Control device, control method, and program

Abstract

Bring the monitored object closer to the desired state. [Solution] A control device comprising an algorithm control unit that controls an algorithm and generates an operation plan for an external device that affects a monitored object; a monitored object monitoring unit that acquires actual measured values ​​of the monitored object; an instruction generation determination unit that generates instructions for the operation plan based on the actual measured values ​​and determines whether to output instructions for the operation plan to the external device; and an instruction output unit that outputs instructions for the operation plan to the external device when the instruction generation determination unit determines that instructions for the operation plan should be output.

Description

[Technical field]

[0001] The present invention relates to a control device, a control method, and a program. [Background technology]

[0002] IT systems are equipped with algorithms that solve problems. The output of an algorithm is not necessarily the overall optimum, and the output may differ depending on the algorithm. In addition, it is difficult to determine how far the performance of an algorithm can be improved. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6697159 Summary of the Invention [Problem to be solved by the invention]

[0004] An object of the present invention is to provide a control device, a control method, and a program for bringing a monitored object closer to a desired state. [Means for solving the problem]

[0005] One aspect of the present invention is a control device comprising: an algorithm control unit that controls an algorithm and generates an operation plan for an external device that affects a monitored object; a monitored object monitoring unit that acquires actual measured values ​​of the monitored object; an instruction generation determination unit that generates instructions for the operation plan based on the actual measured values ​​and determines whether or not to output instructions for the operation plan to the external device; and an instruction output unit that outputs instructions for the operation plan to the external device when the instruction generation determination unit determines that instructions for the operation plan should be output. Effect of the Invention

[0006] According to the present invention, it is possible to bring a monitored object closer to a desired state. [Brief description of the drawings]

[0007] [Figure 1] FIG. 1 is a diagram showing a relationship between systems according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a diagram illustrating an example of a configuration of a control device according to the present embodiment. [Diagram 3] 4 is a flowchart showing the operation of the control device according to the present embodiment. [Figure 4] FIG. 1 is a diagram illustrating a specific example of a system. [Diagram 5] FIG. 13 is a flowchart showing the case where the system is a power system. [Figure 6] FIG. 1 is a diagram illustrating a specific example of a system. [Figure 7] FIG. 13 is a flow chart showing the case where the system is a distribution system. [Figure 8] FIG. 1 is a diagram illustrating a specific example of a system. [Figure 9] FIG. 1 is a diagram illustrating an example of a system configuration. [Figure 10] FIG. 13 is a flowchart when the system is a presenter evaluation system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. FIG. 1 is a diagram showing the relationship of the system according to this embodiment. The system 1 includes a control device 10 , an external device 11 , a monitored object 12 , and status data 13 . The control device 10 monitors the monitoring target 12 and acquires situation data 13. The control device 10 outputs an instruction to the external device 11, triggered by the monitoring target 12. The control device 10 generates an instruction based on the monitoring target 12 and the situation data 13. The external device 11 is a device that affects the monitoring target 12 and the situation data 13.

[0009] 2 is a diagram showing an example of the configuration of the control device 10 according to this embodiment. The control device 10 includes an algorithm control unit 110, a monitoring target monitoring unit 120, a situation data acquisition unit 125, a control scenario execution unit 130, an instruction generation and determination unit 140, an instruction output unit 150, a control scenario input unit 160, and a storage unit 190. The storage unit 190 includes an algorithm storage unit 191, an algorithm execution data storage unit 192, a monitoring target data storage unit 193, a situation data storage unit 194, and a control scenario storage unit 195.

[0010] The algorithm storage unit 191 stores algorithms. The algorithms stored in the algorithm storage unit 191 include an algorithm for planning the operation of the external device 11. The algorithms stored in the algorithm storage unit 191 may include an algorithm for predicting the monitored object 12 and / or the situation data 13.

[0011] The algorithm control unit 110 controls the algorithm stored in the algorithm storage unit 191. The algorithm control unit 110 acquires algorithm execution data by, for example, executing the algorithm stored in the algorithm storage unit 191. The algorithm control unit 110 re-learns the algorithm stored in the algorithm storage unit 191, for example.

