Heating and cooling system of predicting heating and cooling needs for multiple compartment spaces and operating method thereof

Abstract

The present disclosure relates to a method of operating a heating and cooling system, wherein the method of operating a heating and cooling system of the present disclosure may include the steps of: dividing a target space into a plurality of partitioned spaces; generating environmental information for each of the plurality of partitioned spaces using at least one sensor; training a machine learning model based on the environmental information; predicting the heating and cooling needs for the plurality of partitioned spaces using the trained machine learning model; and controlling the operation method of a heating and cooling device according to the predicted heating and cooling needs.

Description

Technology Field

[0001] The present disclosure relates to a heating and cooling system and a method of operating the heating and cooling system, and more specifically, to a heating and cooling system and a method of operating the same that predicts the heating and cooling needs of a plurality of partitioned spaces using a machine learning model learned based on environmental information and controls the operation method of a heating and cooling device according to the predicted heating and cooling needs. Background Technology

[0002] Conventional heating and cooling systems have mostly relied on single-sensor-based control or two-dimensional space management. Generally, the entire indoor space was treated as a single unit, or heating and cooling devices were operated based on average temperature and humidity.

[0003] Conventional heating and cooling systems set their output based on the average value of the entire room, making it impossible to accurately reflect temperature differences between spaces or environmental changes in specific areas. For example, temperatures rise near sunlit windows or in densely populated areas, but the system fails to recognize this, resulting in reduced comfort in those specific spaces.

[0004] Furthermore, conventional heating and cooling systems utilized only a limited number of fixed temperature sensors to measure environmental information at specific locations. Consequently, the lack of environmental data for the entire space made it difficult to accurately determine heating and cooling needs, and control blind spots occurred in areas without fixed sensors. As a result, since heating and cooling were applied with the same output across the entire space, unused areas or unnecessary energy waste occurred.

[0005] Therefore, there is a need for a heating and cooling system that divides the indoor space into multiple compartments to collect environmental information suitable for the indoor environment, acquires information about the indoor environment even in areas without fixed sensors, and provides heating and cooling optimized for the indoor environment. The problem to be solved

[0006] The present disclosure aims to improve the energy efficiency of a heating and cooling system by dividing a target space into three-dimensional partitioned spaces and learning environmental information such as temperature, humidity, and air quality of each partitioned space using a machine learning model, thereby providing heating and cooling optimized for the target space.

[0007] In addition, the present disclosure aims to provide a heating and cooling system capable of accurately predicting heating and cooling needs by measuring environmental information using various sensors, including fixed sensors, mobile sensors, and attached sensors, and estimating environmental information regarding blind spots.

[0008] The problems that this disclosure aims to solve are not limited to those described above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below. means of solving the problem

[0009] A method of operating a heating and cooling system according to one embodiment of the present disclosure may include: dividing a target space into a plurality of partitioned spaces; generating environmental information for each of the plurality of partitioned spaces using at least one sensor; training a machine learning model based on the environmental information; predicting the heating and cooling needs for the plurality of partitioned spaces using the trained machine learning model; and controlling the operation method of a heating and cooling device according to the predicted heating and cooling needs.

[0010] In some embodiments, the step of dividing into a plurality of partitioned spaces may include: obtaining map data for a target space from at least one sensor; obtaining partition information including at least one of the size, shape, and use of the target space based on the map data; and dividing the target space into a plurality of partitioned spaces based on the partition information.

[0011] In some embodiments, the step of generating environmental information may include: generating first environmental information for a first partition space using a first sensor; generating second environmental information for a second partition space using a second sensor; and generating third environmental information for a third partition space based on the first environmental information and the second environmental information.

[0012] In some embodiments, each of the first sensor and the second sensor may include at least one of a fixed sensor fixed at a certain position in the target space, a movable sensor movable within the target space, and an attached sensor attached to a heating and cooling device.

[0013] In some embodiments, the first sensor and the second sensor can each generate at least one of the temperature, humidity, air quality, and atmospheric pressure of the target space as first environmental information and second environmental information.

[0014] In some embodiments, the step of training a machine learning model may include: a step of acquiring environmental information for each of a plurality of partitioned spaces; a step of acquiring information on the operation method of a heating and cooling device; and a step of training a machine learning model by setting the environmental information as an input variable and the operation method information as an output variable.

