Electronic device and method for controlling electronic device

Abstract

An electronic device and a method for controlling the same are disclosed. In detail, an electronic device according to the present disclosure includes: at least one memory storing information related to a first neural network model trained to predict an operation of a refrigerator, and information related to a second neural network model trained to obtain information related to defrosting of the refrigerator; and at least one processor obtaining first data for an operation history of the refrigerator; inputting the first data into a first neural network model to obtain second data of a prediction result for future operation of the refrigerator from the first neural network model; and inputting the second data to the second neural network model to obtain third data from the second neural network model, the third data including information on a degree of frosting when the refrigerator is operated according to the second data and information for controlling a defrosting operation of the refrigerator. Various other embodiments are also possible.

Description

Technical Field

[0001] The present disclosure relates to an electronic device and a control method of the electronic device, and more particularly, to an electronic device for preventing excessive frost in a refrigerator and optimizing a defrosting operation of the refrigerator and a control method thereof. Background Art

[0002] Recently, with the rapid development of artificial intelligence (AI) technology, the technology is being applied to various industrial fields. Specifically, with the combination of AI technology and refrigerator-related technologies, refrigerators of the prior art have gone beyond their existing functions focusing on food preservation and are able to serve as hub devices for Internet of Things (IoT) functions within the home. In addition, as various refrigerator functions other than food preservation are automated and made more efficient, user convenience is improving.

[0003] The refrigerator performs an operation of lowering the temperature inside the refrigerator by using an evaporator, and during this process, frost may be generated due to the freezing of moisture near the evaporator to the surface of the evaporator, and the frost may cause a decrease in refrigerator efficiency. Accordingly, although the refrigerator can perform a defrosting operation for removing the generated frost, based on the prior art, there is still a limitation in effectively removing the frost while maintaining high efficiency of the refrigerator.

[0004] Specifically, in a refrigerator, since frost is generated by various factors of the surrounding environment (external temperature, internal temperature, humidity, etc.), the amount of frost and the speed of frost formation may vary from refrigerator to refrigerator. When the defrost cycle of a refrigerator is too short, the efficiency of the refrigerator may decrease and the power consumption may increase. On the other hand, when the defrost cycle is too long, since the frost cannot be effectively removed, the thickened frost may wrap around the evaporator, resulting in the problem of deterioration of the cooling function and reduced energy efficiency. Summary of the invention

Technical solution

[0005] An electronic device and a control method of the electronic device are provided, which can prevent a decrease in efficiency of a refrigerator by preventing excessive frost in the refrigerator while optimizing a defrosting operation.

[0006] Additional aspects will be set forth in part in the description which follows and, in part, will be apparent from the description, or may be learned by practice of the presented embodiments.

[0007] According to one aspect of the present disclosure, an electronic device includes: at least one memory configured to store information of a first neural network model trained to predict the operation of a refrigerator, and information of a second neural network model trained to obtain information associated with the defrosting of the refrigerator; and at least one processor configured to: obtain first data related to the operation history of the refrigerator; input the first data to the first neural network model, and obtain second data related to the prediction result for the future operation of the refrigerator from the first neural network model; and input the second data to the second neural network model, and obtain third data from the second neural network model, the third data including information related to the degree of frost based on performing the operation of the refrigerator according to the second data, and information related to controlling the defrost operation of the refrigerator.

[0008] The electronic device may further include a communicator, and the at least one processor may further be configured to: based on obtaining third data from the second neural network model, control the communicator to send the third data to the refrigerator as an instruction for the refrigerator to perform a defrost operation according to the third data.

[0009] The information related to controlling the defrost operation of the refrigerator may include information related to a cycle of the defrost operation, information related to a duration of the defrost operation of each cycle, and information related to an intensity of the defrost operation of each cycle.

[0010] At least one processor may also be configured to obtain fourth data by changing information related to the cycle of the defrost operation in the third data to a threshold value based on the cycle of the defrost operation according to information related to controlling the defrost operation being less than a threshold value, and control the communicator to send the fourth data to the refrigerator.

[0011] The at least one processor may also be configured to obtain information related to at least one cause associated with decreased efficiency of the refrigerator based on the first data, and control the communicator to send information related to a guidance message corresponding to the at least one cause to the refrigerator.

[0012] At least one processor may be configured to identify information related to at least one cause based on at least one of information related to the temperature range of the refrigerator, information related to the number of times a door of the refrigerator is opened and closed, information related to the difference between a maximum temperature inside the refrigerator and a control temperature, or information related to an outdoor temperature of the refrigerator, and the first data may include information related to the temperature range of the refrigerator.

[0013] The first data may include information related to the revolutions per minute (RPM) of the refrigerator's fan, power consumption information of the refrigerator's compressor, and temperature information inside the refrigerator, and the first neural network model is trained to obtain the second data based on the first data, data related to the surrounding environment of the refrigerator, and information related to the user of the refrigerator.

[0014] The second data may include a first predicted value of the RPM of the fan, a second predicted value of the compressor power consumption, and a third predicted value of the temperature inside the refrigerator, and the second neural network model is trained to obtain information related to the degree of excessive frosting based on the first predicted value, the second predicted value, and the third predicted value.

[0015] The first neural network model and the second neural network model can be implemented as an integrated neural network model, and the integrated neural network model is trained according to an end-to-end learning method to obtain third data based on the first data.

[0016] The electronic device and the refrigerator may be implemented as an integrated device, and the at least one processor may be further configured to: obtain third data from the second neural network model, and perform a defrost operation of the refrigerator based on the third data.

[0017] According to one aspect of the present disclosure,

[0018] A method for controlling an electronic device includes: obtaining first data related to an operation history of a refrigerator; obtaining second data related to a prediction result for future operation of the refrigerator based on inputting the first data into a first neural network model trained to predict the operation of the refrigerator; and obtaining third data based on inputting the second data into a second neural network model trained to obtain information associated with defrosting of the refrigerator, the third data including information related to a degree of frost based on performing refrigerator operations according to the second data, and information related to controlling the defrost operation of the refrigerator.

[0019] The method may further include: based on obtaining third data from the second neural network model, sending the third data to the refrigerator as an instruction for the refrigerator to perform a defrost operation according to the third data.

[0020] The information related to controlling the defrost operation of the refrigerator may include information related to a cycle of the defrost operation, information related to a duration of the defrost operation of each cycle, and information related to an intensity of the defrost operation of each cycle.