[0012] The algorithm execution data storage unit 192 stores algorithm execution data acquired by executing an algorithm. The algorithm execution data includes external device planning data acquired by executing an algorithm that plans the operation of the external device 11. The algorithm execution data may include monitoring target prediction data acquired by executing an algorithm that predicts the monitoring target 12 and / or situation data prediction data acquired by executing an algorithm that predicts the situation data 13.

[0013] The monitoring target monitor 120 monitors the monitoring target 12 and acquires data from the monitoring target 12 (measurement data of the monitoring target).

[0014] The monitored object data storage unit 193 stores the monitored object actual measurement data.

[0015] The situation data acquisition unit 125 acquires the situation data 13. The situation data acquisition unit 125 may acquire the situation data 13 periodically, or may acquire the situation data 13 when the control device 10 generates an instruction.

[0016] The situation data storage unit 194 stores the situation data 13 .

[0017] The control scenario storage unit 195 stores a control scenario. A control scenario indicates a control method for an algorithm. A control scenario indicates, for example, what control is to be performed for which algorithm and in what order. The control scenario storage unit 195 stores multiple control scenarios, and different control scenarios may be used depending on the monitored object actual measurement data and the situation data 13. When the instruction generation determination unit 140 described below determines to generate an instruction, the control scenario execution unit 130 controls the algorithm control unit 110 to control the algorithm according to the control scenario stored in the control scenario storage unit 195. The control scenario execution unit 130 may select one control scenario from multiple control scenarios based on the monitored target actual measurement data and situation data, and cause the algorithm control unit 110 to control the algorithm according to the selected control scenario.

[0018] The instruction generation determination unit 140 determines whether to generate an instruction based on the monitored target actual measurement data. The instruction generation determination unit 140, for example, calculates the difference between the monitored target predicted data and the monitored target actual measurement data, and determines to generate an instruction when the difference is equal to or greater than a predetermined value. The instruction generation determination unit 140 determines to generate an instruction when, for example, the monitored target actual measurement data is equal to or greater than a predetermined value. The predetermined value is a value stored in advance in the storage unit 190. The instruction output unit 150 outputs an instruction to the external device 11. The instruction is a plan included in the external device plan data.

[0019] The control scenario input unit 160 accepts an input control scenario and records it in the control scenario storage unit 195. The control scenario input unit 160 may display a screen for creating a control scenario with no-code or low-code, and accept the control scenario by editing the control scenario with no-code or low-code.

[0020] FIG. 3 is a flowchart showing the operation of the control device 10 according to this embodiment. In the flowchart shown in FIG. 3, before starting, the algorithm execution data storage unit 192 stores the monitoring target prediction data. The monitoring target monitoring unit 120 acquires the monitoring target actual measurement data from the monitoring target 12 (step S11). The instruction generation determination unit 140 determines whether to generate an instruction based on the monitoring target actual measurement data (step S12). When the instruction generation determination unit 140 determines not to generate an instruction (step S13: NO), the monitoring target monitoring unit 120 performs the operation of step S11 again. Here, the monitoring target monitoring unit 120 may perform the operation of step S11 again after a predetermined time has elapsed. When the instruction generation determination unit 140 determines to generate an instruction (step S13: YES), the situation data acquisition unit 125 acquires the situation data 13 (step S14). When the situation data acquisition unit 125 acquires the situation data 13 periodically, the situation data is called from the situation data storage unit 194. The control scenario executing unit 130 controls the algorithm control unit 110 to control the algorithm in accordance with the control scenario stored in the control scenario storage unit 195 (step S15).

[0021] The algorithm control unit 110 controls the algorithm (step S16). The algorithm control unit 110, for example, executes the algorithm and acquires algorithm execution data. The algorithm control unit 110, for example, re-learns the algorithm. The algorithm control unit 110 records the acquired algorithm execution data in the algorithm execution data storage unit 192 (step S17). The instruction output unit 150 outputs an instruction to the external device 11 so that the external device 11 operates in accordance with the external device plan data included in the algorithm execution data (step S18).

[0022] In this way, the control device 10 can bring the monitored object 12 closer to a desired state. The control device 10 can also control a plurality of algorithms and derive an overall optimal operation as a system.

