JP2022063143A - Air conditioner - Google Patents

Abstract

To provide an air conditioner with an improved prediction accuracy of the presence/absence of a user in an air conditioning space.SOLUTION: An air conditioner has a sensor, a storage part, and a recommendation part. The sensor detects the presence/absence of a person in an air conditioning space. The storage part stores a prediction result of predicting the presence/absence of a user in the air conditioning space by using the detection result of the sensor. The recommendation part selects a recommendation operation which should be recommended for the user, on the basis of the prediction result of the presence/absence of the user in the air conditioning space. When the detection result of the sensor includes a third detection value corresponding to neither a first detection value indicating the presence of the user nor a second detection value indicating the absence of the user, the third detection value is excluded from the detection result of the sensor used in a prediction of the presence/absence of the user in the air conditioning space.SELECTED DRAWING: Figure 14

Description

The present invention relates to an air conditioner.

For example, an air conditioner having a human detection sensor for detecting the presence or absence of a person in an air-conditioned space and setting a timer for the start time of air-conditioning operation using the detection result of the human detection sensor has been proposed (for example, Patent Document 1). ). In Patent Document 1, by comparing the detection results of the human detection sensor for several days with the "rule for determining the presence or absence of the user", the time when the user changes from the absence to the presence of the room in the air-conditioned space is determined. The prediction is made, and the start time of the air conditioning operation is set as a timer based on the prediction result.

Japanese Unexamined Patent Publication No. 11-14121

In the air conditioner described in Patent Document 1, the presence or absence of a user is predicted by using the detection result of the human detection sensor. For example, a temporary cutoff of power supply to the human detection sensor or a heat source other than a human is used. When present in the air-conditioned space, the presence or absence of the user in the air-conditioned space may not be accurately detected. As a result, when the presence / absence detection result in the air-conditioned space is used, the accuracy of predicting the presence / absence of the user in the air-conditioned space is lowered.

In view of such a problem, it is an object of the present invention to provide an air conditioner for improving the accuracy of predicting the presence or absence of a user in an air-conditioned space.

One embodiment of the air conditioner has a sensor, a storage unit, and a recommended unit. The sensor detects the presence or absence of a person in the air-conditioned space. The storage unit stores the prediction result of predicting the presence or absence of the user in the air-conditioned space by using the detection result of the sensor. The recommendation unit selects the recommended operation to be recommended to the user based on the prediction result of the presence or absence of the user in the air-conditioned space. When the detection result of the sensor includes a third detection value that does not correspond to either the first detection value indicating the presence of the user or the second detection value indicating the absence of the user. , The third detection value is excluded from the detection result of the sensor used when predicting the presence or absence of the user in the air-conditioned space.

As one aspect, the accuracy of predicting the presence or absence of the user in the air-conditioned space is improved.

FIG. 1 is an explanatory diagram showing an example of the air conditioning system of the first embodiment. FIG. 2 is a block diagram showing an example of the configuration of an air conditioner. FIG. 3 is a block diagram showing an example of the configuration of the communication adapter. FIG. 4 is an explanatory diagram showing an example of the prediction result of absence. FIG. 5 is a block diagram showing an example of the configuration of the terminal device. FIG. 6 is a block diagram showing an example of the configuration of the server device. FIG. 7 is an explanatory diagram showing an example of data used for generating an absentee pattern. FIG. 8 is an explanatory diagram showing an example of a user's pattern predicted using the absence pattern. FIG. 9A is an explanatory diagram showing an example of a timer setting screen of the terminal device. FIG. 9B is an explanatory diagram showing an example of a recommended screen of the terminal device. FIG. 9C is an explanatory diagram showing an example of a screen for changing the recommended time of the terminal device. FIG. 10 is an explanatory diagram showing an example of a timing chart of each process during the heat sterilization operation. FIG. 11 is an explanatory diagram showing an example of a timing chart of each process during the filter cleaning operation. FIG. 12A is a flowchart showing an example of the processing operation of the CPU of the server device involved in the generation processing for generating the absence pattern. FIG. 12B is a flowchart showing an example of the processing operation of the CPU of the server device involved in the update process for updating the absence / absence pattern. FIG. 13A is a flowchart showing an example of the processing operation of the CPU of the communication adapter related to the recommended processing. FIG. 13B is a flowchart showing an example of the processing operation of the control unit of the indoor unit related to the recommended processing for air conditioning operation in the living room. FIG. 13C is a flowchart showing an example of the processing operation of the control unit of the indoor unit related to the recommended processing for air conditioning operation in the living room. FIG. 13D is a flowchart showing an example of the processing operation of the control unit of the indoor unit related to the recommended processing for air conditioning operation in the bedroom. FIG. 14 is a block diagram showing an example of the configuration of the air conditioner of the second embodiment.

Hereinafter, examples of the air conditioner and the air conditioner system disclosed in the present application will be described in detail with reference to the drawings. The disclosed technique is not limited by the present embodiment. In addition, each of the examples shown below may be appropriately modified as long as it does not cause a contradiction.

<Structure of air conditioning system>
FIG. 1 is an explanatory diagram showing an example of the air conditioning system 1 of the first embodiment. The air conditioner system 1 shown in FIG. 1 includes an air conditioner 2, a communication adapter 3, a router 4, a server device 5, a relay device 6, a terminal device 7, and a communication network 8.

<Structure of air conditioner>
FIG. 2 is a block diagram showing an example of the configuration of the air conditioner 2. The air conditioner 2 shown in FIG. 2 has an indoor unit 21, an outdoor unit 22, and a remote controller 23. The indoor unit 21 is, for example, a part of an air conditioner 2 that is arranged indoors and heats or cools the air in the room which is an air-conditioned space. It is assumed that the indoor unit 21 is provided for each air-conditioned space such as a living room or a bedroom. The indoor unit 21 has a main body 21A, a sensor 21B, a light receiving unit 21C, a control unit 21D, and a memory 21E. The main body 21A is provided with an indoor fan, an indoor heat exchanger, etc. (not shown), and the indoor fan blows out the indoor air that has exchanged heat with the refrigerant supplied from the outdoor unit 22 by the indoor heat exchanger. Room heating, cooling, dehumidification, etc. are performed. The sensor 21B detects the presence or absence of a person in the air-conditioned space. The sensor 21B is, for example, a pyroelectric sensor using infrared rays. When the air conditioner 2 is connected to a commercial power source and power is supplied after the air conditioner 2 is installed, the sensor 21B starts the operation of detecting the presence or absence of a person. After that, unless the power supply is stopped, the presence or absence of a person in the air-conditioned space is continuously detected regardless of the operation / stop of the air conditioner 2. The light receiving unit 21C receives a command signal from the remote controller 23 and transmits the received command signal to the control unit 21D. The memory 21E is an area for storing various information such as for indoor use. The indoor use is information for identifying the use of an air-conditioned space such as a living room or a bedroom. Indoor use is information used to predict user behavior. The control unit 21D controls the entire indoor unit 21. The control unit 21D executes various commands based on the command signal. The outdoor unit 22 is provided with, for example, an outdoor fan, a compressor, and the like. The remote controller 23 is a remote control unit that remotely controls the indoor unit 21 according to the operation of the user.

The control unit 21D has an action prediction unit 21D2, a recommendation unit 21D0, and an extraction unit 21D1. The behavior prediction unit 21D2 predicts the behavior of the user based on the presence / absence prediction result of predicting the presence / absence of the user in the air-conditioned space and the indoor use information for identifying the indoor use of the air-conditioned space. The presence / absence prediction result is information obtained by accumulating the presence / absence prediction result of the user every 10 minutes in the air-conditioned space for 24 hours, which is acquired from the presence / absence prediction unit 34E in the communication adapter 3 described later.

The recommendation unit 21D0 selects the operation to be recommended to the user based on the behavior prediction result of the behavior prediction unit 21D2. The operation includes, for example, an additional function operation such as a heating sterilization operation and a filter cleaning operation in addition to a normal air conditioning operation such as a cooling operation and a heating operation. The heat sterilization operation is an operation in which the indoor heat exchanger in the indoor unit 21 is heated to 55 degrees or higher to sterilize. The filter cleaning operation is an operation for cleaning the filter in the indoor unit 21. The recommendation unit 21D0 transmits, for example, a signal to the user's terminal device to recommend the execution of the selected operation to the user. The recommendation unit 21D0 transmits to the user's terminal device 7 that various air-conditioning operations are recommended via the communication adapter 3, the router 4, the communication network 8, and the router 4.

The behavior prediction unit 21D2 predicts the user's behavior in the air-conditioned space based on the presence / absence prediction result of the user in the air-conditioned space by the presence / absence prediction unit 34E described later and the indoor use information. Then, the recommendation unit 21D0 informs the user's terminal device 7 of the content of the air conditioning operation recommended to the user, such as setting the start time of the air conditioning operation or the stop time of the air conditioning operation, based on the behavior prediction result of the behavior prediction unit 21D2. Send. As the content of the recommended air-conditioning operation, for example, it is recommended to set the timer time for starting the air-conditioning operation according to the wake-up time, the return time, the outing time, and the bedtime. Based on the behavior prediction result of the behavior prediction unit 21D2, the recommendation unit 21D0 transmits a signal to the user's terminal device 7 to recommend the additional function operation different from the air conditioning operation. The content that recommends the additional function operation is, for example, the content that proposes the timer time for starting the heating sterilization operation.

The extraction unit 21D1 extracts a time zone in which an additional function operation different from the normal air-conditioning operation can be executed from the presence / absence prediction result for 24 hours in the air-conditioned space. The time zone in which the additional function operation can be executed is, for example, an absence time of 5 hours or more. The absence time is the absence time of the user in the air-conditioned space extracted from the absence prediction result for 24 hours predicted by the absence prediction unit 34E described later. The extraction unit 21D1 calculates the operable time from the absence time, and compares the operable time with the operating time of the additional function operation stored in advance. Then, when the operable time is equal to or longer than the operating time, the extraction unit 21D1 extracts from the absent time as a time zone in which the additional function operation can be executed.

The communication adapter 3 has a communication function for connecting the indoor unit 21 in the air conditioner 2 and the router 4 by wireless communication, and a control function for controlling the indoor unit 21 by AI (Artificial Intelligence). The communication adapter 3 is arranged for each indoor unit 21. The router 4 is an access point that connects the communication adapter 3 and the communication network 8 by wireless communication using, for example, a WLAN (Wireless Local Area Network) or the like, and also connects the terminal device 7 and the communication network 8 by wireless communication. It is a device of. The communication network 8 is, for example, a communication network such as the Internet. The server device 5 has a function of generating an absence pattern applied to the indoor unit 21, a database for storing operation history data, and the like. The server device 5 is located in a data center, for example. The relay device 6 has a function of connecting to the communication network 8 by communication and also connecting to the server device 5 by communication. The relay device 6 transmits the operation history data and the like used for generating or updating the absence pattern applied to the indoor unit 21 to the server device 5 from the communication adapter 3 via the communication network 8. Further, the relay device 6 transmits the absence pattern generated or updated by the server device 5 to the communication adapter 3 via the communication network 8. The relay device 6 is arranged in, for example, a data center or the like.

The relay device 6 has a first relay unit 6A, a second relay unit 6B, and a third relay unit 6C. The first relay unit 6A transmits various data related to the absence pattern (hereinafter referred to as operation history data) from the communication adapter 3 to the server device 5 via the communication network 8, and the server device 5 generates or updates the data. The presence / absence pattern is transmitted to the communication adapter 3 via the communication network 8. The second relay unit 6B acquires the operating conditions (operating mode such as cooling / heating, set temperature, etc.) of the indoor unit 21 set by the user from outside using the terminal device 7, and obtains the operating conditions of the indoor unit 21. Send to. The third relay unit 6C acquires external data such as weather forecast and calendar information (mainly holiday information) from a communication network 8 such as the Internet, and transmits the acquired external data to the server device 5. Further, the third relay unit 6C transmits external data to the communication adapter 3 via the communication network 8.

<Communication adapter configuration>
FIG. 3 is a block diagram showing an example of the configuration of the communication adapter 3. The communication adapter 3 shown in FIG. 3 has a first communication unit 31, a second communication unit 32, a storage unit 33, and a CPU (Central Processing Unit) 34. The first communication unit 31 is a communication IF (Interface) such as a UART (Universal Asynchronous Receiver Transmitter) that connects the control unit 21D in the indoor unit 21 and the CPU 34 by communication. The second communication unit 32 is a communication unit such as a communication IF such as a WLAN that communicates and connects the router 4 and the CPU 34. The storage unit 33 has, for example, a ROM (Read Only Memory), a RAM (Random Access Memory), and the like, and stores various information such as data and programs. The CPU 34 controls the entire communication adapter 3.

