Electronic equipment and control method of electronic equipment

Abstract

An electronic device and a control method of the electronic device are provided. The electronic device includes first device information based on a hardware specification of the electronic device, second device information on a hardware specification of a first external device, first model information on one or more neural network models included in the first external device, and identifying whether each of the one or more neural network models included in the first external device is suitable for hardware of the electronic device with respect to second model information of the one or more neural network models included in the electronic device, and whether each of the one or more neural network models identified as suitable for hardware of the electronic device is suitable for replacing a neural network included in the electronic device.

Description

[0001] This application is a divisional application of the following application: Application No. 202080084829.8; Application Date: December 4, 2020; Invention Name: "Electronic device and control method of electronic device". TECHNICAL FIELD

[0002] The present application relates to an electronic device and a control method of the electronic device. More particularly, the present application relates to an electronic device and a control method of the electronic device for identifying conversion suitability of a neural network model included in an external device. BACKGROUND

[0003] In recent years, there is an increasing demand from users and industries for a technology for providing customized services for each user through a personalized neural network model. However, on the other hand, there is also an increasing demand for protecting personal data related to user privacy, and thus, in many cases, it is limited to training a neural network model by collecting personal data required for neural network model personalization.

[0004] Accordingly, a technology enabling a neural network model to be used on a device without transmitting personal data to an external server or a cloud, and a technology for transferring information of a personalized neural network model from a specific device to another device through device-to-device communication are attracting attention.

[0005] In the case of transferring information about a personalized neural network model from a specific device to another device, if the types of the devices are different from each other, or even if the types of the devices are the same but the hardware specifications are different, it can not be suitable to transfer the neural network model. Accordingly, when transferring information about a personalized neural network model from a device to another device, it is necessary to perform an identification process about whether it is suitable to transfer the neural network model between different devices.

[0006] In addition, when a user of an electronic device purchases a new electronic device, a technology capable of transferring a personalized neural network model from an existing electronic device to the new electronic device in a highly reliable and efficient method is required.

[0007] The above information is provided solely for the purpose of helping to understand the present disclosure. It is not admitted that any of the above information constitutes prior art to the present disclosure. It is further not admitted that any of the above information is relevant or relevant to the patentability of the present disclosure. SUMMARY

[0008] [TECHNICAL PROBLEM]

[0009] Aspects of the present application are to address at least the above-mentioned problems and / or disadvantages and to provide at least the advantages described below. Accordingly, an aspect of the present application is to provide an electronic device and a control method thereof, which can identify whether a neural network model included in an external device is suitable to be transferred to the electronic device based on information about hardware specifications of each of the electronic device and the external device and information of a neural network model.

[0010] Additional aspects will be set forth in part in the description which follows, and in part will be apparent from the description, or can be learned by practice of the presented embodiments.

[0011] [Technical Solution]

[0012] According to an aspect of the present application, there is provided an electronic device for identifying conversion suitability of a neural network model included in an external device. The electronic device includes a communicator, a memory configured to store first device information about a hardware specification of the electronic device and a hardware suitability identifier identifying a neural network model suitable for hardware of the electronic device, and a processor configured to, based on a received user input, control the communicator to transmit a first signal for requesting information about one or more neural network models included in one or more external devices, receive, as a response to the first signal, a second signal including second device information about a hardware specification of a first external device among the one or more external devices and first model information about the one or more neural network models included in the first external device from the first external device through the communicator, identify whether each of the one or more neural network models included in the first external device is suitable for hardware of the electronic device by inputting the first device information, the second device information, and the first model information into the hardware suitability identifier, control the communicator to transmit a third signal including a request for installation data of the one or more neural network models identified as being suitable for the hardware of the electronic device to the first external device, and receive, as a response to the third signal, a fourth signal including the installation data of the one or more neural network models identified as being suitable for the hardware of the electronic device from the first external device through the communicator, wherein the processor is configured to identify the one or more neural network models included in the first external device as being suitable for the hardware of the electronic device based on a specification of each of a plurality of hardware configurations included in the electronic device being greater than or equal to a specification of a plurality of hardware configurations included in the first external device, and identify one or more neural network models among the one or more neural network models included in the first external device, which have a hardware requirement specification lower than the specification of the plurality of hardware configurations included in the electronic device, as being suitable for the hardware of the electronic device based on a specification of one or more of the plurality of hardware configurations included in the electronic device being less than the specification of the plurality of hardware configurations included in the first external device.

[0013] According to another aspect of the present application, a control method of an electronic device that stores first device information about hardware specifications of the electronic device and a hardware suitability recognizer that identifies neural network models suitable for hardware of the electronic device, and identifies conversion suitability of neural network models included in an external device. The control method includes transmitting a first signal for requesting information about one or more neural network models included in one or more external devices based on a received user input, receiving a second signal including second device information about hardware specifications of a first external device from among the one or more external devices and first model information about one or more neural network models included in the first external device as a response to the first signal, identifying whether each of the one or more neural network models included in the first external device is suitable for hardware of the electronic device by inputting the first device information, the second device information, and the first model information into the hardware suitability recognizer, transmitting a third signal including a request for installation data of the one or more neural network models identified as being suitable for the hardware of the electronic device to the first external device, and receiving a fourth signal including the installation data of the one or more neural network models identified as being suitable for the hardware of the electronic device from the first external device as a response to the third signal, wherein the identifying whether each of the one or more neural network models is suitable for the hardware of the electronic device includes identifying the one or more neural network models included in the first external device as being suitable for the hardware of the electronic device based on specifications of each of a plurality of hardware configurations included in the electronic device being greater than or equal to specifications of a plurality of hardware configurations included in the first external device, and identifying one or more neural network models of the one or more neural network models included in the first external device having hardware requirement specifications lower than the specifications of the plurality of hardware configurations included in the electronic device as being suitable for the hardware of the electronic device based on the specifications of one or more of the plurality of hardware configurations included in the electronic device being less than the specifications of the plurality of hardware configurations included in the first external device.

[0014] In accordance with another aspect of the present disclosure, a non-transitory computer-readable recording medium including a program for executing a control method of an electronic device that stores first device information about hardware specifications of the electronic device and a hardware suitability recognizer that identifies a neural network model suitable for hardware of the electronic device, and identifies a conversion suitability of a neural network model included in an external device. The control method includes transmitting, based on a received user input, a first signal for requesting information about one or more neural network models included in one or more external devices, receiving, as a response to the first signal, a second signal including second device information about hardware specifications of a first external device from among the one or more external devices and first model information about one or more neural network models included in the first external device, identifying, by inputting the first device information, the second device information, and the first model information into the hardware suitability recognizer, whether each of the one or more neural network models included in the first external device is suitable for hardware of the electronic device, transmitting, to the first external device, a third signal including a request for installation data of one or more neural network models identified as being suitable for the hardware of the electronic device, and receiving, as a response to the third signal, a fourth signal including the installation data of the one or more neural network models identified as being suitable for the hardware of the electronic device from the first external device, wherein the identifying whether each of the one or more neural network models is suitable for the hardware of the electronic device includes identifying that the one or more neural network models included in the first external device are suitable for the hardware of the electronic device based on specifications of each of a plurality of hardware configurations included in the electronic device being greater than or equal to specifications of a plurality of hardware configurations included in the first external device, and identifying, as being suitable for the hardware of the electronic device, one or more neural network models among the one or more neural network models included in the first external device, for which a hardware requirement specification is lower than specifications of the plurality of hardware configurations included in the electronic device, based on the specifications of one or more of the plurality of hardware configurations included in the electronic device being less than the specifications of the plurality of hardware configurations included in the first external device.

[0015] In accordance with another aspect of the present application, there is provided an electronic device for identifying conversion suitability of a neural network model included in an external device. The electronic device includes a communicator; a memory configured to store internal model information about one or more neural network models included in the electronic device and a model suitability identifier identifying whether a neural network model is suitable for replacing a neural network model included in the electronic device; and a processor configured to, based on a received user input, control the communicator to transmit a first signal for requesting information about one or more neural network models included in one or more external devices, receive, as a response to the first signal, a second signal including external model information about one or more neural network models included in a first external device from the first external device through the communicator, identify whether each of the one or more neural network models included in the first external device is suitable for replacing a neural network model included in the electronic device by inputting the internal model information and the external model information into the model suitability identifier, control the communicator to transmit a third signal including a request for installation data of one or more neural network models identified as being suitable for replacing the one or more neural network models included in the electronic device to the first external device, and receive, as a response to the third signal, a fourth signal including the installation data of the one or more identified neural network models from the first external device through the communicator, wherein the processor is configured to compare a service type of the one or more neural network models included in the electronic device with a service type of the one or more neural network models included in the first external device based on service type information included in each of the internal model information and the external model information, identify the first neural network model included in the one or more neural network models included in the first external device as being suitable for replacing a second neural network model included in the plurality of neural network models included in the electronic device based on the service type of the first neural network model being identical to a service type of the second neural network model, compare a level of personalization of the first neural network model with a level of personalization of the second neural network model based on information about the level of personalization included in each of the internal model information and the external model information, and identify the first neural network model as being suitable for replacing the second neural network model based on the level of personalization of the first neural network model being higher than the level of personalization of the second neural network model.

[0016] Other aspects, advantages, and salient features of the application will become apparent to those skilled in the art from the following detailed description, which, taken in BRIEF DESCRIPTION OF DRAWINGS

[0017] The above and other aspects, features, and advantages of certain embodiments of the present application will be more apparent from the following description taken in conjunction with the accompanying drawings, in which:

[0018] Figure 1is a flowchart illustrating a control method of an electronic device according to an embodiment of the present application;

[0019] Figure 2 , 3 and 4 are diagrams for specifically describing operations of a hardware suitability identification module for performing a control method of an electronic device according to various embodiments of the present application according to Figure 1

[0020] Figure 5A is a flowchart illustrating a control method of an electronic device according to an embodiment of the present application;

[0021] Figure 5B is a flowchart illustrating a control method of an electronic device according to an embodiment of the present application;

[0022] Figure 6 , 7 and 8 are diagrams for specifically describing operations of a model suitability identification module for performing a control method of an electronic device according to various embodiments of the present application according to Figure 5A and 5B

[0023] Figure 9 is a flowchart for describing a control method of an electronic device according to an embodiment of the present application;

[0024] Figure 10 is a sequence diagram for describing an example of a case where a plurality of external devices exist according to an embodiment of the present application;

[0025] Figure 11 is a diagram for describing a user interface provided by an electronic device according to an embodiment of the present application;

[0026] Figure 12 is a diagram for describing a user interface provided by a first external device according to an embodiment of the present application;

[0027] Figure 13 is a diagram illustrating an example of an electronic device, a first external device, and a second external device according to an embodiment of the present application;

[0028] Figure 14 is a sequence diagram for describing a process of identifying conversion suitability by an electronic device when a neural network model included in a first external device is transferred to a second external device according to an embodiment of the present application;

[0029] Figure 15 is a block diagram illustrating in detail an architecture of a software module included in an electronic device according to an embodiment of the present application;

[0030] Figure 16 ​​is a block diagram showing an architecture of a software module included in a first external device according to an embodiment of the present application in detail;

[0031] Figure 17 is a block diagram schematically showing an architecture of a hardware configuration included in an electronic device according to an embodiment of the present application; and

[0032] Figure 18 is a block diagram showing an architecture of a hardware configuration included in an electronic device according to an embodiment of the present application in more detail.

[0033] Throughout the drawings, like reference numerals will be understood to refer to like parts, components, and structures. DETAILED DESCRIPTION

[0034] The following description with reference to the accompanying drawings is provided to assist in a comprehensive understanding of various embodiments of the present application as defined by the claims and their equivalents. It includes various specific details to assist in that understanding but these are to be taken as examples only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the various embodiments described herein can be made without departing from the scope and spirit of the application. In addition, descriptions of well-known functions and constructions can be omitted for clarity and conciseness.

[0035] The terms and words used in the following description and claims are not limited to the bibliographical meanings, but are merely used to enable a clear and complete understanding of the application by those skilled in the art. Accordingly, it should be apparent to those skilled in the art that the following description of various embodiments of the present application is provided for illustration purpose only and not for the purpose of limiting the present application as defined by the appended claims and their equivalents.

[0036] It is to be understood that the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. Thus, for example, reference to "a component surface" includes reference to one or more of such surfaces.

[0037] The terms used in the present application are merely used to describe specific embodiments, and are not intended to limit the scope of the present application. Singular expressions include plural expressions unless the context clearly dictates otherwise.