[0015] In some embodiments, the operation method information may include at least one of the output of the heating and cooling device, wind speed, wind direction, and operating time.

[0016] A heating and cooling system according to one embodiment of the present disclosure may include: a sensor unit disposed in a target space partitioned into a plurality of partitioned spaces and generating environmental information for each of the plurality of partitioned spaces; and a heating and cooling device whose operation method is adjusted according to a predicted heating and cooling need. The heating and cooling device may include a control unit that partitions the target space into a plurality of partitioned spaces, learns a machine learning model based on environmental information, and predicts the heating and cooling need for the plurality of partitioned spaces using the learned machine learning model.

[0017] In some embodiments, the heating and cooling device may further include a communication unit that communicates with a sensor unit and obtains environmental information from the sensor unit.

[0018] In some embodiments, the control unit obtains map data for a target space from a sensor unit, obtains partition information including at least one of the size, shape, and use of the target space based on the map data, and can partition the target space into a plurality of partitioned spaces based on the partition information.

[0019] In some embodiments, the sensor unit may include a first sensor that generates first environmental information for a first partition space and a second sensor that generates second environmental information for a second partition space, and the control unit may generate third environmental information for a third partition space based on the first environmental information and the second environmental information.

[0020] In some embodiments, each of the first sensor and the second sensor may include at least one of a fixed sensor fixed at a certain position in the target space, a movable sensor movable within the target space, and an attached sensor attached to a heating and cooling device.

[0021] In some embodiments, the first sensor and the second sensor can each generate at least one of the temperature, humidity, air quality, and atmospheric pressure of the target space as first environmental information and second environmental information.

[0022] In some embodiments, the control unit can acquire environmental information for each of a plurality of partitioned spaces from the sensor unit, acquire information on the operation method of the heating and cooling device from the heating and cooling device, set the environmental information as an input variable, and set the operation method information as an output variable to train a machine learning model.

[0023] In some embodiments, the operation method information may include at least one of the output of the heating and cooling device, wind speed, wind direction, and operating time. Effects of the invention

[0024] A heating and cooling system and a method of operation according to an embodiment of the present disclosure can increase the energy efficiency of a heating and cooling system by dividing a target space into three-dimensional partitioned spaces and learning environmental information such as temperature, humidity, and air quality of each partitioned space using a machine learning model, thereby providing heating and cooling optimized for the target space.

[0025] In addition, the heating and cooling system and the method of operation according to the embodiment of the present disclosure can accurately predict the need for heating and cooling by measuring environmental information using various sensors including fixed sensors, mobile sensors, attached sensors, etc., and estimating environmental information regarding blind spots. Brief explanation of the drawing

[0026] FIG. 1 is a drawing showing a heating and cooling system according to an embodiment of the present disclosure. FIG. 2 is a flowchart illustrating the operation method of a heating and cooling system according to an embodiment of the present disclosure. FIG. 3 is a drawing showing a target space divided into a plurality of partitioned spaces according to an embodiment of the present disclosure. FIG. 4 is a diagram illustrating a method for an attached sensor to acquire environmental information for a plurality of partitioned spaces according to an embodiment of the present disclosure. FIG. 5 is a drawing showing map data according to an embodiment of the present disclosure. FIG. 6 is a flowchart illustrating a method of dividing a target space into a plurality of partitioned spaces according to an embodiment of the present disclosure. FIG. 7 is a flowchart illustrating a method for generating environmental information for a plurality of partitioned spaces according to an embodiment of the present disclosure. FIG. 8 is a flowchart illustrating a method for training a machine learning model according to an embodiment of the present disclosure. Specific details for implementing the invention

[0027] Hereinafter, exemplary embodiments according to the present invention will be described in detail with reference to the contents described in the attached drawings. However, the present invention is not limited or restricted by exemplary embodiments. Unless otherwise defined, all terms used in this specification (including technical and scientific terms) shall be used in a meaning that is commonly understood by those skilled in the art to which this disclosure belongs, but this may vary depending on the intent of those skilled in the art, case law, the emergence of new technology, etc.