The storage unit 33 in the communication adapter 3 shown in FIG. 3 has a history memory 33A, an absence / absence pattern memory 33B, a prediction result memory 33C, and an external memory 33D. The history memory 33A temporarily stores the operation history data acquired from the indoor unit 21. The operation history data is, for example, the detection result every 10 minutes of the presence or absence of a person in the indoor space detected by the sensor 21B. The presence / absence pattern memory 33B stores the presence / absence pattern acquired from the server device 5.

As the presence / absence pattern, for example, the past detection result of the sensor 21B, for example, the presence / absence detection result for the past 30 days, the day of the week information, and the holiday information are used, so that the server device 5 uses the presence / absence of the user in the air-conditioned space. It is a pattern generated for each day of the week showing the tendency of. In this embodiment, a maximum of five types of absentee patterns are generated, and the absentee patterns are associated with each day of the week so that it can be determined which absentee pattern the user tends to act on for each day of the week. .. For example, Monday and Tuesday tend to behave in absentee pattern 1, Wednesday and Thursday tend to behave in absentee pattern 2, Thursday and Friday tend to behave in absentee pattern 3, and Saturday is absent. They tend to act in absentee pattern 4, and on Sundays they tend to act in absentee pattern 5. Here, the reason why the detection results for the past 30 days of the sensor 21B are used when generating the absence pattern is as follows. When generating the presence / absence pattern, it is preferable that the detection result of the sensor 21B is as large as possible because the accuracy of the prediction using the presence / absence pattern is improved when the detection result of the sensor 21B is large. On the other hand, if a presence / absence pattern is generated using the detection results of the past 90 days so as to acquire a large number of detection results of the sensor 21B, the air conditioner 2 is frequently installed in the cooling operation. In the case of the beginning of summer or the beginning of winter when heating operation is frequently performed, the summer or winter has passed while the absence pattern is being generated, and the expected result of the absence of the user, which will be described later. It becomes impossible to predict user behavior and recommend air-conditioning operation based on the above in summer and winter. Therefore, in the present embodiment, the accuracy of the absence / absence pattern can be guaranteed, and the behavior prediction of the user and the recommendation of the air-conditioning operation based on the prediction result of the presence / absence of the user can be provided at an appropriate time. Considering that, the absentee detection result of the sensor 21B for the past 30 days is used to generate the absentee pattern. The presence / absence detection results for the past 30 days are information obtained by accumulating the absence / absence detection results every 10 minutes for 30 days. Further, in the present embodiment, the case where the detection results for the past 30 days of the sensor 21B are used when generating the absence pattern is illustrated, but the present invention is not limited to this. It may be changed as appropriate according to the period from the time when the air conditioner 2 is installed to the time when it is frequently used.

Further, the day of the week information is information on the day of the week on Monday, Tuesday, Wednesday, Thursday, Friday, Saturday, and Sunday, and is calculated and obtained by the CPU 34. The holiday information is information for identifying a holiday on Monday, Tuesday, Wednesday, Thursday, Friday, Saturday, and Sunday, and is acquired from the outside via the second communication unit 32. The reason for acquiring holiday information from the outside is that holidays may change from year to year. The prediction result memory 33C stores the presence / absence prediction result for 24 hours, which is the prediction result of the presence / absence of the user every 10 minutes for 24 hours in the air-conditioned space predicted by the presence / absence pattern, for each indoor use. .. The indoor use is information for identifying the use of an air-conditioned space such as a living room or a bedroom. The indoor use is information used when predicting the behavior of the user using the presence / absence prediction result. The CPU 34 can recognize the presence / absence prediction result for 24 hours for each air-conditioned space with reference to the prediction result memory 33C. The external memory 33D stores external data acquired from the outside, such as the above-mentioned holiday information and weather forecast.

The CPU 34 has a collection unit 34A, a transmission unit 34B, a reception unit 34C, a setting unit 34D, and an absence / absence prediction unit 34E.

The collecting unit 34A acquires the detection result of the presence or absence of a person in each air-conditioned space from the indoor unit 21 at a predetermined cycle, for example, every 10 minutes. The air-conditioned space is, for example, an air-conditioned space such as a living room or a bedroom. The collecting unit 34A collects the current detection result of the presence or absence of a person every 10 minutes by the sensor 21B in the acquired air-conditioned space. The presence / absence detection result includes, for example, three types of variables: absence, presence, and indefinite. Of the absentee detection results, "absence" is a detection result when a person cannot be detected in the air-conditioned space. The detection result of this "absence" is the second detection value. Among the detection results of presence / absence, "in-room" is the detection result when a person is detected in the air-conditioned space. The detection result of this "in-room" is the first detection value. Of the absentee detection results, "indefinite" is a third detection value that does not correspond to either presence or absence, that is, does not correspond to either the first detection value or the second detection value. This is a detection result that is not used to generate an absentee pattern. The collecting unit 34A stores the detection result of the presence / absence of each air-conditioned space acquired every 10 minutes in the history memory 33A.

For example, when the transmission unit 34B stores the absence detection results for two days in the history memory 33A, the transmission unit 34B stores the absence detection results for two days stored in the history memory 33A in the server device 5 via the communication network 8. Send to. The server device 5 will generate up to five types of absentee patterns described above using the absentee / absence detection results for the past 30 days sequentially received from the communication adapter 3. The receiving unit 34C receives the presence / absence pattern for each air conditioning space from the server device 5 via the communication network 8, and stores the received absence / absence pattern in the presence / absence pattern memory 33B. The setting unit 34D applies the presence / absence pattern in memory to the presence / absence prediction unit 34E.

The presence / absence prediction unit 34E includes the detection result of the current sensor 21B, that is, the detection result of the presence / absence, which is the detection result of the sensor 21B from the time when the presence / absence is predicted to a predetermined time before, the current day of the week information, and the current day of the week. Using the holiday information, the presence / absence pattern to be used for prediction is selected from the plurality of absence / absence patterns applied by the setting unit 34D. The presence / absence prediction unit 34E predicts the presence / absence of the user in the air-conditioned space using the selected presence / absence pattern, and obtains the presence / absence prediction result for 24 hours. The predetermined time is the time required to obtain the number of data that can guarantee the accuracy when selecting the optimum absentee pattern from a plurality of absentee patterns by looking at the detection result of the absentee immediately before.

Hereinafter, the selection of the absentee pattern used for the prediction and the method of predicting the absenteeism of the user using the selected absentee pattern will be described in detail. In the following explanation, the presence / absence of the user is predicted every day at 8:00, and the presence / absence of the user is predicted for 24 hours from 8:00 on the current day to 8:00 on the next day. do. In the present embodiment, the above 24-hour forecast is divided into two periods, 1) from 8:00 on the current day to 0:00 on the next day, and 2) from 0:00 on the next day to 8:00 on the next day. A total of 24 hours of prediction results will be used.

<1) Prediction of the presence or absence of users from 8:00 on the day to 0:00 on the next day>
First, the absence / absence prediction unit 34E predicts the presence / absence of the user at a time, for example, 8:00 on the current day, a predetermined time before the prediction time, for example, 21:00 on the day before the prediction day. The detection result of the presence or absence of the user detected by the sensor 21B from 1 to 8:00 on the day is acquired. Next, the absence / absence prediction unit 34E compares a plurality of absence / absence patterns with each other, and determines whether there is a difference in each absence / absence pattern. Specifically, it is determined whether or not the difference between the presence / absence patterns is a predetermined value or more. More specifically, the presence / absence of the user every 10 minutes from 0:00 to 8:00 in each absence pattern is compared, and the place where the presence / absence is different (hereinafter referred to as "time zone") is a predetermined value. For example, when the number is less than 10, it is determined that the difference between the absentee patterns is within the allowable range (there is no difference in the absentee patterns from 0:00 to 8:00). On the other hand, when there are, for example, 10 or more time zones in which the presence / absence of the user is different every 10 minutes from 0:00 to 8:00, the difference in each absence pattern exceeds an acceptable range (0:00). There is a difference in the presence / absence pattern from 8:00 to 8:00).

Next, the absence / absence prediction unit 34E selects the presence / absence pattern to be used for prediction based on the comparison result of each of the above-mentioned absence / absence patterns. If the difference between the absentee patterns is less than a predetermined value (there is no difference in the absentee patterns from 0:00 to 8:00), the absentee pattern associated with the day of the week to be predicted is selected. In addition, when the difference between the absentee patterns is equal to or more than a predetermined value (when there is a difference in the absentee patterns from 0:00 to 8:00), the presence or absence of the user acquired from 0:00 to 8:00 is present. The detection result is compared with the presence / absence from 0:00 to 8:00 in each presence / absence pattern, and the presence / absence pattern that most closely matches the detection result is selected. Then, the absence / absence prediction unit 34E extracts the absence / absence from 8:00 to 0:00 in the above-selected absence / absence pattern as the prediction result of the presence / absence of the user from 8:00 on the current day to 0:00 on the next day. do. In this way, the number of absentee patterns to be generated is the number of days of the week by associating each absentee pattern with the day of the week information and predicting the absenteeism of the user according to the comparison result of each absentee pattern. It is possible to accurately predict the presence or absence of the user while reducing the number.

Originally, it is desirable to generate the absentee pattern for each day of the week and select the absentee pattern to be used according to the day of the week on which the absenteeism of the user is actually predicted. This is because if the absence pattern is generated for each day of the week, the accuracy of prediction can be expected to improve accordingly. However, as the number of absentee patterns increases, the amount of communication between the communication adapter 3 and the server device 5 increases, the memory capacity required by the communication adapter increases, and the like, and the air conditioning system 1 becomes available. It takes a heavy load.

Therefore, in the present embodiment, as described above, the maximum number of absentee patterns is five, and the same pattern is applied to the days of the week when the predicted absentee patterns can be regarded as the same. For example, absentee pattern 1 applies to Monday and Tuesday, absentee pattern 2 applies to Wednesday and Thursday, absentee pattern 3 applies to Thursday and Friday, and absentee pattern 4 applies to Saturday. , Absence pattern 5 is applied on Sunday. However, if the absentee pattern is generated so that it can be applied to a plurality of days of the week in this way, the absentee pattern is generated for each day of the week and the absentee pattern is predicted as compared with the case of predicting the absenteeism of the user. The accuracy may decrease.

Therefore, in order to deal with such a situation, in the present embodiment, the method of selecting the presence / absence pattern used for predicting the presence / absence of the user is changed according to the comparison result of each presence / absence pattern. If the difference between the absentee patterns is less than the predetermined value, it is not possible to determine which absentee pattern should be used by using the absentee information of the user acquired up to the predicted time (8:00), so the prediction is made. If you select an absentee pattern that matches the day of the week, the accuracy of the prediction will not decrease. In addition, when the difference between each absentee pattern is greater than or equal to a predetermined value, each absentee pattern can be distinguished. The accuracy of the prediction is ensured by selecting the most similar absentee pattern.

<2) Prediction of the presence or absence of users from 0:00 the next day to 8:00 the next day>
First, the presence / absence prediction unit 34E reads the day of the week following the day on which the presence / absence of the user is predicted from the external memory 33D. Next, the absence / absence prediction unit 34E selects the presence / absence pattern corresponding to the read day of the week from the plurality of absence / absence patterns. Then, the absence / absence prediction unit 34E extracts the presence / absence prediction result of the user from 0:00 of the next day to 8:00 of the next day from the above-selected absence / absence pattern.

At the stage of predicting the presence or absence of the user at 8:00 on the day, 1) Unlike the case of predicting the presence or absence of the user from 8:00 on the day to 0:00 on the next day, the sensor 21B after 8:00 on the day It does not have the detection result of the presence or absence of the user detected in. Therefore, in the prediction of the absence of the user from 0:00 on the next day to 8:00 on the next day, the absence pattern to be used for the prediction is selected based on the day of the next day, and the selected absence pattern is used on the next day. Predict the presence or absence of the user from 0:00 to 8:00 the next day.

