Electronic device configured to switch from short-range wireless communication to cellular wireless communication and method for operating electronic device

Abstract

According to an embodiment, an electronic device and a method for operating the electronic device are provided. The electronic device may comprise: a first communication circuit for supporting short-range wireless communication; a second communication circuit for supporting cellular wireless communication; a memory storing computer programs including instructions; and at least one processor. The instructions, when executed individually or collectively by the at least one processor, may cause the electronic device to: control the first communication circuit to collect data related to signals transmitted and / or received to and / or from an external electronic device through the short-range wireless communication; in order to identify the threshold value of quality of the signals for switching from the short-range wireless communication to the cellular wireless communication, apply the collected data to a model for inferring the threshold value; identify whether the threshold value is valid, partially on the basis of at least one of skewness of the collected data and skewness of a part of the collected data corresponding to the quality of a signal lower than the identified threshold value among the collected data; and switch from the short-range wireless communication to the cellular wireless communication at least partially on the basis of whether the quality of a signal received during a designated time is equal to or lower than the identified threshold value when the identified threshold value is valid.

Description

Electronic device for switching from short-range wireless communication to cellular wireless communication and method of operation of the electronic device

[0001] The present disclosure relates to an electronic device and a method of operating the electronic device, and more specifically to an electronic device that switches from short-range wireless communication to cellular wireless communication.

[0002] With the proliferation of various electronic devices, speed improvements have been achieved for wireless communication that these devices can use. Among the wireless communications supported by recent electronic devices, IEEE 802.11 WLAN (or Wi-Fi) is a standard for implementing high-speed wireless connections on various electronic devices. While the first implemented Wi-Fi could support transmission speeds of up to 1 to 9 Mbps, Wi-Fi 6 technology (or IEEE 802.11ax) can support transmission speeds of up to approximately 10 Gbps.

[0003] The electronic device can support various services using relatively large data (e.g., UHD quality video streaming service, AR (augmented reality) service, VR (virtual reality) service, or MR (mixed reality) service) through wireless communication that supports high transmission speeds, and can also support various other services.

[0004] An electronic device may be connected via short-range wireless communication to an AP capable of providing short-range wireless communication in order to perform short-range wireless communication. While the electronic device is performing short-range wireless communication provided by the AP, the quality of the link established between the AP and the electronic device may change. The electronic device monitors the quality of the link, and if the quality of the link satisfies specified conditions, it may switch from short-range wireless communication to cellular wireless communication.

[0005] While performing short-range wireless communication, the electronic device can check the signal transmitted and / or received via short-range wireless communication. The electronic device can perform a service via cellular wireless communication by checking the quality of the signal received via short-range wireless communication for a period corresponding to a plurality of time slots and confirming that the delay time is greater than a specified size. One of the methods for data transmission and / or reception via cellular wireless communication in the short-range wireless communication is a long-term L2 transition. A long-term L2 transition can be activated if the quality of the signal received for a period corresponding to a plurality of time slots satisfies a specified condition. However, the time required for the transition from short-range wireless communication to cellular wireless communication may be relatively long. If the time required for the transition from short-range wireless communication to cellular wireless communication increases, the quality of the service performed by the electronic device (100) may degrade, and in the case of a real-time service, the performance of the service may be impossible.

[0006] The technical problems to be solved in this document are not limited to those mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art to which this invention belongs from the description below.

[0007] An electronic device according to one example may include a first communication circuit that supports short-range wireless communication. The electronic device may include a second communication circuit that supports cellular wireless communication. The electronic device may include a memory that stores computer programs including instructions. The electronic device may include at least one processor. When the instructions are executed individually or collectively by the at least one processor, the electronic device may control the first communication circuit to collect data related to a signal transmitted and / or received to an external electronic device via the short-range wireless communication. When the instructions are executed individually or collectively by the at least one processor, the electronic device may apply the collected data to a model that infers the threshold value to determine the threshold value of the signal quality for switching from the short-range wireless communication to the cellular wireless communication. When the above instructions are executed individually or collectively by the at least one processor, the electronic device may determine whether the threshold value is valid based, in part, on at least one of the skewness of the collected data and the skewness of a portion of the collected data corresponding to the quality of a signal lower than the identified threshold value among the collected data. When the above instructions are executed individually or collectively by the at least one processor, the electronic device may switch from the short-range wireless communication to the cellular wireless communication based, in part, on whether the quality of a signal received for a specified time is below the identified threshold value when the identified threshold value is valid.