[0028] Furthermore, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise. In certain cases, terms have been selected at the applicant's discretion, and in such cases, their meanings will be described in detail in the relevant explanatory sections. Accordingly, terms used in this disclosure should be defined not merely by their names, but based on their meanings and the content throughout this disclosure.

[0029] Throughout this specification, when a part is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Furthermore, the singular form used in this specification includes the plural form unless specifically stated otherwise. Additionally, the expression "at least one of a, b, and / or c" as used throughout this specification may encompass 'a alone', 'b alone', 'c alone', 'a and b', 'a and c', 'b and c', or 'a, b, and c all'.

[0030] Meanwhile, terms such as "first and / or second" used in this specification may be used to describe various components, but they are used solely for the purpose of distinguishing one component from another and are not intended to limit the scope to the components referred to by such terms. For example, without departing from the scope of the present invention, the first component may be named the second component, and the second component may also be named the first component.

[0031] Additionally, terms such as “…part,” “…module,” etc., as described in this specification refer to a unit that processes at least one function or operation, which may be implemented in hardware or software, or a combination of hardware and software. Furthermore, embodiments of this disclosure may be represented in this specification by functional block configurations and various processing steps. These functional blocks may be implemented by various numbers of hardware and / or software configurations that execute specific functions. For example, embodiments of this disclosure may employ integrated circuit configurations such as memory, processing, logic, look-up tables, etc., which can execute various functions under the control of one or more microprocessors or other control devices.

[0032] Hereinafter, various embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In describing the embodiments, technical details that are well known in the art to which the present invention pertains and are not directly related to the present invention will be omitted. This is to ensure that the essence of the present invention is conveyed more clearly without obscuring it by omitting unnecessary explanations. For the same reason, some components in the accompanying drawings may be exaggerated, omitted, or schematically depicted. Furthermore, the size of each component does not entirely reflect its actual size. Throughout this specification, the same reference numerals may refer to the same or corresponding components.

[0034] FIG. 1 is a drawing showing a heating and cooling system according to an embodiment of the present disclosure.

[0035] Referring to FIG. 1, a heating and cooling system (10) according to one embodiment of the present disclosure may include a heating and cooling device (110) and a sensor unit (120). In the present disclosure, the heating and cooling system (10) may refer to a system that predicts the need for heating and cooling based on environmental information such as temperature, humidity, and air quality of a target space, and controls the heating and cooling device (110) accordingly to provide optimized heating and cooling. In addition, in the present disclosure, the need for heating and cooling may refer to the degree of heating and cooling output required in a specific partitioned space, and may be derived as a result of learning and prediction by a machine learning model (113). The need for heating and cooling may vary by partitioned space, and the operation method of the heating and cooling device (110) may be adjusted based on this.

[0036] The heating and cooling device (110) may include a control unit (111), a communication unit (112), and a machine learning model (113). The heating and cooling device (110) may have its operation method adjusted according to the heating and cooling needs predicted by the control unit (111). Here, the operation method of the heating and cooling device (110) may include at least one of the output, wind speed, wind direction, and operating time of the heating and cooling device (110). The heating and cooling device (110) may be, for example, an air conditioning device such as an air conditioner or a heat pump system.

[0037] The control unit (111) can control the operation of the heating and cooling device (110) and can divide the target space into a plurality of partitioned spaces. In the present disclosure, a partitioned space may refer to a spatial unit that divides the target space subject to heating and cooling into three dimensions, and may be set to individually analyze and control the need for heating and cooling. The size and boundaries of the partitioned spaces may be set differently depending on the size, shape, use, etc. of the target space.

[0038] Additionally, the control unit (111) can process and analyze environmental information collected from the sensor unit (120). In the present disclosure, environmental information may refer to information indicating the indoor environment of the target space, such as the temperature, humidity, air quality, and air pressure of the target space. The control unit (111) can train a machine learning model (113) based on the environmental information, and can control the output, wind direction, wind speed, operating time, etc. of the heating and cooling device (110) according to the heating and cooling needs predicted by the trained machine learning model (113).

[0039] The communication unit (112) can transmit and receive data between the heating and cooling device (110) and the sensor unit (120) or an external device. The communication unit (112) can transmit and receive environmental information, zone information, and predicted heating and cooling needs through wireless or wired communication methods.