[0021] The method may further include: obtaining fourth data by changing information related to the cycle of the defrost operation in the third data to a threshold value based on the cycle of the defrost operation (which is based on information related to controlling the defrost operation) being less than a threshold value; and transmitting the fourth data to the refrigerator.

[0022] The method may further include obtaining information related to at least one cause associated with a decrease in efficiency of the refrigerator based on the first data, and transmitting information related to a guide message corresponding to the at least one cause to the refrigerator.

[0023] According to one aspect of the present disclosure, a non-transitory computer-readable recording medium stores a program executed by at least one processor of an electronic device to perform a method of controlling the electronic device, the method including: obtaining first data related to an operation history of a refrigerator; obtaining second data related to a prediction result for future operation of the refrigerator based on inputting the first data into a first neural network model trained to predict the operation of the refrigerator; and obtaining third data based on inputting the second data into a second neural network model trained to obtain information associated with defrosting of the refrigerator, the third data including information related to a degree of frost based on performing refrigerator operation according to the second data, and information related to controlling the defrost operation of the refrigerator. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The above and other aspects, features and advantages of specific embodiments of the present disclosure will become more apparent from the following description with reference to the accompanying drawings, in which:

[0025] Figure 1 is a flowchart showing a control method of an electronic device according to an embodiment;

[0026] Figure 2 is a flowchart showing a control method of an electronic device according to an embodiment;

[0027] Figure 3 is a flowchart showing a control method of an electronic device according to an embodiment;

[0028] Figure 4 is an example diagram showing a user interface according to an embodiment;

[0029] Figure 5 is a block diagram briefly showing a configuration of an electronic device according to an embodiment; and

[0030] Figure 6 is a block diagram showing in detail the configuration of an electronic device according to an embodiment. DETAILED DESCRIPTION

[0031] The terms used in the specification will be briefly explained, and then the present disclosure will be described in detail.

[0032] Although the terms used in the embodiments of the present disclosure are selected from the general terms widely used at present, considering their functions in the present disclosure, these terms can be changed according to the intentions of those skilled in the art, precedents and the emergence of new technologies. In addition, in some cases, the applicant can arbitrarily select some terms. In this case, the meaning of these terms will be explained in detail in the corresponding part of the description of the present disclosure. Therefore, the terms used in the present disclosure should be defined based on their meanings and the overall content of the present disclosure, rather than simply defined based on the names of these terms.

[0033] Various modifications may be made to the embodiments of the present disclosure, and various types of embodiments may exist. Accordingly, specific embodiments will be shown in the drawings, and these embodiments will be described in detail in the detailed description. However, it should be noted that the various embodiments are not intended to limit the scope of the present disclosure to specific embodiments, but should be interpreted as including all modifications, equivalents or alternatives of the embodiments disclosed herein. When describing the embodiments, the same reference numerals may be used to refer to the same elements.

[0034] In cases where it is determined that a detailed description of related known technologies may unnecessarily obscure the gist of the present disclosure when describing the embodiments, the detailed description will be omitted.

[0035] In addition, the following embodiments can be modified into various forms, and it should be understood that the scope of the technical spirit of the present disclosure is not limited to the following embodiments. On the contrary, the embodiments are provided so that the present disclosure will be comprehensive and complete, and the technical spirit of the present disclosure will be fully conveyed to those skilled in the art.

[0036] The terms used herein are only used to describe a particular embodiment, and do not limit the scope of another embodiment.Unless otherwise specified, a singular expression includes a plural expression.

[0037] In the present disclosure, expressions such as “having”, “may have”, “including”, “may include”, etc. are used to specify the existence of corresponding characteristics (for example, elements such as values, functions, operations or components) without excluding the existence or possibility of additional characteristics.

[0038] In the present disclosure, expressions such as "A or B", "at least one of A and / or B", or "one or more of A and / or B" may include all possible combinations of the items listed together. For example, "A or B", "at least one of A and B", or "at least one of A or B" may refer to all cases including (1) only A, (2) only B, or (3) both A and B.

[0039] As used herein, expressions such as "first", "second", "first", "second", etc. may be used to refer to various elements, regardless of order and / or importance. In addition, it should be noted that these expressions are only used to distinguish one element from another element, without limiting the relevant elements.

[0040] When an element (for example, a first element) is indicated as being “(operably or communicatively) coupled with / to” or “connected to” another element (for example, a second element), it may be understood that the element is directly coupled with / to the other element or coupled through other elements (for example, a third element).

[0041] On the other hand, when an element (for example, a first element) is indicated as being “directly coupled with / coupled to” or “directly connected to” another element (for example, a second element), it can be understood that there are no other elements (for example, a third element) between the certain element and the other element.

[0042] The expression "configured to ..." (or set to )" used in the present disclosure may be used interchangeably with, for example, "suitable for ...", "capable of ...", "designed to ...", "suitable for ...", "made for ...", or "capable of ..." depending on the situation. The term "configured to ..." (or set to )" may not necessarily mean "specially designed to" in terms of hardware.

[0043] On the contrary, in certain cases, the expression "a device configured to..." may mean that the device "may" "perform..." together with another device or component. For example, the phrase "a subprocessor configured to (or set to) perform A, B, or C" may mean a dedicated processor (e.g., an embedded processor) for performing the corresponding operation, or a general-purpose processor (e.g., a central processing unit (CPU) or an application processor) capable of performing the corresponding operation by executing one or more software programs stored in a storage device.

[0044] The term "module" or "component" used in the embodiments herein performs at least one function or operation and can be implemented by hardware or software, or by a combination of hardware and software. In addition, multiple "modules" or multiple "components" other than the "module" or "component" that needs to be implemented as specific hardware can be integrated into at least one module and implemented in at least one processor.

[0045] The various elements and regions in the drawings have been schematically shown. Accordingly, the embodiments of the present disclosure are not limited by the relative sizes and distances shown in the drawings.

[0046] Embodiments according to the present disclosure will be described in detail below with reference to the accompanying drawings to help those skilled in the art understand.

[0047] Figure 1 is a flowchart illustrating a control method of the electronic device 100 according to an embodiment.

