Air conditioning device and operation method thereof

Abstract

This air conditioning device comprises: a sensing module including a first sensor for processing an input signal of a first frequency band corresponding to first sensing data and a second sensor for processing an input signal of a second frequency band corresponding to second sensing data; and at least one processor electrically connected to the sensing module, wherein the at least one processor is configured to: acquire the first sensing data through the first sensor; acquire the second sensing data through the second sensor in a time period during which the first sensing data is acquired; extract amplitude information of at least a partial section of the second sensing data; and adjust an air conditioning setting of the air conditioning device on the basis of the amplitude information of at least the partial section of the second sensing data.

Description

Air conditioning device and method of operation thereof

[0001] The embodiments disclosed in this document relate to an air conditioning device and a method of operating the same.

[0002] With the recent advancement of smart home technology, personalized environmental control technologies utilizing artificial intelligence (AI) and the Internet of Things (IoT) are gaining attention. For example, user-centric control methods can be supported by using sensors included in electronic devices within a smart home (e.g., HVAC systems, display devices) to analyze noise or detect air quality. HVAC systems can provide a comfortable environment for users by controlling the temperature and humidity of indoor spaces, and these adjustments can be performed based on pre-set user input values. As AI and IoT technologies advance, technologies are being developed to finely adjust HVAC conditions by adaptively reflecting the user's state.

[0003] Temperature and humidity control of the air conditioning system can be performed based on manual input values ​​from the user. However, if the user is in a state where manual control of the air conditioning system is difficult (e.g., sleeping), a situation may arise where the system provides humidity and temperature unsuitable for the user's physical condition. For instance, if the temperature of the indoor space where a sleeping user is located is low or dry, it is necessary to identify this and adaptively adjust the air conditioning state.

[0004] Based on the discussion described above, the present disclosure relates to an apparatus and method capable of adaptively adjusting an air conditioning state in consideration of the user's condition.

[0005] According to one embodiment of the present disclosure, an air conditioning device comprises a sensing module including a first sensor that processes an input signal of a first frequency band corresponding to first sensing data and a second sensor that processes an input signal of a second frequency band corresponding to second sensing data, wherein the first sensor is configured to include cough identification and the second sensor is configured to include dry cough identification; and may include at least one processor electrically connected to the sensing module, wherein the at least one processor may be configured to acquire the first sensing data through the first sensor, acquire the second sensing data through the second sensor during the time interval in which the first sensing data is acquired, identify the first sensing data including the cough identification, extract amplitude information of at least a portion of the second sensing data, and adjust the air conditioning settings of the air conditioning device based on the amplitude information of at least a portion of the second sensing data including the dry cough identification.

[0006] In a method of operating an air conditioning device, the method may include: acquiring first sensing data of a first frequency band through a first sensor; acquiring second sensing data of a second frequency band through a second sensor during a time interval in which the first sensing data is acquired; identifying the first sensing data including the identification of a cough; extracting amplitude information of at least a portion of the second sensing data; and adjusting the air conditioning settings of the air conditioning device based on the amplitude information of at least a portion of the second sensing data including a dry cough.

[0007] According to one embodiment of the present disclosure, an air conditioning device may include a sensing module comprising a first sensor that processes an input signal of a first frequency band corresponding to first sensing data and a second sensor that processes an input signal of a second frequency band corresponding to second sensing data; and at least one processor electrically connected to the sensing module, wherein the at least one processor may be configured to acquire the first sensing data through the first sensor, acquire the second sensing data through the second sensor during the time interval in which the first sensing data is acquired, extract amplitude information of at least a portion of the second sensing data, and adjust the air conditioning settings of the air conditioning device based on the amplitude information of at least a portion of the second sensing data.

[0008] A method of operating an air conditioning device may include: an operation of acquiring first sensing data of a first frequency band through a first sensor; an operation of acquiring second sensing data of a second frequency band through a second sensor during a time interval in which the first sensing data is acquired; an operation of extracting amplitude information of at least a portion of the second sensing data; and an operation of adjusting the air conditioning settings of the air conditioning device based on the amplitude information of at least a portion of the second sensing data.

[0009] An air conditioning device according to one embodiment of the present disclosure comprises a sensing module including a first sensor that processes an input signal of a first frequency band and a second sensor that processes an input signal of a second frequency band, and at least one processor electrically connected to the sensing module, wherein the at least one processor is configured to extract amplitude information of at least a portion of the second sensing data in response to identifying first sensing data through the first sensor and to adjust the air conditioning settings of the air conditioning device based on the amplitude information of at least a portion of the second sensing data, and the second sensing data may include data acquired through the second sensor during the time interval in which the first sensing data is acquired.

[0010] According to one embodiment, the at least one processor may be configured to increase at least one of the temperature and humidity of the air conditioning device in response to identifying that the average amplitude value of the at least part of the second sensing data is less than or equal to a predetermined value.

[0011] In one embodiment, the at least one processor is configured to acquire information regarding at least one object included in the area where the second sensing data is sensed, based on the second sensor, and the information regarding the at least one object may include information regarding the location, shape, and movement of the at least one object.

[0012] In one embodiment, the at least one processor may be configured to adjust the airflow of the air conditioning device based on information regarding the location of the at least one object.

[0013] In one embodiment, the information regarding the at least one object may include data regarding a plurality of points obtained from the at least one object.

[0014] In one embodiment, the at least one processor may be configured to identify at least one user corresponding to the at least one object based on data regarding the plurality of points.

[0015] In one embodiment, the air conditioning device further includes a memory and a communication unit electrically connected to the at least one processor, and the at least one processor may be configured to obtain health information of at least one user from the memory or the communication unit and to adjust the air conditioning settings based on the health information of the at least one user.

[0016] In one embodiment, the air conditioning device stores a first machine learning model trained to take sound data acquired through the first sensor as an input value and output whether the sound data corresponds to the first sensing data, and includes a memory electrically connected to the at least one processor, wherein the at least one processor is configured to acquire sound data through the first sensor, divide the sound data into a plurality of time intervals, extract a feature vector based on amplitude information of the plurality of time intervals, and determine whether the sound data is the first sensing data based on the feature vector and the first machine learning model, and the first sensing data may include acoustic data classified as a cough.