[0040] The machine learning model (113) can learn environmental information of the target space and predict the need for heating and cooling according to the control of the control unit (111). The machine learning model (113) can learn the optimal control method for the heating and cooling device (110) by setting environmental information as an input variable and information on the operation method of the heating and cooling device as an output variable, for example. The machine learning model (113) can be implemented in various structures, such as a multilayer perceptron (MLP), a convolutional neural network (CNN), or a recurrent neural network (RNN), for example. In addition, the machine learning model (113) can use various learning methods, such as supervised learning that learns the need for heating and cooling based on existing environmental information and operation method data, reinforcement learning that learns the optimal heating and cooling method by setting the operation results of the heating and cooling device as a reward value, and unsupervised learning that identifies characteristics by space by clustering environmental information.

[0041] The learned machine learning model (113) can predict the heating and cooling needs for each partitioned space based on environmental information and can transmit the heating and cooling needs for each partitioned space to the control unit (111).

[0042] The sensor unit (120) may include a first sensor (121), a second sensor (122), and a third sensor (123). The sensor unit (120) may collect environmental information of a target space and provide the collected environmental information to the communication unit (112) of the heating and cooling device (110).

[0043] The first sensor (121) may, for example, be a fixed sensor fixed at a certain location in the target space. For example, the first sensor (121) may be a temperature sensor, a humidity sensor, a pressure sensor, an air quality sensor for measuring fine dust, etc., a harmful gas detection sensor, etc. For example, the first sensor (121) may be installed on the ceiling or wall of the target space to generate environmental information about the indoor environment of the target space.

[0044] The second sensor (122) may, for example, be a movable sensor capable of moving within the target space. For example, the second sensor (122) may be a sensor included in an electronic product placed in the target space, such as an air purifier or a robot vacuum cleaner. The second sensor (122) can complementarily generate environmental information regarding the indoor environment of the target space that the first sensor (121) cannot cover, and can generate environmental information at various locations within the target space.

[0045] The third sensor (123) may, for example, be an attached sensor attached to the heating and cooling device (110). The third sensor (123) may, for example, be a sensor attached to the outside of the heating and cooling device (110) and may operate under the control of the control unit (111). The third sensor (123) may, for example, include an infrared sensor, a thermal imaging camera, etc. The third sensor (123) may use an infrared sensor or a thermal imaging camera to measure the temperature of an area that is difficult for the first sensor (121) and the second sensor (122) to measure, for example, a wall, a window, or a specific surface inside, or to analyze the temperature distribution of a partitioned space.

[0046] The sensor unit (120) can generate detailed and multifaceted information about the indoor environment of the target space by including various sensors such as fixed, mobile, and attached sensors. The heating and cooling device (110) can accurately predict the heating and cooling needs of multiple partitioned spaces compared to conventional technology by using the environmental information obtained from the sensor unit (120).

[0048] FIG. 2 is a flowchart illustrating the operation method of a heating and cooling system according to an embodiment of the present disclosure.

[0049] FIG. 2 can be described with reference to FIG. 1 described above. Referring to FIG. 2, a method of operation (S100) of a heating and cooling system may include the steps of: dividing a target space into a plurality of partitioned spaces (S110); generating environmental information for each of the plurality of partitioned spaces using at least one sensor (S120); training a machine learning model based on the environmental information (S130); predicting the heating and cooling needs for the plurality of partitioned spaces using the trained machine learning model (S140); and controlling a heating and cooling device according to the predicted heating and cooling needs (S150).

[0050] FIG. 2 illustrates steps S110 to S150 being performed sequentially, but is not limited thereto; some steps may be merged and performed simultaneously, some steps may be omitted, or new steps may be added.

[0051] In step S110, the target space can be divided into a plurality of partitioned spaces. In some embodiments, the control unit (111) can measure the size, shape, use, etc. of the target space through a third sensor (123) including an infrared sensor, a thermal imaging camera, etc., and can divide the target space into a plurality of partitioned spaces based on the measured information. In other embodiments, the control unit (111) can obtain map data including the size, shape, use, etc. of the target space from a second sensor (122), and can divide the target space into a plurality of partitioned spaces based thereon.