[0023] A specific example of the system 1 will be described below. Fig. 4 is a diagram illustrating a specific example of the system 1. The system 1-a is an electric power system. The external device 11-a includes a device for charging a storage battery, a device for charging an electric vehicle, a device for dispatching an electric vehicle, a device for predicting the amount of power generation, and a device for predicting the amount of power demand. The monitored object 12 is a power purchasing device.

[0024] The monitored actual measurement data is an actual measurement value of the amount of power purchased. The monitored forecast data is a forecast value of the amount of power purchased. The external device plan data indicates a plan for the external device 11 to charge a storage battery, a plan to charge an electric vehicle, and a plan to dispatch an electric vehicle. The algorithms stored in the algorithm storage unit 191 include an algorithm for planning charging a storage battery, an algorithm for planning charging an electric vehicle, an algorithm for planning dispatching an electric vehicle, an algorithm for predicting the amount of power purchased, an algorithm for predicting the amount of power generated, and an algorithm for predicting the amount of power demand.

[0025] The status data 13 includes the remaining charge of the storage battery and the reservation status of the electric vehicle.

[0026] FIG. 5 is a diagram showing a flowchart in the case where the system 1 is a power system. In the flowchart shown in FIG. 5, a predicted value of the amount of power purchased is stored in the algorithm execution data storage unit 192 before starting. The monitored object monitoring unit 120 acquires an actual value of the amount of power purchased (step S11-a). The instruction generation determination unit 140 determines whether or not to generate an instruction based on the actual value of the amount of power purchased (step S12-a). When the instruction generation determination unit 140 determines not to generate an instruction (step S13-a: NO), the operation of step S11-a is performed again. Here, the monitored object monitoring unit 120 may perform the operation of step S11-a again after a predetermined time has elapsed. When the instruction generation determination unit 140 determines to generate an instruction (step S13-a: YES), the situation data acquisition unit 125 acquires situation data 13 (remaining amount of storage battery, electric vehicle reservation status, etc.) (step S14-a). The control scenario executing unit 130 controls the algorithm control unit 110 to control the algorithm in accordance with the control scenario stored in the control scenario storage unit 195 (step S15-a).

[0027] The algorithm control unit 110 executes the algorithm to obtain algorithm execution data (step S16-a). The algorithm execution data includes external device plan data, such as a charging plan for the storage battery, a charging plan for the electric vehicle, a dispatching plan for the electric vehicle, a predicted value of the amount of power generation, a predicted value of the amount of power demand, and a predicted value of the amount of power purchased. The predicted value of the amount of power generation and the predicted value of the amount of power demand are used to generate a charging plan for the storage battery, a charging plan for the electric vehicle, and a predicted value of the amount of power purchased. The algorithm control unit 110 records the obtained predicted value of the amount of power purchased and plan data in the algorithm execution data storage unit 192 (step S17-a). The instruction output unit 150 outputs an instruction to the external device 11 so that the external device 11 operates according to the external device plan data (step S18-a). The external device plan data includes a charging plan for the storage battery, a charging plan for the electric vehicle, and a dispatching plan for the electric vehicle, and the external device 11 charges the storage battery, charges the electric vehicle, and dispatches the electric vehicle based on the charging plan for the storage battery, the charging plan for the electric vehicle, and the dispatching plan for the electric vehicle.

[0028] The control scenario executing unit 130 may change the control scenario to be executed based on the charge amount of the storage battery. For example, when the charge amount of the storage battery is equal to or greater than a predetermined amount, the control scenario executing unit 130 causes the algorithm to execute a charging plan for the storage battery. The control scenario executing unit 130 may change the control scenario based on the charge amount of the electric vehicle. For example, when the charge amount of the storage battery is less than a predetermined amount and the charge amount of an electric vehicle that has no reservation is equal to or greater than a predetermined amount, the control scenario executing unit 130 causes the algorithm to execute a charging plan for the electric vehicle. For example, when the charge amount of the storage battery is less than a predetermined amount and the charge amount of an electric vehicle that has no reservation is less than a predetermined amount, the control scenario executing unit 130 does not cause the algorithm to execute anything when the charge amount of the storage battery is less than a predetermined amount and the charge amount of an electric vehicle that has no reservation is less than a predetermined amount. In this case, the status data may include the charge amount of the storage battery and the charge amount of the electric vehicle.