[0017] In one embodiment, the first frequency band may have a smaller value than the second frequency band.

[0018] In one embodiment, at least a portion of the second sensing data may include a portion in which the average change value of the amplitude slope is maintained at or below a predetermined value.

[0019] A method of operating an air conditioning device according to one embodiment of the present disclosure includes, in response to identifying first sensing data of a first frequency band, an operation of extracting amplitude information of at least a portion of second sensing data, and an operation of adjusting the air conditioning settings of the air conditioning device based on the amplitude information of at least a portion of the second sensing data, wherein the second sensing data may include data of a second frequency band acquired during the time interval in which the first sensing data is acquired.

[0020] In one embodiment, the method of operating the air conditioning device may include an operation of increasing at least one of the temperature and humidity of the air conditioning device in response to identifying that the average amplitude value of at least a portion of the second sensing data is less than or equal to a predetermined value.

[0021] In one embodiment, the method of operating the air conditioning device includes the operation of obtaining information regarding at least one object included in the area where the second sensing data is sensed, and the information regarding the at least one object may include information regarding the location, shape, and movement of the at least one object.

[0022] In one embodiment, the method of operating the air conditioning device may include an operation of adjusting the airflow of the air conditioning device based on information regarding the location of the at least one object.

[0023] In one embodiment, the information regarding the at least one object may include data regarding a plurality of points obtained from the at least one object.

[0024] In one embodiment, based on data regarding the plurality of points, the method may include an operation to identify at least one user corresponding to at least one object.

[0025] In one embodiment, the method of operating the air conditioning device may include the operation of obtaining health information of at least one user and the operation of adjusting the air conditioning settings based on the health information of at least one user.

[0026] In one embodiment, the method of operating an air conditioning device includes the operation of acquiring sound data of the first frequency band, the operation of dividing the sound data into a plurality of time intervals, the operation of extracting a feature vector based on amplitude information of the plurality of time intervals, and the operation of determining whether the sound data is the first sensing data based on a first machine learning model trained to take the feature vector and the sound data of the first frequency band as input values ​​and output whether the sound data corresponds to the first sensing data, wherein the first sensing data may include acoustic data classified as a cough.

[0027] In one embodiment, the first frequency band may have a smaller value than the second frequency band.

[0028] In one embodiment, at least a portion of the second sensing data may include a portion in which the average change value of the amplitude slope is maintained at or below a predetermined value.

[0029] The embodiments of the present disclosure provide the effect of maintaining a user's physical condition in a healthy state by adjusting the air conditioning state in consideration of the user's physical condition.

[0030] In addition, the embodiments of the present disclosure provide the effect of maintaining optimal air conditioning conditions around the user during sleep, thereby enabling the user to maintain deep sleep.

[0031] The effects obtainable in the present disclosure are not limited to those mentioned in the various embodiments, and other unmentioned effects will be clearly understood by those skilled in the art to which the present disclosure pertains from the description below.

[0032] FIG. 1 illustrates a block configuration of an air conditioning device according to one embodiment of the present disclosure.

[0033] FIG. 2 illustrates an example of sensing data of an air conditioning device according to one embodiment.

[0034] FIG. 3 illustrates the operation flow of an air conditioning device according to one embodiment.

[0035] FIG. 4 illustrates the operation flow of an air conditioning device according to one embodiment.

[0036] FIG. 5 illustrates the operation flow of an air conditioning device according to one embodiment.

[0037] FIG. 6 illustrates the operation flow of an air conditioning device according to one embodiment.

[0038] FIG. 7 illustrates an example of data processing of an air conditioning device according to one embodiment.

[0039] FIG. 8 illustrates the operation flow of an air conditioning device according to one embodiment.

[0040] In relation to the description of the drawings, the same or similar reference numerals may be used for identical or similar components.

[0041] Various embodiments are described in detail below with reference to the attached drawings. In the following description, specific details, such as detailed configurations and components, are provided merely to aid in a general understanding of the embodiments of the present disclosure. Accordingly, it will be apparent to those skilled in the art that various changes and modifications to the embodiments described herein may be made without departing from the scope and spirit of the present disclosure. Furthermore, descriptions of well-known functions and configurations may be omitted for the sake of clarity and brevity.

[0042] FIG. 1 illustrates a block configuration of an air conditioning device according to one embodiment.

[0043] Referring to FIG. 1, the air conditioning device (100) may include a communication module (130), a processor (110), a driving unit (150), a memory (140), and a sensing module (120).

[0044] In one embodiment, the processor (110) can control the overall operation of the air conditioning device (100).

[0045] In one embodiment, the processor (110) can control the air condition of a first area in response to a control signal (CS) transmitted from an electronic device. For example, the processor (110) can output air (e.g., cold air, warm air, and / or purified air) through a drive unit (150) in response to the control signal (CS). Additionally, if the air conditioning unit (100) is a smart door, the processor (110) can open or close the door through a drive unit (150) in response to the control signal (CS).

[0046] In one embodiment, the driving unit (150) is configured to perform the function of circulating indoor air and controlling the temperature, and can generate wind and blow it out in a desired direction under the control of the processor (110).

[0047] In one embodiment, when the air conditioning device (100) is an air conditioner, the driving unit (150) can output cold air to a specific area.

[0048] In one embodiment, when the air conditioning unit (100) is an air purifier, the driving unit (150) can output purified air to a specific area.

[0049] In one embodiment, when the air conditioning unit (100) is a smart door, the driving unit (150) can open or close the door according to the control of the processor (110).

[0050] In one embodiment, the memory (140) can store operation information (OI) and operation termination information (TI) of the air conditioning device (100). For example, the memory (140) can be implemented as a non-volatile memory.

[0051] In one embodiment, the memory (140) may store a first machine learning model trained to take sound data obtained through a microphone as an input value and output whether the sound data corresponds to acoustic data classified as a cough.

