Server device capable of diagnosing refrigerant leakage and methods therefor

Abstract

A server device is disclosed. The server device comprises: a communication unit for performing communication with at least one electronic device using a refrigerant and a user terminal device corresponding to the at least one electronic device; a memory for storing first and second artificial intelligence models; and a processor. The processor receives usage history data information and stores the usage history data information in the memory when the electronic device using the refrigerant operates, obtains future usage history data and information about a possibility of refrigerant leakage on the basis of usage history data, and transmits, to the user terminal device through the communication unit, recommended usage pattern information for preventing the refrigerant leakage, on the basis of the obtained information.

Description

Server devices capable of diagnosing refrigerant leaks and methods thereof

[0001] The present invention relates to a server device capable of diagnosing refrigerant leakage and a method therefor.

[0002] Advances in electronic technology have led to the introduction of a variety of electronic devices into homes. These include refrigerators, air conditioners, and clothes dryers that use refrigerants.

[0003] Electronic devices that use refrigerants will experience reduced or even no cooling effect if the refrigerant begins to leak.

[0004] It's difficult for users to detect a refrigerant leak early on, and once detected, normal cooling performance is likely to be lost. In devices like refrigerators that store refrigerated or frozen foods, if cooling performance is lost without the user's knowledge, food damage can occur.

[0005] Therefore, a method was needed to detect refrigerant leaks early and take action while maintaining judgment accuracy.

[0006] According to at least one embodiment of the present disclosure, a server device includes a communication unit for performing communication with at least one electronic device using a refrigerant and a user terminal device corresponding to the at least one electronic device, a memory in which first and second artificial intelligence models are stored, and a processor. The processor receives usage history data of the at least one electronic device from the at least one electronic device through the communication unit and stores the data in the memory, obtains future usage history data of the electronic device predicted by the first artificial intelligence model based on the usage history data, obtains information on the possibility of refrigerant leakage of the at least one electronic device diagnosed by the second artificial intelligence model based on the future usage history data, and transmits information on a usage pattern in preparation for refrigerant leakage to the user terminal device through the communication unit based on the obtained information.

[0007] In addition, a diagnostic method according to at least one embodiment of the present disclosure includes the steps of receiving and storing usage history data of the at least one electronic device from the at least one electronic device, obtaining future usage history data of the electronic device predicted by a first artificial intelligence model based on the usage history data, obtaining information on the possibility of refrigerant leakage of the at least one electronic device diagnosed by a second artificial intelligence model based on the future usage history data, and generating information on a recommended usage pattern to prepare for refrigerant leakage based on the obtained information and transmitting the information to a user terminal device corresponding to the at least one electronic device.

[0008] In addition, a non-transitory readable recording medium according to at least one embodiment of the present disclosure stores a program for performing the diagnostic method, including the steps of receiving and storing usage history data of the at least one electronic device from the at least one electronic device, obtaining future usage history data of the electronic device predicted by a first artificial intelligence model based on the usage history data, obtaining information on the possibility of refrigerant leakage of the at least one electronic device diagnosed by a second artificial intelligence model based on the future usage history data, and generating information on a recommended usage pattern to prepare for refrigerant leakage based on the obtained information and transmitting the information to a user terminal device corresponding to the at least one electronic device.

[0009] FIG. 1 is a drawing for explaining the operation of a server device according to at least one embodiment of the present disclosure.

[0010] FIG. 2 is a block diagram illustrating a configuration of a server device according to at least one embodiment of the present disclosure.

[0011] FIG. 3 is a graph illustrating a method for diagnosing a refrigerant leak in a server device according to at least one embodiment of the present disclosure.

[0012] Figures 4 to 6 are graphs showing various examples of usage history data.

[0013] FIG. 7 is a diagram illustrating a process of diagnosing a refrigerant leak using an artificial intelligence model in a server device according to at least one embodiment of the present disclosure.

[0014] FIG. 8 and FIG. 9 are diagrams comparing future usage history data according to an existing usage pattern and future usage history data according to a recommended usage pattern in a server device according to at least one embodiment of the present disclosure.

[0015] FIG. 10 is a graph showing the effect of changes in usage patterns in a server device according to at least one embodiment of the present disclosure.

[0016] Figures 11 and 12 are graphs showing refrigerator overheating and graphs showing refrigerator refrigerant leakage.

[0017] Figures 13 and 14 are graphs for diagnosing whether there is a leak in the low pressure section and graphs for diagnosing whether there is a leak in the high pressure section.

[0018] FIG. 15 is a diagram illustrating examples of UI screens displayed on a display device according to at least one embodiment of the present disclosure.

[0019] FIG. 16 is a block diagram illustrating a configuration of an electronic device according to at least one embodiment of the present disclosure.

[0020] FIG. 17 is a block diagram illustrating a configuration of a user terminal device according to at least one embodiment of the present disclosure.

[0021] FIG. 18 is a flowchart illustrating a diagnostic method of a server device according to at least one embodiment of the present disclosure.

[0022] The terms used in the various embodiments of this disclosure have been selected from widely used, current terms, taking into account the functions of this disclosure. However, these terms may vary depending on the intentions of those skilled in the art, precedents, the emergence of new technologies, etc. Furthermore, in certain cases, terms may be arbitrarily selected by the applicant, and in such cases, their meanings will be described in detail in the description of the relevant disclosure. Therefore, the terms used in this disclosure should be defined based on the meaning of the terms and the overall content of this disclosure, rather than simply their names.

[0023] It should be understood that the various embodiments of the present disclosure and the terminology used therein are not intended to limit the technical features described in the present disclosure to specific embodiments, but include various modifications, equivalents, or substitutes of the embodiments.

[0024] In connection with the description of the drawings, similar reference numerals may be used for similar or related components.

[0025] The singular form of a noun corresponding to an item may include one or more of said items, unless the relevant context clearly indicates otherwise.

[0026] In this disclosure, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" may include any one of the items listed together in the corresponding phrase, or all possible combinations thereof.

[0027] The term "and / or" includes any combination of a plurality of related described elements or any one of a plurality of related described elements.

[0028] Terms such as "first," "second," or "first" or "second" may be used simply to distinguish one component from another and do not qualify the components in any other respect (e.g., importance or order).

[0029] Terms such as "include" or "have" are intended to specify the presence of a feature, number, step, operation, component, part or combination thereof described in the present disclosure, but do not preclude the presence or addition of one or more other features, numbers, steps, operations, components, parts or combinations thereof.

[0030] When a component is said to be “connected,” “coupled,” “supported,” or “in contact with” another component, this includes not only cases where the components are directly connected, coupled, supported, or in contact, but also cases where the components are indirectly connected, coupled, supported, or in contact through a third component.