[0038] In the present application, the expressions "have," "may have," "include," "may include," and the like indicate existence of the corresponding features (e.g., numerical values, functions, operations, components such as parts, or the like) and do not exclude the presence of additional features.

[0039] In the present disclosure, the expressions "A or B", "at least one of A and / or B", "one or more of A and / or B" or the like can include all possible combinations of the items listed. For example, "A or B", "at least one of A and B", or "at least one of A or B" can mean (1) including at least one A, (2) including at least one B, or (3) including both at least one A and at least one B.

[0040] The expressions "first", "second", and the like used in the present disclosure can represent various components regardless of the order and / or importance of the components, will be used only to distinguish one component from the other components, and do not limit the corresponding components.

[0041] When it is mentioned that any component (for example, a first component) is coupled or connected to another component (for example, a second component) (operatively or communicatively), it should be understood that any component is directly coupled / connected to another component, or can be coupled / connected to another component through other components (for example, a third component).

[0042] On the other hand, when it is mentioned that any component (for example, a first component) is "directly coupled" or "directly connected" to another component (for example, a second component), it should be understood that another component (for example, a third component) does not exist between any component and another component.

[0043] According to circumstances, the expression "configured (or set) to" used in the present disclosure can be replaced with "adapted to", "capable of", "designed to", "apt to", "manufactured to", or "able to". The term "configured (or set) to" does not necessarily mean only "designed to" in hardware.

[0044] Alternatively, the expression "configured to" can mean that the device "is able to" with other devices or components in any context. For example, "a processor configured (or set) to perform processes A, B, and C" can refer to a dedicated processor (for example, an embedded processor) for performing the corresponding operations, or a general-purpose processor (for example, a central processing unit (CPU) or an application processor) that can perform the corresponding operations by executing one or more software stored in a memory device.

[0045] In an embodiment, a "module" or a "unit" can perform at least one function or operation, and can be implemented as hardware or software, or as a combination of hardware and software. In addition, a plurality of "modules" or a plurality of "units" can be integrated in at least one module, and can be implemented as at least one processor, except for a "module" or a "unit" that needs to be implemented as a specific hardware.

[0046] On the other hand, various elements and areas in the drawings are shown in the form of a schematic diagram. Therefore, the technical spirit of the present application is not limited by the relative sizes or intervals shown in the drawings.

[0047] The electronic device according to different embodiments of the present application can include at least one of, for example, a smartphone, a tablet Personal Computer (PC), a desktop PC, a notebook PC, or a wearable device. The wearable device can include at least one of a fashion device (e.g., a watch, a ring, a bracelet, an ankle chain, a necklace, glasses, contact lenses, or a Head-Mounted Device (HMD)), a textile or a clothing integral device (e.g., an electronic clothing), a body-attached device (e.g., a skin pad or a tattoo), or a bio-implantable circuit.

[0048] In some embodiments, the electronic device can include a television (TV), a Digital Video Disk (DVD) player, an audio player, a refrigerator, an air conditioner, a cleaner, an oven, a microwave oven, a washing machine, an air cleaner, a set-top box, a home automation control panel, a security control panel, a media box (e.g., HomeSync™ of Samsung Electronics Co., Ltd., Apple TV™, or Google TV™), a game console (e.g., Xbox™ and PlayStation™), an electronic dictionary, an electronic key, a camcorder, or a digital photo frame.

[0049] In other embodiments, the electronic device can include at least one of various medical devices (e.g., various portable medical measuring devices (such as a blood glucose meter, a heart rate meter, a blood pressure meter, a body temperature meter, etc.), a Magnetic Resonance Angiography (MRA), a Magnetic Resonance Imaging (MRI), a Computed Tomography (CT), a photography device, an ultrasonic device, etc.), a navigation device, a Global Navigation Satellite System (GNSS), an Event Data Recorder (EDR), a Flight Data Recorder (FDR), a car infotainment device, ship electronic devices (e.g., a ship navigation device, a gyrocompass, etc.), avionics, security devices, a car head unit, an industrial or home robot, a drone, a financial institution’s automatic teller’s machine (ATM), a shop’s Point Of Sales (POS), or an Internet of Things (IoT) device (e.g., a light bulb, various sensors, an aqueous fire sprinkler, a fire alarm, a thermostat, a street light, a toaster, a sports device, a hot water tank, a heater, a boiler, etc.).

[0050] Hereinafter, embodiments of the present application will be described in detail with reference to the accompanying drawings so that those skilled in the art to which the present application pertains can easily practice the present application.

[0051] Figure 1 is a flowchart illustrating a control method of an electronic device according to an embodiment of the present application.

[0052] Figures 2 to 4is a diagram for specifically describing an operation of a hardware suitability identification module 1100 (see Figure 1 ) of a control method (see Figure 17 ) of an electronic device 100 for performing according to various embodiments of the present application. Figure 2

[0053] First, the "electronic device" according to the present application can be implemented in various types such as a smartphone, a tablet, a notebook computer, a television, and a robot, and is not limited to a specific type of device. Hereinafter, the electronic device according to the present application is referred to as an electronic device 100.

[0054] The neural network model refers to an artificial intelligence model including an artificial neural network, and can be trained through deep learning. For example, the neural network model can include at least one artificial neural network model among a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), or a generative adversarial network (GAN). However, the neural network model according to the present application is not limited to the above-described examples.

[0055] In the electronic device 100 according to the present application, first device information about hardware specifications of the electronic device 100 and the hardware suitability identification module 1100 can be stored.

[0056] The "first device information" refers to information about hardware specifications of the electronic device 100. Specifically, the first device information is a term used to generically refer to information about specifications indicating what performance each of a plurality of hardware included in the electronic device 100 has, and can include detailed information about the presence, the number, the type, and the performance of each of a plurality of hardware components included in the electronic device 100.

[0057] Specifically, the first device information can include information about specifications of a processor included in the electronic device 100, specifications of a memory included in the electronic device 100, and specifications of a data obtainer included in the electronic device 100. The data obtainer is a component that obtains data input to one or more neural network models included in the electronic device 100, and can include at least one of a camera, a microphone, or a sensor included in the electronic device 100.

[0058] The first device information can include performance evaluation information about each of a plurality of hardware included in the electronic device 100. The "performance evaluation information" is a score obtained by comprehensively evaluating the performance of each hardware configuration based on experiments and analysis by experts, and can be pre-stored in the electronic device 100 and can be received and updated from an external server.

[0059] ​The "hardware suitability identification module 1100" refers to a module that identifies a neural network model suitable for the hardware of the electronic device 100. Specifically, the "hardware suitability identification module 1100" can output information about whether it is suitable to execute a neural network model included in an external device by using the hardware of the electronic device 100. In describing the present application, the term "suitable for" can be replaced with terms such as "compatible with" or "alternative to."

[0060] Referring to Figure 1 In operation S110, when a user input is received, the electronic device 100 can transmit a first signal for requesting information related to one or more neural network models included in one or more external devices.

[0061] The "user input" can be received based on a user touch input through a display of the electronic device 100, a user voice received through a microphone of the electronic device 100, or an input of a physical button provided in the electronic device 100, a control signal transmitted by a remote control device for controlling the electronic device 100, etc. The term "transmit" can be used as a meaning including unicast (where a signal or data is transmitted by targeting a specific external device) as well as broadcast (where a signal or data is simultaneously transmitted to all external devices connected to a network, without targeting a specific external device in transmitting the signal or data). The "information related to one or more neural network models" can include second device information and first model information, which will be described later.

[0062] Like the electronic device 100, the "external device" can be implemented as various types such as a smartphone, a tablet, a notebook computer, a television, and a robot, and the type of the external device can also be different from the type of the electronic device 100. The electronic device 100 and the external device can be "connected" to each other, which means that a communication connection is established by exchanging a request and a response of a communication connection between the electronic device 100 and the external device. The communication connection method according to the present application is not particularly limited.

[0063] As a response to the first signal, the electronic device 100 can receive a second signal including second device information about a hardware specification of the first external device and first model information about one or more neural network models included in the first external device from the first external device among the one or more external devices in operation S120. That is, if the first signal corresponding to the request to search for one or more neural network models is received, the first external device can transmit the second signal to the electronic device 100 as a response to the request, and the second signal can include the second device information and the first model information. In describing the present application, the term "first external device" is used as a term to designate an external device capable of transmitting installation data of a neural network model to the electronic device 100. Hereinafter, the first external device according to the present application will be referred to as a first external device 200-1 (see Figure 14 ).

[0064] The first external device 200-1 can perform a user authentication process based on the first user information included in the first signal and the second user information stored in the first external device 200-1, and can also transmit the second signal to the electronic device 100 when the user authentication is completed. The user authentication process or the user suitability recognition process will be described in detail with reference to Figure 9 and 10 .

[0065] The "second device information" refers to information about a hardware specification of the first external device 200-1. Specifically, the second device information is a term to generically refer to information about a specification indicating what performance each hardware included in the first external device 200-1 has, and corresponds to the first device information about the hardware performance of the electronic device 100.

[0066] That is, the second device information can include detailed information about the presence, number, type, and performance of each of a plurality of hardware configurations included in the first external device 200-1, and similar to the case of the first device information, the second device information can also include performance evaluation information of each hardware included in the first external device 200-1. In addition, the second device information can include information about a specification of a processor included in the first external device 200-1, a specification of a memory included in the first external device 200-1, and a specification of a data obtainer included in the first external device 200-1. The data obtainer of the first external device 200-1 is a component that obtains data input to one or more neural network models included in the first external device 200-1, similar to the data obtainer of the electronic device 100, and can include at least one of a camera, a microphone, or a sensor included in the first external device 200-1.

[0067] The "first model information" refers to information about one or more neural network models included in the first external device 200-1. Specifically, the first model information can include information about a service type, information about a level of personalization, and information about a hardware requirement specification of each of the one or more neural network models included in the first external device 200-1.

[0068] At operation S130, if the second signal including the second device information and the first model information is received from the first external device 200-1, the electronic device 100 can input the first device information, the second device information, and the first model information into the hardware suitability identification module 1100 to identify whether each of the one or more neural network models included in the first external device 200-1 is suitable for the hardware of the electronic device 100. That is, if the first device information, the second device information, and the first model information are input, the hardware suitability identification module 1100 can perform the hardware suitability identification process according to different embodiments of the disclosure based on the first device information, the second device information, and the first model information. Hereinafter, the "hardware suitability identification process" will be described with reference to Figures 2 to 4 and Figure 1 The "hardware suitability identification process" will be described in detail. Specifically, the hardware suitability identification process according to the present disclosure can include operations 1 and 2 as shown in Figure 2 and Figure 3

[0069] First, the "step 1" will be described with reference to Figure 1 and 2 By identifying whether the hardware specifications of the electronic device 100 are equal to or superior to the hardware specifications of the first external device 200-1 in all parts based on the first device information stored in the electronic device 100 and the second device information received from the first external device 200-1, the electronic device 100 can perform the hardware suitability identification process on all the neural network models included in the first external device 200-1.

[0070] Specifically, if the specifications of each of the plurality of hardware configurations included in the electronic device 100 are greater than or equal to the specifications of the plurality of hardware configurations included in the first external device 200-1 (Y in S140), at operation S150-1, the electronic device 100 can identify the one or more neural network models included in the first external device 200-1 as being suitable for the hardware of the electronic device 100.

[0071] ​That is, the electronic device 100 can identify the hardware configuration of the first external device 200-1 corresponding to each of the plurality of hardware configurations included in the electronic device 100, and can compare the specifications of each corresponding hardware configuration. Further, as a result of comparing the specifications of each of the plurality of hardware configurations included in the electronic device 100 with the specifications of each of the plurality of hardware configurations included in the first external device 200-1, if the specifications of each of the plurality of hardware configurations included in the electronic device 100 are greater than or equal to the specifications of the plurality of hardware configurations included in the first external device 200-1, this can be estimated as a case in which all one or more neural network models included in the first external device 200-1 can be executed using the hardware of the electronic device 100 regardless of which hardware specifications are required for each of the one or more neural network models included in the first external device 200-1. Accordingly, in this case, the electronic device 100 can identify all one or more neural network models included in the first external device 200-1 as being suitable for the hardware of the electronic device 100.

[0072] Referring to Figure 4 , the hardware suitability identification module 1100 can include a processor suitability identification module 1110, a memory suitability identification module 1120, a camera suitability identification module 1130, a microphone suitability identification module 1140, and a sensor suitability identification module 1150. Further, the electronic device 100 can perform a hardware suitability identification process for each hardware configuration based on information about processor specifications, memory specifications, camera specifications, microphone specifications, and sensor specifications included in the first and second device information through each module included in the hardware suitability identification module 1100.