[0029] Hereinafter, a description will be given of another specific example of the system 1. Fig. 6 is a diagram illustrating a specific example of the system 1. The system 1-b is a delivery system. The external device 11-b includes a device for delivering packages, and the like.

[0030] The monitored actual measurement data is an actual measurement value of the number of delivery delays. The monitored predicted data is a predicted value of the number of delivery delays. The external device plan data indicates a plan for the external device 11 to deliver packages. The algorithms stored in the algorithm storage unit 191 include an algorithm for planning package delivery and an algorithm for predicting the number of delivery delays.

[0031] The situation data 13 includes congestion information.

[0032] FIG. 7 is a diagram showing a flowchart in the case where the system 1-b is a delivery system. In the flowchart shown in FIG. 7, a predicted value of the number of delivery delays is stored in the algorithm execution data storage unit 192 before starting. The monitored object monitoring unit 120 acquires an actual value of the number of delivery delays (step S11-b). The instruction generation determination unit 140 determines whether or not to generate an instruction based on the actual value of the number of delivery delays (step S12-b). When the instruction generation determination unit 140 determines not to generate an instruction (step S13-b: NO), the monitored object monitoring unit 120 performs the operation of step S11-b again. Here, the monitored object monitoring unit 120 may perform the operation of step S11-b again after a predetermined time has elapsed. When the instruction generation determination unit 140 determines to generate an instruction (step S13-b: YES), the situation data acquisition unit 125 acquires situation data 13 (such as traffic congestion information) (step S14-b). The control scenario executing unit 130 controls the algorithm control unit 110 to execute the algorithm in accordance with the control scenario stored in the control scenario storage unit 195 (step S15-b).

[0033] The algorithm control unit 110 acquires algorithm execution data by executing the algorithm (step S16-b). The algorithm execution data includes a delivery route plan, which is external device planning data. The algorithm control unit 110 records the acquired algorithm execution data in the algorithm execution data storage unit 192 (step S17-b). The instruction output unit 150 outputs an instruction to the external device 11 so that the external device 11 operates in accordance with the external device planning data included in the algorithm execution data (step S18-b). The external device planning data includes a delivery route plan, and the external device 11 has a delivery company deliver the package based on the delivery route plan.

[0034] The control scenario executing unit 130 may change the control scenario to be executed depending on the situation. For example, when congestion occurs, the control scenario executing unit 130 executes an algorithm to calculate a route for delivering a package at a specified time. The control scenario executing unit 130 may change the control scenario based on the delivery volume. When the delivery volume is less than a predetermined volume, the control scenario executing unit 130 adds a transport company and recalculates the delivery route. At this time, the situation data may include information on the occurrence or non-occurrence of traffic congestion and delivery volume.

[0035] The predicted number of delivery delays is not updated by executing an algorithm, but may be a predetermined value that does not need to be updated appropriately.

[0036] The following describes another specific example of the system 1. Fig. 8 is a diagram illustrating a specific example of the system 1. The system 1-c is a presenter evaluation system. The external device 11-c includes a device for displaying the analysis results, and the like. A control scenario indicates, for example, what control to perform and in what order for which algorithm, but it may also perform multi-stage control in which a later algorithm performs control based on data generated by the control performed by a previous algorithm. Furthermore, the monitored object monitor 120 may generate monitored object actual measurement data by acquiring data from the monitored object 12 and applying an algorithm stored in the algorithm storage unit 191 to the acquired data.