Then, the absence prediction unit 34E obtains the prediction result of the absence of the user from 8:00 on the day to 0:00 on the next day obtained in 1) and from 0:00 to 8:00 on the next day obtained in 2). Combined with the prediction result of the presence or absence of the user, the presence or absence of the user for 24 hours from 8:00 on the current day to 8:00 on the next day is predicted, and the predicted result is the presence or absence prediction result for 24 hours. Is output to the prediction result memory 33C. The prediction result memory 33C stores the presence / absence prediction result for 24 hours. When the time zone to be predicted includes a holiday, the presence / absence prediction unit 34E considers the time zone to be the same as a holiday and obtains the presence / absence prediction result for 24 hours in the air-conditioned space. Further, the presence / absence prediction unit 34E is the detection result of the presence / absence of "undefined" among the detection results of the sensor 21B used when predicting the presence / absence of the user in the air-conditioned space (the first). (Detected value of 3) is excluded. That is, since the “undefined” absence / absence detection result is excluded and not used for the generation or update of the absence / absence pattern, the accuracy of prediction by the generated / updated presence / absence pattern can be improved.

The presence / absence prediction unit 34E sets the predetermined time at which the presence / absence is predicted, for example, at 8:00 and 20:00 every day until 24 hours after the predetermined time (hereinafter referred to as “second predetermined period”). ) May predict the presence or absence of the user in the air-conditioned space. Specifically, the prediction unit 34E obtains the presence / absence prediction result for 24 hours, which is the prediction result of the presence / absence of the user. The reason for setting 8:00 as the predetermined time is that the behavior pattern of the user after that is likely to be going out → (absent) → returning home, so it is recommended to operate additional functions when absent or when returning home. This is to recommend the start of operation. In addition, the reason why the predetermined time is set to 20:00 is that it is considered that the behavior pattern of the user after that is often going to bed → waking up, so it is recommended to perform good night driving or start driving when waking up. .. The good night operation is an air-conditioned operation that makes the indoor temperature of the bedroom comfortable in order to provide the user with a comfortable sleeping environment. Further, the presence / absence prediction unit 34E improves the prediction accuracy by obtaining the presence / absence prediction results for 24 hours from each of the predetermined times every half day. The presence / absence prediction result for 24 hours is, for example, the prediction result of the presence / absence of the user in the air-conditioned space every 10 minutes (hereinafter referred to as “third predetermined period”). FIG. 4 is an explanatory diagram showing an example of the prediction result of absence for 24 hours. The presence / absence prediction result shown in FIG. 4 is the presence / absence prediction result every 10 minutes from a predetermined time to 24 hours later for each air-conditioned space. The data indicating the prediction result of presence / absence is "1" in the case of being in the room and "0" in the case of absence.

Next, the behavior prediction unit 21D2 determines the daily behavior of the user in the living space (for example, based on the prediction result of the presence or absence of the user in the air-conditioned space and the indoor use information (living room or bedroom) of the air-conditioned space. , Wake-up time, go-out time, return time, bedtime). Then, the recommendation unit 21D0 selects the driving to be recommended to the user based on the behavior predicted by the behavior prediction unit 21D2. Further, the recommendation unit 21D0 recommends the user to execute the operation that should be recommended to the user. Hereinafter, for example, when the indoor unit 21 of the air conditioner 2 is installed in the living room or the bedroom, the control unit 21D of the indoor unit 21 uses the result of predicting the presence or absence of the user in the living room or the bedroom. Explain how to predict daily behavior in the living space (for example, wake-up time, going out time, return time, bedtime), select the recommended driving, and recommend the user to perform the recommended driving. ..

For example, the behavior prediction unit 21D2 of the control unit 21D in the indoor unit 21 in the living room predicts the wake-up time from the presence / absence prediction result, and is referred to as a user's wake-up time zone (hereinafter referred to as “first time zone”). ) And the period used as a criterion for judging whether or not the user is absent from the living room (hereinafter referred to as "fourth predetermined period"). The first time zone is a preset time zone, for example, from 0:00 to 10:50, assuming a time when the user wakes up, goes out of the bedroom, enters the living room, and starts the air conditioning operation. Is. The fourth predetermined period is, for example, three hours or more of continuous absence time used by the user to determine that he / she is sleeping in the bedroom. The behavior prediction unit 21D2 predicts that the timing is the wake-up time when there is a timing in the living room where the first time zone in the absence prediction result changes from the absence for the fourth predetermined period or more to the presence of the room. .. The recommendation unit 21D0 generates a recommendation signal to start the air conditioning operation 15 minutes before the wake-up time predicted by the behavior prediction unit 21D2.

The behavior prediction unit 21D2 predicts the bedtime from the result of the absence prediction, during the time when the user leaves the living room (hereinafter referred to as "fourth time zone") or the period during which the user enters the bedroom (hereinafter referred to as "fourth time zone"). "Fifth predetermined period") is used. The behavior prediction unit 21D2 determines whether or not there is a timing for changing from being in the room to being absent for a fifth predetermined period or longer in the fourth time zone in the absence prediction result. The fourth time zone is a preset time zone, for example, from 17:00 to 23:50, assuming a time when the user stops the air-conditioning operation of the living room at night and leaves the living room. The fifth predetermined period is, for example, three hours or more of continuous absence time used for determining that the user is sleeping. The behavior prediction unit 21D2 leaves the user from the living room when there is a timing when the room changes from being in the living room to being absent for a fifth predetermined period or longer in the fourth time zone in the absence prediction result. The timing at which the patient disappears is predicted to be the bedtime. Then, when the recommendation unit 21D0 predicts the bedtime, the user's terminal sends a recommendation signal to start the air conditioning operation 15 minutes before the wake-up time between 1 hour before the bedtime and the bedtime. It is transmitted to the device 7. In addition, the recommendation unit 21D0 is between 18:00 and 19:00 when there is no timing for changing from being in the room to being absent for a fifth predetermined period or longer in the fourth time zone in the absence prediction result. In addition, a recommended signal to start the air conditioning operation 15 minutes before the wake-up time is transmitted to the terminal device 7 of the user.

In addition, the behavior prediction unit 21D2 uses the user's return time zone (hereinafter referred to as "second time zone") and the fourth predetermined period in predicting the return time from the absence prediction result. The second time zone is a preset time zone, for example, from 13:00 to 22:50, assuming a time when the user returns home, for example, the user enters the living room and starts the air conditioning operation. be. The behavior prediction unit 21D2 predicts that the timing is the time to return home when there is a timing of changing from the absence for the fourth predetermined period or more to the presence of the room in the second time zone in the absence prediction result. The recommendation unit 21D0 generates a recommendation signal to start the air conditioning operation 15 minutes before the return time predicted by the behavior prediction unit 21D2. Then, the recommendation unit 21D0 transmits a recommendation signal to the user's terminal device 7 to start the air conditioning operation 15 minutes before the time of returning home between 11:00 and 12:00.

In addition, the behavior prediction unit 21D2 predicts the time of going out from the result of the absence prediction, the time zone when the user goes out (hereinafter, "third time zone") and whether or not the user is out. The period used as a criterion for judging (hereinafter, "sixth predetermined period") is used. The third time zone is a preset time zone, for example, from 8:00 to 16:50, assuming a time when the user goes out and the air conditioning operation is stopped for a long time. The sixth predetermined period is, for example, a continuous absence time of 5 hours or more, which is used to determine that the user is out. The behavior prediction unit 21D2 predicts that the timing is the time of going out when there is a timing of changing from being in the room to being absent for a sixth predetermined period or more in the third time zone in the absence prediction result. Then, the recommended unit 21D0 heats from 1 hour after the time of going out when the cooling operation or the dehumidifying operation is executed before the predicted absence time and 3 days or more have passed since the previous heating sterilization operation was performed. Generates a recommended signal to start the sterilization operation. Then, the recommendation unit 21D0 transmits a recommendation signal to start the heating sterilization operation to the user's terminal device 7.

In addition, the behavior prediction unit 21D2 predicts the time of going out from the result of the absence prediction, the time zone when the user goes out (hereinafter, "third time zone") and whether or not the user is out. The period used as a criterion for judging (hereinafter, "seventh predetermined period") is used. The seventh predetermined period is, for example, a continuous absence time of 1 hour or more and less than 5 hours, which is used to determine that the user is out. The behavior prediction unit 21D2 predicts that the timing is the time of going out when there is a timing of changing from being in the room to being absent for a seventh predetermined period or more in the third time zone in the absence prediction result. Then, when the integrated operation time of the indoor unit 21 is 200 hours or more, the recommendation unit 21D0 generates a recommended signal to start the filter cleaning operation one hour after the time of going out. Then, the recommendation unit 21D0 transmits a recommendation signal to start the filter cleaning operation to the user's terminal device 7.

It should be noted that the above-mentioned heat sterilization operation and filter cleaning operation may be recommended to the user after the user leaves the living room to go to bed. In this case, if there is a continuous absence time for the sixth predetermined period or more after the time when the user leaves the living room in the fourth time zone, superheat sterilization operation is recommended, and the seventh predetermined period is continuous. If you have absent time, we recommend cleaning the filter.

Further, for example, the behavior prediction unit 21D2 of the indoor unit 21 in the bedroom predicts the bedtime from the presence / absence prediction result, in which the user enters the bedroom in the fourth time zone and the user enters the bedroom. The fifth predetermined period, which is the period to enter, is used. The behavior prediction unit 21D2 determines whether or not there is a timing for changing from the absence of the fifth predetermined period or more to the presence in the bedroom in the fourth time zone in the absence prediction result. The behavior prediction unit 21D2 indicates that the user is present in the bedroom when there is a timing in which the absence for the fifth predetermined period or longer in the bedroom changes to the presence of the room in the fourth time zone in the absence prediction result. This timing is predicted to be the bedtime. Then, when the recommendation unit 21D0 predicts the timing as the bedtime, the recommendation unit 21D0 generates a recommendation signal to start the air conditioning operation at the bedtime. The recommendation unit 21D0 transmits a recommendation signal to the user's terminal device 7 to start the air-conditioning operation at the bedtime from 1 hour before the bedtime to the bedtime.

Further, for example, the behavior prediction unit 21D2 of the control unit 21D in the indoor unit 21 in the bedroom is a room leaving time zone in which the user leaves the bedroom in predicting the leaving time from the presence / absence prediction result. The third time zone and the sixth predetermined period, which is a period used as a criterion for determining whether or not the user is out of the bedroom, are used. The behavior prediction unit 21D2 sets the timing when the bedroom leaves the bedroom to change from being in the room to being absent for a predetermined period or longer in the third time zone in the absence prediction result. Predict. The recommendation unit 21D0 executes the cooling operation or the dehumidifying operation before the leaving time, and when 3 days or more have passed since the previous heating sterilization operation, the heating sterilization operation starts 1 hour after the leaving time. Generates a recommended signal to start. Then, the recommendation unit 21D0 transmits a recommendation signal to start the heating sterilization operation to the user's terminal device 7. The time of leaving the room when the air-conditioned space is a bedroom corresponds to the time of going out when the air-conditioned space is a living room.

In addition, the behavior prediction unit 21D2 predicts the time of leaving the room (wake-up time) from the result of the prediction of presence / absence, and the third time zone, which is the time of leaving the room where the user leaves the bedroom, and the user's bedroom. The seventh predetermined period, which is the period used as a criterion for determining whether or not the person has left the room, is used. The behavior prediction unit 21D2 predicts the timing as the leaving time when there is a timing when the third time zone in the absence prediction result in the bedroom changes from being in the room to being absent for the seventh predetermined period or longer. do. Then, when the integrated operation time of the indoor unit 21 is 200 hours or more, the recommendation unit 21D0 generates a recommended signal to start the filter cleaning operation one hour after the exit time. Then, the recommendation unit 21D0 transmits a recommendation signal to start the filter cleaning operation to the user's terminal device 7.

<Configuration of terminal device>
The terminal device 7 is a communication terminal such as a smartphone of a user who is an administrator among a plurality of users who use the air conditioning system 1. The administrator has the authority to confirm the update and execute the update, and is a user registered in the air conditioning system 1. FIG. 5 is a block diagram showing an example of the configuration of the terminal device 7.

The terminal device 7 shown in FIG. 5 has a communication unit 41, an operation unit 42, a display unit 43, a storage unit 44, and a CPU 45. The communication unit 41 communicates with the communication adapter 3 via the communication network 8 and the router 4. The operation unit 42 is an input interface for inputting various commands. The display unit 43 is an output interface for displaying various information. The storage unit 44 stores various information. The CPU 45 controls the entire terminal device 7. The operation unit 42 has a change unit 42A that changes the second timer time, which is the recommended time on the recommended screen shown in FIG. 9B, which will be described later, according to a predetermined operation.