[0052] In step S120, environmental information for each of the multiple partitioned spaces can be generated using at least one sensor. For example, the sensor unit (120) can generate environmental information such as temperature, humidity, air quality, and atmospheric pressure of the target space through a fixed, mobile, or attached sensor.

[0053] In step S130, a machine learning model can be trained based on environmental information. For example, the machine learning model (113) can learn an optimal control method for the heating and cooling device (110) by setting environmental information as an input variable and information on the operation method of the heating and cooling device as an output variable.

[0054] In step S140, the need for heating and cooling for multiple partitioned spaces can be predicted using a trained machine learning model. For example, the machine learning model (113) trained in step S130 can predict the need for heating and cooling for each partitioned space based on environmental information obtained from the sensor unit (120).

[0055] In step S150, the heating and cooling device can be controlled according to the predicted heating and cooling needs. For example, the heating and cooling device (110) can provide heating and cooling optimized for the target space by adjusting the operating method (output, wind speed, wind direction, operating time, etc.) based on the heating and cooling needs obtained in step S140.

[0056] As described above, the method of operation (S100) of a heating and cooling system according to an embodiment of the present disclosure can increase the energy efficiency of the heating and cooling system by dividing a target space into three-dimensional partitioned spaces and learning environmental information such as temperature, humidity, and air quality of each partitioned space using a machine learning model, thereby providing heating and cooling optimized for the target space.

[0057] In addition, the method of operation (S100) of a heating and cooling system according to an embodiment of the present disclosure measures environmental information using various sensors including fixed sensors, mobile sensors, attached sensors, etc., and estimates environmental information regarding blind spots, thereby accurately predicting the need for heating and cooling compared to conventional technology.

[0059] FIG. 3 is a drawing showing a target space divided into a plurality of partitioned spaces according to an embodiment of the present disclosure.

[0060] FIG. 3 can be described with reference to FIG. 1 and FIG. 2 described above. Referring to FIG. 3, a heating and cooling system according to an embodiment of the present disclosure may include a heating and cooling device (210), a first fixed sensor (221A), a second fixed sensor (221B), a first movable sensor (222A), a second movable sensor (222B), and an attached sensor (223).

[0061] The heating and cooling device (210) may be fixed to one side of the target space (TS) as an example and may control the air flow (W) to provide heating and cooling optimized for the target space (TS).

[0062] The heating and cooling device (210) can divide the target space (TS) into a plurality of partitioned spaces. For example, the heating and cooling device (210) can divide the target space (TS) into a three-dimensional space with mutually orthogonal X-axis, Y-axis, and Z-axis. However, the technical concept of the present disclosure is not limited thereto, and the heating and cooling device (210) may also divide the target space (TS) into a two-dimensional space.

[0063] FIG. 3 illustrates a case where the target space (TS) is divided into 12 partitioned spaces (R11 to R34) for convenience of explanation. Specifically, FIG. 3 illustrates a case where the target space (TS) is divided into 4 spaces along the Y-axis and 3 spaces along the Z-axis. However, this is merely an example, and the heating and cooling device (210) can divide the target space (TS) in various ways considering the size, shape, and use of the target space (TS).

[0064] The target space (TS) may include objects (OB), such as indoor furniture and home appliances, and the heating and cooling device (210) can train a machine learning model by considering the arrangement of the objects (OB). For example, the heating and cooling device (210) can train a machine learning model so that heating and cooling are provided intensively to the objects (OB), or conversely, so that heating and cooling are provided intensively to the space outside the objects (OB). The heating and cooling device (210) can provide heating and cooling intensively to the space where people mainly work or the space where a heat source is located, or to minimize heating and cooling in unused areas to reduce unnecessary energy consumption.

[0065] The first fixed sensor (221A) can be fixed to the ceiling of the target space (TS) and can generate environmental information of the target space (TS). For example, the first fixed sensor (221A) can collect air quality or atmospheric pressure information of the target space (TS).

[0066] The second fixed sensor (221B) can be fixed to the wall of the target space (TS) and can generate environmental information of the target space (TS). For example, the second fixed sensor (221B) can collect temperature or humidity information of the target space (TS).

[0067] The first mobile sensor (222A) can be included in an air purifier and can collect air quality or temperature information of the target space (TS).