[0037] The monitored actual measurement data is an evaluation value of the atmosphere of the conference. The evaluation value of the atmosphere of the conference is calculated by an audience analysis algorithm stored in the algorithm storage unit 191. The audience analysis algorithm is an algorithm that analyzes the reaction of the audience based on data acquired from the audience of the presentation, which is the monitored object 12. The audience analysis algorithm is an algorithm that calculates, for example, an evaluation value of each index of the audience reaction. The audience analysis algorithm includes, for example, at least one of a facial expression analysis algorithm that analyzes the facial expressions of the audience and calculates an evaluation value based on the facial expressions, a voice analysis algorithm that analyzes the voices of the audience and calculates an evaluation value based on the voices, and a survey analysis algorithm that analyzes surveys from the audience and calculates an evaluation value based on the surveys. The evaluation value calculated by the facial expression analysis algorithm is, for example, an evaluation value for each emotion. The evaluation value for each emotion is, for example, an evaluation value for happiness, surprise, anger, confusion, disgust, sadness, fear, and calm. The evaluation value calculated by the voice analysis algorithm is, for example, an evaluation value for the volume of a voice or the overlapping of voices by multiple speakers. The evaluation value calculated by the questionnaire analysis algorithm is, for example, an evaluation value for the level of understanding of the audience.

[0038] The monitored object monitoring unit 120 uses an audience analysis algorithm to calculate an evaluation value of the atmosphere of the conference from an evaluation value calculated from at least one of a facial expression analysis algorithm, a voice analysis algorithm, and a questionnaire analysis algorithm. The evaluation value of the atmosphere of the conference is a value obtained by averaging the evaluation values ​​of each index calculated for each audience member for each index. The evaluation value of the atmosphere of the conference may be an evaluation value calculated for each audience member and for each index instead of the average.

[0039] When the audience analysis algorithm includes two or more algorithms selected from a facial expression analysis algorithm, a voice analysis algorithm, and a questionnaire analysis algorithm, an evaluation value of the atmosphere of the meeting is calculated based on the evaluation values ​​obtained by the two or more algorithms.

[0040] The monitoring target prediction data is a desired value of the evaluation value of the atmosphere of the conference. An index of the desired value of the evaluation value of the atmosphere of the conference corresponds to an index of the evaluation value calculated by the audience analysis algorithm. If the evaluation value of the atmosphere of the conference is an evaluation value for each emotion, the desired value also includes a desired value for each emotion. The instruction generation determination unit 140 determines whether to generate an instruction based on the evaluation value and the desired value of the atmosphere of the conference. For example, in a certain index, the instruction generation determination unit 140 determines to generate an instruction when the difference between the average of the calculated evaluation values ​​and the desired value is equal to or greater than a predetermined value. For example, in a certain index, the instruction generation determination unit 140 determines to generate an instruction when the number of audience members whose difference between the evaluation value and the desired value is equal to or greater than a predetermined value is equal to or greater than a predetermined value. The external device plan data indicates advice to be displayed to the presenter by the external device 11. The algorithms stored in the algorithm storage unit 191 include an advice formulation algorithm. The advice formulation algorithm is an algorithm for formulating advice for the presenter based on the analysis result by the audience analysis algorithm.

[0041] The advice formulation algorithm formulates advice to the presenter to explain in simple terms, for example, when the number of audience members whose evaluation value for the emotion "confusion" calculated by the facial expression analysis algorithm is a predetermined value or more and the number of audience members whose evaluation value for understanding calculated by the questionnaire analysis algorithm is a predetermined value or less is a predetermined value or more. The advice formulation algorithm formulates advice to the audience to mute their microphones, for example, when the number of audience members whose evaluation value of negative emotions (anger, confusion, disgust, sadness, fear) calculated by the facial expression analysis algorithm is equal to or greater than a predetermined value and the evaluation value of voice overlap calculated by the voice analysis algorithm is equal to or greater than a predetermined value. The advice formulation algorithm formulates advice to the presenter to speak louder, for example, when the number of audience members whose evaluation value of negative emotions (anger, confusion, disgust, sadness, fear) calculated by the facial expression analysis algorithm is equal to or greater than a predetermined value and the evaluation value of voice loudness calculated by the voice analysis algorithm is equal to or less than a predetermined value.

[0042] The situation data 13 includes information on the reaction of the audience. The situation data 13 is, for example, the analysis result by a facial expression analysis algorithm, a voice analysis algorithm, or a questionnaire analysis algorithm. The situation data 13 may be the facial expressions, voices, or questionnaires of the audience.