[0031] When we say that a component is "on" another component, this includes not only cases where the component is in contact with the other component, but also cases where there is another component between the two components.

[0032] In the present disclosure, a "module" or "part" performs at least one function or operation and may be implemented as hardware or software, or as a combination of hardware and software. Furthermore, multiple "modules" or multiple "parts" may be integrated into at least one module and implemented as at least one processor (not shown), excluding any "modules" or "parts" that need to be implemented as specific hardware.

[0033] In the present disclosure, the term user may refer to a person using an electronic device (200) or a device used by the person.

[0034] An embodiment of the present disclosure will be described in more detail with reference to the attached drawings below.

[0035] FIG. 1 is a block diagram illustrating a method for diagnosing a refrigerant leak in a server device (100) according to at least one embodiment of the present disclosure.

[0036] The server device (100) can communicate with various electronic devices (200-1 to 200-n) and user terminal devices (300) connected via a network. The devices (200-1 to 200-n, 300) connected to the server device (100) may also be referred to as external devices. The server device (100) may also control at least some of the external devices.

[0037] In FIG. 1, the server device (100) may be implemented as a variety of computing devices, such as a workstation, a cloud, a data drive, or a data station. Furthermore, the network may include both wired and wireless networks. Wired networks include cable networks or telephone networks, while wireless networks may include any network that transmits and receives signals via radio waves. Wired and wireless networks may also be interconnected.

[0038] Specifically, the network may include a wide area network (WAN) such as the Internet, a local area network (LAN) formed around an access point (AP) (access relay), and a short-range wireless network that does not use an access point (AP). Short-range wireless networks may include, but are not limited to, Bluetooth (IEEE 802.15.1), Zigbee (IEEE 802.15.4), Wi-Fi Direct, Near Field Communication (NFC), Z-Wave, etc.

[0039] According to FIG. 1, a server device (100) can diagnose the status of an electronic device (200) based on various data received from one of a plurality of electronic devices (200-1 to 200-n) connected through a network, and provide the diagnosis result to a user terminal device (300).

[0040] If the electronic device (200) is a device that uses a refrigerant, the server device (100) can diagnose whether or not there is a refrigerant leak. Examples of devices that use a refrigerant include refrigerators, air conditioners, clothing care devices, shoe care devices, etc.

[0041] In the following disclosure, the electronic device (200) is described as being implemented as a refrigerator.

[0042] A refrigerator may include storage compartments, such as a refrigerator and a freezer, and at least one door configured to open and close an open side of the storage compartment. The door may be configured to open and close one or more storage compartments, or a single door may be configured to open and close multiple storage compartments. The door may be installed on the front of the main body in a pivotal or sliding manner.

[0043] A refrigerator includes a cold air supply device configured to supply cold air to a storage compartment. The cold air supply device may be implemented as a machine, device, apparatus, and / or a system combining these, which generates cold air and supplies it to various storage compartments, thereby lowering the temperature inside the storage compartment. Specifically, the cold air supply device may generate cold air through a refrigeration cycle involving the compression, condensation, expansion, and evaporation processes of a refrigerant. To this end, the cold air supply device may include a compressor, a condenser, an expansion device, and an evaporator.

[0044] The compressor compresses the gaseous refrigerant into a high-temperature, high-pressure gas. The high-temperature, high-pressure gas compressed by the compressor is then transferred to the condenser. The condenser releases heat as the high-temperature, high-pressure gas passes through it, liquefying it. This low-temperature, high-pressure liquid then passes through a capillary tube. As the low-temperature, high-pressure liquid passes through the capillary tube, its pressure drops. The evaporator vaporizes the low-temperature, low-pressure liquid refrigerant that has passed through the capillary tube. As the evaporator vaporizes the liquid refrigerant, it absorbs heat from the surrounding air, generating cold air. This cold air is then transported by a fan through the air duct to the various storage compartments within the refrigerator, lowering the temperature in these compartments.

[0045] As such, a refrigeration supply device can be implemented as a system with a refrigerant circulation structure. However, refrigerant leakage may occur due to component aging or other defects. In this disclosure, such a situation is referred to as a refrigerant leak.

[0046] When a refrigerant leak occurs, the cooling effect weakens and then disappears completely. Consequently, the electronic device (200) is no longer able to perform any further temperature-lowering operations.

[0047] In the case of an electronic device (200), if the temperature of the storage compartment rises due to a refrigerant leak in a refrigerator, serious problems may occur, such as spoilage of stored food or leakage of water as ice melts. Furthermore, even in the case of air conditioners used in environments that require the maintenance of a specific temperature (e.g., computer rooms, vegetable warehouses, etc.), rather than in general households, problems may arise if the supply of cold air is interrupted due to a refrigerant leak.

[0048] In conventional technology, users typically contact a service center for repairs after noticing a loss of cooling. However, if users fail to quickly recognize a refrigerant leak, or even if they do, they fail to receive prompt service due to issues such as a service waiting list, they inevitably suffer damage caused by the leak.

[0049] Therefore, according to various embodiments of the present disclosure, the server device (100) can perform a diagnosis by predicting a subsequent state in advance before the occurrence of a symptom.

[0050] For convenience of explanation, it is assumed that all electronic devices (200-1 to 200-n) illustrated in Fig. 1 are electronic devices that use refrigerants.

[0051] Electronic devices (200-1 to 200-n) can transmit usage history data to the server device (100) from time to time or periodically. The usage history data may be data accumulated over a certain period of time regarding the operating status or usage status of each electronic device (200-1 to 200-n). For example, the usage history data may include the number of door openings and closings, the door opening and closing interval, the set temperature, and the measured temperature. In addition, the usage history data may include various data such as the number of defrosting operations, the number of dew condensation removal operations, the accumulated door opening time, humidity information, and the operating mode (low-noise mode, power-saving mode, etc.). Specifically, the operating history data may include various raw data such as the following.

[0052] <Example of driving history data>

[0053] Cvcontroltemp, ffan, di, rdoorsensor, finsensor, isensor, cvdefrost, fhmod, rdefrost, fvalve, rcontroltemp, fcontroltemp, rinsensor, rfan, water_dispenser_usage_count, cvdefrostsensorctimeivalve, water_dispenser_operating_time, icemaker_ejection_1, ice_dispenser_operating_time, defrost_delay_exception_cond, rdefrostsensor, cvinsensor, fdoorsensor, cvfan, fdefrostsensordefrost_delay_time, rvalve, idefrost, cvvalve, icemaker_status_2, defrost_delay_release_cond, icemaker_status_1, fdefrost, femod, rcomp, ice_dispenser_usage_count, cvdoorsensor, fcompicemaker_full_flag_1, time, ifan, icemaker_ejection_2, icemaker_full_flag_2

[0054] In the above, various examples of driving history data used in actual refrigerators are described, but not all of this driving history data must be provided to the server device (100), and some of this data may be provided.