[0008] In a recording medium storing at least one program comprising instructions that cause the electronic device to perform operations when executed individually or collectively by at least one processor of the electronic device according to one example, the instructions may cause the electronic device to collect data related to a signal received and / or transmitted from an external electronic device via near-field wireless communication when executed individually or collectively by the at least one processor. The instructions may cause the electronic device to input the collected data to a model that infers the threshold value in order to determine the threshold value of the signal quality for switching from near-field wireless communication to cellular wireless communication when executed individually or collectively by the at least one processor. The instructions may cause the electronic device to determine whether the threshold value is valid based in part on at least one of the skewness of the collected data and the skewness of a portion of the collected data corresponding to a signal quality lower than the determined threshold value among the collected data when executed individually or collectively by the at least one processor. When the above instructions are executed individually or collectively by the at least one processor, the electronic device may switch from the short-range wireless communication to the cellular wireless communication based at least in part on whether the quality of the signal received for a specified time is below the identified threshold value when the identified threshold value is confirmed to be valid.

[0009] A method of operation of an electronic device according to one example may include an operation of collecting data related to a signal received and / or transmitted from an external electronic device via near-field wireless communication. A method of operation of an electronic device may include an operation of applying the collected data to a model that infers the threshold value in order to check the threshold value of the signal quality for switching from the near-field wireless communication to cellular wireless communication. A method of operation of an electronic device may include an operation of checking whether the threshold value is valid based, in part, on at least one of the skewness of the collected data and the skewness of a portion of the collected data corresponding to the signal quality of the collected data that is lower than the confirmed threshold value. If the confirmed threshold value is confirmed to be valid, a method of operation of an electronic device may include an operation of switching from the near-field wireless communication to the cellular wireless communication based, in at least part, on whether the quality of the signal received during a specified time is below the confirmed threshold value.

[0010] According to various embodiments of the present invention, the electronic device and the method of operation of the electronic device allow the electronic device to determine a threshold value for signal quality for transitioning to cellular wireless communication based on data related to a signal transmitted and / or received via near-field wireless communication. The electronic device can determine the validity of the threshold value based on the skewness of the collected data and the skewness of the data related to the signal having a quality lower than the determined threshold value among the collected data. If the threshold value is determined to be valid, the electronic device can transition from near-field wireless communication to cellular wireless communication based at least partially on the fact that the quality of the signal received during a specified time is lower than the threshold value confirmed to be valid. The specified time may be much shorter than the time required for the Long-term L2 transition described above. Accordingly, the electronic device can transition to cellular wireless communication relatively quickly due to the degradation of the quality of near-field wireless communication, and can prevent a degradation of the quality of the service performed by the electronic device.

[0011] The effects obtainable from the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art to which the present disclosure belongs from the description below.

[0012] FIG. 1 is a block diagram of an electronic device according to one embodiment.

[0013] FIG. 2a is a diagram illustrating an example in which an electronic device according to one embodiment performs short-range wireless communication and cellular wireless communication.

[0014] FIG. 2b is a diagram illustrating an example in which an electronic device according to one embodiment performs short-range wireless communication and then switches to cellular wireless communication.

[0015] FIG. 3 is a block diagram of an electronic device according to one embodiment.

[0016] FIG. 4 is a diagram illustrating a model for inferring a threshold value of signal quality for performing a transition from short-range wireless communication to cellular wireless communication in an electronic device according to one embodiment.