<Server device configuration>
FIG. 6 is a block diagram showing an example of the configuration of the server device 5. The server device 5 shown in FIG. 6 has a communication unit 51, a storage unit 52, and a CPU 53. The communication unit 51 is a communication IF for communicating and connecting the relay device 6 and the CPU 53. The storage unit 52 has, for example, an HDD (Hard Disk Drive), a ROM, a RAM, or the like, and stores various information such as data and programs. The CPU 53 controls the entire server device 5.

The storage unit 52 in the server device 5 shown in FIG. 6 has a history data memory 52A and a pattern storage unit 52B. The history data memory 52A stores operation history data such as detection results of absence / absence for two days in the air-conditioned space received from the communication adapter 3. The pattern storage unit 52B stores the presence / absence pattern generated by the server device 5, updates the generated presence / absence pattern using the acquired data, and stores the updated presence / absence pattern.

The CPU 53 in the server device 5 has a receiving unit 53A, an acquisition unit 53B, a generation unit 53C, and a transmission unit 53D.

The receiving unit 53A is connected to the communication adapters 3 of the plurality of indoor units 21 and is detected from the communication adapter 3 for two days in the absence of the air-conditioned space via the router 4, the communication network 8, and the relay device 6. Is received, and the detected result of absence for two days received is stored in the history data memory 52A. The receiving unit 53A receives the day of the week information and the holiday information from the communication adapter 3. The day of the week information may be calculated and obtained by the CPU 53 of the server device 5, and the holiday information may be directly acquired by the server device 5 from the outside. The acquisition unit 53B acquires the day of the week information and holiday information received by the reception unit 53A. The acquisition unit 53B acquires the day of the week information and holiday information received by the reception unit 53A.

FIG. 7 is an explanatory diagram showing an example of data used for generating an absentee pattern. The data used to generate the presence / absence pattern includes the presence / absence detection result as sensor data, the day of the week information as day of the week data, and the holiday information as holiday data. As described above, the presence / absence detection result is the detection result of the presence / absence of a person every 10 minutes of the sensor 21B in the air-conditioned space. Further, as described above, the detection result of "indefinite" absence / absence shall not be used for generating or updating the absence / absence pattern.

The generation unit 53C uses the first predetermined period stored in the history data memory 52A, for example, the absence detection result, the day of the week information, and the holiday information shown in FIG. 7 for 30 days, which are the past detection results. The presence / absence pattern of the user in the air-conditioned space of the indoor unit 21 is generated. The generation unit 53C stores the generated absence / absence pattern in the pattern storage unit 52B. If the time zone of the absentee detection result includes a holiday, the generation unit 53C considers the time zone to be the same as a holiday. After storing the presence / absence pattern in the pattern storage unit 52B, the generation unit 53C stores the presence / absence pattern in the pattern storage unit 52B in the history data memory 52A, for example, using the detection result of the absence / absence for 6 days unused for generation. The presence / absence pattern inside is updated, and the updated presence / absence pattern is stored in the pattern storage unit 52B.

When the air conditioner 2 is installed in the living room, for example, the generation unit 53C is on a weekday, for example, Monday (excluding holidays) from the detection result of the presence / absence of the living room stored in the history data memory 52A. Extract the detection result of absence. Further, the generation unit 53C extracts the presence / absence detection results other than "indefinite" from the above-extracted Monday absence / absence detection results, and based on the extracted living room presence / absence detection results, in the living room on Monday. Generate an absentee pattern that predicts the absenteeism of a person. Further, when the air conditioner 2 is installed in the bedroom, for example, the generation unit 53C detects weekdays, for example, Mondays (excluding holidays) from the detection result of the absence of the bedroom stored in the history data memory 52A. ) Is present or absent detection result is extracted. Further, the generation unit 53C extracts the presence / absence detection results other than "indefinite" from the above-extracted Monday absence / absence detection results, and based on the extracted bedroom presence / absence detection results, in the bedroom on Monday. Generate an absentee pattern that predicts the absenteeism of a person.

Further, the generation unit 53C extracts the presence / absence detection results of holidays and Sundays from the detection results of the presence / absence of the living room stored in the history data memory 52A. Further, the generation unit 53C extracts the presence / absence detection results other than "indefinite" from the extracted holiday / absence detection results, and based on the extracted living room presence / absence detection results, the living room on Sunday. Generate an absentee pattern that predicts the absenteeism of a person in. Further, the generation unit 53C extracts the presence / absence detection results of holidays and Sundays from the detection results of the absence / absence of the bedroom stored in the history data memory 52A. Further, the generation unit 53C extracts the absence detection results other than "indefinite" from the extracted holiday and absence detection results on Sunday, and based on the extracted bedroom absence detection results, the bedroom on Sunday. Generate an absentee pattern that predicts the absenteeism of a person in.

That is, the generation unit 53C generates the presence / absence pattern for each day of the week in the air-conditioned space where the indoor unit 21 is installed. For convenience of explanation, the case of generating the absence pattern for each day of the week is illustrated. For example, the absence pattern for each air-conditioned space on weekdays is set as a weekday from Monday to Friday other than holidays, and the absence pattern is generated for each holiday and Saturday. And Sunday may be a holiday, and the absence pattern for each air-conditioned space on the holiday may be generated. In addition, although holidays, Saturdays, and Sundays are exemplified as holidays, the present invention is not limited to these, and regardless of holidays and holidays on the calendar, for example, Tuesday may be set as a holiday and can be changed as appropriate. ..

FIG. 8 is an explanatory diagram showing an example of the generated user's absence pattern. The absence pattern 1 shown in FIG. 8 is an absence pattern indicating the presence or absence of the user in the air-conditioned space on Monday and Tuesday. Although not shown, the presence / absence pattern of the user in the air-conditioned space from Wednesday to Saturday other than holidays is also predicted. Pattern 2 is an absence pattern indicating the presence or absence of the user in the air-conditioned space on Sundays and holidays.

The generation unit 53C generates or updates the absence pattern for each day of the week in each air-conditioned space based on the absence detection result, the day of the week information, and the holiday information, and stores the generated or updated absence pattern in the pattern storage unit 52B. do. The transmission unit 53D transmits to the communication adapter 3 the presence / absence pattern for each day of the week in the air-conditioned space stored in the pattern storage unit 52B via the relay device 6, the communication network 8, and the router 4.

<Display form of terminal device>
FIG. 9A is an explanatory diagram showing an example of the timer setting screen 70 of the terminal device 7. The timer setting screen 70 shown in FIG. 9A has an operation mode display unit 71 that displays the operation mode currently being operated, a set temperature display unit 72 that displays the current set temperature, and a set air volume display that displays the current set air volume. A unit 73, a first timer display unit 74 that displays the content of the reserved operation set by the user, and a second timer display unit that displays the content of the reserved operation (AI operation proposal) recommended by the air conditioner 2. 75 is displayed. The operation mode display unit 71 displays a mode currently in operation such as a normal air conditioning operation such as cooling, heating, ventilation, and drying, and an additional function operation such as a filter cleaning operation and a heating sterilization operation. The first timer display unit 74 is a first display unit that displays the timer time such as the start time and the end time of the air conditioning operation according to the setting operation of the user. The second timer display unit 75 is a second display unit that displays the timer time such as the start time of the air conditioning operation recommended by the recommended unit 21D0 of the air conditioner 2. By displaying the first timer display unit 74 and the second timer display unit 75 separately on the timer setting screen 70, the user can operate the timer set by the user by the first timer display unit 74. It can be easily distinguished from the AI operation proposal by the second timer display unit 75. As a result, the user can prevent an erroneous operation such as erroneously deleting the AI operation proposal as compared with the case where both are displayed without distinction.

FIG. 9B is an explanatory diagram showing an example of the recommended screen 80 of the terminal device 7. When the second timer display unit 75 on the timer setting screen 70 shown in FIG. 9A is selected by the user, the terminal device 7 displays the recommended screen 80 shown in FIG. 9B. The recommended screen 80 has a reservation execution presence / absence selection unit 81, a second timer time display unit 82 that displays the timer setting time of the AI operation proposal, and a recommended content display unit 83 that displays a sentence explaining the content of the AI operation proposal. And the recommended setting presence / absence selection unit 84 are displayed. The reservation execution presence / absence selection unit 81 is an operation unit that instructs the air conditioner 2 whether or not to execute the reservation. The second timer time display unit 82 displays the timer time recommended by the recommended unit 21D0 of the air conditioner 2. The recommended content display unit 83 pops up the recommended content recommended by the recommended unit 21D0. The recommended content is, for example, "It's going to be cold tomorrow morning. Would you like to make a driving reservation so that you can feel comfortable at 6:00 am?" The recommended setting presence / absence selection unit 84 is an operation unit that instructs the air conditioner 2 whether or not to set the recommended content.

FIG. 9C is an explanatory diagram showing an example of a screen 90 for changing the recommended time of the terminal device 7. When the second timer time display unit 82 on the recommended screen 80 shown in FIG. 9B is selected by the user, the terminal device 7 displays the change screen 90 shown in FIG. 9C. The second timer time display unit 82 corresponds to the change unit 42A, and displays the change screen 90 according to the user's selection operation. The terminal device 7 can freely adjust the second timer time according to the change operation of the second timer time 91 on the change screen 90 by the user. As a result, the user can freely adjust the timer time of the recommended AI operation.

For convenience of explanation, the case where the timer setting screen 70 shown in FIG. 9A, the recommended screen 80 shown in FIG. 9B, and the change screen 90 shown in FIG. 9C are displayed on the terminal device 7 has been illustrated, but the timer setting screen 70 is recommended. The screen 80 and the change screen 90 may be displayed on the remote controller 23, respectively. Further, in the above description, the case where the first timer display unit 74 and the second timer display unit 75 are provided in advance in the terminal device 7, but for example, an air conditioner for which AI operation proposal cannot be originally made. When 2 can make an AI operation proposal by updating a program or the like, one of a plurality of first timer display units 74 may be changed to a second timer display unit 75.

<Recommendation for additional function operation>
Next, recommendations from the air conditioner 2 for additional function operation, which is different from normal air conditioning operation, to the user will be described. The additional function operation of this embodiment includes a heating sterilization operation and a filter cleaning operation. FIG. 10 is an explanatory diagram showing an example of a timing chart of each process during the heat sterilization operation. The recommended unit 21D0 in the air conditioner 2 obtains the presence / absence prediction result for 24 hours, which is the prediction result of the presence / absence prediction unit 34E, and from the prediction result, the sixth predetermined period, for example, 5 hours or more. Detect the time when the absence is expected. Then, the recommended unit 21D0 is subjected to the cooling operation or the dehumidifying operation until immediately before the detected absence time of 5 hours or more (for example, 1 hour before), and 3 days or more have passed since the previous execution of the heating sterilization operation. Only in some cases, heat sterilization operation is recommended to the user. When the cooling operation or the dehumidifying operation is stopped, the air conditioner 2 notifies the terminal device 7 of the recommendation of the heating sterilization operation. If the user who has received the recommendation notification of the heat sterilization operation does not refuse to execute the heat sterilization operation, the air conditioner 2 executes the heat sterilization operation within the detected absence time of 5 hours or more. The heating sterilization operation is executed through the following procedure. First, the air conditioner 2 executes the monitoring operation described later from the time when the cooling operation or the dehumidifying operation is stopped to the first hour of the absence time of 5 hours or more. After the monitoring operation is completed, the heating sterilization operation is executed for 1 hour, and the remaining 3 hours is the cooling period for reducing the indoor temperature and the indoor humidity raised by the heating sterilization operation.

The above-mentioned monitoring operation is an operation for monitoring whether or not a person is actually present in the air-conditioned space by using the detection result of the presence or absence of the sensor 21B. When the additional function operation is the heating sterilization operation, the monitoring time is from the time when the cooling operation or the dehumidifying operation is stopped to the time when the heating sterilization operation is executed, and the presence or absence of the user in the air-conditioned space is set during the monitoring time. Perform a monitoring operation to monitor. Then, if a person is detected in the air-conditioned space during the monitoring operation, the air conditioner 2 does not execute the heat sterilization operation, and the user does not execute this heat sterilization operation. Notify the terminal device 7 of. Note that FIG. 10 shows a case where the cooling operation or the dehumidifying operation is stopped and the monitoring time starts at the time when the person is absent.