[0055] Usage history data may be described in various terms such as status data, driving information, driving history data, usage data, etc., but in this disclosure, it is described as usage history data.

[0056] The server device (100) can acquire future usage history data of the electronic devices (200-1 to 200-n) based on the received usage history data. The future usage history data may be data resulting from predictions of usage history data in a future stage that has not yet occurred. The future usage history data may be described in various terms such as predicted data, state change data, future data, etc., but in the present disclosure, it is described as usage history data.

[0057] The server device (100) can perform a diagnosis for refrigerant leakage or other abnormal conditions based on future usage history data. The server device (100) can provide the diagnosis results to electronic devices (200-1 to 200-n) and terminal devices (300), etc. Alternatively, the server device (100) can store the diagnosis results and use them for subsequent management. Alternatively, the server device (100) can transmit an A / S request signal in advance to a service center server, etc., based on the diagnosis results.

[0058] If a refrigerant leak is predicted, the diagnostic results may include information about the possibility of a refrigerant leak.

[0059] Information about the possibility of a refrigerant leak can include various information such as whether refrigerant is leaking from an electronic device that uses refrigerant, whether refrigerant is likely to leak in the future, where the refrigerant leak is expected to occur, how the refrigerant leak is progressing, and how long it can be repaired.

[0060] If a slight refrigerant leak is occurring or the possibility of a future refrigerant leak is higher than a critical level, the server device (100) may provide information on a recommended usage pattern to prepare for a refrigerant leak to electronic devices (200-1 to 200-n) and terminal devices (300).

[0061] A recommended usage pattern for refrigerant leakage can be a usage pattern suggested to minimize damage caused by refrigerant leakage or to minimize the possibility of refrigerant leakage.

[0062] A usage pattern may include how a user uses an electronic device. For example, if the electronic device (200) is a refrigerator, if the user opens and closes the refrigerator door too frequently, the cold air may dissipate quickly. Accordingly, the time for which the cold air is maintained in the storage compartment in a state of refrigerant leakage may be shortened, and consequently, the A / S period may also be shortened. Alternatively, if the user sets the refrigerator's set temperature excessively low, the refrigerant leakage may be accelerated, causing the refrigerant to disappear quickly. The server device (100) may compare the cold air retention time, the possibility of refrigerant leakage reduction effect, etc. for various usage patterns, and determine at least one recommended usage pattern that can be suggested to the user when a refrigerant leakage occurs.

[0063] Below, the diagnostic method of the above-described server device, the method of using the diagnostic results, etc. are specifically described.

[0064]

[0065] *Figure 2 is a block diagram illustrating the configuration of a server device (100) according to at least one embodiment of the present disclosure.

[0066] Referring to FIG. 2, the server device (100) includes a communication unit (110), a memory (120), and a processor (130).

[0067] The communication unit (110) is configured to communicate with various types of external devices.

[0068] The communication unit (110) may include at least one wireless communication module, at least one wired communication module, etc. Each communication module may be implemented in the form of at least one hardware chip. For example, the wireless communication module may include at least one module among a Wi-Fi module, a Bluetooth module, an infrared communication module, or other communication modules. In addition, the communication unit (110) may include at least one communication chip that performs communication according to various wireless communication standards such as Zigbee, 3G (3rd Generation), 3GPP (3rd Generation Partnership Project), LTE (Long Term Evolution), LTE-A (LTE Advanced), 4G (4th Generation), 5G (5th Generation), etc. The wired communication module may include, for example, at least one among a LAN (Local Area Network) module, an Ethernet module, a pair cable, a coaxial cable, a fiber optic cable, or a UWB (Ultra Wide-Band) module.

[0069] In addition, the communication unit (110) may further include at least one wired input / output interface among HDMI (High Definition Multimedia Interface), MHL (Mobile High-Definition Link), USB (Universal Serial Bus), USB C-type, DP (Display Port), Thunderbolt, VGA (Video Graphics Array) port, RGB port, D-SUB (Dsubminiature), and DVI (Digital Visual Interface).

[0070] The communication unit (110) can receive the usage history data described above or other various data and signals from connected external devices.

[0071] The memory (120) is a configuration for storing or recording various information, data, commands, programs, etc. required for the operation of the server device (100).

[0072] The memory (120) may be implemented as at least one of various memories, such as volatile memory (e.g., dynamic RAM (DRAM), static RAM (SRAM), or synchronous dynamic RAM (SDRAM)), non-volatile memory (e.g., one time programmable ROM (OTPROM), programmable ROM (PROM), erasable and programmable ROM (EPROM), electrically erasable and programmable ROM (EEPROM), mask ROM, flash ROM, flash memory (e.g., NAND flash or NOR flash), hard drive, or solid state drive (SSD).

[0073] In FIG. 2, one memory (120) is illustrated, but the memory (120) may be implemented to include a plurality of memories that each store different types of data or each store data generated at different stages, and at least one of these memories may be implemented as a single chip integrated with the processor (130).

[0074] The memory (120) can store usage history data, etc. received from each external device via the communication unit (110). In addition, the memory (120) can also store programs and data used therefor that can predict future usage history data based on the usage history data as described above, or diagnose abnormal conditions based on these data. For example, the memory (120) can also store at least one artificial intelligence model. The artificial intelligence model will be described in detail later.

[0075] The processor (130) is a component for controlling the overall operation of the server device (100). The processor (130) can control components of the server device (100) by executing a program stored in the memory (120).

[0076] The processor (130) may be implemented as a digital signal processor (DSP), a microprocessor, a GPU (Graphics Processing Unit), an AI (Artificial Intelligence) processor, an NPU (Neural Processing Unit), etc. However, the present invention is not limited thereto, and may include one or more of a central processing unit (CPU), a MCU (Micro Controller Unit), an MPU (micro processing unit), a controller, an application processor (AP), a communication processor (CP), an ARM processor, or may be defined by the relevant term. In addition, the processor (130) may be implemented as a SoC (System on Chip), an LSI (Large Scale Integration) having a built-in processing algorithm, or may be implemented in the form of an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array).

[0077] The processor (130) may execute at least one artificial intelligence model to perform various operations, such as predicting and diagnosing future usage history data as described in FIG. 1. In this case, the processor (130) may be implemented through a combination of software and a general-purpose processor, such as a CPU, an AP, a DSP (Digital Signal Processor), a graphics-only processor, such as a GPU or a VPU (Vision Processing Unit), or an artificial intelligence-only processor, such as an NPU. The processor (130) may also be designed as a hardware structure specialized for processing a specific artificial intelligence model. For example, the processor (130) may be designed as a hardware chip, such as an ASIC or an FPGA, specialized for processing a specific artificial intelligence model.