[0017] FIG. 5 is a diagram illustrating an example of collecting data related to a signal received via short-range wireless communication in an electronic device according to one embodiment.

[0018] FIGS. 6a and 6b are drawings illustrating an example of verifying the validity of a threshold value in an electronic device according to one embodiment.

[0019] FIGS. 7A, 7B, and 7C illustrate an example of verifying the validity of a threshold value based on a plurality of characteristics of a signal in an electronic device according to one embodiment.

[0020] FIG. 8 is a diagram illustrating an example of switching from short-range wireless communication to cellular wireless communication when a threshold value is valid in an electronic device according to one embodiment.

[0021] FIG. 9 is an operation flowchart illustrating the operation method of an electronic device according to one embodiment.

[0022] FIG. 10 is an operation flowchart illustrating the operation method of an electronic device according to one embodiment.

[0023] FIG. 1 is a block diagram of an exemplary electronic device (100) capable of performing the operations described in this document.

[0024] Referring to FIG. 1, the electronic device (100) may be one of various forms of electronic devices, such as a notebook (190), smartphones (191) having various form factors (e.g., a bar-type smartphone (191-1), a foldable-type smartphone (191-2), or a sliderable (or rollable)-type smartphone (191-3)), a tablet (192), a cellular phone (not shown), and other similar computing devices (not shown). The components, their relationships, and their functions illustrated in FIG. 1 are illustrative only and are not intended to limit the implementations described or claimed herein. The electronic device (100) may be referred to as a mobile device, a user device, a multifunction device, a portable device, or a server.

[0025] The electronic device (100) may include components comprising at least one processor (110) (hereinafter referred to as processor (110)), at least one memory (120) (hereinafter referred to as memory (120))11, at least one display (140) (hereinafter referred to as display (140)), at least one image sensor (150) (hereinafter referred to as image sensor (150)), at least one communication circuit (160) (hereinafter referred to as communication circuit (160)), and / or at least one sensor (170) (hereinafter referred to as sensor (170)). The components are merely exemplary. For example, the electronic device (100) may include other components (e.g., power management integrated circuitry (PMIC), audio processing circuit, antenna, rechargeable battery, or input / output interface). For example, some components may be omitted from the electronic device (100). For example, some components may be integrated into a single component.

[0026] The processor (110) may be implemented as one or more IC (integrated circuit (or circuitry)) chips and may perform various data processing operations. The processor (110) may include at least one electrical circuit and may process instructions (or programs, data, etc.) stored in memory (120) individually or collectively in a distributed manner. The processor (110) may include a processor assembly comprising one or more processing circuits. The processor (110) may include any processing circuit that is operative to control the performance and operations of one or more components of the electronic device (100) (e.g., memory (120), display (140), image sensor (150), communication circuit (160), and / or sensor (170)). For example, the processor (110) (e.g., application processor (AP)) may be implemented as a system on chip (SoC) (e.g., a single chip or chipset). For example, the processor (110) may be implemented with a plurality of cores (or at least one core circuit), a plurality of chips, or a plurality of chipsets. For example, the processor (110) may include one or more processing circuits. For example, the processor (110) may include one or more processing circuits configured to perform the various functions of the present disclosure individually and / or collectively. By example, without limitation, at least a portion of the processor (110) may be included in a first chip of the electronic device (100), and at least another portion of the processor (110) may be included in a second chip of the electronic device (100) different from the first chip of the electronic device (100).

[0027] For example, the processor (110) may include a central processing unit (111), a graphics processing unit (112), a neural processing unit (113), an image signal processor (114), a display controller (115), a memory controller (116), a storage controller (117), a communication processor (118), and / or a sensor interface (119). These components of the processor (110) are merely exemplary. For example, the processor (110) may include other components. For example, some components of the processor (110) may be omitted from the processor (110). For example, some components of the processor (110) may be included as separate components of the electronic device (100) outside of the processor (110). For example, some components of the processor (110) (e.g., memory controller (116)) may be included in other components (e.g., at least part of memory (120), an interface (e.g. available for connection to at least one component of the electronic device (100)), a display (140) and / or an image sensor (150)).