[0052] In one embodiment, the sensing module (120) can detect the surrounding environment of the air conditioning device (100) and the state of the user, and perform the function of optimizing the operation of the air conditioning device.

[0053] In one embodiment, the air conditioning device (100) can monitor the temperature, humidity, sound, movement, etc. around the air conditioning device in real time.

[0054] In one embodiment, the sensing module (120) may include a microphone, radar, infrared sensor, temperature and humidity sensor, etc.

[0055] In one embodiment, the sensing module (120) can detect the noise level through the microphone and automatically switch to a quiet mode.

[0056] In one embodiment, the sensing module (120) can recognize voice commands through a microphone.

[0057] In one embodiment, the sensing module (120) can identify the sound of a user coughing through a microphone.

[0058] In one embodiment, the sensing module (120) can detect the location or movement of a person present indoors through radar.

[0059] In one embodiment, the sensing module (120) can determine whether the cough is a dry cough through radar.

[0060] In one embodiment, the sensing module (120) can transmit sensing information to the processor (110).

[0061] In one embodiment, the processor (110) can transmit the sensing information transmitted from the sensing module (120) to another electronic device (e.g., a server device (not shown), a user device (not shown).

[0062] In one embodiment, the communication module (130) can receive a control signal (CS) from the electronic device (401).

[0063] In one embodiment, the communication module (130) can transmit a control signal (CS) to the processor (110).

[0064] In one embodiment, the communication module (130) can transmit operation information (OI) to the electronic device (401).

[0065] In one embodiment, the communication module (130) may transmit operation termination information (TI) to the electronic device (401).

[0066] In one embodiment, a display (not shown) can display the operating status of the air conditioning device (100).

[0067] FIG. 2 illustrates an example of sensing data of an air conditioning device according to one embodiment. The air conditioning device of FIG. 2 may include a device corresponding to the air conditioning device (100) of FIG. 1.

[0068] According to one embodiment, the air conditioning device can acquire data through a sensing module of the air conditioning device (e.g., a sensing module (120)).

[0069] In one embodiment, the air conditioning device can acquire a user's cough sound through a first sensor and a second sensor. The first sensor may include a sensor that processes a signal in a first frequency band as input. For example, the first sensor may include a microphone. Human voices and various environmental noises can be identified through the first sensor. The second sensor may include a sensor that processes a signal in a second frequency band as input. For example, the second sensor may include a radar sensor (e.g., mmWave radar). By emitting a high-frequency signal through the second sensor and analyzing the reflected signal, physical reactions such as a cough sound identified from the user or the user's movement can be detected.

[0070] In one embodiment, the first frequency band may include an audible frequency band. For example, the first frequency band may correspond to 20 Hz to 20 kHz.

[0071] In one embodiment, the second frequency band may be higher than the first frequency band. For example, the second frequency band may include bands of 24 GHz, 60 GHz, and 77-81 GHz.

[0072] In one embodiment, an acoustic signal identified through a first sensor can be converted into an electrical signal, and an air conditioning unit or server unit can analyze the converted electrical signal (e.g., through a machine learning model) to determine whether the identified acoustic signal is a cough sound. For example, the air conditioning unit can analyze the electrical signal identified through the first sensor based on an algorithm that detects a specific frequency pattern and sound pressure of a cough sound.

[0073] In one embodiment, the second sensor can emit a signal in a higher frequency band than the first sensor and can identify the user's cough sound by monitoring the reflected signal. The sensing data obtained through the second sensor may have a higher resolution than the sensing data sensed through the first sensor, and accordingly, it is possible to identify not only whether the user's cough is simply a cough but also whether it is a dry cough. Coughs can be classified into productive coughs accompanied by phlegm and dry coughs not accompanied by phlegm.

[0074] Referring to FIG. 2, the first sensing data (210) and the second sensing data (220) may represent an example of an acoustic signal identified through the first sensor or the second sensor.

[0075] In one embodiment, the first sensing data (210) and the second sensing data (220) may include acoustic data classified as a cough. The first sensing data (210) may include sensing data classified as an exudative cough. The second sensing data (220) may include sensing data classified as a dry cough.

[0076] In one embodiment, the first sensing data (210) may be divided into a first phase (e.g., Explosive phase), a second phase (e.g., Intermediate phase), and a third phase (e.g., Voiced phase). The first phase is the first stage in which air is rapidly released when coughing begins, and a strong, fast, explosive sound may be identified. In the first phase, a peak of very high amplitude may appear for a relatively short period of time, and the amplitude may rise rapidly and then decrease rapidly. The amplitude value of the first phase may be greater than that of other phases. The second phase may represent the stage in which the explosive release of air ends and the remaining air is continuously expelled. An irregular sound may occur as the air exits through the throat. In the second phase, the amplitude may change irregularly and gradually decrease. The amplitude may be relatively high at the beginning of the second phase, but the amplitude may gradually decrease over time. The third phase may represent the final stage of coughing. The third stage may represent a sound produced by the vibration of the vocal cords and may include a stage where the voice is mixed in during the latter part of the cough.

[0077] In one embodiment, the average amplitude value of the second stage of the second sensing data (220) may have a smaller amplitude value than the average amplitude value of the second stage of the first sensing data (210).

[0078] In one embodiment, if it is determined that a user's cough sound has been identified based on an acoustic signal acquired through a first sensor, the air conditioning device may identify second sensing data corresponding to the time interval in which the acoustic signal was acquired. The second sensing data may include acoustic data acquired through the second sensor.

[0079] FIG. 3 illustrates the operation flow of an air conditioning device according to one embodiment. The air conditioning device of FIG. 3 may include a device corresponding to the air conditioning device of FIG. 1 and FIG. 2.

[0080] According to one embodiment, in operation 310, the air conditioning device can determine whether to identify a cough sound.

[0081] In one embodiment, the air conditioning device can monitor whether a cough sound is identified.