[0078] The processor (130) may also transmit a control signal based on data transmitted from each external device. For example, in FIG. 1, assuming that one (200-1) of the electronic devices (200-1 to 200-n) is a refrigerator and the user terminal device (300) is a smartphone owned by the user of the refrigerator, the processor (130) of the server device (100) may transmit various information received from the refrigerator (200-1) to the user terminal device (300). The user terminal device (300) may display the received information on a UI screen. The user may also input various control commands (e.g., changing the set temperature, etc.) on the UI screen. The user terminal device (300) may transmit the input control commands to the server device (100). When a control command is received through the communication unit (110), the processor (130) can control the communication unit (110) to transmit a control signal corresponding to the control command (i.e., a control signal for changing the set temperature) to the refrigerator (200-1).

[0079] The processor (130) can receive usage history data of external devices (200-1 to 200-n) through the communication unit (110). The processor (130) can store the received usage history data in the memory (120).

[0080] Specific examples of usage history data are described in the above section. If the electronic device is a refrigerator and the purpose is to diagnose a possible refrigerant leak, only data related to changes due to refrigerant leakage can be selectively used among the various usage history data described above. For example, fcontroltemp, fdefrostsensor, fdefrost, fdoorsensor, fcomp, fvalve, femod, and defrostsensor - fcontrltemp can be used.

[0081] The processor (130) can acquire future usage history data of each electronic device (200-1 to 200-n) based on usage history data and at least one artificial intelligence model stored in the memory (120). For convenience of explanation, the following describes a case where the server (100) diagnoses the status of one of the electronic devices (200-1 to 200-n) by assigning the reference number 200 to that electronic device.

[0082] The processor (130) obtains future usage history data predicted by the first artificial intelligence model stored in the memory (120) based on the usage history data of the electronic device (200). Specifically, the processor (130) may provide the usage history data as an input value of the first artificial intelligence model, and then obtain future usage history data based on an output value of the first artificial intelligence model.

[0083] In this case, the processor (130) may perform a preprocessing operation to convert the usage history data into a form that can be processed by the first artificial intelligence model. The preprocessing operation may include operations such as normalizing the scale of each piece of information included in the usage history data to a preset range or adjusting the units of each piece of information to the units used in the learning of the first artificial intelligence model.

[0084] The first artificial intelligence model may be a learning model learned based on various usage history data. That is, the manufacturer of the server device (100) or the software manager may input some of the various usage history data already acquired into the first artificial intelligence model, and then compare the output value of the first artificial intelligence model with subsequent time data of the input usage history data and provide the feedback result to the first artificial intelligence model, thereby training the first artificial intelligence model.

[0085] Accordingly, the first artificial intelligence model can output future usage history data that follows the input usage history data.

[0086] The processor (130) can detect refrigerant leaks and other abnormal conditions based on future usage history data. In this case, the processor (130) can detect refrigerant leaks and abnormal conditions using a second artificial intelligence model separately from the first artificial intelligence model.

[0087] When using the second artificial intelligence model, the processor (130) may once again perform a preprocessing operation to transform future usage history data into a form processable by the second artificial intelligence model. For convenience of explanation, the preprocessing operation for the first artificial intelligence model will be referred to as the first preprocessing operation, and the preprocessing operation for the second artificial intelligence model will be referred to as the second preprocessing operation. The second preprocessing operation may be performed in a similar manner to the first preprocessing operation.

[0088] After performing the second preprocessing operation, the processor (130) may input the preprocessed future usage history data into the second artificial intelligence model. The second artificial intelligence model outputs information on the possibility of refrigerant leakage in the electronic device (200) based on the future usage history data. Specifically, the second artificial intelligence model may output information on whether or not a refrigerant leak has occurred, the refrigerant leakage progression, and the predicted timing of the leak.

[0089] Meanwhile, according to another embodiment of the present disclosure, the processor (130) may additionally acquire information on a refrigerant leak location, a recommended usage pattern, or a refrigerant leak progression when used under the recommended usage pattern. The refrigerant leak progression may include a period until the refrigeration / freezing function is lost depending on the refrigerant leak location and the current usage pattern (number of door openings, intervals, time, set temperature, etc.). A method for acquiring this information will be described in detail with reference to the drawings in the following section.

[0090] FIG. 3 is a graph illustrating a method for diagnosing a refrigerant leak in a server device according to at least one embodiment of the present disclosure and the resulting effects. Specifically, the graph represents changes in fdefrost, which is data on the defrosting operation of a freezer among usage history data. The defrosting operation is an operation to remove frost that has formed. The defrosting operation can be performed in various ways. According to one example, the refrigerator can melt the frost by operating a heater provided on one side of a cooler provided in the freezer. In FIG. 3, the horizontal axis represents time, and the vertical axis represents temperature. The refrigerator can perform the defrosting operation continuously or periodically based on the sensing value of the frost detection sensor, which can cause the temperature of the freezer to change frequently. The refrigerator can collect such usage history data at preset time intervals and then transmit it to the server device (100).

[0091] In Figure 3, x represents usage history data provided by the refrigerator. x can be data up to time t2. In Figure 3, a similar pattern continues from time 0 to time t1, but a slightly rising pattern appears in the t1-t2 interval. This can be seen as a precursor to a refrigerant leak.

[0092] The processor (130) of the server device (100) can obtain future usage history data (y) following the usage history data using the first artificial intelligence model. Since a data section corresponding to a precursor phenomenon is included, the future history data output from the first artificial intelligence model can be in a form that shows a large change after a certain period of time. The processor (130) can predict the possibility of refrigerant leakage and the timing of the leakage by inputting the future usage history data (y) into the second artificial intelligence model. FIG. 3 shows a state in which refrigerant is predicted to leak at time t3. Referring to FIG. 3, it can be seen that the prediction result of the second artificial intelligence model is obtained at time t2, before the refrigerant leakage becomes serious.

[0093] According to the prior art, an abnormality can be detected only when the actual temperature rises above a reference value, and thus, a refrigerant leak can only be detected at time t3. According to the present disclosure, it can be seen that a refrigerant leak can be diagnosed approximately 13.2 days faster than the prior art. According to the present disclosure, the possibility of a refrigerant leak can be diagnosed in advance before the refrigerant actually leaks or, even if the refrigerant leaks, at a time when the cooling effect is not significantly reduced, so that a quick response can be taken before the damage becomes severe. For example, if the server device (100) provides the diagnosis result to the user terminal device (300) of the refrigerator (200), the user can check the diagnosis result and directly request A / S from the service center device, reduce the number of uses to prevent the loss of cold air, or move food to an icebox or other refrigerator for storage. Alternatively, the server device (100) can directly request A / S from the service center device. A service center device may be a server device or terminal device operated by a service center to receive service applications.