Further, the heating sterilization operation is an operation in which the indoor heat exchanger of the indoor unit 21 is heated to 55 degrees to sterilize as described above. By executing the heat sterilization operation, the room temperature and the room humidity in the air-conditioned space will rise. Therefore, after the heat sterilization operation is executed, a cooling period is provided as a time until the room temperature and the room humidity increased by the heat sterilization operation decrease. The cooling period is a preparation time that should be provided from the end of the heating sterilization operation to the normal air conditioning operation. As a result, it is possible to avoid a situation in which the user is uncomfortable in the air-conditioned space due to the heat sterilization operation.

FIG. 11 is an explanatory diagram showing an example of a timing chart of each process during the filter cleaning operation. The recommended unit 21D0 in the air conditioner 2 detects the absence time of 1 hour or more and less than 5 hours in the absence prediction result for 24 hours, which is the prediction result of the absence prediction unit 34E, and also When the integrated operation time of the indoor unit 21 is 200 hours or more, the filter cleaning operation is recommended to the user. When the user accepts the recommended filter cleaning operation, the air conditioner 2 has a monitoring operation in the first hour and a filter cleaning operation in the next 20 minutes within the absence time of 1 hour or more and less than 5 hours. To execute. The monitoring operation is an operation of monitoring whether or not a person is actually absent in the air-conditioned space by using the detection result of the presence or absence of the sensor 21B. Specifically, of the absence time of 1 hour or more and less than 5 hours, the first 1 hour is the monitoring time before starting the filter cleaning operation, and the presence / absence of the user in the air-conditioned space is defined as the monitoring time. Perform a monitoring operation to monitor. Then, during the monitoring operation, the terminal device 7 in which a person is detected in the air-conditioned space is notified. As a result, it is possible to avoid a situation in which the user is uncomfortable in the air-conditioned space due to the filter cleaning operation.

As described above, in the air conditioning system 1 of the present embodiment, the execution of the additional function operation which may cause discomfort to the user when executed while the user is in the room is predicted. Recommended according to the length of the user's absence. As a result, the indoor heat exchanger of the indoor unit 21 can be sterilized and the filter can be automatically cleaned without causing discomfort to the user.

<Generation of absence pattern in air conditioning system>
Next, the generation of the absence pattern in the air conditioning system 1 of this embodiment will be described. FIG. 12A is a flowchart showing an example of the processing operation of the CPU 53 of the server device 5 involved in the generation processing for generating the absence pattern. The generation process is a process of first generating an absentee pattern after the air conditioner 2 is later installed in the air-conditioned space. In FIG. 12A, the receiving unit 53A in the CPU 53 of the server device 5 periodically communicates with the communication adapter 3 at 0:00 every day, and detects the presence / absence of the air-conditioned space for two days from the communication adapter 3. It is determined whether or not it has been received (step S11). The communication adapter 3 is stored in the history memory 33A until the detection result of absence for two days is obtained. When the receiving unit 53A receives the absence detection results for two days (step 11: Yes), the receiving unit 53A stores the received two days' worth of absence detection results in the history data memory 52A of the storage unit 52 (step 11: Yes). S12). The generation unit 53C in the CPU 53 determines whether or not the detection result of absence for 30 days has been stored in the history data memory 52A (step S13). When the presence / absence detection result for 30 days is stored in the generation unit 53C (step S13: Yes), the generation unit 53C is based on the memory absence / absence detection result, the day of the week information, and the holiday information, and is used for each day of the week in the air-conditioned space. Generate an absentee pattern (step S14). When the acquisition unit 53B in the CPU 53 acquires the absence detection results for two days, it also acquires the day of the week information and the holiday information of the detection day of the absence detection results for two days. Alternatively, the server device 5 links the day of the week information and the holiday information acquired by the server device 5 to the detection results of absence for two days. Further, although the generation unit 53C exemplifies the case where the absence pattern for each day of the week is generated, two absence patterns on holidays or weekdays may be generated and can be changed as appropriate.

The generation unit 53C stores the generated absence / absence pattern in the pattern storage unit 52B (step S15). The transmission unit 53D in the CPU 53 transmits the presence / absence pattern stored in the pattern storage unit 52B to the communication adapter 3 (step S16), and ends the processing operation of FIG. 12A.

When the receiving unit 53A does not receive the detection result of absence for two days for each air-conditioned space in the process of step S11 (step S11: No), the process returns to the process of step S11. Further, when the detection result of absence for 30 days is not stored in the process of step S13 (step S13: No), the receiving unit 53A returns to the process of step S11.

When the CPU 53 of the server device 5 stores the presence / absence detection result for 30 days for each air-conditioned space from the communication adapter 3, the CPU 53 is based on the detection result for 30 days for each air-conditioned space, the day of the week information, and the holiday information. , Generates an absence pattern for each day of the week that predicts the presence or absence of a user in an air-conditioned space. Then, the CPU 53 transmits the generated absence / absence pattern to the communication adapter 3. As a result, the server device 5 can provide the communication adapter 3 with the presence / absence pattern for each day of the week used in the air-conditioned space.

FIG. 12B is a flowchart showing an example of the processing operation of the CPU 53 of the server device 5 involved in the update process for updating the already generated absence / absence pattern. The update process is a process of updating the contents of the presence / absence pattern stored in the pattern storage unit 52B. In FIG. 12B, the receiving unit 53A periodically communicates with the communication adapter 3 at 0:00 every day, and determines whether or not the communication adapter 3 has received the detection result of absence for two days for each air-conditioned space. (Step S21). The communication adapter 3 is stored in the history memory 33A until the detection result of absence for two days is obtained. When the receiving unit 53A receives the detection result of absence for two days for each air-conditioned space (step S21: Yes), the receiving unit 53A stores the received detection result of absence for two days in the history data memory 52A of the storage unit 52. Store (step S22). The generation unit 53C determines whether or not the detection result of absence for 6 days unused for generation is stored in the history data memory 52A (step S23).

When the generation unit 53C has stored the absence detection results for 6 days unused for generation (step S23: Yes), the generation unit 53C is an air-conditioned space based on the storage absence detection results, day of the week information, and holiday information. The absence pattern of each day of the week is updated (step S24). The generation unit 53C stores the presence / absence pattern of each day of the week for each updated air-conditioned space in the pattern storage unit 52B (step S25). The transmission unit 53D transmits the presence / absence pattern of each day of the week stored in the pattern storage unit 52B to the communication adapter 3 (step S26). Then, the receiving unit 53A returns to the process of step S21 in order to determine whether or not the detection result of presence / absence for two days for each air-conditioned space has been received.

When the receiving unit 53A does not receive the detection result of absence for two days in the process of step S21 (step S21: No), the process returns to the process of step S21. Further, when the detection result of absence for 6 days unused for generation is not stored in the process of step S23 (step S23: No), the receiving unit 53A returns to the process of step S21.

After the absence pattern is generated, the CPU 53 obtains the absence detection result for 6 days from the communication adapter 3 based on the absence detection result for 6 days, the day of the week information, and the holiday information for each air-conditioned space. Update the absence pattern of each day of the week for each air-conditioned space. Then, the CPU 53 transmits the updated absence / absence pattern to the communication adapter 3. As a result, the server device 5 can provide the communication adapter 3 with the latest absence pattern for each day of the week used in the air-conditioned space.

FIG. 13A is a flowchart showing an example of the processing operation of the CPU 34 of the communication adapter 3 related to the recommended processing. In FIG. 13A, the presence / absence prediction unit 34E in the CPU 34 in the communication adapter 3 determines whether or not the current time is the predicted time (step S30). The predicted time is a predetermined time set in advance, for example, 8:00 or 20:00 every day described above. When the current time is the predicted time (step S30: Yes), the presence / absence prediction unit 34E outputs the detection result of the presence / absence up to a predetermined time, for example, 24 hours before the current predicted time to the indoor unit of the air conditioner 2. It is determined whether or not it was acquired from 21 (step S31). For convenience of explanation, the predetermined time is set to 24 hours, but the predetermined time is not limited to this, and may be, for example, a time zone from 21:00 the day before to 0:00 on the day and 0:00 on the day to the predicted time. , Can be changed as appropriate.

When the presence / absence prediction unit 34E acquires the presence / absence detection result up to 24 hours before the current predicted time (step S31: Yes), the presence / absence detection result acquired from the plurality of absence / absence patterns in the air-conditioned space. And the day of the week information is used to select the presence / absence pattern to be used for the presence / absence prediction in the air-conditioned space (step S32). The presence / absence prediction unit 34E predicts the presence / absence of the user 24 hours after the present using the selected presence / absence pattern (step S33). The behavior prediction unit 21D2 of the control unit 21D in the indoor unit 21 determines whether or not the installation location of the indoor unit 21 is a bedroom based on the indoor use information (step S34).

When the installation location of the indoor unit 21 is not a bedroom (step S34: No), the behavior prediction unit 21D2 executes the air conditioning operation recommended process in the living room (step S35), and returns to the process of step S30. Further, when the installation location of the indoor unit 21 is a bedroom (step S34: Yes), the behavior prediction unit 21D2 executes the air conditioning operation recommended process in the bedroom (step S36), and returns to the process of step S30. If the current time is not the predicted time (step S30: No), the presence / absence prediction unit 34E returns to the process of step S30. Further, if the absence / absence prediction unit 34E has not acquired the presence / absence detection result up to 24 hours before the current predicted time (step S31: No), the process returns to the process of step S31.

The communication adapter 3 predicts the presence or absence of the user from the predicted time to 24 hours after the predicted time using the presence / absence pattern selected using the current detection result of the sensor and the daytime information, and then installs the indoor unit 21. When is a bedroom, the air-conditioning operation recommended process in the bedroom is executed, and when the installation location of the indoor unit 21 is not the bedroom, the air-conditioning operation recommended process in the living room is executed. As a result, it is possible to recommend to the user the air-conditioning operation according to the behavior prediction result of the user, which will be described later with reference to FIGS. 13B to 13D. For convenience of explanation, the bedroom and the living room are exemplified as the air-conditioned space, but the space is not limited to this, and may be a dressing room of a bathroom, a toilet, or the like, and can be changed as appropriate.

Next, the recommended processing for air-conditioning operation in the living room in step S35 of FIG. 13A will be described. 13B and 13C are flowcharts showing an example of the processing operation of the control unit 21D of the indoor unit 21 related to the recommended processing for air conditioning operation in the living room. The indoor unit 21 described with reference to FIGS. 13B and 13C is an indoor unit installed in the living room. In FIG. 13B, the behavior prediction unit 21D2 in the control unit 21D in the indoor unit 21 has a fourth predetermined period, for example, in the first time zone (0:00 to 10:50) in the presence / absence prediction result. It is determined whether or not there is a timing for changing from absent in the living room for 3 hours or more to being in the room (step S41). As described above, the first time zone is a time zone in which it is assumed that the user gets up, for example, goes out of the bedroom, enters the living room, and starts the air-conditioning operation.

When the behavior prediction unit 21D2 has a timing of changing from absent for a fourth predetermined period or longer to being in the room within the first time zone (step S41: Yes), the behavior prediction unit 21D2 predicts the timing as the wake-up time (step S42). ). After predicting the wake-up time, the recommendation unit 21D0 generates a recommended signal to start the air-conditioning operation 15 minutes before the wake-up time (step S43). Next, the behavior prediction unit 21D2 is in the fourth time zone (17:00 to 23:50) in the absence prediction result for a fifth predetermined period, for example, three hours or more from the presence in the living room. It is determined whether or not there is a timing to change to absence (step S44). The fourth time zone is a time zone in which the user is expected to stop the air conditioning operation of the living room at night and leave the living room, for example, from 17:00 to 23:50, or the user is at night. It is a time zone assuming the time when the air conditioning operation of the living room is started and the living room is entered, for example, from 17:00 to 23:50.

When the behavior prediction unit 21D2 has a timing of changing to the absence of the fifth predetermined period or more in the fourth time zone (step S44: Yes), the behavior prediction unit 21D2 predicts the timing as the bedtime. Then, when the behavior prediction unit 21D2 can predict the bedtime, the recommendation unit 21D0 outputs the recommended signal generated in step S43 from one hour before the bedtime to the bedtime by the communication adapter 3, the router 4, and the router 4. The user's terminal device 7 is transmitted via the communication network 8 and the router 4 (step S45), and the recommended process for air-conditioning operation in the living room shown in FIG. 13B is completed. As a result, the user can easily set the second timer time for starting the air conditioning operation 15 minutes before the wake-up time in the living room, based on the recommended content on the display screen of the terminal device 7.