[0082] In one embodiment, the air conditioning device may acquire an acoustic signal through a microphone. The air conditioning device may analyze the acquired acoustic signal, and if the analyzed acoustic signal is classified as a cough sound, it may determine that a cough sound has been identified. For example, the air conditioning device may determine whether the acquired acoustic signal is a cough sound by using a machine learning model trained to predict whether the acoustic signal is a cough sound with the acoustic signal as an input value. The operation flow for classifying the acoustic signal as a cough sound may be described in detail in the drawings described below.

[0083] In one embodiment, the air conditioning device may perform operation 320 if a cough sound is identified in operation 310.

[0084] According to one embodiment, in operation 320, the air conditioning device can determine whether the identified cough is a dry cough.

[0085] In one embodiment, the air conditioning device can determine whether the identified cough sound is a dry cough sound based on data acquired through a radar sensor.

[0086] In one embodiment, the air conditioning device can determine whether the cough sound is a dry cough sound by analyzing second sensing data, which is data identified through a radar sensor during the time interval in which an acoustic signal identified as a cough sound is identified through a microphone.

[0087] In one embodiment, the air conditioning device divides the second sensing data into at least three time intervals and can determine whether the cough sound is a dry cough sound based on the amplitude information of the middle time interval among the three divided intervals. For example, if the average amplitude value of the middle time interval is smaller than a value predetermined by the user, the cough sound can be determined to be a dry cough sound. For example, by comparing the average amplitude value of the middle time interval with the average amplitude value of the middle time interval of another cough sound recognized as a productive cough rather than a dry cough, it can be determined whether the identified cough sound is a dry cough.

[0088] In one embodiment, the air conditioning device uses data acquired through a second sensor as an input value and, based on a machine learning model trained to output whether the sound is a dry cough, can determine whether the second sensing data corresponding to the first sensing data corresponds to a dry cough sound. In other words, based on a machine learning model trained to predict whether the user's cough sound is a dry cough, it can determine whether the cough sound identified by the user is a dry cough.

[0089] In one embodiment, the air conditioning device can determine whether the cough sound is a dry cough based on the change in amplitude of the cough sound over time intervals and the magnitude of the amplitude value.

[0090] According to one embodiment, in operation 330, the air conditioning device can control the air conditioning settings.

[0091] In one embodiment, the air conditioning unit may change the temperature or humidity settings of the air conditioning unit. For example, the air conditioning unit may increase the set humidity. For example, the air conditioning unit may activate the humidification function of the air conditioner to alleviate dry air in the room. For example, the air conditioning unit may deactivate the activated dehumidification function. For example, the air conditioning unit may activate the air purification function. For example, the air conditioning unit may activate the ventilation mode. For example, the air conditioning unit may adjust the temperature to an appropriate temperature. For example, the air conditioning unit may provide warm air by raising the set temperature. For example, the air conditioning unit may reduce the cold air to prevent dryness.

[0092] In one embodiment, the air conditioning unit can control a drive unit (e.g., drive unit (150)) so that the airflow generated by the air conditioning unit is directed toward a specific area. For example, the air conditioning unit can activate an indoor air circulation mode to allow the airflow to circulate better. For example, the air conditioning unit can control a drive unit to change the direction of the wind generated from the air conditioning unit. For example, the air conditioning unit can identify a user who has a dry cough and the area where the user is located, and control a drive unit of the air conditioning unit so that the wind is directed toward an area other than the user and the area where the user is located.

[0093] FIG. 4 illustrates the operation flow of an air conditioning device according to one embodiment. The operation flow of FIG. 4 may include all or part of the operations described in the operation flow illustrated in FIG. 3. In the description of FIG. 4, descriptions that overlap with the descriptions in FIG. 1 to FIG. 3 may be omitted.

[0094] According to one embodiment, in operation 410, the air conditioning device can extract amplitude information of at least a portion of the second sensing data in response to identifying the first sensing data.

[0095] In one embodiment, the air conditioning device may include a first sensor (e.g., a microphone) that processes an input signal of a first frequency band and a second sensor (e.g., a mmWave radar) that processes an input signal of a second frequency band. The first frequency band may include an audible frequency band. For example, the first frequency band may correspond to 20 Hz to 20 kHz. The second frequency band may be higher than the first frequency band. For example, the second frequency band may include bands of 24 GHz, 60 GHz, and 77-81 GHz.

[0096] In one embodiment, the first sensing data may include acoustic data classified as a cough sound among acoustic signals around the air conditioning device.

[0097] In one embodiment, when the air conditioning device identifies an acoustic signal through a first sensor, it can determine whether the acoustic signal corresponds to a cough sound. The operation flow of the air conditioning device determining the acoustic signal as a cough sound can be described in detail in the description of FIG. 8 below.

[0098] In one embodiment, the second sensing data may include data acquired through the second sensor during the time interval in which the first sensing data is acquired. In other words, the first sensing data may include data identified as a cough sound among the data acquired through the microphone, and the second sensing data may include data acquired through the second sensor as data corresponding to said data.

[0099] In one embodiment, at least a portion of the second sensing data may include a second section (e.g., an intermediate phase).

[0100] In one embodiment, the second section may be divided according to a predetermined period.

[0101] In one embodiment, the first section, the second section, and the third section may have the same length.

[0102] In one embodiment, the lengths of the first, second, and third sections may be determined based on the change in amplitude.

[0103] In one embodiment, the first, second, and third sections may be determined based on the average value of the amplitude.

[0104] According to one embodiment, in operation 420, the air conditioning device may adjust the air conditioning settings of the air conditioning device based on amplitude information of at least a portion of the second sensing data. The second sensing data may refer to sensing data obtained through the second sensor during a time interval in which acoustic data classified as an acoustic signal through the first sensor (microphone) is identified.

[0105] In one embodiment, the air conditioning device may increase at least one of the temperature and humidity of the air conditioning device in response to identifying that the average amplitude value of at least a portion of the second sensing data is less than or equal to a predetermined value.

[0106] In one embodiment, the air conditioning device can obtain information regarding at least one object included in the area where the second sensing data is sensed, based on the second sensor.