[0094] In Fig. 3, a case in which usage history data related to the operation of the statue is used is described, but as described above, various types of usage history data can be used for the above-described diagnosis.

[0095] Figures 4 to 6 are graphs showing examples of various usage history data.

[0096] In Figures 4 to 6, the horizontal axis commonly represents time. First, Figure 4 is a graph showing sensing value information (fdoorsensor) of a door sensor installed in a refrigerator.

[0097] In Figure 4, each graph can represent the number of door openings per unit time or the cumulative opening time. For example, if the unit time is set to 1 hour, the vertical axis can be a count axis representing the number of times the door was opened in 1 hour, or a time axis representing the total time the door was kept open for 1 hour.

[0098] The processor (130) of the server device (100) may also calculate the door opening frequency based on the number of door openings per hour. Information related to door openings may be used as data for predicting the progression of refrigerant leakage or determining recommended usage patterns.

[0099] Figure 5 is a graph showing sensing value information from a refrigerator's temperature sensor, and Figure 6 is a graph showing the refrigerator's set temperature. In Figures 5 and 6, the vertical axis can represent temperature. According to Figure 5, a pattern of increasing temperature can be observed based on 5,000 hours. According to Figure 6, a pattern of decreasing set temperature can be observed based on 5,600 hours.

[0100] The processor (130) of the server device (100) can use this usage history data and other usage history data to predict the possibility of leakage, the timing of leakage, etc. before the refrigerant leaks as described above.

[0101]

[0102] *Figure 7 is a diagram for explaining the operation of an artificial intelligence model used in a server device according to at least one embodiment of the present disclosure. Figure 7 shows an artificial intelligence model having a CNN1D (Convolutional Neural Network 1 Dimension) + LSTM (Long Short Term Memory) structure.

[0103] When input data (410) of a certain time unit (e.g., 1000 hours), i.e., future usage history data, is input, the processor (130) applies a one-dimensional CNN for a preset time (e.g., 100 hours) to extract a feature map (420) for each section.

[0104] The processor (130) can learn the time series characteristics of each section using LSTM (440). The processor (130) can diagnose abnormal conditions, such as refrigerant leakage, based on the learned model. That is, the processor (130) can diagnose a refrigerant leakage if the probability of the final result having a sigmoid probability value (0 to 1) of 0.7 or higher is present.

[0105] The processor (130) may reduce the data size of the feature map (420) by using a pooling layer (430). In addition, the processor (130) may perform data flattening through a flattening layer (flattenLayer, 450).

[0106]

[0107] *Finally, the processor (130) derives a probability value for each hour from the results inferred for each 100-hour period through neural network operations via multiple layers (460). For example, if the output values ​​of the second artificial intelligence model are sequentially output in the order of 0.12, 0.21, 0.68, 0.80, 0.91, etc., it can be predicted that a leak will occur at the 4th time (104 hours) when the value exceeds the preset threshold of 0.7.

[0108] Meanwhile, if an abnormal condition such as a refrigerant leak is predicted, the extent of damage caused by the abnormal condition may differ depending on whether the user maintains the existing usage pattern or improves the usage pattern. Accordingly, the processor (130) of the server device (100) may provide a recommended usage pattern to minimize damage caused by a refrigerant leak.

[0109] Figures 8 and 9 are graphs showing future usage history data according to existing usage patterns and future usage history data according to recommended usage patterns.

[0110] In Figures 8 and 9, t1 represents the diagnosis time, and t2 represents the loss of cooling function. In Figure 8, if the existing usage pattern is maintained, the diagnosis is made at approximately 390 hours (t1). Based on the diagnosis, the loss of cooling function is predicted to occur at approximately 610 hours (t2).

[0111] On the other hand, in the case of Fig. 8, it can be seen that the diagnosis time point t1 is the same as Fig. 8, but the cooling function loss time point t2 is predicted to be approximately 850 hours.

[0112] Based on this data, it appears that changing usage patterns could significantly extend the life of the refrigerator. The shelf life of the refrigerator could even be equal to its service life.

[0113] The processor (130) can predict the timing of refrigerant leakage using the first and second artificial intelligence models while varying the usage pattern, and compare the predicted results to identify a usage pattern that can preserve cold air for the longest possible time. The processor (130) can determine the identified usage pattern as a recommended usage pattern and provide it to an external device.

[0114] When a user checks the recommended usage pattern displayed on their user terminal device (300) or refrigerator (200), the recommended usage pattern can be utilized as a user guide to maintain cold air for as long as possible. If the user changes their usage pattern based on the recommended usage pattern, the repair period can be extended.

[0115] Figure 10 is a graph showing the repairable period according to changes in usage patterns.

[0116] Specifically, the z2 graph shows the change in refrigerant amount when used with the current usage pattern, the z1 graph shows the change in refrigerant amount when the number of door openings or frequency increases compared to the current, and the z3 graph shows the change in refrigerant amount when changed to the recommended usage pattern.

[0117] Assuming that the minimum refrigerant amount is y2, if the diagnosis is made at time x2 and the current usage pattern is maintained (z2), the repairable period can be up to time x3. After time x3, the refrigerant amount drops below the minimum standard, so it can be predicted that the refrigeration or freezing effect will be significantly reduced.

[0118] On the other hand, if the user changes the current usage pattern based on the recommended usage pattern and the number of door openings decreases (z3), the repairable period can be extended to point x4.

[0119] On the other hand, if the user opens and closes the door more frequently than currently (z1), the repairable period may be shortened by more than x3.

[0120] Figures 11 and 12 are graphs showing refrigerator overheating and graphs showing refrigerator refrigerant leakage.

[0121] As described above, diagnosis based on future usage history data can diagnose not only refrigerant leaks but also various other abnormalities. For example, it can diagnose over-cooling, which is excessive condensation.

[0122] Figure 11 shows future usage history data in which over-attachment is predicted to occur, and Figure 12 shows future usage history data in which refrigerant leakage is predicted to occur.

[0123] In FIGS. 11 and 12, the x graph represents the internal temperature, and the y graph represents the external temperature. As shown in FIGS. 11 and 12, since the graph pattern may vary depending on each state, the processor (130) may determine the type of abnormal state based on this.

[0124] Specifically, the processor (130) can diagnose a refrigerator overheating when the internal temperature rises and the defrost temperature falls, as shown in FIG. 11. The processor (130) can diagnose a refrigerator refrigerant leak when the internal temperature rises and the defrost temperature rises, as shown in FIG. 12.