[0068] The second mobile sensor (222B) can move within the target space (TS) and can collect environmental information at various locations within the target space (TS). The second mobile sensor (222B) can be included in a robot vacuum cleaner and can collect environmental information such as floor temperature and humidity of the target space (TS).

[0069] The attached sensor (223) is attached to the heating and cooling device (210) and may include an infrared sensor, a thermal imaging camera, etc. The attached sensor (223) can measure the temperature distribution of specific areas such as walls, windows, and furniture surfaces of the target space (TS), or visually analyze temperature changes within the partitioned space.

[0071] FIG. 4 is a diagram illustrating a method for an attached sensor to acquire environmental information for a plurality of partitioned spaces according to an embodiment of the present disclosure.

[0072] FIG. 4 can be explained with reference to FIG. 1 to FIG. 3 described above. Content in FIG. 4 that overlaps with FIG. 3 will be omitted.

[0073] Referring to FIG. 4, the attached sensor (223) can, for example, set reference points (P11, P12, P14, P31, P33) for temperature measurement in partitioned spaces (R11, R12, R14, R21, R22, R23, R33) that are adjacent to the floor, ceiling, and wall of the target space (TS) among the partitioned spaces (R11, R12, R14, R31, R33) that do not include the first fixed sensor (221A), the second fixed sensor (221B), the first movable sensor (222A), and the second movable sensor (222B), and are within the measurable range of the attached sensor (223). An attached sensor (223) can obtain temperature information for partitioned spaces (R11, R12, R14, R31, R33) containing reference points (P11, P12, P14, P31, P33) by, for example, irradiating infrared light (IR) onto each of the reference points (P11, P12, P14, P31, P33) and then detecting the infrared radiation energy reflected from each of the reference points (P11, P12, P14, P31, P33).

[0074] The heating and cooling device (210) can generate temperature information for compartment spaces (R21, R22, R23) that are difficult to measure temperature for because they are not adjacent to the floor, ceiling, or wall surface of the target space (TS) or are not within the measurable range of the attached sensor (223), based on the temperature information of the compartment spaces adjacent to the said compartment space.

[0075] For example, the heating and cooling device (210) can generate temperature information for the R22 partition space by applying interpolation to the temperature information for the R12 space and the R32 space, which are adjacent spaces to the R22 space. For example, the heating and cooling device (210) may use linear interpolation, which assumes that the temperatures of the R12 space, the R22 space, and the R32 space will change linearly, or inverse distance weighting, which weights the inverse of the distance from the R22 space.

[0076] The heating and cooling device (210) can generate temperature information for partitioned spaces (R21, R22, R23) where temperature measurement is difficult by using interpolation.

[0078] FIG. 5 is a drawing showing map data according to an embodiment of the present disclosure.

[0079] FIG. 5 can be explained with reference to FIG. 1 to FIG. 4 described above.

[0080] Referring to FIG. 5, the target space (TS) may include a first object (OB1), a second object (OB2), and a third object (OB3). As illustrated in FIG. 3, the second movable sensor (222B) can move in various directions within the target space (TS) and can generate map data including the size, shape, etc. of the target space (TS). The map data can be used by the heating and cooling device (210) to divide the target space (TS) into a plurality of partitioned spaces.

[0082] FIG. 6 is a flowchart illustrating a method of dividing a target space into a plurality of partitioned spaces according to an embodiment of the present disclosure.

[0083] FIG. 6 can be described with reference to FIG. 1 to FIG. 5. Referring to FIG. 6, a method (S210) for dividing a target space into a plurality of partitioned spaces may include the step of obtaining map data for the target space from at least one sensor (S211), the step of obtaining partition information including at least one of the size, shape, and use of the target space based on the map data (S212), and the step of dividing the target space into a plurality of partitioned spaces based on the partition information (S213). The method (S210) for dividing a target space into a plurality of partitioned spaces illustrated in FIG. 6 may, for example, correspond to step S110 of FIG. 2.

[0084] FIG. 6 illustrates steps S211 to S213 being performed sequentially, but is not limited thereto; some steps may be merged and performed simultaneously, some steps may be omitted, or new steps may be added.

