracting the equipment control setting candidates is clearly indicated, so that the equipment manager can select the equipment control settings while checking that the selected settings match his or her preferences, and can more easily make decisions.

[0097] Sixth Embodiment Hereinafter, differences from the above-described embodiments will be mainly described with reference to the drawings.

[0098] ***Description of Configuration*** Fig. 14 shows an example of the configuration of an equipment control system 90 according to this embodiment. The equipment control device 100 according to this embodiment further includes a dialogue-based learning unit 610.

[0099] The interactive learning unit 610 presents one or more questions to the equipment manager and obtains answers to each question from the equipment manager. Each question is intended to understand the preferences of the equipment manager. The interactive learning unit 610 also trains the inference model 131 based on each answer obtained from the equipment manager. In this embodiment, the inference model 131 is trained based on the selection results from candidates for equipment control settings that have actually been optimized, and also based on the answers from the equipment manager.

[0100] ***Explanation of Operation*** Below, the differences between the operation during learning of the equipment control device 100 according to the present embodiment and the operation during learning of the equipment control device 100 according to embodiment 1 will be explained. Fig. 15 is a flowchart showing an example of the operation of the dialogue-based learning unit 610. This operation will be explained using Fig. 15.

[0101] (Step S601) The dialogue-based learning unit 610 presents questions for grasping the preferences of the facility manager to the facility manager via the display device 30.

[0102] (Step S602) The facility manager inputs answers to each question into the input device. After the answers have been input, the dialogue-based learning unit 610 proceeds to step S603.

[0103] (Step S603) The dialogue-based learning unit 610 receives each response from the facility manager from the input device 40, and learns the inference model 131 based on each received response.

[0104] ***Explanation of the Effects of Embodiment 6*** Normally, a large amount of work must be performed to optimize equipment control setting candidates and to collect and record the selection results made by the equipment manager. Therefore, it takes a considerable amount of time to train the inference model 131 with sufficiently high inference accuracy. On the other hand, according to this embodiment, by training the inference model 131 based on the answers obtained by the interactive learning unit 610, it is possible to complete the training of the inference model 131 in a relatively short time.

[0105] Seventh Embodiment Hereinafter, differences from the above-described embodiments will be mainly described with reference to the drawings.

[0106] ***Configuration Description*** Fig. 16 shows an example configuration of an equipment control system 90 according to this embodiment. In this embodiment, an inference model that has learned the preferences of other equipment managers is transferred to the equipment control device 100 to extract candidates for equipment control settings. The equipment control device 100 according to this embodiment further includes a data acquisition unit 710.

[0107] The data acquisition unit 710 acquires an inference model for other people 731.

[0108] The other-person inference model 731 is an inference model that learns the preferences of others. The preferences of others are preferences of an equipment manager other than the equipment manager for the equipment control device 100, and are preferences regarding equipment control settings. The preferences of others may also be preferences regarding each piece of equipment other than each piece of equipment controlled by the equipment control device 100. The learning method of the other-person inference model 731 may be the same as the learning method of the inference model 131 in other embodiments. The other-person inference model 731 is also called an other equipment manager preference inference model.

[0109] In addition to the functions of the learning unit 130 in the above-mentioned embodiment, the learning unit 130 in this embodiment has the function of receiving an inference model for other people 731 from the data acquisition unit 710 and transferring the received inference model for other people 731 to the inference model 131.

[0110] ***Description of Operation*** The operation of the equipment control device 100 according to this embodiment is the same as the operation of the equipment control device 100 according to the above-described embodiment. However, during inference, the other-person inference model 731 acquired by the data acquisition unit 710 may be used as the inference model 131.

[0111] ***Explanation of the Effects of Embodiment 7*** Normally, it takes a long time to complete the training of a model that infers the preferences of an equipment manager. However, according to this embodiment, by transferring the other-person inference model 731 related to the preferences of another equipment manager, the time required to train the inference model 131 can be shortened. Here, the closer the preferences of another equipment manager learned by the other-person inference model 731 are to the preferences of the equipment manager using the equipment control device 100, the shorter the time required to train the inference model 131 can be. Furthermore, when there is a difference between these preferences, the inference model 131 can be retrained based on the selection results of the equipment manager using the equipment control device 100, thereby generating an inference model 131 that is suited to the preferences of the equipment manager using the equipment control device 100.