[0125] These diagnostic operations may be performed by, but are not necessarily limited to, a second artificial intelligence model, and may also be performed in a rule-based manner by comparing predictions with previously stored graph patterns.

[0126] Meanwhile, as described above, the refrigerant circulates within the refrigerant circulation line. In this case, the location of the refrigerant leak may vary. If the location of the refrigerant leak varies, the power consumption value of the electronic device (200) may also vary.

[0127] Specifically, the processor (130) can predict a refrigerant leak location within at least one electronic device (200) based on a change pattern of power consumption values ​​consumed by at least one electronic device (200) among future usage history data.

[0128] If the processor (130) has a pattern of increasing power consumption, it can predict a high-pressure part in a refrigerant circulation line through which refrigerant flows within at least one electronic device (200) where the flow pressure is higher than a reference pressure as a refrigerant leak site. In addition, if the processor (130) has a pattern of slightly decreasing power consumption, it can predict a low-pressure part in a refrigerant circulation line through which refrigerant flows within at least one electronic device (200) where the flow pressure is lower than a reference pressure as a refrigerant leak site.

[0129] Figures 13 and 14 are graphs illustrating leakage in a low-pressure section and a high-pressure section, respectively, according to at least one embodiment of the present disclosure. For example, if a slight decrease in power consumption is detected, it can be determined that refrigerant is leaking between the compressor outlet and the expansion valve inlet (high-pressure section), and if an upward trend in power consumption is detected, it can be determined that refrigerant is leaking between after the expansion valve and the compressor inlet (low-pressure section).

[0130] In Figures 13 and 14, the horizontal axis represents time, and the vertical axis represents power consumption. Here, power consumption may be the total power consumption calculated by adding up the power consumption used in each component within the refrigerator (200).

[0131] Through repeated experiments, it was confirmed that different power consumption change patterns were obtained depending on the location of refrigerant leakage within the refrigerant circulation system.

[0132] The processor (130) searches for a pattern matching the power consumption change pattern of the refrigerator (200) among the information on the power consumption change pattern by part stored in the memory (120), and can predict the refrigerant leakage part based on the pattern.

[0133] Referring to Figure 13, power consumption is maintained in a constant pattern and then increases overall at a certain point in time. If this pattern is detected, the processor (130) can predict that refrigerant will leak from the low-pressure section.

[0134] Referring to Figure 14, power consumption is maintained in a constant pattern, then slightly decreases at a certain point in time, and then irregularly increases significantly. If a pattern like Figure 14 is detected, the processor (130) can predict that refrigerant will leak from the high-pressure section.

[0135] Based on the acquired information, the process can transmit information on recommended usage patterns to prevent refrigerant leakage to the user terminal device (300) via the communication unit (110).

[0136] When the possibility of a refrigerant leak in the refrigerator is diagnosed, the processor (130) can determine a recommended usage pattern to alleviate the temperature rise rate in the refrigerator and freezer compartments of the refrigerator due to the refrigerant leak, and transmit information on the diagnosis result and the determined recommended usage pattern to the user terminal device (300) through the communication unit (110).

[0137] When information such as diagnosis results and recommended usage patterns are transmitted to at least one of an electronic device (200) and a user terminal device (300), these devices (200, 300) can display a UI screen including the transmitted information. If they are equipped with a display for displaying a UI screen, these devices (200, 300) can be described as display devices.

[0138] FIG. 15 is a diagram illustrating a UI screen displayed on a user terminal device according to at least one embodiment of the present disclosure. FIG. 15 illustrates a user terminal device (300) implemented in the form of a mobile phone as an example.

[0139] The user terminal device (300) can store an application for controlling the electronic device (200). When the application is executed, the user terminal device (300) can display a UI screen for the electronic device (200). Various menus or information can be displayed on the UI screen. As described above, if information such as the status diagnosis results and recommended usage patterns of the electronic device (200) are provided from the server device (100), the user terminal device (300) can display a notification message therefor. FIG. 15 illustrates a case where a notification message such as "An abnormal refrigerator temperature has been detected. Please contact the service center" is displayed.

[0140] When the user touches the notification message, the user terminal device (300) can additionally display related messages such as checking the amount of refrigerant that may be the cause of an abnormal refrigerator temperature.

[0141] When the user confirms the related message, the user terminal device (300) can display a UI screen including various information such as the leak location and predicted leak time, as well as various menus.

[0142] According to Fig. 15, various menus such as refrigerant leakage progress graph, service center connection, on-site service reservation, AI confirmation, and no diagnosis content display are displayed, but are not necessarily limited to this, and the type, number, display location, display form, etc. of the menus can be modified in various ways.

[0143] Meanwhile, in the various embodiments described above, the server device (100) is illustrated and described as being capable of performing not only management and control but also diagnostic operations for each external device, but these operations may also be divided and processed by multiple different server devices. For example, the server device (100) may collect usage history data, etc. and transmit them to a separately provided AI prediction server (not shown). As described in the above-described section, the AI ​​prediction server may diagnose a condition or abnormality that may occur in the future using at least one artificial intelligence model and transmit the diagnosis result to the server device (100). The server device (100) may provide the received diagnosis result to the user terminal device (300) or the electronic device (200).

[0144] FIG. 16 is a block diagram illustrating a configuration of an electronic device (200) according to at least one embodiment of the present disclosure. The electronic device (200) may include a processor (220), a memory (230), a communication unit (240), and a plurality of sensors (210-1 to 210-m). Specific examples of the processor (220), the memory (230), and the communication unit (240) among the configurations of FIG. 16 have been described in the aforementioned FIG. 2, and therefore, a redundant description thereof will be omitted.

[0145] As described above, the electronic device (200) is an electronic device that uses a refrigerant and can be implemented as various devices such as a refrigerator or air conditioner. The following description will be based on the case where it is implemented as a refrigerator.

[0146] The electronic device (200) can communicate with the server device (100).

[0147] Multiple sensors (210-1 to 210-m) are configured to detect various information such as the refrigerator's internal temperature, humidity, and the number of times the door is opened and closed.

[0148] The processor (220) can acquire various usage history data based on values ​​sensed by a plurality of sensors (210-1 to 210-m). The processor (220) can store the acquired usage history data in the memory (230).

[0149] In the case of an electronic device (200) used in a system such as FIG. 1, the processor (220) can transmit usage history data to the server device (100) via the communication unit (240). When the processor (220) receives a diagnosis result from the server device (100), it can store the diagnosis result in the memory (230) and display the diagnosis result via a display (not shown) provided therein.

[0150] Meanwhile, according to another embodiment, the processor (220) may directly diagnose the status of the electronic device (200) based on the usage history data.