[0107] In one embodiment, information regarding at least one object may include information regarding the location, shape, and movement of at least one object. For example, information regarding at least one object may include information regarding the user's location, shape, and movement of the user (e.g., movement of the chest).

[0108] In one embodiment, the air conditioning device can adjust the airflow of the air conditioning device based on information regarding the location of at least one object. For example, the air conditioning device can control a driving unit so that the airflow is not directed toward the location of a user who has a dry cough, i.e., the area where the second sensing data is sensed.

[0109] In one embodiment, information regarding at least one object may include data regarding a plurality of points obtained from said at least one object. FIG. 7 illustrates an example of data processing of an air conditioning device according to one embodiment. Referring to FIG. 7, information regarding at least one object may include information regarding a 3D point cloud illustrated in the first step (710), the second step (720), the third step (730), and the fourth step (740).

[0110] In one embodiment, information regarding at least one object may be generated based on the time of flight (ToF) and signal strength of a signal received after a signal emitted through a second sensor is reflected from an object (user) around the air conditioning unit. The at least one object information may include a 3D point cloud. The at least one object information may include 3D coordinate data of the space adjacent to the air conditioning unit. For example, the at least one object information may include spatial information such as distance, height, and size to a specific object adjacent to the air conditioning unit. The at least one object information may be used by the air conditioning unit to identify the shape and location of the object and to detect the object's movement (e.g., coughing, dry coughing, simple movement) in real time.

[0111] In one embodiment, the point cloud may include data regarding a plurality of points constituting the 3D space surrounding the air conditioning unit. The point cloud may include XYZ coordinate values ​​of points constituting objects surrounding the air conditioning unit. The XYZ coordinate values ​​may include spatial information regarding the location of each point relative to the air conditioning unit. The point cloud may include the intensity values ​​of the points. Intensity may indicate the intensity value of light reflected back from each point, and the characteristics of the object may be precisely analyzed based on the intensity. For example, a metal surface may exhibit high intensity, while a highly absorbent surface may exhibit low intensity.

[0112] In one embodiment, the air conditioning device can identify at least one user corresponding to at least one object based on data regarding a plurality of points.

[0113] In one embodiment, the air conditioning device can obtain health information of the at least one user from a memory or the communication unit.

[0114] In one embodiment, the air conditioning device can adjust the air conditioning settings based on health information of at least one user.

[0115] In one embodiment, the air conditioning device can acquire sound data through a first sensor. The air conditioning device can divide the sound data into a plurality of time intervals. The air conditioning device can extract a feature vector based on amplitude information of the plurality of time intervals. The air conditioning device can determine whether the sound data is sound data of a first type based on the feature vector and a first machine learning model.

[0116] In one embodiment, at least a portion of the second sensing data may include a portion in which the average change value of the amplitude slope is maintained at or below a predetermined value.

[0117] FIG. 5 illustrates the operation flow of an air conditioning device according to one embodiment. The air conditioning device of FIG. 5 may include a device corresponding to the air conditioning device of FIG. 1 to FIG. 4. In the description of FIG. 5, descriptions of parts that overlap with those described in FIG. 1 to FIG. 4 may be omitted. FIG. 5 may include all or part of the operation details of FIG. 3 and FIG. 4.

[0118] According to one embodiment, in operation 510, the air conditioning device may determine whether the identified cough is a dry cough. Operation 510 may include all of the operation contents according to operation 320, operation 410, and operation 420.

[0119] In one embodiment, the air conditioning device can determine whether the identified cough sound is a dry cough sound based on data acquired through a radar sensor.

[0120] In one embodiment, the air conditioning device can determine whether the cough sound is a dry cough sound by analyzing second sensing data, which is data identified through a radar sensor during the time interval in which an acoustic signal identified as a cough sound is identified through a microphone.

[0121] In one embodiment, the air conditioning device divides the second sensing data into at least three time intervals and can determine whether the cough sound is a dry cough sound based on the amplitude information of the middle time interval among the three divided intervals. For example, if the average amplitude value of the middle time interval is smaller than a value predetermined by the user, the cough sound can be determined to be a dry cough sound. For example, by comparing the average amplitude value of the middle time interval with the average amplitude value of the middle time interval of another cough sound recognized as a productive cough rather than a dry cough, it can be determined whether the identified cough sound is a dry cough.

[0122] In one embodiment, the air conditioning device uses data acquired through a second sensor as an input value and, based on a machine learning model trained to output whether the sound is a dry cough, can determine whether the second sensing data corresponding to the first sensing data corresponds to a dry cough sound. In other words, based on a machine learning model trained to predict whether the user's cough sound is a dry cough, it can determine whether the cough sound identified by the user is a dry cough.

[0123] In one embodiment, the air conditioning device can determine whether the cough sound is a dry cough based on the change in amplitude of the cough sound over time intervals and the magnitude of the amplitude value.

[0124] In one embodiment, the second sensing data may include data acquired through the second sensor during the time interval in which the first sensing data is acquired. In other words, the first sensing data may include data identified as a cough sound among the data acquired through the microphone, and the second sensing data may include data acquired through the second sensor as data corresponding to said data.

[0125] In one embodiment, at least a portion of the second sensing data may include a second section (e.g., an intermediate phase).

[0126] In one embodiment, the second section may be divided according to a predetermined period.

[0127] In one embodiment, the first section, the second section, and the third section may have the same length.

[0128] In one embodiment, the lengths of the first, second, and third sections may be determined based on the change in amplitude.

[0129] In one embodiment, the first, second, and third sections may be determined based on the average value of the amplitude.

[0130] According to one embodiment, the second sensing data may refer to sensing data obtained through the second sensor during a time interval in which acoustic data classified as an acoustic signal through the first sensor (microphone) is identified.

[0131] In one embodiment, the air conditioning device may determine that the identified cough is a dry cough in response to identifying that the average amplitude value of at least a portion of the second sensing data is less than or equal to a predetermined value.