[0028] The processor (110) may cause other components of the electronic device (100) to perform various operations by executing instructions stored in memory (120). The CPU (111) (or central processing circuit) may be configured to control the components of the processor (110) based on the execution of instructions stored in memory (120) (e.g., volatile memory (121) and / or non-volatile memory (122)). The GPU (112) (or graphics processing circuit) may be configured to execute parallel operations (e.g., rendering). The NPU (113) (or neural processing circuit, or AI (artificial intelligence) chip) may be configured to execute operations for an artificial intelligence model (e.g., convolution computation). An ISP (114) (or image signal processing circuit) may be configured to process a raw image acquired through an image sensor (150) into a format suitable for a component within the electronic device (100) or a component of the processor (110). A display controller (115) (or display control circuit, or DPU (display processing unit)) may be configured to process an image acquired from a CPU (111), GPU (112), ISP (114), or memory (120) (e.g., volatile memory (121)) into a format suitable for a display (140). A memory controller (116) (or memory control circuit) may be configured to control reading data from the volatile memory (121) and writing data to the volatile memory (121). A storage controller (117) (or storage control circuit) may be configured to control reading data from the non-volatile memory (122) and writing data to the non-volatile memory (122).The CP (118) (communication processing circuit) may be configured to process data obtained from a component of the processor (110) into a format suitable for transmitting to another electronic device via the communication circuit (160), or to process data obtained from another electronic device via the communication circuit (160) into a format suitable for processing by the component of the processor (110). For example, the communication circuit (160) may include one or more communication circuits. The sensor interface (119) (or sensing data processing circuit, sensor hub) may be configured to process data regarding the state of the electronic device (100) and / or the state around the electronic device (100), obtained through the sensor (170), into a format suitable for the component of the processor (110).

[0029] Memory (120) may include one or more storage media (or one or more storage devices). For example, memory (120) may include a memory assembly comprising one or more storage media. For example, the one or more storage media may include a hard drive, a permanent memory such as flash memory, read-only memory (ROM) (e.g., non-volatile memory (122)), a semi-permanent memory such as random access memory (RAM) (e.g., volatile memory (121)), any other suitable type of storage (or storage assembly), or any combination thereof. Memory (120) may include a cache memory, which is one or more different types of memory used to temporarily store data for a function or feature of the electronic device (100). As an example not limited to, the cache memory may be included within the processor (110). The memory (120) may be fixedly embedded within the electronic device (100) or incorporated into one or more suitable types of components (e.g., a SIM (subscriber identity module) card and / or an SD (secure digital) card) that can be repeatedly inserted into and removed from the electronic device (100).

[0030] For example, memory (120) may store one or more software applications, such as operating system (or system) software applications, firmware software applications, driver software applications, plugin (e.g., add-in, add-on, and / or applet) software applications, and / or any other suitable software applications. For example, the one or more software applications may include instructions executable by the processor (110). For example, memory (120) may store instructions that can be called by an application programming interface (API). For example, memory (120) may store instructions within a library.

[0031] FIG. 2a is a diagram illustrating an example in which an electronic device according to one embodiment performs short-range wireless communication and cellular wireless communication.

[0032] An electronic device (e.g., the electronic device (100) of FIG. 1) may support short-range wireless communication. Short-range wireless communication may include Wi-Fi as defined in IEEE 802.11, but may include various short-range wireless communications other than Wi-Fi. If the short-range wireless communication is Wi-Fi, the electronic device (100) may perform the role of a STA (station) as defined in IEEE 802.11. The electronic device (100) may be connected to an external electronic device (210) via short-range wireless communication and may transmit and / or receive data via short-range wireless communication. The external electronic device (210) may perform the role of an AP (access point) as defined in IEEE 802.11.