[0151]

[0152] *Specifically, the memory (230) can store the first and second artificial intelligence models described above. The processor (220) can acquire future usage history data using the first artificial intelligence model, and then use the second artificial intelligence model to predict and diagnose the possibility of a refrigerant leak in advance.

[0153] The processor (220) may display the diagnosis results on its own display (not shown) or transmit them to the user terminal device (300) owned by the user through the communication unit (240). Alternatively, the processor (220) may apply for A / S in advance to the service center device based on the identification information of the pre-registered service center device. In this case, the processor (220) may apply for A / S when the user inputs an A / S reception request through the display or the user terminal device (300), but is not necessarily limited thereto, and may apply automatically without user intervention.

[0154] FIG. 17 is a block diagram illustrating the configuration of a user terminal device (300) according to an embodiment of the present disclosure. The user terminal device (300) may include a processor (320), a memory (330), a communication unit (310), and a display (340). Specific examples of the processor (320), the memory (330), and the communication unit (310) have been described in the section regarding FIG. 2, and therefore, redundant description is omitted.

[0155] The user terminal device (300) may be an electronic device such as a smartphone. However, this is merely an example, and the user terminal device (300) may be various electronic devices that the user can carry, such as a tablet PC or laptop. Furthermore, the user terminal device (300) may be implemented as various wearable devices that can be worn on the user's body, such as a smartwatch or smart gear.

[0156] An application capable of controlling various electronic devices (200-1 to 200-n) may be stored in the memory (330). For example, if the electronic devices (200-1 to 200-n) are various home appliances such as a refrigerator, an air conditioner, a TV, a washing machine, a vacuum cleaner, a projector, and an air purifier placed in a single household, the user may register information about each home appliance in advance in the server device (100) through the application and control them remotely through the server device (100). The user may create his / her own user account in advance in the server device (100) and register information about the electronic devices (200-1 to 200-n) he / she uses in the user account.

[0157] When a user runs an application after registration, the processor (320) configures an execution screen of the application and displays it on the display (340). The execution screen of the application may be the UI screen described above. When a user selects an electronic device, for example, a refrigerator, on the UI screen, the processor (320) may display a UI screen indicating the current status of the refrigerator, etc. An example of the UI screen is illustrated in FIG. 15, but various other UI screens may be provided.

[0158] In the various embodiments described above, the case where the server device (100) or the AI ​​prediction server or the electronic device (200) diagnoses the future state of the electronic device (200) has been described, but according to another embodiment of the present disclosure, the user terminal device (300) may also diagnose the state of the electronic device (200).

[0159] For example, when usage history data of an electronic device (200) is received through a communication unit (310), the processor (320) stores the usage history data in a memory (330). The processor (320) performs a diagnosis based on the usage history data using at least one artificial intelligence model stored in the memory (330). Since the method for generating future usage history data and the diagnosis method have been described in the various embodiments described above, a duplicate description will be omitted.

[0160] The processor (320) can transmit the diagnostic results to a server device (100) or a service center device through a communication unit (310), or display them through a display (340).

[0161] FIG. 18 is a flowchart illustrating a diagnostic method of a server device according to various embodiments of the present invention.

[0162] According to FIG. 18, the server device receives and stores usage history data of at least one electronic device using a refrigerant from at least one electronic device (S1810).

[0163] The server device obtains future usage history data using the stored usage history data and the first artificial intelligence model (S1820).

[0164] The server device diagnoses the possibility of a refrigerant leak in at least one electronic device using future usage history data and a second artificial intelligence model (S1830).

[0165] The server device generates information on a recommended usage pattern for preventing refrigerant leakage based on the diagnosis result and transmits the information to at least one electronic device or a corresponding user terminal device (S1840).

[0166] Since the method for obtaining future usage history data and the method for diagnosing the possibility of refrigerant leakage have been described in the various embodiments described above, a duplicate description will be omitted.

[0167] The diagnostic method of Fig. 18 can be performed on electronic devices such as refrigerators, but is not necessarily limited thereto, and can also be performed on air conditioners or other various devices that use refrigerants.

[0168] Additionally, although the various embodiments described above have been described based on the use of the first and second artificial intelligence models, at least one of these artificial intelligence models may be replaced with a software module that operates in a rule-based manner.

[0169] The diagnostic method described in Fig. 18 can be performed by devices having various configurations such as those of Fig. 2, Fig. 16, and Fig. 17 described above, but is not necessarily limited thereto, and can also be performed by devices having various configurations.

[0170] The various embodiments described above may be implemented as a single embodiment, or at least one embodiment may be combined with each other in whole or in part and implemented together in one device.

[0171] According to the various embodiments described above, abnormal conditions, such as refrigerant leaks, can be diagnosed in advance. Furthermore, damage caused by abnormal conditions can be minimized by providing recommended usage patterns that are improved over current usage patterns.

[0172] The various embodiments described above can be implemented as software including instructions stored in a machine-readable storage medium that can be read by a machine (e.g., a computer). The device is a device that can call instructions stored in the storage medium and operate according to the called instructions, and may include an electronic device (e.g., a server device, an electronic device, a user terminal device, etc.) according to the disclosed embodiments. When an instruction is executed by a processor, the processor can perform a function corresponding to the instruction directly or by using other components under the control of the processor. The instruction may include code generated or executed by a compiler or interpreter. The machine-readable storage medium can be provided in the form of a non-transitory computer-readable storage medium. Here, 'non-transitory' means that the storage medium does not contain a signal and is tangible, but does not distinguish between data being stored semi-permanently or temporarily in the storage medium.

[0173] Additionally, according to one embodiment of the present disclosure, the method according to the various embodiments described above may be provided as included in a computer program product.

[0174] Specifically, a non-transitory readable storage medium or a computer program product storing computer instructions that cause an operation to be performed, including a step of receiving and storing usage history data of at least one electronic device, a step of obtaining future usage history data of the electronic device predicted by a first artificial intelligence model based on the usage history data, a step of obtaining information on the possibility of refrigerant leakage of at least one electronic device diagnosed by a second artificial intelligence model based on the future usage history data, and a step of generating information on a recommended usage pattern to prepare for refrigerant leakage based on the obtained information and transmitting the information to a user terminal device corresponding to at least one electronic device, may be provided.

[0175] The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or online through an application store (e.g., Play Store™). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created in a storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0176] In addition, computer instructions or programs for performing the diagnostic methods and the like according to the various embodiments described above may be stored in a non-transitory computer-readable medium. The computer instructions stored in such a non-transitory computer-readable medium, when executed by a processor of a specific device, cause the specific device to perform processing operations in the device according to the various embodiments described above. A non-transitory computer-readable medium refers to a medium that stores data semi-permanently and can be read by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specific examples of non-transitory computer-readable media may include a CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM, etc.