[0132] In one embodiment, the air conditioning device can detect vocal cord vibrations occurring in the user's neck area in a non-contact manner by using electromagnetic waves in a high-frequency band (e.g., 30 GHz or higher) through a second sensor. The air conditioning device can determine the identified cough as a normal cough if the vocal cord vibration is clear, long, and repetitive, and as a dry cough if the vocal cord vibration is weak or occurs intermittently. The air conditioning device can analyze amplitude data and learn cough patterns by utilizing machine learning models (RNN, LSTM), etc.

[0133] According to one embodiment, if the air conditioning device determines that the cough identified in operation 510 is a dry cough, the air conditioning device may perform operation 520.

[0134] According to one embodiment, in operation 520, the air conditioning device can track a person who has coughed.

[0135] In one embodiment, the air conditioning device can identify a person who has coughed based on second sensing data acquired through a second sensor. Information regarding objects existing adjacent to the air conditioning device can be acquired through the second sensor, and a person who has coughed can be identified based on said information.

[0136] In one embodiment, the air conditioning device senses the shape and movement of an object adjacent to the air conditioning device and can identify a user who has a dry cough based on the sensed shape and movement of the object. For example, if the shape of an object present in the area where the dry cough occurred corresponds to the shape of a person lying down, and the air conditioning device detects that a part of the object (e.g., the chest area of ​​a person) is moving rapidly, the air conditioning device can determine that the object is a user who has a dry cough.

[0137] According to one embodiment, in operation 530, the air conditioning device can control the air conditioning settings of the air conditioning device. For example, since the identified cough is a dry cough, the temperature of the air being emitted can be raised or lowered to optimize the humidity of the space around the air conditioning device so as to alleviate the dry cough. For example, the air conditioning device can disable the humidification mode or the dehumidification mode. For example, the air conditioning device can control the direction of the airflow so that the airflow emitted by the air conditioning device is not directed directly toward the user who coughed.

[0138] FIG. 6 illustrates the operation flow of an air conditioning device according to one embodiment. The air conditioning device of FIG. 6 may include all devices corresponding to the air conditioning devices of FIG. 1 to FIG. 5. In the description of FIG. 6, descriptions identical to those described in FIG. 1 to FIG. 5 may be omitted. The operation of FIG. 6 may include all the operation of FIG. 3 to FIG. 5.

[0139] According to one embodiment, in operation 610, the air conditioning device can obtain information regarding at least one object included in the area where the second sensing data is sensed.

[0140] In one embodiment, the air conditioning device can obtain information regarding at least one object included in the area where the second sensing data is sensed, based on the second sensor.

[0141] In one embodiment, information regarding at least one object may include information regarding the location, shape, and movement of at least one object. For example, information regarding at least one object may include information regarding the user's location, shape, and movement of the user (e.g., movement of the chest).

[0142] In one embodiment, the air conditioning device can adjust the airflow of the air conditioning device based on information regarding the location of at least one object. For example, the air conditioning device can control a driving unit so that the airflow is not directed toward the location of a user who has a dry cough, i.e., the area where the second sensing data is sensed.

[0143] In one embodiment, information regarding at least one object may include data regarding a plurality of points obtained from said at least one object. FIG. 7 illustrates an example of data processing of an air conditioning device according to one embodiment. Referring to FIG. 7, information regarding at least one object may include information regarding a 3D point cloud illustrated in the first step (710), the second step (720), the third step (730), and the fourth step (740).

[0144] In one embodiment, information regarding at least one object may be generated based on the time of flight (ToF) and signal strength of a signal received after a signal emitted through a second sensor is reflected from an object (user) around the air conditioning unit. The at least one object information may include a 3D point cloud. The at least one object information may include 3D coordinate data of the space adjacent to the air conditioning unit. For example, the at least one object information may include spatial information such as distance, height, and size to a specific object adjacent to the air conditioning unit. The at least one object information may be used by the air conditioning unit to identify the shape and location of the object and to detect the object's movement (e.g., coughing, dry coughing, simple movement) in real time.

[0145] In one embodiment, the point cloud may include data regarding a plurality of points constituting the 3D space surrounding the air conditioning unit. The point cloud may include XYZ coordinate values ​​of points constituting objects surrounding the air conditioning unit. The XYZ coordinate values ​​may include spatial information regarding the location of each point relative to the air conditioning unit. The point cloud may include the intensity values ​​of the points. Intensity may indicate the intensity value of light reflected back from each point, and the characteristics of the object may be precisely analyzed based on the intensity. For example, a metal surface may exhibit high intensity, while a highly absorbent surface may exhibit low intensity.

[0146] According to one embodiment, in operation 620, the air conditioning device can identify at least one user corresponding to at least one object.

[0147] In one embodiment, the air conditioning device can identify at least one user corresponding to at least one object based on data regarding a plurality of points.

[0148] Referring to FIG. 7, in the first step (710), the air conditioning device can obtain information regarding at least one object, namely data regarding multiple points. In the second step (720), the air conditioning device can group multiple points to generate at least one candidate region. In the third step (730), the air conditioning device can analyze the points included in at least one candidate region to identify a specific shape, and determine a region where the identified specific shape is determined to correspond to a human shape as a user. In the fourth step (740), the air conditioning device can identify a specific user (e.g., Alice, Bob) corresponding to the shape of the user identified through the points of the region.

[0149] According to one embodiment, in operation 630, the air conditioning device can control air conditioning settings based on information regarding at least one user. The information regarding at least one user may include user identification information, status information (current body temperature, heart rate, fatigue level, etc.), health information (information on diseases possessed), user location information, etc.

[0150] In one embodiment, the air conditioning device may control the actuator of the air conditioning device to provide a temperature and humidity optimized for the user based on information regarding at least one user. For example, the air conditioning device may change the temperature and humidity set to the preferred temperature and humidity for each identified user. For example, if the identified user has a specific disease, the air conditioning device may control the temperature and humidity so as not to exacerbate the disease. For example, the air conditioning device may control the air conditioning settings so that airflow is not formed to the location where a user who has coughed is present.