[0048] The electronic device 100 according to the embodiment may refer to a device that can predict the operation of a refrigerator and obtain information for controlling the defrost operation of the refrigerator. The electronic device 100 according to the embodiment may be implemented as a server as a device separate from the refrigerator, and in this case, the electronic device 100 may obtain information for controlling the defrost operation of the refrigerator, and control the defrost operation to be performed by the refrigerator by sending the obtained information to the refrigerator. The electronic device 100 may be implemented as a device integrated with the refrigerator, and in this case, the electronic device 100 may obtain information for controlling the defrost operation of the refrigerator, and control the defrost operation of the refrigerator based on the obtained information.

[0049] In other words, the electronic device 100 according to the embodiment can be implemented not only as a device separated from the refrigerator, but also as the refrigerator itself. Accordingly, the following description by distinguishing the electronic device 100 from the refrigerator is only for the convenience of description, and does not necessarily mean that the electronic device 100 according to the embodiment can only be implemented as a separate device distinguished from the refrigerator.

[0050] The refrigerator can keep food at a low temperature by continuously repeating the generation of cold air by compressing, condensing, expanding, and evaporating the refrigerant. Specifically, when the refrigerant in a compressed liquid state passes through the evaporator of the refrigerator, the refrigerant can absorb heat energy as the refrigerant evaporates according to the pressure difference, and accordingly, the temperature inside the refrigerator can be reduced. In addition, because the refrigerant lowers its temperature as the refrigerant passes through the evaporator, the moisture around the evaporator may freeze and form frost on the surface of the evaporator, and the refrigerator can periodically perform a defrost operation to remove the generated frost. In the present disclosure, the term "defrost operation" may be replaced with terms such as, for example, but not limited to, a defrost process, a defrost step, and the like.

[0051] In a refrigerator, since frost is generated as a function of various factors of the surrounding environment (external temperature, internal temperature, humidity, etc.), the amount of frost and the speed of formation may vary depending on each refrigerator. However, when the defrost cycle of a refrigerator is too short, the efficiency of the refrigerator may decrease and power consumption may increase. On the other hand, when the defrost cycle is too long, since the frost cannot be effectively removed, thick frost may wrap around the evaporator, resulting in a decrease in cooling function and a decrease in energy efficiency.

[0052] Accordingly, because it is necessary to predict the frost in the refrigerator in advance and optimize the defrost cycle, the following will refer to Figure 1 Embodiments of the present disclosure are described.

[0053] like Figure 1 As shown, the electronic device 100 according to the embodiment may obtain first data representing an operation history of a refrigerator ( S110 ).

[0054] In describing the present disclosure, the term "first data" may be used as a term to collectively refer to data representing the operation history of a refrigerator. Specifically, the operation history of a refrigerator may include parameters associated with the operation of the refrigerator, data representing the state of the refrigerator when the refrigerator is operated, and the like. Then, the operation history of the refrigerator may include the operation history from the past to the current time point, and whether to include data until a random time point in the past into the first data may vary according to the embodiment.

[0055] For example, the first data may include at least one of information about the revolutions per minute (RPM) of a fan included in the refrigerator, information about the power consumption of a compressor included in the refrigerator, and information about the temperature inside the refrigerator. In addition, the first data may also include information about the number of times a door of the refrigerator is opened and closed, and at least one of information such as a sensed value of a sensor inside the refrigerator, a sensed value of a defrost sensor of the refrigerator, etc. In addition, in addition to the above examples, as long as it is data representing the operation history of the refrigerator, the data may be included in the first data.

[0056] The electronic device 100 may input the first data to the first neural network model and obtain second data representing a prediction result for future operation of the refrigerator ( S120 ).

[0057] The first neural network model may refer to a neural network model trained to obtain a prediction result for the future operation of the refrigerator. Specifically, if the first data is input to the first neural network model, the first neural network model may be trained to output a prediction result for whether the refrigerator will perform any operation in the future based on the operation history of the refrigerator included in the first data. The operation at which point in time in the future is predicted may vary according to the embodiment.

[0058] In describing the present disclosure, the term "second data" may be used as a term to collectively refer to data representing a prediction result for refrigerator operation. Specifically, data such as a prediction result for refrigerator operation or an operation history of the refrigerator, parameters associated with the operation of the refrigerator, refrigerator state data representing the operation of the refrigerator, etc. may be included in the second data.

[0059] For example, the second data may include at least one of a first predicted value for the RPM of a fan included in the refrigerator, a second predicted value for power consumption of a compressor included in the refrigerator, and a third predicted value for the internal temperature of the refrigerator.

[0060] That is, the first data may be data representing the operation history from the past to the current time point, and the second data may be prediction data for the future based on the first data. The two differ in the time point of obtaining, but the first data and the second data are similar in that they basically both include parameters associated with the operation of the refrigerator, and state data representing the refrigerator when the refrigerator is operated. However, the first data and the second data do not necessarily include the same type of information, and the information included in the first data may not be included in the second data, and the information included in the second data may not be included in the first data.

[0061] According to an embodiment, the first neural network model may be trained to obtain second data based on data related to the surrounding environment of the refrigerator together with the first data and information related to the user of the refrigerator. For example, the data related to the surrounding environment may include information related to the temperature, humidity, location, etc. around the refrigerator, and the information related to the user may include user personal profile information, information related to the user's usage history, etc.

[0062] The electronic device 100 may input the second data to the second neural network model and obtain third data including information on the degree of frost when the refrigerator operation is performed according to the second data and information for controlling the defrosting operation of the refrigerator (S130).

[0063] The second neural network model may refer to a neural network model trained to obtain information associated with the defrost operation of the refrigerator. Specifically, when the second data according to the output of the first neural network model is input to the second neural network model, the second neural network model may be trained to obtain third data based on the correlation between various parameters included in the second data and the evaporator of the refrigerator, the third data including: information related to the degree of frost on the evaporator, and information for controlling the defrost operation of the refrigerator.

[0064] According to an embodiment, the second neural network model may be trained to obtain information related to the degree of excessive frosting based on the first prediction value, the second prediction value, and the third prediction value as described above.

[0065] According to an embodiment, the second neural network model may be trained to obtain only information related to the degree of frost, and the electronic device 100 may obtain information for controlling the defrost operation of the refrigerator based on the information related to the degree of frost obtained by the second neural network model.

[0066] In describing the present disclosure, the term "third data" may be used as a term to collectively refer to data associated with the defrosting operation of the refrigerator. Specifically, the third data may include at least one of information related to the degree of frost and information for controlling the defrosting operation.