[0085] In step S211, map data for the target space can be obtained from at least one sensor. For example, a second mobile sensor (222B) can obtain map data for the target space (TS) by moving through the target space (TS) and collecting data regarding distance, size, and obstacles.

[0086] In step S212, partition information including at least one of the size, shape, and use of the target space can be obtained based on map data. For example, the heating and cooling device (210) can set a space of a specific size or shape in the map data as a partition standard. For example, partition information for the target space (TS) can be obtained according to the use of the space.

[0087] In step S213, the target space can be divided into multiple partitioned spaces based on partition information. For example, the heating and cooling device (210) can divide the target space (TS) three-dimensionally in the X-axis, Y-axis, and Z-axis directions, or two-dimensionally as needed.

[0089] FIG. 7 is a flowchart illustrating a method for generating environmental information for a plurality of partitioned spaces according to an embodiment of the present disclosure.

[0090] FIG. 7 can be described with reference to FIG. 1 through 6 described above. Referring to FIG. 7, a method (S220) for generating environmental information for a plurality of partitioned spaces may include a step (S221) of generating first environmental information for a first partitioned space using a first sensor, a step (S222) of generating second environmental information for a second partitioned space using a second sensor, and a step (S223) of generating environmental information for a third partitioned space based on the first environmental information and the second environmental information. The method (S220) for generating environmental information for a plurality of partitioned spaces illustrated in FIG. 7 may, for example, correspond to step S120 of FIG. 2.

[0091] FIG. 7 illustrates steps S221 to S223 being performed sequentially, but is not limited thereto; some steps may be merged and performed simultaneously, some steps may be omitted, or new steps may be added.

[0092] In step S221, first environmental information for the first compartment space can be generated using the first sensor. For example, the first fixed sensor (221A) can measure the temperature and humidity of the first compartment space.

[0093] In step S222, second environmental information for the second compartment space can be generated using the second sensor. For example, the second mobile sensor (222B) can be mounted on a robot vacuum cleaner or the like to collect air quality information on the floor or under furniture.

[0094] In step S223, environmental information for the third compartment space can be generated based on the first environmental information and the second environmental information. For example, the heating and cooling device (210) can generate environmental information for the third compartment space by applying linear interpolation or inverse distance weighting, etc., based on the compartment space information obtained in the adjacent steps S221 and S222.

[0096] FIG. 8 is a flowchart illustrating a method for training a machine learning model according to an embodiment of the present disclosure.

[0097] FIG. 8 can be described with reference to FIG. 1 to FIG. 7. Referring to FIG. 8, a method for training a machine learning model (S230) may include the step of obtaining environmental information for each of a plurality of partitioned spaces (S231), the step of obtaining information on the operation method of a heating and cooling device (110) (S232), and the step of training a machine learning model by setting the environmental information as an input variable and the operation method information as an output variable (S233).

[0098] The method (S230) for training a machine learning model illustrated in FIG. 8 may, for example, correspond to step S130 of FIG. 2.

[0099] FIG. 8 illustrates steps S231 to S233 being performed sequentially, but is not limited thereto; some steps may be merged and performed simultaneously, some steps may be omitted, or new steps may be added.

[0100] In step S231, environmental information for each of the multiple partitioned spaces can be obtained. For example, the sensor unit (120) can collect temperature, humidity, and air quality data for the partitioned spaces of the target space (TS) and provide them to the control unit (111).

[0101] In step S232, information on the operation method of the heating and cooling device (110) can be obtained. For example, the control unit (111) can obtain data such as output, wind speed, wind direction, and operating time while the heating and cooling device (110) is in operation, or can store information on the operation method of the heating and cooling device (110) when the heating and cooling device (110) is manufactured.

[0102] In step S233, a machine learning model can be trained by setting environment information as an input variable and operation method information as an output variable. For example, the machine learning model (113) can learn the correlation between environment information and operation method by using a convolutional neural network (CNN), for instance.

[0104] The above descriptions are specific embodiments for carrying out the present disclosure. The present disclosure will include not only the embodiments described above, but also embodiments that are simply modified or can be easily modified. Furthermore, the present disclosure will include technologies that can be easily modified and implemented using the embodiments described above. Accordingly, the scope of the present disclosure should not be limited to the embodiments described above, but should be defined by the claims set forth below as well as equivalents to the claims of the present disclosure.