[0073] For example, if the specifications of the processor, the memory, the camera, the microphone, and the sensor included in the electronic device 100 are all greater than or equal to the specifications of the processor, the memory, the camera, the microphone, and the sensor included in the first external device 200-1, the electronic device 100 can identify all one or more neural network models included in the first external device 200-1 as being suitable for the hardware of the electronic device 100. At this time, the electronic device 100 can perform a hardware suitability identification process for each hardware configuration in the order of the processor, the memory, the camera, the microphone, and the sensor, however, there is no specific order limitation in the hardware suitability identification process for each hardware configuration according to the present application.

[0074] In the above, it has been described that the specifications of the processor, the memory, the camera, the microphone, and the sensor included in each of the electronic device 100 and the first external device 200-1 are compared, but this is only for convenience of description, and according to the present application, the electronic device 100 can compare the specifications of each detailed component included in the processor, the memory, the camera, the microphone, and the sensor.

[0075] For example, the electronic device 100 can also perform the hardware suitability identification process by comparing the specifications of the electronic device 100 and the first external device 200-1 with respect to a central processing unit (CPU), a graphics processing unit (GPU), and a neural processing unit (NPU) in the processor, with respect to a random access memory (RAM) and a read-only memory (ROM) in the memory, and with respect to each sensor such as a global positioning system (GPS) sensor, a gyro sensor, an acceleration sensor, and a laser radar sensor in the sensor. Examples of the detailed components included in the processor, the memory, the camera, the microphone, and the sensor are not limited to the above examples.

[0076] According to one embodiment of the present application, the specifications of the hardware configuration included in the electronic device 100 are greater than or equal to the specifications of the hardware configuration included in the first external device 200-1, which can mean that all of the specifications indicating the performance of the hardware configuration included in the electronic device 100 are superior to or at least equal to all of the specifications indicating the performance of the hardware configuration included in the first external device 200-1.

[0077] For example, if the number of cores of the CPU included in the electronic device 100 is 8, the number of threads is 16, the clock speed is 3.6 GHz, and the capacity of the cache is 8 MB, and the number of cores of the CPU included in the first external device 200-1 is 4, the number of threads is 8, the clock speed is 3.3 GHz, and the capacity of the cache is 8 MB, the electronic device 100 can identify that the performance of the CPU of the electronic device 100 is greater than or equal to the performance of the CPU of the first external device 200-1. In this example, the number of cores, the number of threads, the clock speed, and the cache are exemplified as performance indicators of the CPU, but performance indicators such as bus speed and thermal design power (TDP) can be additionally considered.

[0078] According to another embodiment, the specification of the hardware configuration included in the electronic device 100 is greater than or equal to the specification of the hardware configuration included in the first external device 200-1, which can mean that the performance evaluation information indicating the performance of the hardware configuration included in the electronic device 100 is higher than the performance evaluation information indicating the performance of the hardware configuration included in the first external device 200-1. As described above, the performance evaluation information is a score obtained by comprehensively evaluating the performance of each hardware configuration based on experts' experiments and analysis, and can be included in the first device information and the second device information. For example, if the CPU included in the electronic device 100 has a score of 97 according to the performance evaluation information, and the CPU included in the first external device 200-1 has a score of 86 according to the performance evaluation information, the electronic device 100 can identify that the performance of the CPU of the electronic device 100 is higher than the performance of the CPU of the first external device 200-1.

[0079] Second, according to one embodiment of the present application, it will be described with reference to Figure 1 and 3 "Operation 2" is described. By identifying whether the hardware specification of the electronic device 100 is equal to or superior to the hardware requirement specification of each of the one or more neural network models included in the first external device 200-1 based on the first device information stored in the electronic device 100 and the first model information received from the first external device 200-1, the electronic device 100 can perform a hardware suitability identification process on each of the neural network models included in the first external device 200-1.

[0080] With reference to Figure 3 , Step 2 of the hardware suitability identification process can be performed only when Step 1 of the hardware suitability identification process as described above fails. That is, as a result of performing Step 1 of the hardware suitability identification process as described above, if it is identified that at least one of the one or more neural network models included in the first external device 200-1 is not suitable for the hardware of the electronic device 100, the electronic device 100 can perform Step 2 of the hardware suitability identification process.

[0081] Specifically, if at least one specification of the plurality of hardware configurations included in the electronic device 100 is less than the specification of the plurality of hardware configurations included in the first external device 200-1 (N in S140), at operation S150-2, the electronic device 100 can identify, among the one or more neural network models included in the first external device 200-1, at least one neural network model having a hardware requirement specification lower than the specification of the plurality of hardware configurations included in the electronic device 100 as being suitable for the hardware of the electronic device 100.

[0082] That is, as a result of comparing the specifications of each of the plurality of hardware configurations included in the electronic device 100 with the specifications of each of the plurality of hardware configurations included in the first external device 200-1, if the specifications of at least one of the plurality of hardware configurations included in the electronic device 100 are less than the specifications of the plurality of hardware configurations included in the first external device 200-1, it can be said that this is a case in which all of the neural network models suitable for execution using the hardware of the electronic device 100 can be identified only when the hardware requirement specifications of each of the one or more neural network models included in the first external device 200-1 are individually compared with the specifications of the plurality of hardware configurations included in the electronic device 100.

[0083] Accordingly, in this case, the electronic device 100 can identify whether all of the hardware requirement specifications of the one or more neural network models included in the first external device 200-1 are less than the specifications of the plurality of hardware configurations included in the electronic device 100 by comparing the hardware requirement specifications for the one or more neural network models included in the first external device 200-1 with the specifications of the plurality of hardware configurations included in the electronic device 100.

[0084] For example, if all of the hardware requirement specifications of the first neural network model included in the first external device 200-1 are less than the specifications of the plurality of hardware configurations included in the electronic device 100, the electronic device 100 can identify the first neural network model as being suitable for the hardware of the electronic device 100. On the other hand, if at least one of the hardware requirement specifications of the second neural network model included in the first external device 200-1 is greater than or equal to the specifications of the plurality of hardware configurations included in the electronic device 100, the electronic device 100 can identify the second neural network model as being unsuitable for the hardware of the electronic device 100. As described above, information regarding the hardware requirement specifications of each of the one or more neural network models included in the first external device 200-1 can be included in the first model information received from the first external device 200-1.

[0085] The various methods of comparing the specifications of the plurality of hardware configurations included in the electronic device 100 with the specifications of each of the plurality of hardware configurations included in the first external device 200-1 in step 1 can be applied to the method of comparing the specifications of the plurality of hardware configurations included in the electronic device 100 with the hardware requirement specifications of the one or more neural network models included in the first external device 200-1 in step 2. Accordingly, a redundant description of the method of comparing the specifications of the plurality of hardware configurations included in the electronic device 100 with the hardware requirement specifications of the one or more neural network models included in the first external device 200-1 in step 2 is omitted.

[0086] In comparing the hardware requirement specifications of each of the one or more neural network models included in the first external device 200-1 with the specifications of the plurality of hardware configurations included in the electronic device 100, the hardware specifications of the electronic device 100 at the time of product release can be compared with the hardware requirement specifications of each of the one or more neural network models included in the first external device 200-1, however, in comparing the hardware requirement specifications of each of the one or more neural network models included in the first external device 200-1 with the specifications of the plurality of hardware configurations included in the electronic device 100, the hardware specifications of the electronic device 100 available at the time of comparison can also be compared with the hardware requirement specifications of each of the one or more neural network models included in the first external device 200-1.

[0087] As described above, the comparison of the specifications of the plurality of hardware configurations included in the electronic device 100 with the specifications of the plurality of hardware configurations included in the first external device 200-1 in step 1 is based on the premise that the respective configurations correspond to each other and that the comparison objects exist. That is, if there is a hardware configuration included in the first external device 200-1 but not included in the electronic device 100, the electronic device 100 can perform the hardware suitability recognition process according to step 2, unless the hardware configuration can be replaced with another hardware configuration included in the electronic device 100.

[0088] Further, as described above, the comparison of the specifications of the plurality of hardware configurations included in the electronic device 100 with the hardware requirement specifications of the one or more neural network models included in the first external device 200-1 in step 2 is also based on the premise that the respective configurations correspond to each other and that the comparison objects exist. That is, if there is a hardware configuration requested in the hardware requirement specifications of the neural network models of the first external device 200-1 but not included in the electronic device 100, the electronic device 100 can recognize the neural network model as not suitable for the hardware of the electronic device 100, unless the hardware configuration can be replaced with another hardware configuration included in the electronic device 100.

[0089] As described above, if at least one neural network model suitable for the hardware of the electronic device 100 is recognized in the one or more neural network models included in the first external device 200-1, the electronic device 100 can transmit a third signal including a request for installation data of the recognized one or more neural network models to the first external device 200-1 at operation S160. Further, as a response to the third signal, the electronic device 100 can receive a fourth signal including installation data of at least one neural network model recognized as suitable for the hardware of the electronic device 100 from the first external device 200-1 at operation S170.

[0090] That is, if a third signal including a request for installation data of one or more identified neural network models is transmitted to the first external device 200-1, the first external device 200-1 can transmit the installation data of the one or more identified neural network models to the electronic device 100. Also, if the installation data of the one or more identified neural network models is received, the electronic device 100 can install the one or more identified neural network models based on the received installation data. Accordingly, the electronic device 100 can execute at least one neural network model personalized by the first external device 200-1 in the electronic device 100 by replacing one or more of a plurality of neural network models included in the electronic device 100 with the one or more identified neural network models. According to an embodiment of the present application, the personalization of the neural network model will be described later with reference to FIGS. 6 to 8. Figures 5A to 8

[0091] In detail, the installation data received from the first external device 200-1 can include identification information of each of the one or more identified neural network models, and configuration information required to install the one or more identified neural network models. The "configuration information" can include information on the structure and type of a neural network included in the neural network model, the number of layers included in the neural network, the number of nodes of each layer, the weight value of each node, and the connection relationship between a plurality of nodes.

[0092] Meanwhile, "installing" the neural network model can include "switching" the neural network model included in the electronic device 100 to the neural network model of the first external device 200-1. Also, "switching" the neural network model included in the electronic device 100 to the neural network model included in the external device can include a case where some neural network models of the electronic device 100 are replaced with some neural network models of the external device, such as a case where only the weight value of the node included in the neural network model of the electronic device 100 is changed to the weight value of the node included in the neural network model of the external device, and a case where the entire neural network model of the electronic device 100 is replaced with the entire neural network model of the external device.

[0093] According to the various embodiments described above with reference to Figures 1 to 4 According to the various embodiments described above with reference to

[0094] Figure 5A is a flowchart illustrating a control method of an electronic device according to an embodiment of the present application.

[0095] Figure 5B ​is a flowchart illustrating a control method of an electronic device according to an embodiment of the present application.

[0096] Figures 6 to 8 is a diagram for specifically describing an operation of a model suitability identification module for performing a control method of an electronic device according to Figure 5A

[0097] In the above, the hardware suitability identification process according to the present application is described with reference to Figures 1 to 4 However, according to another embodiment of the present application, the electronic device 100 can perform a "model suitability identification process" on each of the neural network models included in the first external device of the electronic device 100. Hereinafter, the model suitability identification process according to the present application will be described in detail with reference to Figures 5A to 8

[0098] First, the electronic device 100 can further store second model information and a model suitability identification module 1200, as well as the first device information, the second device information, and the hardware suitability identification module 1100 as described above.

[0099] The "second model information" refers to information about one or more neural network models included in the electronic device 100. Specifically, the second model information can include information about a service type and information about a level of personalization of each of the one or more neural network models included in the electronic device 100.

[0100] The "model suitability identification module 1200" refers to a module that identifies a neural network model suitable for replacing a neural network model included in the electronic device 100. With reference to Figure 6 Based on the second model information stored in the electronic device 100 and the first model information received from the first external device 200-1, the "model suitability identification module 1200" can output information about whether it is suitable to replace the neural network model included in the electronic device 100 with the neural network model included in the external device.

[0101] With reference to Figure 5A If one or more neural network models suitable for the hardware of the electronic device 100 are identified (U in S210), at operation S220, the electronic device 100 can input the first model information and the second model information into the model suitability identification module 1200 to identify whether each of the one or more neural network models identified as suitable for the hardware of the electronic device 100 is suitable for replacing the neural network model included in the electronic device 100.