[0067] Here, the information about the degree of frosting may include information about the amount of frost formed with respect to the evaporator of the refrigerator and information about the result of determining whether there is excessive frost with respect to the evaporator.

[0068] The information for controlling the defrost operation of the refrigerator may include at least one of information related to the cycle of the defrost operation (defrost operation cycle), information related to the duration of the defrost operation of each defrost cycle, and information related to the intensity of the defrost operation of each defrost cycle. Here, the information related to the duration of the defrost operation of each defrost cycle may refer to information related to the length of the interval in which each defrost operation is performed when the defrost operation is performed in each cycle, and the information related to the intensity of the defrost operation of each defrost cycle may refer to information used to determine parameters for forming each defrost operation when the defrost operation is performed in each cycle.

[0069] In the above, the first data and the second data have been described as being input to the first neural network model and the second neural network model, respectively, but specifically, the first data and the second data may be input to the first neural network model and the second neural network model after being respectively converted into feature values ​​(vectors) corresponding thereto. In addition, the first data and the second data may be input to the first neural network model and the second neural network model after performing a preprocessing process such as processing, deleting, and extracting data on the first data and the second data.

[0070] In the above, the first neural network model and the second neural network model have been described under the assumption that they are implemented as separate neural network models, but this is only one embodiment, and the first neural network model and the second neural network model may be implemented as an integrated neural network model, and in this case, the integrated neural network model may be trained according to an end-to-end learning method to obtain third data based on the first data.

[0071] As described above, when the third data is obtained, the electronic device 100 can directly or indirectly control the defrost operation of the refrigerator by using the third data. Specifically, if the electronic device 100 and the refrigerator are implemented as separate devices, the electronic device 100 can send the third data to the refrigerator so that the refrigerator performs a defrost operation according to the third data. If the electronic device 100 and the refrigerator are implemented as one device, the electronic device 100 can control the defrost operation of the refrigerator based on the third data. If the electronic device 100 and the refrigerator are implemented as one device, the first neural network model and the second neural network model can be implemented in the electronic device 100 in an on-device form.

[0072] According to the above-described embodiment, the electronic device 100 can prevent excessive frost in the refrigerator while preventing the efficiency of the refrigerator from being reduced by optimizing the defrosting operation.

[0073] Figure 2 is a flowchart illustrating a control method of the electronic device 100 according to an embodiment.

[0074] exist Figure 1 In the description of , the following embodiment has been described: information related to the defrost cycle of the refrigerator is obtained based on the third data as the output of the second neural network model, and the defrost cycle of the refrigerator is controlled based on the information related to the defrost cycle. However, if according to Figure 1 If the defrost cycle determined by the embodiment is too short, the efficiency of the refrigerator may be greatly reduced due to excessive and frequent execution of the defrost operation.

[0075] Accordingly, according to an embodiment, the electronic device 100 may set a threshold for the defrost cycle, and when the defrost cycle determined based on the third data is less than the threshold, the defrost cycle of the refrigerator is limited to the threshold. Figure 2 Embodiments that consider thresholds for defrost cycles are described. Figure 2 When describing the electronic device 100 and the refrigerator, for ease of description, the electronic device 100 and the refrigerator will be described as being implemented as separate devices, but it should be understood that the features of such an embodiment can be implemented by the electronic device 100 and the refrigerator as one device.

[0076] like Figure 2 As shown, when the third data (S210) is obtained, the electronic device 100 can identify whether the defrost operation cycle is less than a preset threshold (S220). Specifically, the electronic device 100 can identify the defrost operation cycle of the electronic device 100 included in the third data, and identify whether the identified defrost operation cycle is less than a preset threshold. Here, the preset threshold may refer to a defrost cycle value set by a developer or a user, and may be changed according to the embodiment.

[0077] If the defrost operation cycle is identified as being greater than or equal to the preset threshold (S220-N), the electronic device 100 may transmit the third data to the refrigerator (S230). Then, based on the above, the refrigerator may perform the defrost operation according to the third data.

[0078] On the other hand, if the defrost operation cycle is identified as being less than the preset threshold value (S220-Y), the electronic device 100 may obtain fourth data (S240) by changing the information related to the defrost operation cycle to the threshold value. That is, when describing the present disclosure, the term "fourth data" may be used to refer to data generated by replacing the defrost operation cycle with the threshold value among the information included in the third data, and the remaining information to be retained.

[0079] When obtaining the fourth data, the electronic device 100 may obtain fifth data including information related to at least one cause associated with the decrease in refrigerator efficiency based on the first data (S250). Specifically, the electronic device 100 may identify information related to at least one cause based on at least one of the following: information related to the temperature range of the refrigerator included in the first data, information related to the number of times the door of the refrigerator is opened and closed, information related to the difference between the maximum temperature inside the refrigerator and the control temperature, and information related to the outdoor temperature of the refrigerator.

[0080] Here, information related to the reasons associated with the decrease in refrigerator efficiency may include: information that the temperature range of the refrigerator exceeds the normal range, information that the number of times the refrigerator door is opened and closed exceeds the normal range, information that the difference between the maximum temperature inside the refrigerator and the control temperature exceeds the normal range, and information that the outdoor temperature of the refrigerator exceeds the normal range.

[0081] When the fourth data and the fifth data are obtained, the electronic device 100 may transmit the fourth data and the fifth data to the refrigerator (S260). Here, the fifth data may include information related to the guide message corresponding to at least one reason. Figure 3 The process of identifying the cause associated with the efficiency reduction of the refrigerator and the specific type of the guide message is described in more detail. According to an embodiment, only one of the fourth data or the fifth data may be transmitted to the refrigerator.

[0082] According to the above reference Figure 2 According to the described embodiment, when the defrost cycle of the refrigerator determined based on the third data is too short, the electronic device 100 can effectively prevent the efficiency of the refrigerator from being reduced by limiting the defrost cycle to a threshold value.

[0083] Figure 3 is a flowchart showing a control method of the electronic device 100 according to an embodiment. Figure 4 is a diagram showing an example of a user interface according to an embodiment.

[0084] exist Figure 2 In the description of FIG. 1 , an embodiment of obtaining fifth data including information related to the cause of the decrease in refrigerator efficiency has been described. Figure 3 A process of identifying a cause associated with a decrease in efficiency of a refrigerator and a type of a guide message corresponding to the identified cause is described in more detail.