[0112] ***Other Embodiments*** The above-described embodiments can be freely combined, or any of the components of each embodiment can be modified, or any of the components can be omitted from each embodiment. Furthermore, the embodiments are not limited to those shown in embodiments 1 to 7, and various modifications are possible as needed. The procedures described using flowcharts, etc., can be modified as appropriate.

[0113] 11 processor, 12 memory, 13 auxiliary storage device, 14 input / output IF, 15 communication device, 18 processing circuit, 19 signal line, 20 equipment management device, 30 display device, 40 input device, 90 equipment control system, 100 equipment control device, 110 optimization calculation unit, 120 memory unit, 130 learning unit, 131 inference model, 140 extraction unit, 150 display unit, 160 input unit, 170 selection unit, 180 communication unit, 510 condition collection unit, 610 interactive learning unit, 710 data acquisition unit, 731 inference model for others.

Claims

An equipment control device that supports decision-making regarding equipment control settings, an optimization calculation unit that uses optimization technology to create a plurality of equipment control setting candidates as elements of a created candidate group within an equipment controllable range; an extraction unit that extracts one or more equipment control setting candidates from the creation candidate group as elements of an extraction candidate group using an inference model that has learned preferences of an equipment manager regarding equipment control settings; An equipment control device comprising: 　 The equipment control device further includes: a display unit that displays each element of the extraction candidate group to the facility manager; a storage unit that records, as learning data, data linking the extraction candidate group with an element selected from the extraction candidate group by the equipment manager; a learning unit that learns the inference model based on the learning data; The equipment control device according to claim 1 , comprising: 　 The equipment control device according to claim 2 , wherein the display unit displays each element of the creation candidate group to the equipment manager, and displays each element of the extraction candidate group as a recommended solution to the equipment manager. 　 The equipment control device according to claim 3 , wherein the display unit displays to the equipment manager the reasons why each element in the group of extraction candidates was extracted. 　 the extraction unit extracts one or more equipment control setting candidates as elements of a re-extraction candidate group around the selected element within the equipment controllable range after the equipment manager selects an element from the extraction candidate group; The equipment control device according to claim 2 , wherein the display unit displays each element of the re-extraction candidate group to the equipment manager.

6. An equipment control device according to claim 2, wherein the display unit displays candidates for each equipment control setting that are not included in the group of extracted candidates to the equipment manager when none of the elements of the group of extracted candidates is selected by the equipment manager. 　 the storage unit records, as the learning data, data linking the extraction candidate group, an element selected from the extraction candidate group by the equipment manager, and a selection condition that is a condition considered when the equipment manager selects an element from the extraction candidate group; The equipment control device according to claim 2 , wherein the learning unit further learns the inference model based on the selection conditions. 　 The equipment control device according to claim 7 , wherein the display unit displays to the equipment manager information indicating conditions corresponding to reasons for extracting each element of the extraction candidate group. 　 The equipment control device further includes: an interactive learning unit that presents one or more questions to the facility manager to understand the preferences of the facility manager, obtains answers to each question from the facility manager, and learns the inference model based on the obtained answers; The equipment control device according to any one of claims 1 to 8, comprising: 　 The equipment control device further includes: a data acquisition unit that acquires an inference model for other users that has learned preferences of other users, which are preferences regarding equipment control settings of equipment managers different from the equipment manager; Equipped with The equipment control device according to claim 2 , wherein the learning unit transfers the inference model for other users to the inference model. 　 An equipment control method executed by an equipment control device that is a computer that supports decision-making regarding equipment control settings, comprising: The equipment control device uses an optimization technique to create a plurality of equipment control setting candidates as elements of a created candidate group within an equipment controllable range; An equipment control method in which the equipment control device uses an inference model that has learned the equipment manager's preferences regarding equipment control settings to extract one or more equipment control setting candidates from the created candidate group as elements of an extracted candidate group. 　 An equipment control program executed by an equipment control device that is a computer that supports decision-making regarding equipment control settings, an optimization calculation process that uses optimization technology to create multiple equipment control setting candidates as elements of a creation candidate group within the equipment controllable range; an extraction process for extracting one or more equipment control setting candidates from the created candidate group as elements of an extracted candidate group using an inference model that has learned the preferences of an equipment manager regarding equipment control settings; An equipment control program that causes the equipment control device to execute the above.

Images