The recommendation unit 21D0 is generated in step S43 between 18:00 and 19:00 when there is no timing to change to the absence of the fifth predetermined period or longer in the fourth time zone (step S44: No). The recommended signal is transmitted to the user's terminal device 7 via the communication adapter 3, the router 4, the communication network 8, and the router 4 (step S46), and the recommended process for air-conditioning operation in the living room shown in FIG. 13B is completed. As a result, the user can easily set the second timer time for starting the air conditioning operation 15 minutes before the wake-up time in the living room, based on the recommended content on the display screen of the terminal device 7.

When the behavior prediction unit 21D2 does not have the timing to change from the absence for the fourth predetermined period or more to the living room in the first time zone (step S41: No), the second time zone in the absence prediction result. At (13:00 to 22:50), it is determined whether or not there is a timing for changing from absent to a room in a living room for a fourth predetermined period, for example, 3 hours or more (step S47). As described above, the second time zone is a time zone in which it is assumed that the user returns home, enters the living room, for example, and starts the air conditioning operation.

When the behavior prediction unit 21D2 has a timing of changing from being absent in the living room for a fourth predetermined period or longer to being in the room in the second time zone (step S47: Yes), the behavior prediction unit 21D2 predicts the timing as the time to return home (step S47: Yes). Step S48). The recommendation unit 21D0 generates a recommendation signal to start the air conditioning operation 15 minutes before the return time after predicting the return time (step S49). The recommendation unit 21D0 transmits the generated recommended signal between 11:00 and 12:00 to the user's terminal device 7 via the communication adapter 3, the router 4, the communication network 8, and the router 4 (step S50). The recommended processing for air-conditioning operation in the living room shown in FIG. 13B is completed. As a result, the user can easily set the second timer time of the start of the air conditioning operation 15 minutes before the return time in the living room based on the recommended content on the display screen of the terminal device 7.

The recommended screen 80 of the terminal device 7 that has received the recommended signals transmitted in each of the processes of steps S45, S46, and S50 displays the contents such as the recommended content display unit 83 shown in FIG. 9B. The user can choose to receive (set) or not receive (do not set) the recommended air conditioning operation recommendations.

The behavior prediction unit 21D2 shifts to M1 shown in FIG. 13C when there is no timing for changing from absent for a fourth predetermined period or longer to being in the room in the second time zone (step S47: No). In M1 shown in FIG. 13C, the behavior prediction unit 21D2 is in the third time zone (8:00 to 16:50) in the absence prediction result for a sixth predetermined period from the presence in the living room, for example, 5. It is determined whether or not there is a timing to change to the absence for more than an hour (step S51). The third time zone is a time zone in which it is assumed that the air conditioning operation will be stopped for a long time due to the user going out. If there is a timing in which the behavior prediction unit 21D2 changes from being in the living room to being absent for the sixth predetermined period or more in the third time zone (step S51: Yes), the behavior prediction unit 21D2 predicts the timing as the outing time (step S51: Yes). Step S52). The recommendation unit 21D0 determines whether or not the cooling operation or the dehumidifying operation has been performed before the absentee time after predicting the timing as the outing time, and 3 days or more have passed since the previous heating sterilization operation was executed. Determination (step S53).

When the recommended unit 21D0 is performing the cooling operation or the dehumidifying operation before the absence time, and 3 days or more have passed since the previous execution of the heating sterilization operation (step S53: Yes), 1 hour after the time of going out. Generates a recommended signal to start the heat sterilization operation from (step S54). Then, the recommendation unit 21D0 transmits the generated recommended signal to the user's terminal device 7 via the communication adapter 3, the router 4, the communication network 8, and the router 4 (step S55), and the air conditioning operation in the living room shown in FIG. 13B. End the recommended process. As a result, the user can easily set the second timer time for starting the heat sterilization operation one hour after the time of going out in the living room, based on the recommended content on the display screen of the terminal device 7.

When the recommended unit 21D0 has performed the cooling operation or the dehumidifying operation before the absence time in step S53, and three days or more have not passed since the previous execution of the heating sterilization operation (step S53: No). The process proceeds to M2 shown in FIG. 13B, and the recommended process for air-conditioning operation in the living room is completed.

When the behavior prediction unit 21D2 does not have a timing to change from being in the living room to being absent for the sixth predetermined period or more in the third time zone (step S51: No), the third of the absentee prediction results. It is determined whether or not there is a timing for changing from being in the living room to being absent within the seventh predetermined period, for example, 1 hour or more and less than 5 hours (step S56). When there is a timing when the behavior prediction unit 21D2 changes from being in the living room to being absent within the seventh predetermined period in the third time zone (step S56: Yes), the behavior prediction unit 21D2 predicts the timing as the outing time (step S56: Yes). Step S57).

After predicting the timing as the outing time, the recommendation unit 21D0 determines whether or not the integrated operation time of the indoor unit 21 is 200 hours or more (step S58). When the integrated operation time of the indoor unit 21 is 200 hours or more (step S58: Yes), the recommendation unit 21D0 generates a recommendation signal to start the filter cleaning operation one hour after the time of going out (step S59). The recommendation unit 21D0 returns to the process of step S55 in order to transmit the generated recommended signal to the user's terminal device 7 via the communication adapter 3, the router 4, the communication network 8, and the router 4. As a result, the user can easily set the second timer time for starting the filter cleaning operation one hour after the time of going out in the living room, based on the recommended content on the display screen of the terminal device 7.

Although not shown, the recommended content is displayed on the recommended content display unit 83 on the recommended screen 80 of the terminal device 7 that has received the recommended signal transmitted in each process of step S54 and step S59. However, in the case of the recommendation of additional function operation, unlike the recommendation of air conditioning operation, the user is informed that the additional function operation is to be executed, and the additional function operation is performed unless the user refuses to execute the additional function operation. Will be executed. If the user does not want to execute the additional function operation, it is recommended that the execution refusal of the additional function operation can be selected.

When there is no timing for the behavior prediction unit 21D2 to change from being in the living room to being absent within the seventh predetermined period in the third time zone (step S56: No), the air-conditioned operation in the living room shown in FIG. 13B. End the recommended process. If the integrated operation time of the indoor unit 21 is not 200 hours or more (step S58: No), the recommendation unit 21D0 proceeds to M2 shown in FIG. 13B and ends the recommended air conditioning operation process in the living room.

Next, the recommended processing for air-conditioning operation in the bedroom in step S36 of FIG. 13A will be described. FIG. 13D is a flowchart showing an example of the processing operation of the control unit 21D of the indoor unit 21 related to the recommended processing for air conditioning operation in the bedroom. The indoor unit 21 described with reference to FIG. 13D is an indoor unit installed in the bedroom. In FIG. 13D, the action prediction unit 21D2 in the control unit 21D in the indoor unit 21 has a fifth predetermined period, for example, during the fourth time zone (17:00 to 23:50) in the absence prediction result. It is determined whether or not there is a timing to change from absent in the bedroom for 3 hours or more to being in the room (step S61). As described above, the fourth time zone is a time zone assuming a time when the user starts the air-conditioning operation of the bedroom at night and enters the bedroom, for example, from 17:00 to 23:50.

When the behavior prediction unit 21D2 has a timing of changing from absenteeism for a fifth predetermined period or longer to being in the room in the fourth time zone (step S61: Yes), the timing when the user enters the bedroom is defined as the bedtime. Predict (step S62). After predicting the bedtime, the recommendation unit 21D0 generates a recommendation signal to start the air conditioning operation at the bedtime (step S63). The recommendation unit 21D0 transmits the generated recommended signal from one hour before the bedtime to the bedtime to the user's terminal device 7 via the communication adapter 3, the router 4, the communication network 8, and the router 4 (step). S64), the processing operation related to the air conditioning operation recommended processing in the bedroom shown in FIG. 13D is terminated. As a result, the user can easily set the second timer time of the start of the air-conditioned operation of the bedtime in the bedroom based on the recommended content on the display screen of the terminal device 7.

The recommended screen 80 of the terminal device 7 that has received the recommended signal transmitted in each process of step S64 displays the content such as the recommended content display unit 83 shown in FIG. 9B, and the user is recommended for air conditioning. The recommended air-conditioning operation is executed by receiving (setting) the recommended operation.

When the behavior prediction unit 21D2 does not have the timing to change from the absence for the fifth predetermined period or more to the presence of the room in the fourth time zone (step S61: No), the behavior prediction unit 21D2 has the third time zone in the absence prediction result. At (8:00 to 16:50), it is determined whether or not there is a timing for changing from being in the bedroom to being absent for a sixth predetermined period, for example, 5 hours or more (step S65). When there is a timing when the behavior prediction unit 21D2 changes from being in the bedroom to being absent for the sixth predetermined period or more in the third time zone (step S65: Yes), the timing is set as the time when the bedroom leaves the room. Predict (step S66). The recommendation unit 21D0 predicts that the timing is the time of leaving the room, and then performs the cooling operation or the dehumidifying operation before the time of leaving the room, and whether or not three days or more have passed since the previous execution of the heating sterilization operation. (Step S67).

When the cooling operation or the dehumidifying operation is performed before the room leaving time and 3 days or more have passed from the previous execution of the heating sterilization operation (step S67: Yes), the recommended unit 21D0 is 1 of the room leaving time. A recommended signal to start the heat sterilization operation after a certain time is generated (step S68). Then, the recommendation unit 21D0 transmits the generated recommended signal to the user's terminal device 7 via the communication adapter 3, the router 4, the communication network 8, and the router 4 (step S69), and the air-conditioned operation in the bedroom shown in FIG. 13D. End the recommended process. As a result, the user can easily set the second timer time for starting the heat sterilization operation one hour after the time of leaving the room in the bedroom, based on the recommended content on the display screen of the terminal device 7.

Although not shown, the recommended content is displayed on the recommended content display unit 83 on the recommended screen 80 of the terminal device 7 that has received the recommended signal transmitted in each process of step S69 and step S73. However, in the case of the recommendation of additional function operation, unlike the recommendation of air conditioning operation, the user is informed that the additional function operation is to be executed, and the additional function operation is performed unless the user refuses to execute the additional function operation. Will be executed.

The recommendation unit 21D0 performs the cooling operation or the dehumidifying operation before the room leaving time in step S67, and three days or more have passed since the previous execution of the heating sterilization operation (step S67: No). The recommended processing for air-conditioning operation in the bedroom shown in 13D is completed.

When there is no timing for the behavior prediction unit 21D2 to change from being in the bedroom to being absent for a predetermined period or longer in the sixth time zone (step S65: No), the third of the absentee prediction results. It is determined whether or not there is a timing during which the time zone changes from being in the bedroom to being absent within the seventh predetermined period, for example, from 1 hour or more to less than 5 hours (step S70). When the behavior prediction unit 21D2 has a timing of changing from being in the bedroom to being absent within the seventh predetermined period in the third time zone (step S70: Yes), the timing is set as the time of leaving the bedroom. Predict (step S71).

After predicting the timing as the exit time, the recommendation unit 21D0 determines whether or not the integrated operation time of the indoor unit 21 is 200 hours or more (step S72). When the integrated operation time of the indoor unit 21 is 200 hours or more (step S72: Yes), the recommendation unit 21D0 generates a recommendation signal to start the filter cleaning operation 1 hour after the exit time (step S73). .. The recommendation unit 21D0 returns to the process of step S69 in order to transmit the generated recommended signal to the user's terminal device 7 via the communication adapter 3, the router 4, the communication network 8, and the router 4. As a result, the user can easily set the second timer time for starting the filter cleaning operation one hour after the time of leaving the room in the bedroom, based on the recommended content on the display screen of the terminal device 7.

When there is no timing for the behavior prediction unit 21D2 to change from being in the bedroom to being absent within the seventh predetermined period in the third time zone (step S70: No), the air-conditioned operation in the bedroom shown in FIG. 13D. End the recommended process. Further, when the integrated operation time of the indoor unit 21 is not 200 hours or more (step S72: No), the recommendation unit 21D0 ends the air conditioning operation recommendation process in the bedroom shown in FIG. 13D.