[0085] like Figure 3As shown, when the first data is obtained (S310), the electronic device 100 can identify whether the temperature of the refrigerator is within the normal range (S320). Then, if the temperature of the refrigerator is identified as being outside the normal range (S320-N) based on the identification, the electronic device 100 can provide a guidance message for requesting a service engineer to come to the door (S325). That is, because when it is identified that excessive frost has occurred due to the reason that the temperature of the refrigerator is outside the normal range, it is preferred to request a service engineer to come to the door to receive repairs for the refrigerator, the electronic device 100 can provide the user with a guidance message for suggesting requesting a service engineer to come to the door.

[0086] If the temperature of the refrigerator is identified as being within the normal range based on the identification (S320-Y), the electronic device 100 may identify whether the number of times the door of the refrigerator is opened and closed is within the normal range (S330). Then, if the number of times the door is opened and closed is identified as being beyond the normal range based on the identification (S330-N), the electronic device 100 may provide a guidance message for excessive number of times the door is opened and closed (S335). That is, because the user prefers to reduce the number of times the door is opened and closed when it is identified that excessive frosting has occurred due to the reason that the temperature of the refrigerator is beyond the normal range, the electronic device 100 may provide the user with a guidance message for suggesting reducing the number of times the door is opened and closed.

[0087] If the number of times the door of the refrigerator is opened and closed is identified as being within a normal range based on the identification (S330-Y), the electronic device 100 may identify whether the difference between the maximum temperature and the control temperature inside the refrigerator is within a normal range (S340). Then, if the difference between the maximum temperature and the control temperature inside the refrigerator is identified as being beyond a normal range based on the identification (S340-N), the electronic device 100 may provide a guidance message for putting too much high-temperature food in at one time (S345). That is, because the user prefers not to put too much high-temperature food in at one time when it is identified that excessive frost has occurred due to the difference between the maximum temperature and the control temperature inside the refrigerator being beyond a normal range, the electronic device 100 may provide the user with a guidance message for suggesting not to put too much high-temperature food in at one time.

[0088] If the difference between the maximum temperature and the control temperature inside the refrigerator is identified as being within the normal range based on the identification (S340-Y), the electronic device 100 may identify whether the outdoor temperature of the refrigerator is within the normal range (S350). Then, if the outdoor temperature of the refrigerator is identified as being outside the normal range based on the identification (S350-N), the electronic device 100 may provide a guidance message that the installation condition of the refrigerator is a poor condition (S355). That is, since it is preferred to change the installation condition of the refrigerator when it is identified that excessive frost has occurred due to the reason that the outdoor temperature of the refrigerator is outside the normal range, the electronic device 100 may provide the user with a guidance message for suggesting to change the installation condition of the refrigerator.

[0089] If the outdoor temperature of the refrigerator is identified as being within the normal range based on the identification (S350-Y), the electronic device 100 may provide a guidance message for excessive amount of food stored in the refrigerator (S360). In other words, because the possibility of excessive frosting due to excessive amount of food is high when the temperature of the refrigerator, the number of times the door is opened and closed, the difference between the maximum temperature in the refrigerator and the control temperature, and even the outdoor temperature are all within the normal range, the electronic device 100 may provide the user with a guidance message suggesting reducing the amount of food stored in the refrigerator.

[0090] The above guidance message can be provided not only through the display, speaker, etc. included in the refrigerator, but also through the display, speaker, etc. of the user terminal connected to the refrigerator. Figure 4 As shown, the display of the user terminal may display a user interface (UI) including a guidance message such as "Since there is too much food stored in the refrigerator, the temperature may not be properly controlled. Please store less than or equal to 80% of the total capacity of food." In addition, as Figure 4 As shown, the UI may include a UI item for receiving a user's response to the guidance message ( Figure 4 Confirm and Cancel in the .

[0091] Figure 3 and Figure 4 Only an embodiment according to the present disclosure is shown, and the order of identifying the cause associated with the efficiency reduction of the refrigerator, the type of the guide message, the method of displaying the guide message, etc. may be different from the reference Figure 3 and Figure 4 The examples described are implemented differently.

[0092] The above reference can be realized by using the program Figure 1 , Figure 2 and Figure 3The described control method of the electronic device 100 is provided to the electronic device 100. Specifically, a program including the control method of the electronic device 100 may be stored in a non-transitory computer-readable medium.

[0093] Specifically, a non-transitory computer-readable medium including a program for executing a control method for an electronic device 100, the control method including: obtaining first data representing an operation history of a refrigerator; obtaining second data representing a prediction result for future operation of the refrigerator based on inputting the first data into a first neural network model for predicting the operation of the refrigerator; and obtaining third data based on inputting the second data into a second neural network model for obtaining information associated with defrosting of the refrigerator, the third data including information related to a degree of frost when the operation of the refrigerator is performed according to the second data, and information for controlling the defrost operation of the refrigerator.

[0094] According to the above reference Figure 3 According to the described embodiment, the electronic device 100 can take appropriate measures to prevent the efficiency of the refrigerator from decreasing by identifying the cause associated with the efficiency decrease of the refrigerator and providing a guide message corresponding thereto to the user.

[0095] Figure 5 1 is a block diagram briefly showing the configuration of the electronic device 100 according to the embodiment. Figure 6 is a block diagram showing in detail the configuration of the electronic device 100 according to the embodiment.

[0096] like Figure 5 As shown, the electronic device 100 according to the embodiment may include a memory 110 and a processor 120. Figure 6 As shown, the electronic device 100 may further include a communicator 130, an inputter 140 and an outputter 150. However, Figure 5 and Figure 6 The configuration shown is only an example, and other configurations may be used in the implementation of the present disclosure. Figure 5 and Figure 6 In addition to the configurations shown in , new configurations may be added, or some configurations may be omitted.

[0097] In the memory 110, at least one instruction associated with the electronic device 100 may be stored. In addition, an operating system (O / S) for driving the electronic device 100 may be stored in the memory 110. In addition, various software programs or applications for the electronic device 100 to operate according to various embodiments of the present disclosure may be stored in the memory 110. In addition, the memory 110 may include a semiconductor memory (e.g., a flash memory), a magnetic storage medium (e.g., a hard disk), and the like.