[0043] FIG. 9 is a diagram illustrating an example of the configuration of the system 1-c. The control device 10-c, the external device 11-c, and the monitoring target 12-c are connected via a network, and are capable of transmitting and receiving data. The external device 11-c is a display device that displays advice to the presenter of the conference. The audience reaction monitoring device, which is the monitoring target 12-c, is equipped with a camera, a microphone, and a questionnaire acquisition device corresponding to each audience member. The audience reaction monitoring device acquires facial expression data of each audience member, questionnaire data, and voice data of the presenter, and outputs them to the control device 10-c. The audience reaction monitoring device may further include a camera and a microphone corresponding to the presenter, and a display device and a speaker corresponding to the audience and the presenter, and may be used for a conference between the presenter and the audience of the conference.

[0044] In addition, an external device 11-c corresponding to the audience may be provided so that the audience of the conference can participate in the conference as a presenter. In addition, a presenter of the conference may participate in the conference as an audience by providing the monitoring target 12-c with a questionnaire acquisition device corresponding to the presenter. The audience reaction monitoring device may also acquire facial expression data of the presenter, questionnaire data, and voice data of each audience member from a camera, microphone, and questionnaire acquisition device corresponding to the presenter, and output the acquired data to the control device 10-c. The control device 10-c may also analyze the facial expression data of the presenter, the questionnaire data, and the voice data of each audience member using the audience analysis algorithm.

[0045] FIG. 10 is a diagram showing a flowchart in the case where the system 1-c is a presenter evaluation system. In the flowchart shown in FIG. 10, a desired value of the evaluation value of the atmosphere of the conference is stored in the algorithm execution data storage unit 192 before the start. The monitoring target monitoring unit 120 calculates the evaluation value of the atmosphere of the conference (step S11-c). The instruction generation determination unit 140 determines whether or not to generate an instruction based on the evaluation value of the atmosphere of the conference (step S12-c). When the instruction generation determination unit 140 determines not to generate an instruction (step S13-c: NO), the monitoring target monitoring unit 120 performs the operation of step S11-c again. Here, the monitoring target monitoring unit 120 may perform the operation of step S11-c again after a predetermined time has elapsed. When the instruction generation determination unit 140 determines to generate an instruction (step S13-c: YES), the situation data acquisition unit 125 acquires situation data 13 (such as participant reaction information) (step S14-c). The situation data acquiring unit 125 does not need to newly acquire data used in calculating the monitored target actual measurement data (for example, evaluation values ​​calculated by a facial expression analysis algorithm, a voice analysis algorithm, and a questionnaire analysis algorithm).

[0046] The situation data 13 may include attribute information of the presenter and the audience. The attribute information may be age, industry, etc. The situation data 13 may also include an evaluation value related to the habits of the presenter. The advice to be formulated may vary depending on the attributes of the presenter and the audience, and the habits of the presenter. The control scenario executing unit 130 controls the algorithm control unit 110 to execute the algorithm according to the control scenario stored in the control scenario storage unit 195 (step S15-c). Here, the control scenario is a scenario for executing an advice formulation algorithm. The control scenario may indicate multi-stage control in which an advice formulation algorithm, which is a latter-stage algorithm, formulates advice based on the analysis results of at least one of the preceding algorithms, which are a facial expression analysis algorithm, a voice analysis algorithm, and a questionnaire analysis algorithm.

[0047] The algorithm control unit 110 acquires algorithm execution data by executing the algorithm (step S16-c). The algorithm execution data includes advice for the presenter. The algorithm control unit 110 records the acquired algorithm execution data in the algorithm execution data storage unit 192 (step S17-c). The instruction output unit 150 outputs an instruction to the external device 11 so that the external device 11 operates in accordance with the external device planning data included in the algorithm execution data (step S18-c). The external device planning data includes advice for the presenter, and the external device 11 shows feedback to the presenter of the meeting based on the advice to the presenter. The feedback may be, for example, a diagram showing the atmosphere of the meeting.

[0048] In remote meetings, it is difficult for the presenter to read the atmosphere of the meeting because the audience's expressions cannot be seen and they may not make any comments. System 1-c analyzes the atmosphere of the meeting from the audience's reactions and generates and presents advice to the presenter, allowing the presenter to infer the atmosphere of the meeting.

[0049] Other Embodiments Although one embodiment of the present invention has been described in detail above with reference to the drawings, the specific configuration is not limited to the above, and various design changes, etc. are possible within the scope that does not deviate from the gist of the present invention.