[0102] Specifically, as Figure 7 ​​As illustrated, the model suitability recognition process according to the present application can include two processes performed through each of the model type suitability recognition module 1210 and the personalization level suitability recognition module 1220, and thus, hereinafter, after each process included in the model suitability recognition process is described in detail, the control method according to an embodiment of the present application will be described again.

[0103] First, as illustrated, Figure 7 As illustrated, based on information about a service type included in each of the first model information and the second model information, the "model type suitability recognition module 1210" can recognize a neural network model having the same service type by comparing the service type of each of one or more neural network models included in the electronic device 100 with the service type of each of one or more neural network models recognized as suitable for the hardware of the electronic device 100.

[0104] The "type of neural network model" can be classified according to input / output information of the neural network model and a function of the corresponding neural network model. For example, when both the first neural network model and the second neural network model are neural network models that provide a speech recognition service by inputting a speech signal according to a user's utterance and outputting text corresponding to the user's speech, the model type suitability recognition module 1210 can recognize that the service type of the first neural network model and the service type of the second neural network model are the same as each other.

[0105] Second, as illustrated, Figure 7 As illustrated, based on information about a personalization level included in each of the first model information and the second model information, the "personalization level suitability recognition module 1220" can recognize a neural network model having a higher personalization level among neural network models having the same service type by comparing the personalization levels between the neural network models having the same service type.

[0106] The "personalization level of a neural network model" refers to a degree to which a neural network model is updated according to a user after the neural network model is installed in the electronic device 100, based on personalization data related to the user of the electronic device 100, when the neural network model is trained. The "personalization data" refers to training data used to personalize a neural network model included in an external device. According to an embodiment of the present application, the operation of the personalization level suitability recognition module 1220 will be described in more detail with reference to Figure 7 and 8 The operation of the personalization level suitability recognition module 1220 will be described in more detail.

[0107] Specifically, the level of personalization can be determined based on "information about the history of the user". The information about the history of the user can include information about the number of times, frequency, and duration of use of the neural network model used by the user. For example, if the second neural network model included in the electronic device 100 is used 100 times in 1 month, it can be determined that this has a higher level of personalization than when the first neural network model included in the external device is used 30 times in 1 month or 100 times in 2 months.

[0108] Referring to Figure 8 , the information about the history of the user using the neural network model 2000 included in the electronic device 100 can include a case in which the user uses the neural network model 2000 based on data acquired through another electronic device 100 connected to the electronic device 100 (type 2 in Figure 8 ), and a case in which the user uses the neural network model 2000 included in the electronic device 100 based on data acquired through the electronic device 100 (type 1 in Figure 8 ).

[0109] For example, a case in which the neural network model 2000 included in the smartphone is used when an image acquired by the robot cleaner connected to the smartphone is transmitted to the smartphone, and a case in which the neural network model 2000 included in the smartphone is used by the user based on the image acquired through the smartphone, can be included in the history of using the neural network model 2000 included in the smartphone.

[0110] The level of personalization can also be determined according to "information about the feedback of the user". The information about the feedback of the user can include direct evaluation information input by the user for the use result after using the neural network model 2000 and indirect evaluation information related to the use result (type 3 in Figure 8 ).

[0111] For example, when the user directly inputs positive evaluation information for the application including the neural network model 2000 after using the neural network model 2000 in the electronic device 100, the level of personalization of the neural network model 2000 can increase. On the other hand, when the user directly inputs negative evaluation information for the application including the neural network model 2000 after using the neural network model 2000 in the electronic device 100, the level of personalization of the neural network model 2000 can increase. On the other hand, when the same content of the user input is repeatedly input to the neural network model 2000, it can be indirectly confirmed that the user is not satisfied with the output of the neural network model 2000, and thus, the level of personalization of the neural network model 2000 can decrease.

[0112] The level of personalization can be quantitatively calculated according to a weighted sum of various types of information used to evaluate the above-described level of personalization. Specifically, referring to Figure 8 The level of personalization can be calculated by summing values obtained by multiplying each "number of times per type" by a preset "weight per type" for evaluating the level of personalization.

[0113] For example, when the user inputs direct evaluation information for an application including the neural network model 2000, the highest weight can be assigned, when data (such as an image captured using a camera of the electronic device 100 or a voice acquired using a microphone of the electronic device 100) acquired from the electronic device 100 is input to the neural network model 2000, the second highest weight can be assigned, and when data received from another electronic device 100 connected to the electronic device 100 (rather than the electronic device 100) is input to the neural network model 2000, the third highest weight can be assigned. Furthermore, values obtained by multiplying each type of the above-described number of times per type by the weight per type can become a weighted sum per type, and a value obtained by adding all types of the weighted sum per type can be a quantitative value indicating the level of personalization of the neural network model 2000.

[0114] Referring again to Figure 5A If the service type of the first neural network model, which is identified as being suitable for the hardware of the electronic device 100, is the same as the service type of the second neural network model included in the plurality of neural network models included in the electronic device 100 (Y in operation S230), the electronic device 100 can compare the level of personalization of the first neural network model and the level of personalization of the second neural network model based on the information about the level of personalization included in each of the first model information and the second model information. Furthermore, if the level of personalization of the first neural network model is higher than the level of personalization of the second neural network model (Y in operation S240), the first neural network model can be identified as being suitable for replacing the second neural network model at operation S250.

[0115] If the above-described model suitability identification process is performed at operation S260, the electronic device 100 can transmit a third signal including a request for installation data of at least one neural network model identified as being suitable for replacing the neural network model included in the electronic device 100 to the first external device 200-1. That is, when the third signal is transmitted to the first external device 200-1 after not only the hardware suitability identification process but also the model suitability identification process is performed, the third signal can include a request for installation data of at least one neural network model identified when the model suitability identification process is performed.

[0116] As a response to the third signal, the electronic device 100 can receive a fourth signal including installation data of one or more identified neural network models from the first external device 200-1 at operation S270. That is, when the third signal is transmitted to the first external device 200-1 after not only the hardware suitability identification process but also the model suitability identification process is performed, the fourth signal received as a response to the third signal can include installation data of at least one neural network model identified when the model suitability identification process is performed.

[0117] In the above, the embodiment in which the model suitability identification process is performed after the hardware suitability identification process is performed has been described, however, according to the present disclosure, there is no time sequence restriction between the hardware suitability identification process and the model suitability identification process. Specifically, the electronic device 100 can first input the first model information and the second model information into the model suitability identification module 1200 to identify whether it is suitable to replace the first neural network model with the second neural network model. Further, if it is determined that it is suitable to replace the first neural network model with the second neural network model, the electronic device 100 can also determine whether it is suitable to use the hardware of the electronic device 100 to execute the second neural network model by comparing the hardware performance of the electronic device 100 and the hardware performance required to execute the second neural network model.

[0118] In the above, it has been described that the personalization level of the first neural network model and the personalization level of the second neural network model are compared only when the service type of the first neural network model included in the first external device 200-1 and the service type of the second neural network model included in the electronic device 100 are the same. However, according to another embodiment of the present disclosure, when there is no neural network model having the same service type as that of the first neural network model included in the first external device 200-1 in the electronic device 100, the electronic device 100 can also identify that it is suitable to transfer the first neural network model to the electronic device 100 without identifying the personalization level of the first neural network model.

[0119] In the above, the embodiment in which the model suitability process is additionally performed for each of one or more neural network models identified as being suitable for the hardware of the electronic device 100 after the hardware suitability identification process is performed has been described, but the present disclosure is not limited thereto. That is, according to another embodiment of the present disclosure, the electronic device 100 can also receive installation data of a neural network model satisfying model suitability from the first external device 200-1 by performing only the model suitability identification process without performing the hardware suitability identification process. Hereinafter, the embodiment in which installation data is received from the first external device 200-1 by performing only the model suitability identification process will be described. Figure 5B However, in the embodiment in which installation data is received from the first external device 200-1 by performing only the model suitability identification process, the electronic device 100 can also receive installation data of a neural network model satisfying model suitability from the first external device 200-1 by performing only the model suitability identification process without performing the hardware suitability identification process. Figure 5BRedundant descriptions of the same content as described above will be omitted in the following description.

[0120] Referring to Figure 5B At operation S205, when a user input is received, the electronic device 100 can transmit a first signal for requesting information related to one or more neural network models included in one or more external devices. Further, at operation S215, in response to the first signal, the electronic device 100 can receive, from a first external device 200-1 among the one or more external devices, a second signal including external model information about one or more neural network models included in the first external device 200-1. Hereinafter, within the scope of limitations of embodiments as illustrated in Figure 5B , the term "external model information" has the same meaning as the term "first model information" in the description of Figures 1 to 5A .

[0121] At operation S220, if the second signal including the external model information is received from the first external device 200-1, the electronic device 100 can input the internal model information stored in the electronic device and the external model information received from the first external device 200-1 into the model suitability identification module 1200 to identify whether each of the identified one or more neural network models suitable for the model electronic device 100 is suitable for replacing the neural network model included in the electronic device 100. Hereinafter, within the scope of limitations of embodiments as illustrated in Figure 5B , the term "internal model information" is used with the same meaning as the term "second model information" in the description of Figure 5A .

[0122] As described above, the model suitability identification procedure according to the present disclosure can include a model type suitability identification procedure and a personalization level suitability identification procedure performed by each of the model type suitability identification module 1210 and the personalization level suitability identification module 1220, as illustrated in Figure 7 .

[0123] Specifically, if the service type of a first neural network model included in one or more neural network models in the first external device 200-1 is the same as the service type of a second neural network model included in a plurality of neural network models in the electronic device 100 (Y in operation S230), the electronic device 100 can compare the personalization level of the first neural network model and the personalization level of the second neural network model based on the information on the personalization level included in each of the internal model information and the external model information. Further, at operation S250, if the personalization level of the first neural network model is higher than the personalization level of the second neural network model (Y in operation S240), it can be identified that the first neural network model is suitable for replacing the second neural network model.

[0124] At operation S260, if the above-described model suitability identification process is performed, the electronic device 100 can transmit a third signal including a request for installation data of at least one neural network model identified as suitable for replacing the neural network model included in the electronic device 100 to the first external device 200-1. Further, at operation S270, as a response to the third signal, the electronic device 100 can receive a fourth signal including installation data of one or more identified neural network models from the first external device 200-1.

[0125] According to the above description with reference to Figures 5A to 8 The various embodiments described above, when transferring a neural network model from an external device, the electronic device 100 can determine whether to transfer the neural network model by identifying whether it is suitable to replace the neural network model included in the electronic device 100 based on the degree of personalization of the neural network model included in the external device, and accordingly, the efficiency and reliability of learning can be further improved.

[0126] Figure 9 is a flowchart for describing a control method of the electronic device 100 according to an embodiment of the present application.

[0127] Figure 10 is a sequence diagram for describing an example of a case where a plurality of external devices exist according to an embodiment of the present application.

[0128] In the above, the hardware suitability recognition process and the model suitability recognition process according to the present application have been described, but according to another embodiment of the present application, a user suitability recognition process can also be performed before the hardware suitability recognition process and the model suitability recognition process. The "user suitability recognition process" is a process of recognizing whether a user of the electronic device 100 is suitable for using a neural network model of an external device, and can be referred to as a "user authentication process". In the present application, the term "conversion compatibility" can be used as a meaning including hardware suitability, model suitability, and user suitability. Hereinafter, the user suitability recognition process will be described with reference to Figure 9 and 10 The user suitability recognition process will be described in detail.

[0129] In the description of Figures 1 to 8 , it has been described based on the following premise: when the electronic device 100 transmits a first signal for requesting information related to one or more neural network models included in the first external device 200-1 to the first external device 200-1, the external device transmits a second signal including second device information about the hardware specifications of the first external device 200-1 and first model information about one or more neural network models included in the first external device 200-1 to the electronic device 100 as a response to the first signal.

[0130] However, before the external device provides the second device information and the first model information to the electronic device 100, the user suitability recognition process can be performed by the external device, or the user suitability recognition process can be performed by the electronic device 100. In the user suitability recognition process, because the first user information and the second user information can be used, the first user information can include at least one of account information about a user of the electronic device 100 or identification information about the electronic external device, and the second user information can include at least one of account information about a user of the first external device 200-1 and identification information about the first external device 200-1.

[0131] Referring to Figure 9 , the electronic device 100 according to the present application can perform the user suitability recognition process. Specifically, as shown in Figure 9 , the user suitability recognition process can be performed by a user suitability recognition module 1300 included in the electronic device 100.