[0098] Specifically, various software modules for the electronic device 100 to operate according to various embodiments of the present disclosure may be stored in the memory 110, and the processor 120 may control the operation of the electronic device 100 by executing the various software modules stored in the memory 110. That is, the processor 120 may access the memory 110, and the reading / writing / modification / deletion / update of data may be performed by the processor 120.

[0099] In the present disclosure, the term “memory 110 ” may be used as a meaning including the memory 110 , a read-only memory (ROM), a random access memory (RAM) in the processor 130 , or a memory card (e.g., a micro SD card, a memory stick) installed to the electronic device 100 .

[0100] Specifically, according to various embodiments of the present disclosure, the memory 110 may store information related to a first neural network model for predicting refrigerator operation, and information related to a second neural network model for obtaining information associated with refrigerator defrosting. Here, the information related to the first neural network model and the information related to the second neural network model may include learning data for training the first neural network model and the second neural network model, and information related to the layers and parameters that form the first neural network model and the second neural network model, respectively. In addition, according to the present disclosure, the memory 110 may store first data, second data, third data, fourth data, and fifth data. In addition, the memory 110 may store information associated with a decrease in the efficiency of the refrigerator.

[0101] In addition to the above, various information required within the scope of achieving the purpose of the present disclosure may be stored in the memory 110 , and the information stored in the memory 110 may be updated by being received from an external device or input by a user.

[0102] The processor 120 may control the overall operation of the electronic device 100. Specifically, the processor 120 may be connected with the configuration of the electronic device 100 including the memory 110, and control the overall operation of the electronic device 100 by executing at least one instruction stored in the memory 110 as described above.

[0103] The processor 120 may be implemented in various ways. For example, the processor may be implemented as at least one of an application specific integrated circuit (ASIC), an embedded processor, a microprocessor, a hardware control logic, a hardware finite state machine (FSM), or a digital signal processor (DSP). The term "processor 120" used herein may be used as a meaning including a central processing unit (CPU), a graphics processing unit (GPU), a main processing unit (MPU), etc.

[0104] According to an embodiment, the processor 120 can obtain first data representing the operation history of the refrigerator, input the first data into a first neural network model and obtain second data representing a prediction result for future operation of the refrigerator, and input the second data into a second neural network model and obtain third data, the third data including information related to the degree of frost when the refrigerator operation is performed according to the second data, and information for controlling the defrost operation of the refrigerator.

[0105] According to an embodiment, the processor 120 may obtain fourth data by changing information related to the defrost operation cycle in the third data to a threshold value based on the defrost operation cycle according to the information for controlling the defrost operation being less than a preset threshold value, and control the communicator 130 to send the fourth data to the refrigerator. Then, the processor 120 may obtain information related to at least one cause associated with a decrease in refrigerator efficiency based on the first data, and control the communicator 130 to send information related to a guide message corresponding to the at least one cause to the refrigerator.

[0106] Because the above reference Figure 1 , Figure 2 , Figure 3 and Figure 4 Various embodiments according to the present disclosure based on the control of the processor 120 are described, so redundant descriptions for substantially the same descriptions will be omitted.

[0107] The communicator 130 may include a circuit and perform communication with an external device. Specifically, the processor 120 may receive various data or information from an external device connected through the processor 130 and transmit various data or information to the external device.

[0108] The communicator 130 may include at least one of a Wi-Fi module, a Bluetooth module, a wireless communication module, a near field communication (NFC) module, and an ultra-wideband (UWB) module. Specifically, the Wi-Fi module and the Bluetooth module may perform communication in a Wi-Fi method and a Bluetooth method, respectively. When the Wi-Fi module or the Bluetooth module is used, various connection information such as a service set identifier (SSID) is first sent and received, and various information may be sent and received after communication connection is performed by using various connection information.

[0109] In addition, the wireless communication module can perform communication according to various communication standards (such as but not limited to IEEE, ZigBee, third generation (3G), third generation partnership project (3GPP), long term evolution (LTE), fifth generation (5G), etc.). In addition, the NFC module can use the 13.56MHz band among various radio frequency identification (RFID) bands (such as but not limited to 135kHz, 13.56MHz, 433MHz, 860-960MHz, 2.45GHz, etc.) to perform communication in an NFC method. In addition, the UWB module can accurately measure the time of arrival (ToA) (i.e., the time when the pulse arrives at the target object) and the angle of arrival (AoA) (i.e., the angle at which the pulse arrives from the transmission device) through communication between UWB antennas. Therefore, accurate distance and position recognition can be achieved within an error range of tens of centimeters (cm) indoors.

[0110] Specifically, according to various embodiments of the present disclosure, the processor 120 may also receive first data representing an operation history of the refrigerator from the refrigerator through the communicator 130 .

[0111] In addition, when the third data is obtained through the second neural network model, the processor 120 can control the communicator 130 to send the third data to the refrigerator so that the refrigerator performs a defrost operation according to the third data.

[0112] Then, the processor 120 may control the communicator 130 to transmit the fourth data and the fifth data according to the present disclosure to the refrigerator as described above, and control the communicator 130 to transmit the fifth data to the user terminal.

[0113] Specifically, the processor 120 may include a plurality of modules (e.g., an operation history data collection module, a future operation data prediction module, an excessive frost identification and defrost cycle prediction module, a threshold cycle identification module). In addition, each module may be implemented with a hardware module or a software module. Information related to the module may be stored in the memory 110, and the processor 120 may implement the embodiments according to the present disclosure through the module by loading the information of the module stored in the memory 110.

[0114] The operation history data collection module 121 may refer to a module for collecting data representing the operation history of the refrigerator. Specifically, the operation history data collection module 121 may receive parameters associated with the operation of the refrigerator from the past to the current time point, data representing the state of the refrigerator when the refrigerator is operated, etc. from the refrigerator through the communicator 130 to collect data representing the operation history (i.e., first data).

[0115] The future operation data prediction module 122 may refer to a module for obtaining a prediction result for the future operation of the refrigerator. Specifically, when the first data is obtained through the operation history data collection module 121, the future operation data prediction module 122 may input the first data into the first neural network model and obtain the second data (i.e., the prediction result for the future operation of the refrigerator).