<Effect of Example 1>
In the communication adapter 3 of the first embodiment, one presence / absence pattern is selected from a plurality of presence / absence patterns by using at least the current detection result of the sensor 21B. Further, the communication adapter 3 predicts the presence / absence for 24 hours in the air-conditioned space by using the selected presence / absence pattern. Further, the communication adapter 3 transmits the presence / absence prediction result for 24 hours, which is the presence / absence prediction result, to the air conditioner 2. The air conditioner 2 transmits recommended signals for recommending various air-conditioning operations to the user's terminal device 7 via the communication adapter 3 based on the acquired results of presence / absence prediction for 24 hours. As a result, the user can realize the air-conditioned operation in accordance with the daily rhythm and obtain a comfortable air-conditioned space by executing the recommended contents of the recommended signal.

The server device 5 generates an absentee pattern using the past absentee detection result, the day of the week information, and the holiday information detected by the sensor 21B in the first predetermined period, for example, 30 days. As a result, it is possible to acquire a highly accurate presence / absence pattern in the air-conditioned space.

The communication adapter 3 uses the selected absence pattern, for example, at a predetermined time of 8:00 or 20:00 every day, and a user in an air-conditioned space from the predetermined time to a second predetermined period, for example, 24 hours. Predict the absence of 24 hours of absence. Further, the communication adapter 3 transmits the presence / absence prediction result for 24 hours, which is the presence / absence prediction result, to the air conditioner 2. Then, the air conditioner 2 transmits a recommended signal for recommending various air-conditioning operations to the user's terminal device 7 via the communication adapter 3 based on the acquired 24 hours' worth of absence prediction results. As a result, the user can receive the recommendation of the air-conditioned operation according to the daily rhythm using the presence / absence prediction result from the predetermined time to 24 hours later.

The communication adapter 3 predicts the absence of the user every 10 minutes for 24 hours, which is the absence of the user in the air-conditioned space every 10 minutes, for example, for a third predetermined period using the selected absence pattern. Further, the communication adapter 3 transmits the presence / absence prediction result for 24 hours, which is the presence / absence prediction result, to the air conditioner 2. Then, the air conditioner 2 transmits a recommended signal for recommending various air-conditioning operations to the user's terminal device 7 via the communication adapter 3 based on the acquired 24 hours' worth of absence prediction results. As a result, the user can receive the recommendation of the air-conditioned operation according to the daily rhythm using the presence / absence prediction result every 10 minutes for 24 hours.

The air conditioner 2 is a terminal device of the user that recommends setting the start time of the air conditioning operation or the stop time of the air conditioning operation based on the presence / absence prediction result for 24 hours in the air conditioning space predicted by the communication adapter 3. Send to 7. As a result, the user can realize a comfortable air-conditioned space in line with the daily rhythm by following the recommended contents according to the recommended signal without searching for the operating time zone of the air-conditioned operation such as good night operation.

The air conditioner 2 transmits a recommended signal recommending an additional function operation different from the air-conditioned operation to the user's terminal device 7 based on the predicted presence / absence prediction result for 24 hours in the predicted air-conditioned space. As a result, the user does not have to search for the driving time zone of the additional function driving, but by following the recommended contents according to the recommended signal, the user follows the daily rhythm and does not feel discomfort, and the additional function driving. Can be realized.

The air conditioner 2 is used in the absence prediction result for 24 hours in the air-conditioned space when the air-conditioned space is a room such as a living room where the user spends most of the time other than bedtime. The timing at which the person changes from being absent to being in the room is predicted to be the time when the user wakes up or returns home. Then, the air conditioner 2 transmits, for example, a recommended signal for recommending the setting of the start time of the air conditioning operation to the terminal device 7 of the user based on the timing when the user changes from being absent to being in the living room. As a result, the user can easily set the start time of the air-conditioning operation in the living room at the time of waking up.

The air conditioner 2 predicts that the timing at which the user changes from being in the room to being absent is the time when the user goes out or the time when the user goes to bed in the results of the absence prediction for 24 hours in the air-conditioned space corresponding to the indoor use information. Then, the air conditioner 2 transmits a recommended signal recommending an additional function operation different from the air-conditioned operation to the user's terminal device 7 based on the timing when the user changes from being in the room to being absent in the living room. As a result, the user can easily set the additional function operation in the living room at the time of going out or the time of bedtime without searching for the operation time zone of the additional function operation.

In the air conditioner 2, when the air-conditioned space is a room used by the user at bedtime, for example, a bedroom, the user is changed from absent to the room in the absentee prediction result for 24 hours in the air-conditioned space. Predict the changing timing as the user's bedtime. Then, the air conditioner 2 transmits, for example, a recommended signal for recommending the setting of the start time of the air conditioning operation to the terminal device 7 of the user based on the timing when the user changes from the absence to the room in the bedroom. As a result, the user can easily set the start time of the air-conditioning operation in the bedroom at bedtime.

The air conditioner 2 predicts the timing at which the user changes from being in the room to being absent as the wake-up time of the user in the presence / absence prediction result for 24 hours in the air-conditioned space corresponding to the indoor use information. Then, the air conditioner 2 transmits a recommended signal recommending an additional function operation different from the air-conditioned operation to the user's terminal device 7 based on the timing when the user changes from being in the room to being absent in the bedroom. As a result, the user can easily set the additional function operation in the bedroom at the wake-up time without searching for the operation time zone of the additional function operation.

The air conditioner 2 is present from a state in which the period predicted to be absent is a fourth predetermined period, for example, 3 hours or more, based on the presence / absence prediction result for 24 hours for each air-conditioned space corresponding to the indoor use information. The timing of changing to the room is predicted to be the wake-up time or the return time of the user. As a result, the air conditioner 2 can predict the wake-up time or the return time of the user with high accuracy.

The air conditioner 2 starts absent for a fifth predetermined period, for example, 3 hours or more, based on the absence prediction result for 24 hours for each air-conditioned space corresponding to the indoor use information. Predict the timing as the user's outing time or bedtime. As a result, the air conditioner 2 can predict the time when the user goes out or the time when the user goes to bed with high accuracy.

The air conditioner 2 is air-conditioned when the period predicted to be absent is the sixth predetermined period, for example, 5 hours or more, based on the presence / absence prediction result for 24 hours for each air-conditioned space corresponding to the indoor use information. An additional function different from the operation A recommended signal recommending the operation is transmitted to the terminal device 7 of the user. As a result, the user can easily set the additional function operation in a time zone in which the user does not feel uncomfortable without searching for the additional function operation time zone.

<Modified example of Example 1>
In the communication adapter 3 of the first embodiment, the presence / absence pattern to be used for prediction is selected from the plurality of absence / absence detection results, the day of the week information, and the holiday information, and the selected absence / absence pattern is selected. Although the case of predicting the presence / absence of the user in the air-conditioned space is illustrated by using the above, the server device 5 may predict the presence / absence of the user in the air-conditioned space. In this case, the server device 5 includes a detection result of presence / absence from a predetermined time for predicting the presence / absence of a user in the air-conditioned space to a predetermined time before, a day of the week information, and a holiday information from a plurality of absence / absence patterns. Is used to select the presence / absence pattern to be used for prediction, and the selected presence / absence pattern is used to predict the presence / absence of the user in the air-conditioned space. Then, the server device 5 transmits the presence / absence prediction result to the air conditioner 2 via the communication adapter 3. As a result, the server device 5 can generate the absence pattern and predict the absence, so that the processing load on the communication adapter 3 side can be reduced.

In the air conditioner system 1 of the first embodiment, the case where the indoor unit 21 of the air conditioner 2 transmits the recommended signal to the terminal device 7 of the user via the communication adapter 3 is illustrated, but the remote controller 23 of the air conditioner 2 is used. It may be sent and can be changed as appropriate.

The absence / absence prediction unit 34E selects and selects the absence / absence pattern to be used for prediction from the plurality of absence / absence patterns using the detection result of absence / absence before a predetermined time from a predetermined time, the day of the week information, and the holiday information. An example is shown in which the presence / absence pattern is used to predict the presence / absence for 24 hours in an air-conditioned space. However, even if there is no holiday information, the prediction unit 34E may select the absence pattern to be used for prediction by using the absence detection result from the predetermined time to the predetermined time before and the day of the week information.

The recommendation unit 21D0 selects and selects the recommended operation to be recommended to the user based on the user's behavior prediction result (homecoming time, going out time, bedtime, etc.) predicted by the behavior prediction unit 21D2. The case of recommending is illustrated. However, the recommendation unit 21D0 may select the recommended operation to be recommended to the user based on the behavior prediction result of the user and execute the selected recommended operation. As a result, the user can save the trouble of confirming the recommended operation to be recommended.

Further, in the air conditioner system 1, the air conditioner 2, the communication adapter 3, and the server device 5 are used, the server device 5 is used to generate the absence pattern, the communication adapter 3 is used to predict the presence or absence, and the recommended signal for starting the air conditioning operation. An example is shown in which the transmission is shared by the indoor unit 21 of the air conditioner 2. However, the communication adapter 3 may execute the prediction of absence and the transmission of the recommended signal for starting the air conditioning operation, that is, all the processes of FIGS. 13B, 13C and 13D may be executed by the communication adapter 3, and may be changed as appropriate. It is possible.

In addition, for convenience of explanation, an example of a person who works in the daytime as a user is illustrated. The case of predicting that is illustrated. However, in the case of a person who works in the middle of the night as a user, the timing may be predicted as the time to return home, and can be changed as appropriate.

Further, the air conditioner 2 may be made to execute each process of generation / absence pattern generation, presence / absence prediction, generation of recommended signal for starting air conditioning operation, and transmission. explain. By assigning the same reference numerals to the same configurations as those in the first embodiment, the description of the overlapping configurations and operations will be omitted.

<Structure of air conditioner>
FIG. 14 is a block diagram showing an example of the configuration of the air conditioner 2A of the second embodiment. In the indoor unit 210 in the air conditioner 2A shown in FIG. 14, in addition to the main body 21A, the sensor 21B, the light receiving unit 21C, and the control unit 21D, the acquisition unit 21E, the presence / absence pattern 21F, the generation unit 21G, and the presence / absence are present. It has a prediction unit 21H. The acquisition unit 21E acquires the day of the week information. The presence / absence pattern 21F is a pattern in which the presence / absence pattern indicating the presence / absence of the user in the air-conditioned space is generated for each day of the week.

The generation unit 21G generates the absence / absence pattern 21F using the detection result of the presence / absence of the sensor 21B, the day of the week information, and the holiday information. When the time zone of the detection result of the presence / absence of the sensor 21B includes a holiday, the generation unit 21G considers the time zone to be the same as a holiday. Of the absentee detection results, the "indefinite" absentee detection result is not used for the absentee pattern 21F. The presence / absence prediction unit 21H uses the presence / absence detection result from a predetermined time to a predetermined time before the time when the presence / absence of the user is predicted from a plurality of absence / absence patterns 21F to be used for prediction. Select an absentee pattern. Further, the presence / absence prediction unit 21H predicts the presence / absence of the user in the air-conditioned space by using the selected presence / absence pattern. The behavior prediction unit 21D2 in the control unit 21D transmits recommended signals for recommending various air-conditioning operations to the user terminal device 7 based on the presence / absence prediction result of the user in the air-conditioned space by the presence / absence prediction unit 21H.

The generation unit 21G generates the absence / absence pattern 21F using the detection result of absence / absence detected by the sensor 21B in the first predetermined period, for example, 30 days. The generation unit 21G stores the detection result of the presence / absence of the sensor 21B in a storage unit (not shown) without going through the communication adapter 3, and generates or generates the absence / absence pattern 21F using the detection result of the presence / absence in storage. In order to update, the generation process shown in FIG. 12 is executed.

The presence / absence prediction unit 21H uses the selected presence / absence pattern to create an air-conditioned space at a predetermined time, for example, at 8:00 or 20:00 every day, for a second predetermined period from the predetermined time, for example, 24 hours later. Predict the presence or absence of the user in. The presence / absence prediction unit 21H predicts the presence / absence of the user in the air-conditioned space for a third predetermined period, for example, every 10 minutes. When the predicted time zone includes a holiday, the presence / absence prediction unit 21H regards the time zone as the same as a holiday and predicts the absence / absence for 24 hours in the air-conditioned space. Further, the presence / absence prediction unit 21H excludes the “indefinite” presence / absence detection result from the presence / absence detection result of the sensor 21B used when predicting the presence / absence of the user in the air-conditioned space. The presence / absence prediction unit 21H executes the processes of steps S30, S31, S32, S33 and S34 shown in FIG. 13A.