[0132] The "user suitability recognition module 1300" refers to a module that recognizes whether a user of the electronic device 100 is suitable for using a neural network model included in the first external device 200-1 based on first user information stored in the electronic device 100 and second user information received from the first external device 200-1.

[0133] In particular, the first user information can be stored in the electronic device 100. Also, the electronic device 100 can transmit a first signal for requesting information related to one or more neural network models included in the first external device 200-1 to the first external device 200-1. If the first signal is received, the first external device 200-1 can transmit second user information to the electronic device 100. If the second user information is received, the electronic device 100 can perform a user suitability recognition process based on the first user information and the second user information.

[0134] In particular, if the account information about the user of the electronic device 100 included in the first user information matches the account information about the user of the first external device 200-1 included in the second user information, the electronic device 100 can recognize that the user of the electronic device 100 is suitable for using the neural network model included in the first external device 200-1. On the other hand, if the account information about the user of the electronic device 100 included in the first user information does not match the account information about the user of the first external device 200-1 included in the second user information, the electronic device 100 can recognize that the user of the electronic device 100 is not suitable for using the neural network model included in the first external device 200-1.

[0135] In the above, it has been described that the user suitability is satisfied when the account information about the user of the electronic device 100 matches the account information about the user of the first external device 200-1, but the present disclosure is not limited thereto. That is, according to an embodiment, when the user account of the electronic device 100 has a higher authority than the user account of the first external device 200-1, and, even when the account for the user of the electronic device 100 is included in the same group as the account previously registered as the user of the first external device 200-1, the user suitability according to the present disclosure can be satisfied.

[0136] According to another embodiment, the external device that receives the first signal can also cause the user authentication by transmitting a second signal including the encrypted second device information and the encrypted first model information to the electronic device 100 instead of transmitting the second user information to the electronic device 100. In particular, if a password or biometric information (e.g., fingerprint information, iris information, etc.) for decrypting the encrypted second device information and the encrypted first model information is input, the electronic device 100 can recognize that the user of the electronic device 100 is suitable for using the neural network model included in the first external device 200-1. The encryption and decryption method and the authentication process required for decryption are not particularly limited.

[0137] Reference Figure 10The user suitability identification process can be performed by the first external device 200-1 according to the present application. Specifically, the user suitability identification process is not shown but can be performed by the user suitability identification module 1300 included in the first external device 200-1.

[0138] Referring to Figure 10 At operation S1010, the electronic device 100 can receive a first user input, and at operation S1020, can transmit a first signal for requesting information related to one or more neural network models included in one or more external devices to the first external device 200-1 according to the first user input.

[0139] At operation S1030, if the first signal is received, the first external device 200-1 can perform a user suitability identification process based on first user information included in the first signal and second user information stored in the first external device 200-1.

[0140] Specifically, if account information about a user of the electronic device 100 included in the first user information matches account information about a user of the first external device 200-1 included in the second user information, the first external device 200-1 can identify that the user of the electronic device 100 is suitable for using the neural network model included in the first external device 200-1. On the other hand, if the account information about the user of the electronic device 100 included in the first user information does not match the account information about the user of the first external device 200-1 included in the second user information, the first external device 200-1 can identify that the user of the electronic device 100 is not suitable for using the neural network model included in the first external device 200-1. If the first user information is not included in the first signal received from the electronic device 100, the first external device 200-1 can receive the first user information by transmitting a request for the first user information to the electronic device 100.

[0141] At operation S1040, if it is identified that the user of the electronic device 100 is suitable for using the neural network models included in the first external device 200-1, the first external device 200-1 can transmit a second signal including second device information about the hardware specifications of the first external device 200-1 and first model information about the one or more neural network models included in the first external device 200-1 to the electronic device 100. On the other hand, if it is identified that the user of the electronic device 100 is not suitable for using the neural network models included in the first external device 200-1, the first external device 200-1 can not transmit the second signal to the electronic device 100. In addition, if the second signal is not received from the first external device 200-1 within a preset time, the electronic device 100 can provide a user notification indicating that the request for information related to the one or more neural network models included in the first external device 200-1 has been rejected.

[0142] As a result of performing the user suitability identification process as described above, if it is identified that the user of the electronic device 100 is suitable for using the neural network models included in the first external device 200-1, the electronic device 100 can perform a hardware suitability identification process and a model suitability identification process according to the present application.

[0143] That is, at operation S1050, if the second signal is received, the electronic device 100 can identify at least one neural network model of the one or more neural network models included in the first external device 200-1 as being suitable for the hardware of the electronic device 100 based on the first device information, the second device information, and the first model information about the hardware specifications of the electronic device 100. In addition, at operation S1060, the electronic device 100 can identify at least one neural network model suitable for replacing the neural network model included in the electronic device 100 among the one or more neural network models identified as being suitable for the hardware of the electronic device 100 based on the first model information and the second model information about the one or more neural network models included in the electronic device 100. The hardware suitability identification process and the model suitability identification process have been described with reference to FIGS. 10A and 10B. Figures 1 to 8 Detailed description, therefore, a redundant description of specific content will be omitted.

[0144] If the hardware suitability identification process and the model suitability identification process are performed, the electronic device 100 can receive a second user input at operation S1070, and can request installation data of at least one neural network model selected according to the second user input from the first external device 200-1 at operation S1080. In addition, if the installation data of the neural network model is requested, the first external device 200-1 can transmit the installation data of the at least one selected neural network model to the electronic device 100 at operation S1090.

[0145] In the above, an embodiment in which the first external device 200-1 performs a user suitability recognition process, the electronic device 100 performs a hardware suitability recognition process and a model suitability recognition process has been described, but the present application is not limited thereto. That is, according to another embodiment of the present application, the first external device 200-1 can also perform all of the user suitability recognition process, the hardware suitability recognition process and the model suitability recognition process according to the present application.

[0146] According to the various embodiments described above with reference to Figure 9 and 10 , it is only possible to determine whether to transfer the neural network model when it is recognized that the user of the electronic device 100 is suitable for using the neural network model included in the external device through the user authentication process, and thus, in the process of transferring the neural network model, it is possible to improve the security and reliability of the system.

[0147] Figure 11 is a diagram for describing a user interface provided by the electronic device 100 according to an embodiment of the present application.

[0148] With reference to Figure 11 , the electronic device 100 according to the present application can display a user interface (UI) for receiving a user input on a display of the electronic device 100. Further, the electronic device 100 can receive a user input for searching for one or more neural network models included in one or more first external devices 200-1 through the user interface. For example, the user input for searching for at least one neural network model can be received according to a user interaction of selecting a "find" UI element 2110 among a plurality of UI elements included in the user interface.

[0149] According to the user input, the electronic device 100 can transmit a first signal for requesting information related to one or more neural network models included in one or more first external devices 200-1. In response to the first signal, the electronic device 100 can receive identification information about the first external device 200-1 and identification information about the neural network model included in each of the one or more first external devices 200-1 from each of the one or more first external devices 200-1. Further, the electronic device 100 can display the received identification information about the first external device 200-1 and the identification information about the neural network model in the user interface. For example, the electronic device 100 can display information indicating that the first external device 200-1 called device A includes neural network models called model A1, model A2 and model A3, and that the first external device 200-1 called device B includes neural network models called model B1 and model B2 in the user interface.

[0150] In particular, the electronic device 100 can display, in the user interface, UI elements indicating whether each neural network model is a neural network model satisfying the conversion suitability according to the present application, and identification information about the first external device 200-1 and identification information about the neural network model. For example, the electronic device 100 can display the UI elements 2120 and 2130 in the form of "checkable check boxes" to indicate that the model A1 and the model A2 included in the device A are neural network models satisfying the conversion suitability. Also, the electronic device 100 can display the UI element 2140 in the form of "non-checkable check box" to indicate that the model A3 included in the device A is a neural network model not satisfying the conversion suitability. In the case where the models B1 and B2 are included in the device B, the electronic device 100 can display the UI element 2150 for indicating that the conversion suitability recognition process according to the present application is "in progress".

[0151] After displaying the UI elements indicating whether each neural network model is a neural network model satisfying the conversion suitability according to the present application, the electronic device 100 can receive a user input for selecting one or more neural network models to be installed in the electronic device 100 among the one or more neural network models satisfying the conversion suitability. For example, the user input for selecting one or more neural network models to be installed in the electronic device 100 can be received according to a user interaction of selecting one UI element 2130 among the UI elements 2120 and 2130 displayed on the display. In this case, the electronic device 100 can display the UI element 2130 in the form of "selected check box" as shown to indicate that the model A2 is selected. Figure 11

[0152] After selecting one or more neural network models to be installed in the electronic device 100, if a user input for installing the selected one or more neural network models in the electronic device 100 is received, the electronic device 100 can transmit a request for installation data of the one or more selected neural network models to each first external device 200-1 including the one or more selected neural network models. For example, the user input for installing the one or more selected neural network models in the electronic device 100 can be received according to a user interaction of selecting an "install" UI element 2160 among a plurality of UI elements included in the user interface.

[0153] As a response to the request for installation data of the one or more selected neural network models, the electronic device 100 can receive the installation data of the one or more selected neural network models and install the corresponding neural network models in the electronic device 100 based on the installation data.

[0154] ​In the above, an embodiment in which the electronic device 100 displays a UI element indicating whether the neural network model satisfies the conversion suitability has been described. In the present disclosure, the satisfaction of the conversion suitability means that all conditions required for each of the embodiments of the hardware suitability, the model suitability, and the user suitability are satisfied, and the non-satisfaction of the conversion suitability means that at least some of the conditions required for each of the embodiments of the hardware suitability, the model suitability, and the user suitability are not satisfied.

[0155] According to the above reference Figure 11 to the described embodiments, the electronic device 100 can improve the convenience of the user and the efficiency of the process of transferring the neural network model by requesting and receiving only the installation data of the selected neural network model of the first external device 200-1 whose neural network model satisfies the conversion suitability according to the present disclosure.

[0156] Figure 12 is a diagram for describing a user interface provided by the first external device 200-1 according to an embodiment of the present disclosure.

[0157] In Figure 11 , a user interface provided by the electronic device 100 has been described, but according to another embodiment, a user interface for receiving a user input according to the present disclosure can be displayed on the display of the first external device 200-1. As Figure 12 indicated, the user interface represents a user interface for installing one or more applications included in the first external device 200-1 on the electronic device 100.

[0158] Referring to Figure 12 , the user interface can include UI elements representing applications included in the first external device 200-1. For example, as Figure 12 indicated, the user interface can include a UI element 2210 representing a "Call and Contacts" application, a UI element 2220 representing a "Message" application, a UI element 2230 representing an "AI Secretary" application, a UI element representing a "gallery" application 2250, and the like.

[0159] Further, the user interface can include UI elements representing neural network models included in each of the applications in the first external device 200-1. Referring again to Figure 12 , the user interface can include a UI element 2240 representing a neural network model called "AI Model X" included in the "AI Secretary" application, and a UI element 2260 representing a neural network model called "AI Model Y" included in the "gallery" application.

[0160] The first external device 200-1 can receive user input via a user interface for selecting one or more applications among a plurality of applications included in the first external device 200-1. For example, the first external device 200-1 can receive user input for selecting the "Call and Contacts" application, the "AI Secretary" application, and the "Gallery" application among the plurality of applications included in the first external device 200-1. Figure 12 In this context, UI elements in the form of "checkboxes" indicate that they are selected applications.

[0161] If user input for selecting one or more applications is received, the first external device 200-1 can send the installation data of one or more selected applications to the electronic device 100. For example, user input for selecting one or more applications can be received based on user interaction for selecting the "send" element 1270 from among multiple UI elements included in the user interface.

[0162] The first external device 200-1 can send second device information regarding its hardware specifications, first model information regarding the neural network model included in each of one or more selected applications, and installation data for the one or more selected applications to the user electronic device 100. Furthermore, the electronic device 100 can perform the hardware suitability identification process and model suitability identification process as described above based on the second device information received from the first external device 200-1, the first model information stored in the electronic device 100, and the first device information and second model information. Subsequently, if a request for installation data of a neural network model identified as satisfying hardware suitability and model suitability is received from the electronic device 100, the first external device 200-1 can send the identified neural network model's installation data to the electronic device 100.

[0163] At least some installation data of the application and installation data of the neural network model can be sent directly from the first external device 200-1 to the electronic device 100, and can also be sent to the electronic device 100 through a server that provides installation data of the application or installation data of the neural network model.