Claims

Claim 1 A method of operating a heating and cooling system comprising: a step of dividing a target space into a plurality of partitioned spaces; a step of generating environmental information for each of the plurality of partitioned spaces using at least one sensor; a step of training a machine learning model based on the environmental information; a step of predicting the heating and cooling needs for the plurality of partitioned spaces using the trained machine learning model; and a step of controlling the operation method of a heating and cooling device according to the predicted heating and cooling needs. Claim 2 A method of operation of a heating and cooling system according to claim 1, wherein the step of dividing the target space into a plurality of partitioned spaces comprises: a step of obtaining map data for the target space from at least one sensor; a step of obtaining partition information including at least one of the size, shape, and use of the target space based on the map data; and a step of dividing the target space into the plurality of partitioned spaces based on the partition information. Claim 3 A method of operation of a heating and cooling system according to claim 1, wherein the step of generating environmental information comprises: generating first environmental information for a first partition space using a first sensor; generating second environmental information for a second partition space using a second sensor; and generating third environmental information for a third partition space based on the first environmental information and the second environmental information. Claim 4 A method of operation of a heating and cooling system according to claim 3, wherein each of the first sensor and the second sensor comprises at least one of a fixed sensor fixed at a certain position in the target space, a movable sensor movable within the target space, and an attached sensor attached to the heating and cooling device. Claim 5 A method of operation of a heating and cooling system according to claim 3, wherein each of the first sensor and the second sensor generates at least one of the temperature, humidity, air quality, and atmospheric pressure of the target space as the first environmental information and the second environmental information. Claim 6 A method of operation of a heating and cooling system according to claim 1, wherein the step of training the machine learning model comprises: a step of obtaining environmental information for each of the plurality of partitioned spaces; a step of obtaining information on the operating method of the heating and cooling device; and a step of training the machine learning model by setting the environmental information as an input variable and setting the operating method information as an output variable. Claim 7 In claim 6, the above-mentioned operating method information includes at least one of the output, wind speed, wind direction, and operating time of the above-mentioned heating and cooling device, a method of operating a heating and cooling system. Claim 8 A heating and cooling system comprising: a sensor unit disposed in a target space divided into a plurality of partitioned spaces and generating environmental information for each of the plurality of partitioned spaces; and a heating and cooling device whose operation method is adjusted according to a predicted heating and cooling need, wherein the heating and cooling device comprises a control unit that divides the target space into a plurality of partitioned spaces, trains a machine learning model based on the environmental information, and controls the heating and cooling device according to the heating and cooling need predicted by the trained machine learning model. Claim 9 A heating and cooling system according to claim 8, wherein the heating and cooling device communicates with the sensor unit and further comprises a communication unit that acquires environmental information from the sensor unit. Claim 10 A heating and cooling system according to claim 8, wherein the control unit acquires map data for the target space from the sensor unit, acquires partition information including at least one of the size, shape, and use of the target space based on the map data, and partitions the target space into the plurality of partition spaces based on the partition information. Claim 11 In claim 8, the sensor unit comprises a first sensor that generates first environmental information for a first partition space and a second sensor that generates second environmental information for a second partition space, and the control unit generates third environmental information for a third partition space based on the first environmental information and the second environmental information, a heating and cooling system. Claim 12 A heating and cooling system according to claim 11, wherein each of the first sensor and the second sensor comprises at least one of a fixed sensor fixed at a certain position in the target space, a movable sensor movable within the target space, and an attached sensor attached to the heating and cooling device. Claim 13 A heating and cooling system according to claim 11, wherein each of the first sensor and the second sensor generates at least one of the temperature, humidity, air quality, and atmospheric pressure of the target space as the first environmental information and the second environmental information. Claim 14 A heating and cooling system according to claim 8, wherein the control unit acquires environmental information for each of the plurality of partitioned spaces from the sensor unit, acquires information on the operation method of the heating and cooling device from the heating and cooling device, sets the environmental information as an input variable, and sets the operation method information as an output variable to train the machine learning model. Claim 15 In claim 14, the above-mentioned operating method information comprises at least one of the output, wind speed, wind direction, and operating time of the above-mentioned heating and cooling device, a heating and cooling system.

Images