[0050] The processing of the control device 10, the external device 11, or the monitored object 12 in the above-mentioned embodiment may be realized by a computer using software. In that case, a program for realizing this function may be recorded in a computer-readable recording medium, and the program recorded in the recording medium may be read into a computer system and executed to realize the function. The term "computer system" as used herein includes hardware such as an OS and peripheral devices. The term "computer-readable recording medium" refers to portable media such as flexible disks, optical magnetic disks, ROMs, and CD-ROMs, and storage devices such as hard disks built into a computer system. The term "computer-readable recording medium" may also include a medium that dynamically holds a program for a short period of time, such as a communication line when a program is transmitted via a network such as the Internet or a communication line such as a telephone line, and a medium that holds a program for a certain period of time, such as a volatile memory inside a computer system that is a server or client in that case. The above-mentioned program may be a program for realizing a part of the above-mentioned function, or may be a program that can realize the above-mentioned function in combination with a program already recorded in the computer system, or may be a program that is realized using a programmable logic device such as an FPGA (Field Programmable Gate Array). [Explanation of symbols]

[0051] 1 system, 10 control device, 11 external device, 12 monitored object, 13 situation data, 110 algorithm control unit, 120 monitored object monitoring unit, 125 situation data acquisition unit, 130 control scenario execution unit, 140 instruction generation determination unit, 150 instruction output unit, 160 control scenario input unit, 190 memory unit, 191 algorithm memory unit, 192 algorithm execution data memory unit, 193 monitored object data memory unit, 194 situation data memory unit, 195 control scenario memory unit

Claims

1. A control device that plans an operation of an external device that affects an evaluation index of a monitoring target in order to set the value of the evaluation index for evaluating the monitoring target to a desired value, comprising: an algorithm control unit that controls an algorithm for planning an operation of the external device when a difference between a predicted value of the evaluation index calculated from an operation plan and an actual measured value of the evaluation index is equal to or greater than a predetermined value, and generates a new operation plan for the external device based on situation data that is different from data of the value of the evaluation index and that is influenced by the external device; an instruction output unit that outputs an instruction based on the operation plan to the external device and causes the external device to perform an operation based on the operation plan; A control device comprising:

2. The algorithm control unit creates the operation plan by controlling the algorithm according to a control scenario that indicates a method of executing the algorithm when a difference between the predicted value and the actual measured value is equal to or greater than a predetermined value. The control device according to claim 1 .

3. The algorithm control unit executes an algorithm according to a specific control scenario selected from a plurality of control scenarios when the actual measured value of the monitored object satisfies a predetermined condition. The control device according to claim 2.

4. The control scenario indicates a method of executing a multi-stage algorithm in which a subsequent algorithm performs control based on data generated by a control performed by a previous algorithm. The control device according to claim 2.

5. The value of the evaluation index is the amount of purchased electricity, The external device includes at least one device selected from the group consisting of a storage battery charging device, an electric vehicle charging device, and an electric vehicle dispatching device; The status data includes at least one of a remaining charge of a storage battery and an electric vehicle reservation status. A control device according to any one of claims 1 to 4.

6. The value of the evaluation index is the number of delivery delays, the external device is a parcel delivery device; The situation data is traffic congestion information. A control device according to any one of claims 1 to 4.

7. The value of the evaluation index is an evaluation value of the atmosphere of the meeting, The external device is an analysis result display device, The situation data is reaction information of presenters and audience of the conference. A control device according to any one of claims 1 to 4.

8. A control method by a computer for planning an operation of an external device that affects an evaluation index of a monitoring target in order to set the value of the evaluation index for evaluating the monitoring target to a desired value, comprising: an algorithm control step of controlling an algorithm for planning an operation of the external device when a difference between a predicted value of the evaluation index calculated from an operation plan and an actual measured value of the evaluation index is equal to or greater than a predetermined value, and generating a new operation plan for the external device based on situation data that is different from data of the value of the evaluation index and that is influenced by the external device; an instruction output step of outputting an instruction based on the operation plan to the external device and causing the external device to perform an operation based on the operation plan; The control method includes:

9. A program for executing the control method described in claim 8.

Images