[0033] The electronic device (100) may support cellular wireless communication. If the electronic device (100) supports cellular wireless communication, it may be connected via cellular wireless communication to a base station (220) included in a cellular network that supports cellular wireless communication, and may transmit and / or receive data via cellular wireless communication.

[0034] The electronic device (100) can transmit and / or receive data via cellular wireless communication when short-range wireless communication is disabled, and when short-range wireless communication is enabled (e.g., when the electronic device (100) receives user input to enable short-range wireless communication, or when an application that performs a service using short-range wireless communication is enabled), it can discover an external electronic device (210) that supports short-range wireless communication and connect with the discovered external electronic device (210) to perform short-range wireless communication.

[0035] However, the electronic device (100) may find it difficult to perform short-range wireless communication if the quality of the link established (or created, set) between the external electronic device (210) and the electronic device (100) deteriorates. The electronic device (100) may switch from short-range wireless communication to cellular wireless communication upon detecting that the quality of the link (or the quality of the signal received from the external electronic device (210)) has deteriorated. Switching from short-range wireless communication to cellular wireless communication may refer to switching from a state in which the electronic device (100) performs data transmission and / or reception via short-range wireless communication to a state in which the electronic device (100) performs data transmission and / or reception via cellular wireless communication.

[0036] An example of an electronic device (100) switching from short-range wireless communication to cellular wireless communication is described later in FIG. 2b.

[0037] FIG. 2b is a diagram illustrating an example in which an electronic device according to one embodiment performs short-range wireless communication and then switches to cellular wireless communication.

[0038] An electronic device (e.g., the electronic device (100) of FIG. 1) can transmit and / or receive a signal to an external electronic device (e.g., the external electronic device (210) of FIG. 2a) via short-range wireless communication. While performing short-range wireless communication, the electronic device (100) can check (or measure, monitor) the quality of the signal transmitted and / or received via short-range wireless communication.

[0039] According to one example, the electronic device (100) can check the quality of a signal received via short-range wireless communication for a plurality of specified times (231, 232, 233, 234, 235, and 236). The quality of the signal received via short-range wireless communication may be represented by at least one parameter related to the quality of the signal. According to one example, the quality of the signal received via short-range wireless communication may refer to the latency of the signal. The latency of the signal may be a parameter related to the difference between the time when the external electronic device (210) transmitted the signal and the time when the electronic device (100) received the signal. The electronic device (100) can check (or determine) the latency based on the difference between the time when the external electronic device (210) transmitted the signal and the time when the signal was received, which is included in the signal received from the external electronic device (210). The electronic device (100) can perform a transition from short-range wireless communication to cellular wireless communication (237) based on receiving a signal having a delay time greater than a specified size (e.g., latency outage threshold) for a plurality of specified times (233, 234, 235, and 236) continuously (or repeatedly).

[0040] The switching method illustrated in FIG. 2b may be referred to as Long-term L2 transition (or smart network switching). A switching using the switching method illustrated in FIG. 2b may be performed when a signal having a delay time greater than a specified size is received for a plurality of specified times (233, 234, 235, and 236). The switching method illustrated in FIG. 2b may increase the time required for switching to cellular wireless communication by confirming (or monitoring) the signal for a plurality of specified times (233, 234, 235, and 236). For example, if the size of the specified times (233, 234, 235, and 236) is about 3 seconds, the electronic device (100) may switch to cellular wireless communication after a maximum of 12 seconds have passed. If the time required to switch from short-range wireless communication to cellular wireless communication increases, the quality of the service performed by the electronic device (100) may be degraded, and in the case of a real-time service, the performance of the service may be impossible. Below, an example of switching from short-range wireless communication to cellular wireless communication based on the characteristics (or quality) of a signal received by the electronic device (100) during a single specified period is described.

[0041] FIG. 3 is a block diagram of an electronic device according to one embodiment.