[0164] According to the above reference Figure 12 In the described embodiment, after performing the process of identifying the suitability of the neural network model included in the selected application, the installation data of the neural network model can be sent from the first external device 200-1 to the electronic device 100. While sending the installation data of the user-selected application from the first external device 200-1 to the electronic device 100, user convenience can be further improved. Specifically, Figure 12Embodiments of the electronic device 100 according to the present application can be applied to a case where at least some information about applications and neural network models included in the first external device 200-1 (old device) is collectively transmitted to the electronic device 100 (new device) in an initial setting of the electronic device (new device).

[0165] Figure 13 FIG. 1 is a diagram illustrating an example of an electronic device, a first external device, and a second external device according to an embodiment of the present application.

[0166] Figure 14 FIG. 2 is a sequence diagram for describing a process in which, when a neural network model included in a first external device is transferred to a second external device, an electronic device identifies conversion suitability according to an embodiment of the present application.

[0167] Referring to Figure 13 , the electronic device 100 according to the present application can be implemented as a smartphone, the first external device 200-1 can be implemented as a robot cleaner, and the second external device 200-2 can be implemented as a smart companion robot. That is, the types of the electronic device 100, the first external device 200-1, and the second external device 200-2 according to the present application can be different from each other. In the present application, the term "first external device 200-1" is used as a term to designate an external device capable of transmitting installation data of a neural network model to the electronic device 100, and the term "second external device 200-2" is used as a term to designate an external device capable of receiving installation data of a neural network model from the first external device 200-1.

[0168] On the other hand, when a neural network model included in the first external device 200-1 is transferred to the second external device 200-2, because when the first external device 200-1 and the second external device 200-2 do not include a display as Figure 13 indicated in FIG. 1, a user interface as described above with reference to Figure 11 and 12 may not be displayed, there is a problem in that it is difficult to receive a user input for performing a conversion suitability identification process according to an embodiment of the present application. In addition, when the first external device 200-1 and the second external device 200-2 do not include a software module according to the present application, there is a problem in that a conversion suitability identification process according to the present application cannot be performed by the first external device 200-1 or the second external device 200-2.

[0169] Accordingly, according to an embodiment of the present application, the electronic device 100 can receive a user input, and can perform a hardware suitability identification process and a model suitability identification process based on information received from the first external device 200-1 and the second external device 200-2.

[0170] Referring to Figure 14At operation S1410, the electronic device 100 can receive a first user input. Further, at operation S1420-1, the electronic device 100 can transmit, to the first external device 200-1, a request for first device information about a hardware specification of the first external device 200-1 and first model information about one or more neural network models included in the first external device 200-1 according to the first user input, and can transmit, to the second external device 200-2, a request for second device information about a hardware specification of the second external device 200-2 and second model information about one or more neural network models included in the second external device 200-2 at operation S1420-2.

[0171] With Figures 1 to 12 Unlike the description of Figure 13 and 14 , the first device information is used as a term specifying information about a hardware specification of the first external device 200-1, the second device information is used as a term specifying information about a hardware specification of the second external device 200-2, the first model information is used as a term specifying information about one or more neural network models included in the first external device 200-1, and the second model information is used as a term specifying information about one or more neural network models included in the second external device 200-2.

[0172] In response to the request received from the electronic device 100, at operation S1430-1, the first external device 200-1 can transmit the first device information and the first model information to the electronic device 100, and at operation S1430-2, the second external device 200-2 can transmit the second device information and the second model information to the electronic device 100.

[0173] If the first device information and the first model information are received from the first external device 200-1 and the second device information and the second model information are received from the second external device 200-2, at operation S1440, the electronic device 100 can identify one or more neural network models suitable for the hardware of the second external device 200-2 among the one or more neural network models included in the first external device 200-1 based on the first device information, the second device information, and the first model information. Further, at operation S1450, the electronic device 100 can identify one or more neural network models suitable for replacing the neural network models included in the second external device 200-2 among the one or more neural network models identified as being suitable for the hardware of the first external device 200-1 based on the first model information and the second model information. In reference to Figure 13 and 14In the described embodiments, the hardware suitability recognition process and the model suitability recognition process as described above can be similarly applied.

[0174] If the hardware suitability recognition process and the model suitability recognition process are performed, the electronic device 100 can receive a second user input at operation S1460. Furthermore, the electronic device 100 can transmit a request for installation data of one or more neural network models selected according to the second user input to the first external device 200-1 at operation S1470. If the request for the installation data of the one or more selected neural network models is received, the first external device 200-1 can transmit the installation data of the one or more selected neural network models to the second external device 200-2 at operation S1480. The first external device 200-1 can transmit the installation data of the one or more selected neural network models to the electronic device 100, and the electronic device 100 can also transmit the received installation data to the second external device 200-2.

[0175] According to the above-described embodiments with reference to Figure 13 and 14 , the electronic device 100 can serve as an intermediate device between the first external device 200-1 and the second external device, thereby improving the efficiency and reliability of the process of transferring the neural network model between the external devices not including the display or not including the software module according to the present application

[0176] Figure 15 is a block diagram illustrating in detail an architecture of a software module included in the electronic device 100 according to an embodiment of the present application.

[0177] With reference to Figure 15 , the electronic device 100 according to the present application can include software modules such as a neural network model installation module 1500 and a neural network model performance monitor. Furthermore, the neural network model installation module can include a suitability recognition module, a neural network model switching module 1510, and a neural network model fine-tuning module 1520, and the neural network model performance monitor 1700 can include a personalization level monitor 1710 and a hardware requirement specification monitor 1720.

[0178] The "suitability recognition module" refers to a conceptual module that collectively refers to a module capable of recognizing conversion suitability according to the present invention. Specifically, as described above, the suitability recognition module can include the hardware suitability recognition module 1100, the model suitability recognition module 1200, and the user suitability recognition module 1300. Furthermore, the hardware suitability recognition module 1100, the model suitability recognition module 1200, and the user suitability recognition module 1300 can perform a hardware suitability recognition process, a model suitability recognition process, and a user suitability recognition process according to different embodiments of the present invention based on the first device information and the second model information stored in the electronic device 100, and the second device information and the first model information received from the external device. In Figure 15 the user information is shown in a form included in the first device information, but this is only related to an embodiment. The detailed operation of the hardware suitability recognition module 1100, the model suitability recognition module 1200, and the user suitability recognition module 1300 is described above with reference to Figures 1 to 14 therefore, redundant descriptions are omitted.

[0179] The "neural network model switching module" refers to a module that switches the neural network model included in the electronic device 100 to the neural network model included in the external device based on installation data of the neural network model received from the external device. Specifically, the neural network model switching module can switch the neural network model included in the electronic device 100 to the neural network model included in the external device based on the structure and type of the neural network included in the neural network model, the number of layers included in the neural network, the number of nodes of each layer, the weight value of each node, and the connection relationship between a plurality of nodes included in the installation data.

[0180] The "switching" of the neural network model included in the electronic device 100 to the neural network model included in the external device can include a case where some of the neural network models of the electronic device 100 are replaced with some of the neural network models of the external device, such as a case where only the weight values of the nodes included in the neural network model of the electronic device 100 are changed to the weight values of the nodes included in the neural network model of the external device, and a case where the entire neural network model of the electronic device 100 is replaced with the entire neural network model of the external device.

[0181] The "neural network model fine-tuning module" refers to a module that switches the neural network model included in the electronic device 100 to the neural network model included in the external device and then fine-tunes the details. Specifically, the neural model fine-tuning module can adjust the number of nodes of each layer and the weight values of each node included in the neural network model by reflecting detailed differences between the hardware specifications of the electronic device 100 and the hardware specifications of the external device, thereby making the neural network model more suitable for the electronic device 100. In addition, the neural network model fine-tuning module can adjust parameters related to personalization of the neural network model based on the personalization data received from the external device. As described above, the "personalization data" refers to training data used to personalize the neural network model included in the external device.

[0182] If the neural network model is switched / adjusted according to the neural network model switching module and the neural network model fine-tuning module, information about the neural network model can be stored / updated as second model information.

[0183] The "personalization level monitor" refers to a module that monitors the level of personalization of the neural network model included in the electronic device 100. In particular, when the second neural network model included in the external device is installed while the first neural network model included in the electronic device 100 is personalized to some extent, the personalization level monitor can acquire information about the level of personalization of the first neural network model and transmit the acquired information to the suitability identification module. In addition, the suitability identification module can identify whether the second neural network model is suitable to replace the first neural network model by comparing the information about the level of personalization of the first neural network model received from the personalization level monitor and the information about the level of personalization of the second neural network model received from the external device.

[0184] The "hardware requirement specification monitor" refers to a module for monitoring the hardware specifications required to execute the neural network model included in the electronic device 100. Specifically, the hardware requirement specification monitor can acquire information about the hardware specifications required to execute each of one or more neural network models included in the electronic device 100, and such information can be stored as information included in the second model information. The "hardware specification information" included in the first device information is information about the hardware specifications at the time of product release of the electronic device 100, or information about the hardware requirement specifications at the time of model suitability determination, which is different from the hardware requirement specification information of the neural network model acquired through the hardware requirement specification monitor.

[0185] The software modules included in the electronic device 100 have been described above, but this is only according to embodiments of the present application, and new configurations can be added or some modules can be omitted in addition to the illustrated modules. Also, at least two or more of the software modules according to the present application can be implemented as one integrated module.

[0186] Figure 16 is a block diagram illustrating in detail an architecture of software modules included in the first external device 200-1 according to an embodiment of the present application.

[0187] Referring to Figure 16 , the first external device 200-1 can include software modules such as a neural network model installation module 1600 and a neural network model performance monitor 1700. Also, the neural network model installation module 1600 can include a neural network model description information management module 1610 and a neural network model installation information management module 1620, and the neural network model performance monitor can include a personalization level monitor 1710 and a hardware requirement specification monitor 1720.

[0188] The "neural network model description information management module 1610" refers to a module that collectively manages information required to determine the conversion suitability of the neural network model included in the first external device 200-1. Specifically, the neural network model description information management module 1610 can transmit second device information and first model information to the electronic device 100.

[0189] As described above, the second device information is information about the hardware specifications of the first external device 200-1, and specifically refers to a term used to broadly refer to information about specifications indicating what performance each hardware included in the first external device 200-1 has. Also, the first model information is information about one or more neural network models included in the first external device 200-1, and can specifically include information about a service type, information about a personalization level, and information about a hardware requirement specification of each of the one or more neural network models included in the first external device 200-1.

[0190] Also, the neural network model description information management module 1610 can collectively manage various information such as identification information, performance, and version information of each neural network model included in the first external device 200-1.

[0191] The "neural network model installation information management module 1620" refers to a module that manages installation data of a neural network model. Specifically, the neural network model installation information management module 1620 can transmit installation data of one or more neural network models to the electronic device 100 in response to an installation data request received from the electronic device 100. Specifically, the installation data can include identification information of each of the one or more neural network models, and configuration information required to install the one or more identified neural network models. The "configuration information" can include a structure and a type of a neural network included in the neural network model, a number of layers included in the neural network, a number of nodes of each layer, a weight value of each node, and a connection relationship between a plurality of nodes.

[0192] In addition, the neural network model installation information management module 1620 can transmit personalization data of one or more neural network models to the electronic device 100 together with the installation data of the one or more neural network models.

[0193] The "personalization level monitor 1710" refers to a module that monitors a personalization level of a neural network model included in the first external device 200-1. Specifically, the personalization level monitor 1710 can output information on the personalization level of the neural network model included in the first external device 200-1 based on information on a history of the user and information on feedback of the user. As described above, the information on the history of the user can include information on a number of times, a frequency, and a duration that the user uses the neural network model, and the information on the feedback of the user can include direct evaluation information on a use result input by the user after using the neural network model and indirect evaluation information related to the use result.

[0194] The "hardware requirement specification monitor 1720" refers to a module that monitors a hardware specification required to execute a neural network model included in the first external device 200-1. Specifically, the hardware requirement specification monitor 1720 can acquire information on a hardware specification required to execute each of one or more neural network models included in the first external device 200-1, and such information can be stored as information included in the first model information.

[0195] The software modules included in the first external device 200-1 have been described above, but this is only according to an embodiment of the present application, and a new configuration can be added or some modules can be omitted in addition to the illustrated modules. In addition, at least two or more neural network models among the software modules according to the present application can be implemented as an integrated neural network model.

[0196] Figure 17 FIG. 1 is a block diagram schematically illustrating an architecture of a hardware configuration included in an electronic device according to an embodiment of the present application.

[0197] Figure 18 is a block diagram illustrating an architecture of a hardware configuration included in an electronic device according to an embodiment of the present application in more detail.