[0151] FIG. 8 illustrates the operation flow of an air conditioning device according to one embodiment. The air conditioning device of FIG. 8 may include all devices corresponding to the air conditioning devices of FIG. 1 to FIG. 7. In the description of FIG. 8, descriptions that overlap with the descriptions in FIG. 1 to FIG. 7 may be omitted. The operation content of FIG. 8 specifically describes the operation content of operation 310 of FIG. 3, and may include all operation content for determining whether acoustic data identified through a first sensor (microphone) is first sensing data (data identified as a cough sound).

[0152] According to one embodiment, in operation 810, the air conditioning device can acquire acoustic data. The air conditioning device can acquire acoustic data generated in a space adjacent to the air conditioning device through a first sensor (microphone). In the following description, analyzing the signal acquired through the first sensor is given as an example, but this is merely an example, and acoustic data can also be acquired through a second sensor (radar or lidar).

[0153] In one embodiment, acoustic data may be collected at a sampling rate greater than a predetermined value. In acquiring acoustic data, a noise removal filter may be used. A plurality of sensors may be used to acquire acoustic data.

[0154] According to one embodiment, in operation 820, the air conditioning device can divide acoustic data into time intervals of a predetermined length and extract feature vectors.

[0155] In one embodiment, the air conditioning device can process acoustic data by dividing it into time intervals of a predetermined length. For example, the window size may be 25ms to 50ms.

[0156] In one embodiment, the air conditioning device can extract a feature vector based on amplitude data for each time interval of the acquired acoustic data. The air conditioning device can perform preprocessing to normalize the extracted feature vector so that it can be input into a learning model.

[0157] According to one embodiment, in operation 830, the air conditioning device can determine acoustic data as cough or non-cough.

[0158] In one embodiment, the air conditioning device can determine acoustic data as a cough or a non-cough using a machine learning model (on-device AI) stored in the memory of the air conditioning device. The air conditioning device can determine acoustic data as a cough or a non-cough using a model trained to determine whether it is a cough using acoustic data regarding cough sounds and acoustic data regarding non-cough sounds.

[0159] In one embodiment, if the acoustic data is determined to be a cough sound, the air conditioning device may perform an additional operation to determine whether the cough sound is a dry cough sound.

[0160] In one embodiment, if the air conditioning unit determines that the identified cough sound is a dry cough sound, it can measure the temperature and humidity of the space adjacent to the air conditioning unit and determine a reference humidity based on information regarding the user who coughed. The air conditioning unit can control the humidity based on the determined reference humidity. The air conditioning unit can define a humidity control time. The humidity control time can be defined by summing the time taken to detect the cough sound with a radar sensor, the time taken to analyze the signal and send a command to the humidity control unit, the physical operation delay time of the humidity control unit, the weighted time based on cough factors (cough sound loudness, duration, frequency), and the time for how quickly the humidity control function reaches the set target humidity.

[0161] An air conditioning device according to one embodiment of the present disclosure comprises a sensing module including a first sensor that processes an input signal of a first frequency band and a second sensor that processes an input signal of a second frequency band, and at least one processor electrically connected to the sensing module, wherein the at least one processor is configured to extract amplitude information of at least a portion of the second sensing data in response to identifying first sensing data through the first sensor and to adjust the air conditioning settings of the air conditioning device based on the amplitude information of at least a portion of the second sensing data, wherein the first sensing data includes acoustic data classified as a cough, and the second sensing data may include data acquired through the second sensor during the time interval in which the first sensing data is acquired.

[0162] According to one embodiment, the at least one processor may be configured to increase at least one of the temperature and humidity of the air conditioning device in response to identifying that the average amplitude value of the at least part of the second sensing data is less than or equal to a predetermined value.

[0163] In one embodiment, the at least one processor is configured to acquire information regarding at least one object included in the area where the second sensing data is sensed, based on the second sensor, and the information regarding the at least one object may include information regarding the location, shape, and movement of the at least one object.

[0164] In one embodiment, the at least one processor may be configured to adjust the airflow of the air conditioning device based on information regarding the location of the at least one object.

[0165] In one embodiment, the at least one processor may include information regarding the at least one object, which may include data regarding a plurality of points obtained from the at least one object.

[0166] In one embodiment, the at least one processor may be configured to identify at least one user corresponding to the at least one object based on data regarding the plurality of points.

[0167] In one embodiment, the air conditioning device further includes a memory and a communication unit electrically connected to the at least one processor, and the at least one processor may be configured to obtain health information of at least one user from the memory or the communication unit and to adjust the air conditioning settings based on the health information of the at least one user.

[0168] In one embodiment, the air conditioning device may include a memory electrically connected to at least one processor, which stores a first machine learning model trained to take sound data acquired through the first sensor as an input value and output whether the sound data corresponds to acoustic data classified as a cough, and the at least one processor may be configured to acquire sound data through the first sensor, divide the sound data into a plurality of time intervals, extract a feature vector based on amplitude information of the plurality of time intervals, and determine whether the sound data is first sensing data based on the feature vector and the first machine learning model.

[0169] In one embodiment, the first frequency band may have a smaller value than the second frequency band.

[0170] In one embodiment, at least a portion of the second sensing data may include a portion in which the average change value of the amplitude slope is maintained at or below a predetermined value.

[0171] A method of operating an air conditioning device according to one embodiment of the present disclosure includes, in response to identifying first sensing data of a first frequency band, an operation of extracting amplitude information of at least a portion of second sensing data, and an operation of adjusting the air conditioning settings of the air conditioning device based on the amplitude information of at least a portion of the second sensing data, wherein the first sensing data includes acoustic data classified as a cough, and the second sensing data may include data of a second frequency band acquired during the time interval in which the first sensing data is acquired.

[0172] In one embodiment, the method of operating the air conditioning device may include an operation of increasing at least one of the temperature and humidity of the air conditioning device in response to identifying that the average amplitude value of at least a portion of the second sensing data is less than or equal to a predetermined value.

[0173] In one embodiment, the method of operating the air conditioning device includes the operation of obtaining information regarding at least one object included in the area where the second sensing data is sensed, and the information regarding the at least one object may include information regarding the location, shape, and movement of the at least one object.