[0116] The over-frost recognition and defrost cycle prediction module 123 may refer to a module for obtaining information related to the degree of frost when the operation of the refrigerator is performed, and information for controlling the defrost operation of the refrigerator. Specifically, when the second data is obtained by the future operation data prediction module 122, the over-frost recognition and defrost cycle prediction module 123 may input the second data into the second neural network model, and obtain third data (i.e., information related to the degree of frost for the evaporator, and information for controlling the defrost operation of the refrigerator).

[0117] The threshold cycle identification module 124 may refer to a module for identifying whether the defrost cycle determined based on the third data is less than a threshold value, and for performing an operation according to the identification result. Specifically, when the third data is obtained by the over-frost identification and defrost cycle prediction module 123, the threshold cycle identification module 124 may identify whether the defrost operation cycle is less than a preset threshold value, and if the defrost operation cycle is less than the preset threshold value, obtain the fourth data by changing the information related to the defrost operation cycle to the threshold value. According to an embodiment, the process of obtaining the fifth data according to the present disclosure, and even the process of controlling the communicator 130 to send the fourth data and the fifth data to the refrigerator or the user terminal can be performed by the threshold cycle identification module 124.

[0118] The above modules are only used to describe that operations performed by the processor 120 may be performed by the modules respectively, and other modules except the above modules may be added, or some modules among the above modules may be omitted.

[0119] The input 140 may include a circuit, and the processor 120 may receive a user command for controlling the operation of the electronic device 100 through the input 140. Specifically, the input 140 may be composed of a configuration such as, for example but not limited to, a microphone, a camera (not shown), a remote control signal receiver (not shown), etc. In addition, the input 140 may be implemented in a form included in a display such as a touch screen. Specifically, the microphone may receive a voice signal and convert the received voice signal into an electrical signal.

[0120] According to various embodiments of the present disclosure, the processor 120 may receive a user command for obtaining information on a frost degree according to the present disclosure and information for controlling a defrost operation of the refrigerator through the inputter 140 .

[0121] The outputter 150 may include a circuit, and the processor 120 may output various functions that may be performed by the electronic device 100 through the outputter 150. In addition, the outputter 150 may include at least one of a display, a speaker, and an indicator.

[0122] The display may output image data by the control of the processor 120. Specifically, the display may output an image pre-stored in the memory 110 by the control of the processor 120. Specifically, the display according to the embodiment may also display a user interface stored in the memory 110. The display may be implemented as a liquid crystal display (LCD) panel, an organic light emitting diode (OLED), etc., and the display may also be implemented as a flexible display, a transparent display, etc. according to circumstances. However, the display according to the present disclosure is not limited to a specific type.

[0123] The speaker may output audio data by the control of the processor 120 , and the indicator may light up by the control of the processor 120 .

[0124] Specifically, according to various embodiments of the present disclosure, when the electronic device 100 and the refrigerator are implemented as one integrated device, the processor 120 may output a guidance message corresponding to at least one cause associated with the reduced efficiency of the refrigerator through the outputter 150. For example, the processor 120 may control the display to display a user interface including the guidance message, and control the speaker to output the guidance message in the form of a voice signal.

[0125] According to various embodiments of the present disclosure as described above, the electronic device 100 can prevent the efficiency of the refrigerator from being reduced by preventing excessive frost in the refrigerator while also optimizing the defrosting operation.

[0126] In addition, the electronic device 100 can effectively prevent the efficiency of the refrigerator from being reduced by limiting the defrost cycle to a threshold value based on the defrost cycle of the refrigerator being too short determined by using the neural network model.

[0127] Furthermore, the electronic device 100 may take appropriate measures to prevent the efficiency of the refrigerator from being reduced by identifying a cause associated with the efficiency reduction of the refrigerator and providing a guide message corresponding thereto to the user.

[0128] The above-mentioned functions associated with the first neural network model and the second neural network model may be executed by the memory 110 and the processor 120 .

[0129] The processor 120 may include one or more processors 120. At this time, the one or more processors 120 may be a general-purpose processor 120 (e.g., a central processing unit (CPU) or an application processor (AP)), a graphics-specific processor 120 (e.g., a graphics processing unit (GPU) or a visual processing unit (VPU)), or an artificial intelligence-specific processor 120 (e.g., a neural processing unit (NPU)).

[0130] The one or more processors 120 may be configured to control so as to process input data according to predefined operation rules or artificial intelligence models stored in the non-volatile memory 110 and the volatile memory 110. The predefined operation rules or artificial intelligence models may be formed by learning.

[0131] The rules or models created by learning can refer to artificial intelligence models of predefined operating rules or desired characteristics formed by applying a learning algorithm to multiple learning data. Learning can be performed in the machine itself that executes artificial intelligence according to the present disclosure, or can be performed by a separate server / system.

[0132] The artificial intelligence model may include multiple neural network layers. Each layer may include multiple weight values, and the processing of the layer is performed by processing the processing results of the previous layer and the multiple weight values. Examples of neural networks may include convolutional neural networks (CNNs), deep neural networks (DNNs), recurrent neural networks (RNNs), restricted Boltzmann machines (RBMs), deep belief networks (DBNs), bidirectional recurrent deep neural networks (BRDNNs), generative adversarial networks (GANs), and Deep-Q networks, and the neural networks of the present disclosure are not limited to the above examples unless otherwise specified.

[0133] A learning algorithm may be a method for training a predetermined target machine (e.g., a robot) to make decisions or predictions on its own using a plurality of learning data. Examples of learning algorithms may include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, and the learning algorithms of the present disclosure are not limited to the above examples unless otherwise specified.

[0134] The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, "non-transitory storage medium" only means that the storage medium is a tangible device and does not include signals (e.g., electromagnetic waves), and the term does not distinguish whether data is semi-permanently stored or temporarily stored in the storage medium. In an example, the "non-transitory storage medium" may include a buffer that temporarily stores data.

[0135] According to an embodiment, a method according to various embodiments included in a computer program product may be provided. The computer program product may be exchanged between a seller and a buyer as a commodity. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., a compact disc read-only memory (CD-ROM)), or distributed online (e.g., downloaded or uploaded) through an application store (e.g., PLAYSTORE™) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product (e.g., a downloadable application) may be at least temporarily stored in a manufacturer's server, an application store's server, or a machine-readable storage medium (e.g., the memory 110 of the relay server), or temporarily generated.