[0198] Referring to Figure 17 , the electronic device 100 according to an embodiment of the present application includes a communicator 110, a storage 120, and a processor 130. In addition, as Figure 18 indicated, the electronic device 100 according to an embodiment of the present application can further include a data obtainer 140 and a data outputter 150. However, the configurations as Figure 17 and 18 indicated are merely examples, and in implementing the present application, a new configuration can be added or some configurations can be omitted in addition to the configurations as Figure 17 and Figure 18 indicated.

[0199] The communicator 110 can include a circuit and communicate with an external device. Specifically, the processor 130 can receive various data or information from an external device connected through the communicator 110, and can also transmit various data or information to the external device.

[0200] The communicator 110 can include at least one of a wireless fidelity (Wi-Fi) module, a Bluetooth module, a wireless communication module, or a near field communication (NFC) module. Specifically, each of the Wi-Fi module and the Bluetooth module can perform communication in a Wi-Fi manner and a Bluetooth manner. In the case of using the Wi-Fi module or the Bluetooth module, various connection information such as a service set identifier (SSID) is first transmitted and received, connection communication is performed using the connection information, and then various information can be transmitted and received.

[0201] In addition, the wireless communication module can perform communication according to various communication protocols such as Institute of Electrical and Electronics Engineers (IEEE), Zigbee, third generation (3G), third generation partnership project (3GPP), long term evolution (LTE), fifth generation (5G), etc. In addition, the NFC module can perform communication in an NFC manner using a 13.56 MHz band among various radio frequency identification (RF-ID) bands such as 135 kHz, 13.56 MHz, 433 MHz, 860 to 960 MHz, and 2.45 GHz.

[0202] Specifically, in different embodiments according to the present application, the communicator 110 can transmit, to the first external device 200-1, a first signal for requesting information related to one or more neural network models included in the first external device 200-1, and a third signal including installation data of the one or more neural network models. In addition, as a response to the first signal, the communicator 110 can receive, from the first external device 200-1, a second signal including second device information of a hardware specification of the first external device 200-1 and first model information of the one or more neural network models included in the first external device 200-1, and as a response to the third signal, receive a fourth signal including installation data of one or more identified neural network models.

[0203] One or more instructions regarding the electronic device 100 can be stored in the memory 120. In addition, the memory 120 can store an operating system (O / S) for driving the electronic device 100. In addition, the memory 120 can further store various software programs or applications for operating the electronic device 100 according to various embodiments of the present application. In addition, the memory 120 can include a semiconductor memory such as a flash memory, or a magnetic storage medium such as a hard disk.

[0204] Specifically, the memory 120 can store various software modules for operating the electronic device 100 according to different embodiments of the present application, and the processor 130 can execute the various software modules stored in the memory 120 to control the operation of the electronic device 100. That is, the memory 120 is accessed by the processor 130, and reading, writing, correction, deletion, update, etc. of data in the memory 120 can be performed by the processor 130.

[0205] On the other hand, in the present application, the term memory 120 can be used as a meaning including a read-only memory (ROM) (not shown) in the processor 130, a random access memory (RAM) (not shown), or a memory card (not shown) (for example, a micro secure digital (SD) card or a memory stick) installed in the electronic device 100.

[0206] Specifically, in various embodiments according to the present application, the memory 120 can store first device information regarding a hardware specification of the electronic device 100, and second model information regarding one or more neural network models included in the electronic device 100. In addition, the memory 120 can store, as described above with reference to FIG. 1, the first device information and the second model information in a form of a table. Figure 15The various modules described, including the hardware suitability identification module 1100, the model suitability identification module 1200, and the user suitability identification module 1300. In addition, various information required within the scope of achieving the object of the present application can be stored in the memory 120, and the information stored in the memory 120 can also be updated when received from an external device or input by a user.

[0207] The processor 130 controls the overall operation of the electronic device 100. Specifically, the processor 130 can be connected to the configuration of the electronic device 100 including the communicator 110 and the memory 120 as described above, and can execute one or more instructions stored in the memory 120 as described above to control the overall operation of the electronic device 100.

[0208] The processor 130 can be implemented in various ways. For example, the processor 130 can be implemented as at least one of an application-specific integrated circuit (ASIC), an embedded processor, a microprocessor, hardware control logic, hardware finite state machine (FSM), or a digital signal processor (DSP). On the other hand, in the present application, the term processor 130 can be used as a meaning including a central processing unit (CPU), a graphics processing unit (GPU), a main processing unit (MPU), etc.

[0209] Specifically, in different embodiments according to the present application, when a user input is received, the processor 130 can control the communicator 110 to transmit a first signal for requesting information related to one or more neural network models included in one or more external devices, can receive a second signal including second device information about the hardware specifications of the first external device 200-1 and first model information about one or more neural network models included in the first external device 200-1 as a response to the first signal from the first external device 200-1 among the one or more external devices through the communicator 110, can identify whether each of the one or more neural network models included in the first external device 200-1 is suitable for the hardware of the electronic device 100 by inputting the first device information, the second device information, and the first model information to the hardware suitability identification module 1100, can control the communicator 110 to transmit a third signal including a request for installation data of one or more neural network models identified as suitable for the hardware of the electronic device 100 to the first external device 200-1, and can receive a fourth signal including the installation data of one or more neural network models identified as suitable for the hardware of the electronic device 100 from the first external device 200-1 as a response to the third signal through the communicator 110.

[0210] Further, if one or more neural network models suitable for the hardware of the electronic device 100 are identified, the processor 130 can also identify whether each of the one or more neural network models identified as being suitable for the hardware of the electronic device 100 is suitable for replacing a neural network model included in the electronic device 100 by inputting the first model information and the second model information into the model suitability identification module 1200. The above is described with reference to FIG. 12. Figures 1 to 16 Various embodiments according to the present application are described based on the control of the processor 130, and thus redundant descriptions will be omitted.

[0211] The data obtainer 140 can include circuitry, and the processor 130 can obtain various types of data used in the electronic device 100 through the data obtainer 140. Specifically, the data obtainer 140 can include a camera 141, a microphone 142, a sensor 143, etc.

[0212] The camera 141 can obtain an image of at least one object. Specifically, the camera 141 can include an image sensor, and the image sensor can convert light entering through a lens into an electrical image signal. Further, the microphone 142 can receive a voice signal and convert the received voice signal into an electrical signal.

[0213] The sensor 143 can detect various information inside and outside the electronic device 100. Specifically, the sensor 143 can include at least one of a global positioning system (GPS) sensor, a gyro sensor, an acceleration sensor (accelerometer), a laser radar sensor, an inertial sensor (inertial measurement unit (IMU)), or a motion sensor. Further, the sensor 143 can include various types of sensors such as a temperature sensor, a humidity sensor, an infrared sensor, and a biological sensor.

[0214] Specifically, in various embodiments according to the present application, the data obtainer 140 can obtain data input to one or more neural network models included in the electronic device 100. For example, the processor 130 can obtain image data input to a neural network model related to object recognition through the camera 141, and can obtain a voice signal input to a neural network model related to voice recognition through the microphone 142. Further, the processor 130 can also obtain location information input to a neural network model related to autonomous driving through at least one sensor 143 of a GPS sensor or a laser radar sensor.

[0215] The data outputter 150 can include circuitry, and the processor 130 can output various functions that the electronic device 100 can perform through the data outputter 150. Specifically, the data outputter 150 can include at least one of a display 151, a speaker 152, or an indicator 153.

[0216] The display 151 can output image data. Specifically, the display 151 can display an image or a user interface stored in the memory 120 under the control of the processor 130. The display 151 can be implemented as a liquid crystal display (LCD) panel, an organic light emitting diode (OLED), etc., and in some cases, can also be implemented as a flexible display, a transparent display, etc. However, the display 151 according to the present application is not limited to a specific kind. The display 151 can be implemented in the form of a touch display and be configured to receive a touch interaction of a user. The speaker 152 can output audio data under the control of the processor 130, and the indicator 153 can be illuminated under the control of the processor 130.

[0217] Specifically, in various embodiments according to the present application, the display 151 can display a user interface including information about neural network models satisfying hardware suitability and model suitability according to the present application. In addition, the processor 130 can receive a user input for selecting one or more neural network models among one or more neural network models through the user interface.

[0218] If it is identified that there is no neural network model satisfying hardware suitability and model suitability among neural network models included in the external device, the processor 130 can also output a user notification to indicate that all neural network models included in the external device do not satisfy conversion suitability according to the present application. The user notification can be output in the form of visual information through the display 151 and can be output in the form of audio information through the speaker 152 or in the manner of the indicator 153 being illuminated.

[0219] On the other hand, the control method of the electronic device 100 according to the above-described embodiments can be implemented through a program and provided to the electronic device 100. Specifically, a program including the control method of the electronic device 100 can be stored in a non-transitory computer readable medium and provided.

[0220] In detail, in a non-transitory computer-readable recording medium including a program for executing the control method of the electronic device 100, the control method of the electronic device 100 can include, when a user input is received, transmitting a first signal for requesting information related to one or more neural network models included in one or more external devices, receiving a second signal including second device information about a hardware specification of a first external device 200-1 and first model information about one or more neural network models included in the first external device 200-1 from the first external device 200-1 among the one or more external devices as a response to the first signal through the communicator 110, identifying whether each of the one or more neural network models included in the first external device 200-1 is suitable for hardware of the electronic device 100 by inputting the first device information, the second device information, and the first model information into the hardware suitability identification module 1100, transmitting a third signal including a request for installation data of the one or more neural network models identified as being suitable for the hardware of the electronic device 100 to the first external device 200-1, and receiving a fourth signal including the installation data of the one or more neural network models identified as being suitable for the hardware of the electronic device 100 from the first external device 200-1 through the communicator 110 as a response to the third signal.

[0221] Further, identifying whether each of the one or more neural network models included in the first external device 200-1 is suitable for the hardware of the electronic device 100 can include identifying the one or more neural network models included in the first external device 200-1 as being suitable for the hardware of the electronic device 100 when a specification of each of a plurality of hardware configurations included in the electronic device 100 is greater than or equal to specifications of a plurality of hardware configurations included in the first external device 200-1, and identifying one or more neural network models of the one or more neural network models included in the first external device 200-1 as being suitable for the hardware of the electronic device 100 when a hardware requirement specification of the one or more neural network models is lower than the specifications of the plurality of hardware configurations included in the electronic device 100, when the specifications of one or more of the plurality of hardware configurations included in the electronic device 100 are less than the specifications of the plurality of hardware configurations included in the first external device 200-1.

[0222] The non-transitory computer-readable medium is not a medium that stores data for a short time, such as a register, a cache, the memory 120, or the like, but refers to a machine-readable medium that stores data semi-permanently. Specifically, the various applications or programs described above can be stored and provided in a non-transitory computer-readable medium such as a compact disc (CD), a digital versatile disc (DVD), a hard disk, a Blu-ray disc, a universal serial bus (USB), a memory 120 card, a read-only memory (ROM), or the like.

[0223] In the above, the control method of the electronic device 100 and the computer-readable recording medium including a program for executing the control method of the electronic device 100 have been briefly described, but this is merely to omit redundant descriptions, and various embodiments of the electronic device 100 can also be applied to the control method of the electronic device 100 and the computer-readable recording medium including a program for executing the control method of the electronic device 100.

[0224] According to various embodiments as described above, when a neural network model is transmitted from an external device, the electronic device 100 can determine whether to transmit the neural network model by identifying whether it is suitable to transmit the neural network model to the electronic device 100, and accordingly, the efficiency and reliability of learning can be significantly improved.

[0225] The functions related to the above-described neural network model can be performed by the memory 120 and the processor 130. The processor 130 can be configured as one or more processors 130. At this time, the one or more processors 130 can be a general-purpose processor 130 such as a CPU, an AP, or the like, a graphics-specialized processor 130 such as a GPU, a VPU, or the like, or an artificial intelligence-specialized processor such as an NPU. The one or more processors 130 perform control to process input data according to a pre-defined operation rule or an artificial intelligence model stored in the non-volatile memory 120 and the volatile memory 120. The pre-defined operation rule or the artificial intelligence model is characterized in that it is created through training.

[0226] Here, "created through training" means a pre-defined operation rule or an artificial intelligence model having an intended characteristic created by applying a learning algorithm to a large amount of learning data. Such learning can be performed in the device itself that performs artificial intelligence according to the present application, or can also be performed through a separate server / system.