[0174] In one embodiment, the method of operating the air conditioning device may include an operation of adjusting the airflow of the air conditioning device based on information regarding the location of the at least one object.

[0175] In one embodiment, the information regarding the at least one object may include data regarding a plurality of points obtained from the at least one object.

[0176] In one embodiment, based on data regarding the plurality of points, the method may include an operation to identify at least one user corresponding to at least one object.

[0177] In one embodiment, the method of operating the air conditioning device may include the operation of obtaining health information of at least one user and the operation of adjusting the air conditioning settings based on the health information of at least one user.

[0178] In one embodiment, the method of operating the air conditioning device may include the operation of acquiring sound data of the first frequency band, the operation of dividing the sound data into a plurality of time intervals, the operation of extracting a feature vector based on amplitude information of the plurality of time intervals, and the operation of determining whether the sound data is the first sensing data based on a first machine learning model trained to take the feature vector and the sound data of the first frequency band as input values ​​and output whether the sound data corresponds to acoustic data classified as cough.

[0179] In one embodiment, the first frequency band may have a smaller value than the second frequency band.

[0180] In one embodiment, at least a portion of the second sensing data may include a portion in which the average change value of the amplitude slope is maintained at or below a predetermined value.

[0181] The term “module” as used in the various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit, for example. A module may be a component formed integrally, or a minimum unit of said component or a part thereof that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0182] Various embodiments of this document may be implemented as software (e.g., a program) containing one or more instructions stored in a storage medium (e.g., internal memory or external memory) that is readable by a machine (e.g., an electronic device). For example, a processor (e.g., a processor) of a machine (e.g., an electronic device (101)) may call at least one of the one or more instructions stored in the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code that can be executed by an interpreter. The storage medium readable by the machine may be provided in the form of a non-transitory storage medium. Here, "non-transitory" simply means that the storage medium is a tangible device and does not contain a signal (e.g., electromagnetic waves), and this term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily in the storage medium.

[0183] According to one embodiment, the method according to the various embodiments disclosed herein may be provided by being included in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or an application store (e.g., Play Store). TMIt can be distributed online (e.g., downloaded or uploaded) through ) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0184] According to various embodiments, each component (e.g., module or program) of the components described above may include a singular or multiple entities, and some of the multiple entities may be separated and placed in other components. According to various embodiments, one or more of the components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Generally or additionally, multiple components (e.g., module or program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the multiple components in the same or similar manner as those performed by the corresponding component among the multiple components prior to integration. According to various embodiments, operations performed by the module, program, or other components may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. In an air conditioning system, A sensing module comprising a first sensor that processes an input signal of a first frequency band corresponding to first sensing data and a second sensor that processes an input signal of a second frequency band corresponding to second sensing data; It includes at least one processor electrically connected to the above-mentioned sensing module, and The above at least one processor is: Acquire the first sensing data through the first sensor, and In the time interval during which the first sensing data is acquired, the second sensing data is acquired through the second sensor, and Extract amplitude information of at least a portion of the second sensing data, and A device configured to adjust the air conditioning settings of the air conditioning device based on amplitude information of at least a portion of the second sensing data.

2. In Claim 1, The above at least one processor is: A device configured to increase at least one of the temperature and humidity of the air conditioning device in response to identifying that the average amplitude value of at least a section of the second sensing data is less than or equal to a predetermined value.

3. In Claim 2, The above at least one processor is: Based on the second sensor, the second sensing data is configured to obtain information regarding at least one object included in the area where the second sensing data is sensed, and A device comprising information regarding at least one object, wherein the information regarding the at least one object includes information regarding the location, shape, and movement of the at least one object.

4. In Claim 3, The above at least one processor is: A device configured to adjust the airflow of the air conditioning device based on information regarding the location of at least one object.

5. In Claim 3, The device, wherein information regarding at least one object includes data regarding a plurality of points obtained from at least one object.

6. In Claim 5, The above-mentioned at least one processor is, A device configured to identify at least one user corresponding to at least one object based on data regarding the plurality of points above.

7. In Claim 4, It further includes a memory and a communication unit electrically connected to the above-mentioned at least one processor, and The above-mentioned at least one processor is, At least one user's health information is obtained from the above memory or the above communication unit, and A device configured to adjust the air conditioning settings based on the health information of at least one user.

8. In Claim 1, A first machine learning model is stored that takes sound data obtained through the first sensor as an input value and outputs whether the sound data corresponds to the first sensing data, and the memory is electrically connected to the at least one processor. The above at least one processor is: Sound data is acquired through the first sensor above, and The above sound data is divided into multiple time intervals, and A feature vector is extracted based on the amplitude information of the above multiple time intervals, and It is configured to determine whether the sound data is the first sensing data based on the above feature vector and the above first machine learning model, and The above first sensing data includes acoustic data classified as a cough, in a device.

9. In Claim 1, A device in which the first frequency band is smaller than the second frequency band.

10. In Claim 1, A device in which at least a portion of the second sensing data includes a portion of which the average change value of the amplitude slope is maintained at or below a predetermined value.

11. In the method of operating an air conditioning device, Operation of acquiring first sensing data of a first frequency band through a first sensor, The operation of acquiring second sensing data of a second frequency band through a second sensor during the time interval in which the first sensing data is acquired, The operation of extracting amplitude information of at least a portion of the second sensing data, A method comprising adjusting the air conditioning settings of the air conditioning device based on amplitude information of at least a portion of the second sensing data.

12. In Claim 11, A method comprising the operation of increasing at least one of the temperature and humidity of the air conditioning device in response to identifying that the average amplitude value of at least a portion of the second sensing data is less than or equal to a predetermined value.

13. In Claim 12, The method includes an operation of obtaining information regarding at least one object included in the area where the second sensing data is sensed, and A method in which information regarding at least one object includes information regarding the location, shape, and movement of at least one object.

14. In Claim 13, A method comprising the operation of adjusting the airflow of the air conditioning device based on the information regarding the location of at least one object.

15. In Claim 13, A method in which information regarding at least one object includes data regarding a plurality of points obtained from at least one object.

Images