The behavior prediction unit 21D2 is based on the prediction result of the presence / absence of the user in the air-conditioned space by the presence / absence prediction unit 21H and the indoor use information (living room or bedroom) of the air-conditioned space, and the user's day in the living space. Predicts behavior (for example, wake-up time, outing time, return time, bedtime). Then, the recommendation unit 21D0 selects the operation to be recommended to the user based on the predicted behavior. Further, the recommendation unit 21D0 recommends the user to execute the operation that should be recommended to the user. The recommendation unit 21D0 transmits a recommended signal recommended to the user to the remote controller 23. Further, the recommendation unit 21D0 executes the air-conditioning operation recommendation process in the living room of step S35 shown in FIG. 13A or the air-conditioning operation recommendation process in the bedroom of step S36 shown in FIG. 13A.

The extraction unit 21D1 extracts a time zone in which an additional function operation different from the normal air-conditioning operation can be executed from the time zone of the presence / absence prediction result for 24 hours in the air-conditioned space. The time zone in which the additional function operation can be executed is, for example, an absence time of 5 hours or more. Based on the presence / absence prediction result of the user in the air-conditioned space by the presence / absence prediction unit 21D0, the recommendation unit 21D0 sends a recommended signal for recommending additional function operation such as heating sterilization operation and filter cleaning operation, which are different from the air-conditioning operation, to the remote controller 23. Send to. Although the recommendation unit 21D0 exemplifies the case where the recommended signal is transmitted to the remote controller 23, if the recommendation unit 21D0 has a means for communicating with the user's terminal device 7, the recommended signal may be transmitted to the user's terminal device 7. Well, it can be changed as appropriate.

<Effect of Example 2>
The air conditioner 2A of the second embodiment selects one presence / absence pattern from a plurality of absence / absence patterns by using at least the current detection result of the sensor 21B. The air conditioner 2A predicts the presence / absence for 24 hours in the air-conditioned space using the selected presence / absence pattern. Further, the air conditioner 2A transmits a recommended signal for recommending various air-conditioning operations to the remote controller 23 based on the presence / absence prediction result for 24 hours. As a result, the user can realize the air-conditioned operation in accordance with the daily rhythm and obtain a comfortable air-conditioned space by executing the recommended contents according to the recommended signal.

The air conditioner 2A generates an absence pattern using the absence detection result, the day of the week information, and the holiday information detected by the sensor 21B in the first predetermined period, for example, 30 days. As a result, it is possible to acquire a highly accurate presence / absence pattern in the air-conditioned space.

The air conditioner 2A is used in an air-conditioned space using the selected absence pattern, for example, at a predetermined time of 8:00 or 20:00 every day for a second predetermined period from the predetermined time, for example, 24 hours. Predict the absence of a person for 24 hours. Then, the air conditioner 2A transmits a recommended signal for recommending various air-conditioning operations to the remote controller 23 based on the presence / absence prediction result for 24 hours. As a result, the user can receive the recommendation of the air-conditioned operation according to the daily rhythm using the presence / absence prediction result from the predetermined time to 24 hours later.

The air conditioner 2A predicts the absence of the user every 10 minutes for 24 hours, which is the absence of the user in the air-conditioned space for a third predetermined period, for example, every 10 minutes, using the selected absence pattern. Then, the air conditioner 2A transmits a recommended signal for recommending various air-conditioning operations to the remote controller 23 based on the presence / absence prediction result for 24 hours. As a result, the user can receive the recommendation of the air-conditioned operation according to the daily rhythm using the presence / absence prediction result every 10 minutes for 24 hours.

The air conditioner 2A transmits to the remote control 23 a recommended signal for recommending the setting of the start time of the air conditioning operation or the stop time of the air conditioning operation based on the predicted presence / absence prediction result for 24 hours in the predicted air conditioning space. As a result, the user can realize a comfortable air-conditioned space in line with the daily rhythm by following the recommended contents according to the recommended signal without searching for the operating time zone of the air-conditioned operation such as good night operation.

The air conditioner 2A transmits to the remote controller 23 a recommended signal recommending an additional function operation different from the air-conditioned operation, based on the predicted presence / absence prediction result for 24 hours in the predicted air-conditioned space. As a result, the user does not have to search for the driving time zone of the additional function driving, but by following the recommended contents according to the recommended signal, the user follows the daily rhythm and does not feel discomfort, and the additional function driving. Can be realized.

The behavior prediction unit 21D2 is used in the absence prediction result for 24 hours in the air-conditioned space when the air-conditioned space is a room such as a living room where the user spends most of the time other than bedtime. The timing at which the person changes from being absent to being in the room is predicted as the time when the user wakes up or returns home. Further, the recommendation unit 21D0 transmits, for example, a recommended signal for recommending the setting of the start time of the air conditioning operation to the remote controller 23 based on the timing when the user changes from the absence to the presence of the room in the living room. As a result, the user can easily set the start time of the air-conditioning operation in the living room at the time of waking up.

The behavior prediction unit 21D2 predicts the timing at which the user changes from being in the room to being absent as the user's outing time or bedtime in the absence prediction result for 24 hours in the air-conditioned space corresponding to the indoor use information. The recommendation unit 21D0 transmits to the remote controller 23 a recommendation signal for recommending an additional function operation different from the air-conditioning operation, based on the timing when the user changes from being in the room to being absent in the living room. As a result, the user can easily set the additional function operation in the living room at the time of going out or the time of bedtime without searching for the operation time zone of the additional function operation.

When the air-conditioned space is a room used by the user at bedtime, for example, in the behavior prediction unit 21D2, the user is changed from absent to the room in the absence prediction result for 24 hours in the air-conditioned space. Predict the changing timing as the user's bedtime. The recommendation unit 21D0 transmits, for example, a recommended signal for recommending the setting of the start time of the air conditioning operation to the remote controller 23 based on the timing when the user changes from the absence to the presence of the room in the bedroom. As a result, the user can easily set the start time of the air-conditioning operation in the bedroom at bedtime.

The behavior prediction unit 21D2 predicts the timing at which the user changes from being in the room to being absent as the wake-up time of the user in the absence prediction result for 24 hours in the air-conditioned space corresponding to the indoor use information. The recommendation unit 21D0 transmits to the remote controller 23 a recommendation signal for recommending an additional function operation different from the air-conditioning operation, based on the timing when the user changes from being in the room to being absent in the bedroom. As a result, the user can easily set the additional function operation in the bedroom at the wake-up time without searching for the operation time zone of the additional function operation.

The behavior prediction unit 21D2 is present from a state in which the period predicted to be absent is a fourth predetermined period, for example, 3 hours or more, based on the absence prediction result for 24 hours for each air-conditioned space corresponding to the indoor use information. The timing of changing to the room is predicted to be the wake-up time or the return time of the user. As a result, the air conditioner 2A can predict the wake-up time or the return time of the user with high accuracy.

The behavior prediction unit 21D2 starts the absence for a fifth predetermined period, for example, 3 hours or more, based on the absence prediction result for 24 hours for each air-conditioned space corresponding to the indoor use information. Predict the timing as the user's outing time or bedtime. As a result, the air conditioner 2 can predict the time when the user goes out or the time when the user goes to bed with high accuracy.

The recommendation unit 21D0 operates the air-conditioning operation when the period predicted to be absent is the sixth predetermined period, for example, 5 hours or more, based on the absence prediction result for 24 hours for each air-conditioned space corresponding to the indoor use information. A recommended signal for recommending additional function operation different from the above is transmitted to the remote controller 23. As a result, the user can easily set the additional function operation without searching for the time zone of the additional function operation.

<Modified example of the example>
The first predetermined period, the second predetermined period, the third predetermined period, the fourth predetermined period, the fifth predetermined period, the sixth predetermined period, and the seventh predetermined period of Examples 1 and 2 are It can be changed as appropriate. Further, the first time zone, the second time zone, the third time zone, and the fourth time zone can be changed as appropriate.

Further, the heating sterilization operation is exemplified, for example, in the case where the heating sterilization operation for 1 hour is started after the monitoring operation, but the operation time is not limited to this and can be changed as appropriate. Further, in the heating sterilization operation, an example was shown in which the heating sterilization operation was completed after a cooling period of 3 hours after the heating sterilization operation of 1 hour, but the cooling operation was executed during the cooling period to shorten the cooling period. It may be changed and can be changed as appropriate.

The presence / absence pattern used for predicting the presence / absence of the user is a maximum of 5 in consideration of an increase in the amount of communication between the communication adapter 3 and the server device 5 and an increase in the memory capacity required for the communication adapter. An example of up to a pattern was explained. However, if it is not necessary to consider the amount of communication and the memory capacity can be increased, the presence / absence pattern of the user is generated for each day of the week and the presence / absence pattern according to the predicted day of the week is used. You may predict your absence.

Further, each component of each of the illustrated parts does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each part is not limited to the one shown in the figure, and all or part of them may be functionally or physically distributed / integrated in any unit according to various loads and usage conditions. Can be configured.

Further, various processing functions performed by each device are performed on a CPU (Central Processing Unit) (or a microcomputer such as an MPU (Micro Processing Unit) or an MCU (Micro Controller Unit)) in whole or in any part thereof. You may try to do it. Further, the various processing functions may be executed in whole or in any part on a program to be analyzed and executed by a CPU (or a microcomputer such as an MPU or MCU) or on hardware by wired logic. Needless to say.

1 Air conditioning system 2, 2A Air conditioner 3 Communication adapter 5 Server device 7 Terminal device 21,210 Indoor unit 21B Sensor 21D0 Recommended section 21D2 Behavior prediction section 21E Acquisition section 21F Absence pattern 21G Generation section 21H Presence / absence prediction section 34E Absence prediction unit 53B acquisition unit 53C generation unit

Claims (11)

Sensors that detect the presence or absence of people in air-conditioned spaces,
A storage unit that stores a prediction result that predicts the presence or absence of a user in the air-conditioned space using the detection result of the sensor, and a storage unit.
Based on the prediction result of the presence or absence of the user in the air-conditioned space, the recommended unit for selecting the recommended operation to be recommended for the user, and the recommended unit.
Have,
When the detection result of the sensor includes a third detection value that does not correspond to either the first detection value indicating the presence of the user or the second detection value indicating the absence of the user. An air conditioner comprising excluding the third detection value from the detection result of the sensor used when predicting the presence or absence of the user in the air-conditioned space. The recommended part is
The air conditioner according to claim 1, wherein the user is recommended to perform the selected recommended operation. The acquisition department that acquires day of the week information,
A plurality of absentee patterns generated by using the past detection results of the sensor and the day of the week information and showing the tendency of the user to be absent in the air-conditioned space.
Using the current detection result of the sensor and the day of the week information, one presence / absence pattern is selected from the plurality of presence / absence patterns, and the presence / absence of the user in the air-conditioned space is used using the selected presence / absence pattern. The presence / absence prediction unit that predicts
Have more
The presence / absence prediction unit is
The air conditioner according to claim 1 or 2, wherein the third detection value is excluded from the current detection result of the sensor when predicting the presence or absence of the user in the air-conditioned space. The air conditioner according to claim 3, further comprising a generation unit that generates the absence pattern by using the detection result of the sensor and the day of the week information. The generator is
The air conditioner according to claim 4, wherein the presence / absence pattern is generated by using the detection result detected by the sensor in the first predetermined period. The presence / absence prediction unit is
The air conditioner according to claim 3, wherein the presence or absence of the user in the air-conditioned space from the predetermined time to the second predetermined period is predicted at a predetermined time. The presence / absence prediction unit is
The air conditioner according to claim 6, wherein the presence or absence of the user in the air-conditioned space is predicted at a third predetermined period. The recommended part is
The claim is characterized in that the user is recommended to set the start time of the air conditioning operation or the stop time of the air conditioning operation based on the prediction result of the presence or absence of the user in the air conditioning space by the presence / absence prediction unit. The air conditioner according to any one of 3 to 6. The recommended part is
Any of claims 3 to 6, wherein an additional function operation different from the air-conditioned operation is selected as the recommended operation based on the prediction result of the presence / absence of the user in the air-conditioned space by the presence / absence prediction unit. The air conditioner described in one. Further having an indoor unit with a heat exchanger,
For the additional function operation,
The air conditioner according to claim 9, further comprising a heat sterilization operation for heating and sterilizing the heat exchanger. The sensor is
A claim characterized in that the presence / absence detection operation of the person is started in response to the power supply to the air conditioner, and the presence / absence detection operation of the person is continued regardless of the start or stop of the air conditioning operation. Item 6. The air conditioner according to any one of Items 3 to 10.

Images