[0227] The artificial intelligence model can include a plurality of neural network layers. Each layer has a plurality of weight values, and layer computation is performed by computing the computation result of the previous layer and the plurality of weight values. Examples of the neural network include a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a generative adversarial network (GAN), and a deep Q-network, and the neural network in the present application is not limited to the above-described examples unless otherwise specified.

[0228] The learning algorithm is a method of training a predetermined target device (e.g., a robot) using a large amount of learning data so that the predetermined target device can make a decision or predict itself. Examples of the learning algorithm include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, and the learning algorithm in the present application is not limited to the above-described examples unless otherwise specified.

[0229] Machine-readable storage media may be provided in the form of non-transitory storage media. The term "non-transitory" means only that the storage medium is a tangible device and does not include signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently in the storage medium and cases where data is temporarily stored in the storage medium. For example, "non-transitory storage media" may include buffers for temporarily storing data.

[0230] According to embodiments, methods based on different embodiments of the invention may be included and provided in a computer program product. The computer program product can be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., an optical disc read-only memory (CD-ROM)), or distributed online (e.g., downloaded or uploaded) through an app store (e.g., the Play Store™), or distributed directly between two user devices (e.g., smartphones) (e.g., downloaded or uploaded). In the case of online distribution, at least a portion of the computer program product (e.g., a downloadable application) may be stored at least temporarily in a machine-readable storage medium, such as the memory of a manufacturer's server, an app store's server, or a relay server, or may be temporarily generated.

[0231] Each component (e.g., a module or program) according to the different embodiments described above may include a single entity or multiple entities, and some of the sub-components described above may be omitted, or other sub-components may be included in different embodiments. Optionally or additionally, some components (e.g., modules or programs) may be integrated into one entity to perform the same or similar functions performed by the individual components prior to integration.

[0232] According to different embodiments, operations performed by modules, programs or other components may be performed sequentially, in parallel, iteratively or heuristically, or at least some operations may be performed in a different order or omitted, or other operations may be added.

[0233] On the other hand, the term "device" or "module" used in this invention includes a unit consisting of hardware, software, or firmware, and can be used interchangeably with terms such as logic, logic block, component, or circuit. A "device" or "module" can be a component formed as a whole or the smallest unit performing one or more functions or a portion thereof. For example, the module can be configured as an application-specific integrated circuit (ASIC).

[0234] Various embodiments of the present application can be implemented by software including instructions stored in a machine (e.g., computer)-readable storage medium. The machine is an apparatus that reads the stored instructions from the storage medium and operates according to the instructions being read, and can include an electronic device (e.g., electronic device 100) according to the disclosed embodiments.

[0235] When the instructions are executed by the processor 130, the processor 130 can directly or using other components under the control of the processor 130 perform functions corresponding to the instructions. The instructions can include code generated or executed by a compiler or an interpreter.

[0236] While the present application has been shown and described with reference to various embodiments thereof, it will be understood by those skilled in the art that various changes in form and details can be made therein without departing from the spirit and scope of the application as defined by the appended claims and their equivalents.

Claims

1. An electronic device comprising: a communicator; a memory storing first device information about a hardware specification of the electronic device and one or more computer programs; and one or more processors communicatively coupled to the communicator and the memory, wherein the one or more computer programs include computer-executable instructions that, when executed by the one or more processors alone or collectively, cause the electronic device to: based on receiving a user input, control the communicator to transmit a first signal for requesting information related to one or more neural network models included in one or more external devices, receive, through the communicator, a second signal from a first external device among the one or more external devices as a response to the first signal, the second signal including second device information about a hardware specification of the first external device and first model information about one or more neural network models included in the first external device, based on the first device information, the second device information, and the first model information, identify whether each of the one or more neural network models included in the first external device is suitable for hardware of the electronic device, and perform installation of one or more neural network models identified as suitable for the hardware of the electronic device. the one or more computer programs further include computer-executable instructions that, when executed by the one or more processors alone or collectively, cause the electronic device to: 2.The electronic device of claim 1, wherein, identify whether each of the one or more neural network models included in the first external device is suitable for the hardware of the electronic device by inputting the first device information, the second device information, and the first model information into a hardware suitability identifier, based on identifying whether each of the one or more neural network models included in the first external device is suitable for the hardware of the electronic device: control the communicator to transmit a third signal to the first external device, the third signal including a request for installation data of one or more neural network models identified as suitable for the hardware of the electronic device, receive, through the communicator, a fourth signal from the first external device as a response to the third signal, the fourth signal including the installation data of the one or more neural network models identified as suitable for the hardware of the electronic device, and based on the installation data, perform installation of one or more neural network models identified as suitable for the hardware of the electronic device. the one or more computer programs further include computer-executable instructions that, when executed by the one or more processors alone or collectively, cause the electronic device to:

3. The electronic device of claim 2, wherein, based on a specification of each of a plurality of hardware configurations included in the electronic device being greater than or equal to a specification of a plurality of hardware configurations included in the first external device, identify that the one or more neural network models included in the first external device are suitable for the hardware of the electronic device, and ​ based on the specifications of one or more of the plurality of hardware configurations included in the electronic device being less than the specifications of the plurality of hardware configurations included in the first external device, one or more of the one or more neural network models included in the first external device having a hardware requirement specification that is less than the specifications of the plurality of hardware configurations included in the electronic device are identified as being suitable for the hardware of the electronic device. 4.The electronic device of claim 3, wherein the first device information including information regarding a specification of the one or more processors, a specification of the memory, and a specification of a data obtainer included in the electronic device, wherein the data obtainer included in the electronic device obtains data input to the one or more neural network models included in the electronic device, and includes at least one of a camera, a microphone, or a sensor included in the electronic device, wherein the second device information includes information regarding a specification of a processor included in the first external device, a specification of a memory included in the first external device, and a specification of a data obtainer included in the first external device, wherein the data obtainer included in the first external device obtains data input to the one or more neural network models included in the first external device, and includes at least one of a camera, a microphone, or a sensor included in the first external device, and wherein the first model information includes information regarding a hardware requirement specification of each of the one or more neural network models included in the first external device. 5.The electronic device of claim 4, wherein, the memory storing second model information regarding the one or more neural network models included in the electronic device, and a model suitability identifier for identifying neural network models suitable for replacing the one or more neural network models included in the electronic device, wherein the one or more computer programs further include computer-executable instructions that, when executed by the one or more processors alone or collectively, cause the electronic device to, based on the one or more neural network models suitable for the hardware of the electronic device being identified, identify whether each of the one or more neural network models identified as being suitable for the hardware of the electronic device is suitable for replacing the one or more neural network models included in the electronic device by inputting the first model information and the second model information into the model suitability identifier, wherein the third signal includes a request for installation data of the one or more neural network models identified as being suitable for replacing the one or more neural network models included in the electronic device, and wherein the fourth signal includes the installation data of the one or more neural network models identified as being suitable for replacing the one or more neural network models included in the electronic device. 6.The electronic device of claim 5, wherein, The first model information further includes information on a service type and information on a level of personalization of each of the one or more neural network models included in the first external device, and wherein the second model information further includes information on a service type and information on a level of personalization of each of the one or more neural network models included in the electronic device.

7. The electronic device of claim 6, wherein, The one or more computer programs further include computer-executable instructions that, when executed by the one or more processors alone or collectively, cause the electronic device to: compare, based on the information on a service type included in each of the first model information and the second model information, a service type of the one or more neural network models included in the electronic device with a service type of the one or more neural network models included in the first external device identified as being suitable for hardware of the electronic device, based on a service type of a first neural network model of the one or more neural network models included in the first external device being identified as being suitable for hardware of the electronic device being identical to a service type of a second neural network model of the one or more neural network models included in the electronic device, compare, based on the information on a level of personalization included in each of the first model information and the second model information, a level of personalization of the first neural network model with a level of personalization of the second neural network model, and based on the level of personalization of the first neural network model being higher than the level of personalization of the second neural network model, determine that the first neural network model is suitable to replace the second neural network model.

8. The electronic device of claim 7, wherein identify the level of personalization of the first neural network model based on at least one of information on a usage history of a user of the first external device with respect to the first neural network model and information on feedback of a user of the first external device with respect to the first neural network model, and wherein the level of personalization of the second neural network model is identified based on at least one of information on a usage history of a user of the electronic device with respect to the second neural network model and information on feedback of a user of the electronic device with respect to the second neural network model.

9. The electronic device of claim 3, wherein receive, from the first external device, the second signal through the communicator upon completion of user authentication based on first user information with respect to the electronic device and second user information with respect to the first external device, wherein the first user information includes at least one of account information with respect to a user of the electronic device or identification information with respect to the electronic device, and wherein the second user information includes at least one of account information of a user of the first external device or identification information of the first external device.

10. The electronic device of claim 3, further comprising a display, wherein, The one or more computer programs also include computer executable instructions that, when executed by the one or more processors, individually or collectively, cause the electronic device to: control the display to display a user interface including information of the one or more neural network models identified as suitable for hardware of the electronic device, and receive a user input through the user interface for selecting one or more neural network models among the one or more neural network models identified as suitable for hardware of the electronic device, wherein the third signal includes a request for installation data of the one or more selected neural network models, and wherein the fourth signal includes the installation data of the one or more selected neural network models. 11.A control method performed by an electronic device storing first device information about hardware specifications of the electronic device, the control method comprising: transmitting, by the electronic device, a first signal for requesting information related to one or more neural network models included in one or more external devices based on receiving a user input; receiving, by the electronic device, a second signal from a first external device among the one or more external devices as a response to the first signal, the second signal including second device information about hardware specifications of the first external device and first model information about one or more neural network models included in the first external device; identifying, by the electronic device, whether each of the one or more neural network models included in the first external device is suitable for hardware of the electronic device based on the first device information, the second device information, and the first model information, and performing, by the electronic device, installation of one or more neural network models identified as suitable for hardware of the electronic device. 12.The control method of claim 11, wherein the identifying further comprising identifying whether each of the one or more neural network models included in the first external device is suitable for hardware of the electronic device by inputting the first device information, the second device information, and the first model information into a hardware suitability identifier, and wherein the performing comprises, based on identifying whether each of the one or more neural network models included in the first external device is suitable for hardware of the electronic device: transmitting a third signal to the first external device, the third signal including a request for installation data of one or more neural network models identified as suitable for hardware of the electronic device; receiving a fourth signal from the first external device as a response to the third signal, the fourth signal including the installation data of the one or more neural network models identified as suitable for hardware of the electronic device; and performing installation of the one or more neural network models identified as suitable for hardware of the electronic device based on the installation data.

13. The control method according to claim 12, wherein the identifying further comprising: identifies the one or more neural network models included in the first external device as being suitable for hardware of the electronic device based on the specifications of each of the plurality of hardware configurations included in the electronic device being greater than or equal to the specifications of the plurality of hardware configurations included in the first external device, and identifies one or more neural network models, among the one or more neural network models included in the first external device, having a hardware requirement specification lower than the specifications of the plurality of hardware configurations included in the electronic device as being suitable for hardware of the electronic device based on the specifications of one or more of the plurality of hardware configurations included in the electronic device being less than the specifications of the plurality of hardware configurations included in the first external device.

14. The control method of claim 13, wherein the first device information includes information on a specification of a processor included in the electronic device, a specification of a memory included in the electronic device, and a specification of a data obtainer included in the electronic device, wherein the data obtainer included in the electronic device obtains data input to the one or more neural network models included in the electronic device, and includes at least one of a camera, a microphone, or a sensor included in the electronic device, wherein the second device information includes information on a specification of a processor included in the first external device, a specification of a memory included in the first external device, and a specification of a data obtainer included in the first external device, wherein the data obtainer included in the first external device obtains data input to the one or more neural network models included in the first external device, and includes at least one of a camera, a microphone, or a sensor included in the first external device, and wherein the first model information includes information on a hardware requirement specification of each of the one or more neural network models included in the first external device.

15. The control method of claim 14, wherein, the electronic device further stores second model information on the one or more neural network models included in the electronic device, and a model suitability recognizer for identifying a neural network model suitable for replacing the one or more neural network models included in the electronic device, wherein the control method further includes, based on the one or more neural network models suitable for hardware of the electronic device being identified, identifying whether each of the one or more neural network models identified as being suitable for hardware of the electronic device is suitable for replacing the one or more neural network models included in the electronic device by inputting the first model information and the second model information to the model suitability recognizer wherein the third signal includes a request for installation data of the one or more neural network models identified as being suitable for replacing the one or more neural network models included in the electronic device, and The fourth signal includes installation data of one or more neural network models identified as suitable for replacing the one or more neural network models included in the electronic device.

Images