[0177] Although the preferred embodiments of the present disclosure have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above, and various modifications may be made by a person skilled in the art to which the present disclosure pertains without departing from the gist of the present disclosure as claimed in the claims, and such modifications should not be understood individually from the technical idea or prospect of the present disclosure.

Claims

1. For server devices, A communication unit for performing communication with at least one electronic device using a refrigerant and a user terminal device corresponding to the at least one electronic device; Memory in which the first and second artificial intelligence models are stored; and a processor; including; The above processor, Receiving usage history data of at least one electronic device from at least one electronic device through the communication unit and storing it in the memory, Based on the above usage history data, future usage history data of the electronic device predicted by the first artificial intelligence model is obtained, Obtain information on the possibility of refrigerant leakage of at least one electronic device diagnosed by the second artificial intelligence model based on the above future usage history data, A server device that transmits information on a recommended usage pattern for preventing refrigerant leakage to at least one electronic device or the user terminal device through the communication unit based on the information obtained above.

2. In paragraph 1, At least one electronic device of the above, Includes refrigerator, The above processor, A server device that, when the possibility of a refrigerant leak in the refrigerator is diagnosed, determines the recommended usage pattern to alleviate the temperature rise rate of the refrigerator and freezer compartment of the refrigerator due to the refrigerant leak, and transmits the diagnosis result and information on the determined recommended usage pattern to the user terminal device through the communication unit.

3. In paragraph 2, The processor performs a first preprocessing operation to make the usage history data stored in the memory into a form processable by the first artificial intelligence model, and inputs the preprocessed usage history data into the first artificial intelligence model. A server device that performs a second preprocessing operation to transform the future usage history data acquired by the first artificial intelligence model into a form processable by the second artificial intelligence model, and inputs the preprocessed future usage history data into the second artificial intelligence model.

4. In paragraph 1, The above processor, A server device that predicts a refrigerant leak location within at least one electronic device based on a change pattern in a power consumption value consumed by at least one electronic device among the future usage history data.

5. In paragraph 4, The above processor, If the above power consumption value is a pattern of increasing, a high pressure section in the refrigerant circulation line through which the refrigerant flows within at least one electronic device, in which the flow pressure is higher than the reference pressure, is predicted as the refrigerant leakage section, A server device that predicts a low-pressure section in the refrigerant circulation line where the flow pressure is lower than the reference pressure as the refrigerant leakage section if the above power consumption value is a pattern of slight reduction.

6. In paragraph 1, The above processor, A server device characterized in that, when the above refrigerant leakage is predicted, the cooling maintenance period within the electronic device in the case where use continues with a usage pattern corresponding to the usage history data is predicted using the first artificial intelligence model, and the prediction result is transmitted to at least one of a service center device corresponding to the electronic device and the user terminal device through the communication unit.

7. In paragraph 1, The above processor, A server device, wherein, when the above refrigerant leakage is predicted, the cooling maintenance period within the electronic device when used in a plurality of usage patterns is predicted using the first artificial intelligence model, and the usage pattern with the longest cooling maintenance period among the plurality of usage patterns is determined as the recommended usage pattern in preparation for the above refrigerant leakage.

8. A diagnostic method of a server device for diagnosing the status of at least one electronic device using a refrigerant, A step of receiving and storing usage history data of at least one electronic device from at least one electronic device; A step of obtaining future usage history data of the electronic device predicted by the first artificial intelligence model based on the usage history data; A step of obtaining information on the possibility of refrigerant leakage of at least one electronic device diagnosed by a second artificial intelligence model based on the future usage history data; A diagnostic method, comprising: a step of generating information on a recommended usage pattern for preparing for a refrigerant leak based on the acquired information, and transmitting the information to at least one electronic device or a user terminal device corresponding to the at least one electronic device.

9. In paragraph 8, At least one electronic device of the above, Includes refrigerator, The step of generating information about the above recommended usage pattern and transmitting it to a user terminal device corresponding to at least one electronic device is: When the possibility of refrigerant leakage in the above refrigerator is diagnosed, a step of determining the recommended usage pattern to alleviate the temperature rise rate in the refrigerator and freezer compartments of the above refrigerator due to the refrigerant leakage; A diagnostic method, comprising: a step of transmitting information on the above diagnostic results and the determined recommended usage pattern to the user terminal device.

10. In paragraph 8, A step of performing a first preprocessing operation to make the above usage history data into a form processable by the first artificial intelligence model; A diagnostic method further comprising: a step of performing a second preprocessing operation for converting the future usage history data acquired by the first artificial intelligence model into a form processable by the second artificial intelligence model.

11. In paragraph 8, A diagnostic method further comprising: a step of predicting a refrigerant leak location within at least one electronic device based on a change pattern of a power consumption value consumed by at least one electronic device among the future usage history data.

12. In paragraph 11, The above predicting steps are: If the above power consumption value is a pattern of increasing, a step of predicting a high pressure section of the refrigerant circulation line through which the refrigerant flows within the at least one electronic device, in which the flow pressure is higher than the reference pressure, as the refrigerant leakage section; and A diagnostic method, comprising: a step of predicting a low-pressure portion of the refrigerant circulation line in which the flow pressure is lower than the reference pressure as the refrigerant leakage portion if the above power consumption value is a pattern of slight reduction; 13. In paragraph 8, If the above refrigerant leakage is predicted, a step of predicting the cooling maintenance period within the electronic device when use continues with a usage pattern corresponding to the usage history data using the first artificial intelligence model; A diagnostic method, characterized in that it further comprises a step of transmitting the prediction result to at least one of a service center device corresponding to the electronic device and the user terminal device.

14. In paragraph 8, The step of generating information about the above recommended usage pattern and transmitting it to a user terminal device corresponding to at least one electronic device is: If the above refrigerant leakage is predicted, a step of predicting the cooling maintenance period within the electronic device when used in multiple usage patterns using the first artificial intelligence model; A diagnostic method, comprising: a step of determining a usage pattern having the longest cooling maintenance period among the plurality of usage patterns as a recommended usage pattern to prepare for refrigerant leakage.

15. A non-transitory readable recording medium storing a program for performing a diagnostic method for diagnosing the condition of at least one electronic device using a refrigerant, The above diagnostic method is, A step of receiving and storing usage history data of at least one electronic device from at least one electronic device; A step of obtaining future usage history data of the electronic device predicted by the first artificial intelligence model based on the usage history data; A step of obtaining information on the possibility of refrigerant leakage of at least one electronic device diagnosed by a second artificial intelligence model based on the future usage history data; A non-transitory readable recording medium, comprising: a step of generating information on a recommended usage pattern for preparing for a refrigerant leak based on the acquired information, and transmitting the information to at least one electronic device or a user terminal device corresponding to the at least one electronic device.

Images