[0136] As described above, each element (e.g., module or program) according to various embodiments may be formed by a single entity or multiple entities, and some of the above sub-elements may be omitted, or other sub-elements may also be included in various embodiments. Alternatively or additionally, some elements (e.g., modules or programs) may be integrated into one entity and perform the same or similar functions as performed by each corresponding element before integration.

[0137] According to various embodiments, operations performed by a module, program or other element may be performed sequentially, in parallel, repeatedly or in a heuristic manner, or at least some operations may be performed in a different order, at least some operations may be omitted, or different operations may be added.

[0138] The term "component" or "module" used in the present disclosure may include a unit configured as hardware, software, or firmware, and may be used interchangeably with terms such as, for example, but not limited to, logic, logic block, component, circuit, etc. A "component" or "module" may be a component formed as a whole, or the smallest unit or part of a component that performs one or more functions. For example, a module may be formed as an application specific integrated circuit (ASIC).

[0139] Various embodiments of the present disclosure may be implemented with software including instructions stored in a machine-readable storage medium (e.g., a computer). The machine may call the stored instructions from the storage medium, and as a device operable according to the called instructions, may include an electronic device according to the above-described embodiments (e.g., electronic device 100).

[0140] Based on the instruction being executed by the processor 120, the processor 120 may perform a function corresponding to the instruction directly or using other elements under the control of the processor 120. The instruction may include a code generated by a compiler or executed by an interpreter.

[0141] Although the present disclosure has been illustrated and described with reference to various exemplary embodiments of the present disclosure, it will be understood that the various exemplary embodiments are intended to be illustrative rather than restrictive. Those skilled in the art will appreciate that various changes can be made in form and details without departing from the true spirit and full scope of the present disclosure and including the appended claims and their equivalents.

Claims

1. An electronic device, comprising: at least one memory configured to store information of a first neural network model trained to predict operation of a refrigerator and information of a second neural network model trained to obtain information associated with defrosting of the refrigerator; as well as At least one processor configured to: obtaining first data related to an operation history of the refrigerator, inputting the first data into the first neural network model, and obtaining second data related to a prediction result for future operation of the refrigerator from the first neural network model, and The second data is input into the second neural network model, and third data is obtained from the second neural network model, wherein the third data includes information related to the degree of frost based on the operation of the refrigerator performed according to the second data, and information related to controlling the defrost operation of the refrigerator.

2. The electronic device according to claim 1, further comprising: communicator, Wherein, the at least one processor is further configured to: based on obtaining the third data from the second neural network model, control the communicator to send the third data to the refrigerator as an instruction for the refrigerator to perform a defrost operation according to the third data.

3. The electronic device according to claim 2, wherein: The information related to controlling the defrost operation of the refrigerator includes information related to a cycle of the defrost operation, information related to a duration of the defrost operation of each cycle, and information related to an intensity of the defrost operation of each cycle.

4. The electronic device according to claim 3, wherein: The at least one processor is further configured to: obtaining fourth data by changing the information related to the cycle of the defrost operation in the third data to the threshold value based on the cycle of the defrost operation according to the information related to controlling the defrost operation being less than a threshold value, and The communicator is controlled to send the fourth data to the refrigerator.

5. The electronic device according to claim 4, wherein: The at least one processor is further configured to: Based on the first data, obtaining information related to at least one cause, the at least one cause being associated with a decrease in efficiency of the refrigerator, and The communicator is controlled to transmit information related to a guide message to the refrigerator, the guide message corresponding to the at least one reason.

6. The electronic device according to claim 5, wherein: The at least one processor is further configured to: identify information related to the at least one cause based on at least one of information related to the temperature range of the refrigerator, information related to the number of times a door of the refrigerator is opened and closed, information related to a difference between a maximum temperature inside the refrigerator and a control temperature, or information related to an outdoor temperature of the refrigerator, and The first data includes information related to the temperature range of the refrigerator.

7. The electronic device according to claim 1, wherein: The first data includes information about RPM of a fan of the refrigerator, power consumption of a compressor of the refrigerator, and internal temperature of the refrigerator, and The first neural network model is trained to obtain the second data based on the first data, data related to the surrounding environment of the refrigerator, and information related to the user of the refrigerator.

8. The electronic device according to claim 7, wherein: The second data includes a first predicted value of the RPM of the fan, a second predicted value of the power consumption of the compressor, and a third predicted value of the internal temperature of the refrigerator, and The second neural network model is trained to obtain information related to the degree of excessive frosting based on the first prediction value, the second prediction value and the third prediction value.

9. The electronic device according to claim 1, wherein: The first neural network model and the second neural network model are implemented as an integrated neural network model, and the integrated neural network model is trained according to an end-to-end learning method to obtain the third data based on the first data.

10. The electronic device according to claim 1, wherein: The electronic device and the refrigerator are implemented as one integrated device, and Wherein, the at least one processor is further configured to: obtain the third data from the second neural network model, and perform a defrost operation of the refrigerator based on the third data.

11. A method for controlling an electronic device, the method comprising: obtaining first data related to an operation history of the refrigerator; obtaining second data related to a prediction result for future operation of the refrigerator based on inputting the first data into a first neural network model trained to predict operation of the refrigerator; as well as Based on inputting the second data into a second neural network model trained to obtain information associated with defrosting of the refrigerator, third data is obtained, the third data including information related to the degree of frost based on performing operations of the refrigerator according to the second data, and information related to controlling the defrost operation of the refrigerator.

12. The method according to claim 11, further comprising: Based on obtaining the third data from the second neural network model, the third data is sent to the refrigerator as an instruction for the refrigerator to perform a defrost operation according to the third data.

13. The method according to claim 12, wherein: The information related to controlling the defrost operation of the refrigerator includes information related to a cycle of the defrost operation, information related to a duration of the defrost operation of each cycle, and information related to an intensity of the defrost operation of each cycle.

14. The method according to claim 13, further comprising: obtaining fourth data by changing the information related to the cycle of the defrost operation in the third data to the threshold value based on the cycle of the defrost operation according to the information related to controlling the defrost operation being less than a threshold value, and The fourth data is sent to the refrigerator.

15. The method according to claim 14, further comprising: Based on the first data, obtaining information related to at least one cause, the at least one cause being associated with a decrease in efficiency of the refrigerator; as well as Information related to a guide message is transmitted to the refrigerator, the guide message corresponding to the at least one reason.

Images