[0042] According to one example, an electronic device (e.g., the electronic device (100) of FIG. 1) may include a first communication circuit (310) (e.g., the communication circuit (160) of FIG. 1), a processor (320) (e.g., the processor (110) of FIG. 1), a memory (330) (e.g., the memory (120) of FIG. 1) and / or a second communication circuit (340) (e.g., the communication circuit (160) of FIG. 1).

[0043] The first communication circuit (310) may be a communication circuit that supports short-range wireless communication. The short-range wireless communication may include various short-range wireless communications that the electronic device (100) can support. For example, the short-range wireless communication may be Wi-Fi.

[0044] The second communication circuit (340) may be a communication circuit that supports cellular wireless communication. Cellular wireless communication may include various types of cellular wireless communication that the electronic device (100) can support. For example, cellular wireless communication may include 5th generation cellular wireless communication (new radio), 4th generation cellular wireless communication (long-term evolution), and / or 3rd generation cellular wireless communication (3G).

[0045] The first communication circuit (310) and the second communication circuit (340) may include various circuit structures used for modulating and / or demodulating signals within the electronic device (100). For example, the first communication circuit (310) may modulate a baseband signal into a radio frequency (RF) band signal to output it through an antenna (not shown), or demodulate an RF band signal received through the antenna into a baseband signal and transmit it to a processor (320).

[0046] The processor (320) is electrically or operatively connected to the first communication circuit (310) and the second communication circuit (340) and can control the first communication circuit (310) and the second communication circuit (340). The processor (320) may include at least one processor, and at least one processor may perform the following operations individually or collectively.

[0047] The memory (330) can store instructions that can be executed by the processor (320). The operation of the processor (320) described below can be performed according to the execution of the instructions stored in the memory (330).

[0048] The processor (320) can control the first communication circuit (310) to discover (or search for) an access point (AP) that supports short-range wireless communication in order to perform short-range wireless communication. The first communication circuit (310), based on the control of the processor (320), can discover an external electronic device (e.g., the external electronic device (210) of FIG. 2a) that acts as an AP and perform a series of procedures (e.g., authentication procedure, coupling procedure, and / or security setup procedure) to connect with the external electronic device (210) via short-range wireless communication. When the processor (320) is connected with the external electronic device (210) via short-range wireless communication, the processor (320) can transmit a signal containing data via short-range wireless communication to the external electronic device (210) and / or receive a signal containing data via short-range wireless communication from the external electronic device (210).

[0049] The processor (320) may collect (or verify, monitor) data related to a signal transmitted and / or received via short-range wireless communication while performing short-range wireless communication. Data related to a signal transmitted and / or received via short-range wireless communication may refer to data related to the quality of the link established between the electronic device (100) and the external electronic device (210). For example, data related to the signal may include at least one parameter among the quality of the signal (e.g., RSSI (received signal strength indicator)), the delay time of the signal, the success rate of receiving the signal, and the success rate of transmitting the signal. The processor (320) may control the first communication circuit (310) to obtain data related to a signal transmitted and / or received via short-range wireless communication. The first communication circuit (310) may obtain data related to a signal transmitted and / or received via short-range wireless communication and transmit it to the processor (320).

[0050] The processor (320) may store a first model for verifying (or inferring) a threshold value of signal quality for switching from short-range wireless communication to cellular wireless communication on memory included in the processor (320) or on memory (330) existing outside the processor (320). The first model may be an artificial intelligence model learned based on data related to a signal transmitted via short-range wireless communication and data related to a signal received via short-range wireless communication. The first model may be an artificial intelligence model learned by the manufacturer of the electronic device (100) using various technologies (e.g., machine learning, neural network learning, self-organizing map, hidden Markov model, or convolution neural network learning). The first model may be authorized to have data transmitted and / or received via short-range wireless communication, and may determine (or infer) a threshold value of signal quality for transitioning from short-range wireless communication to cellular wireless communication based on the data transmitted and / or received via short-range wireless communication. The first model may determine (or verify, determine, infer) whether the determined (or inferred) threshold value is a valid value. According to one example, the first model may be referred to as a model for link transition decision.

[0051] According to one example, the first model can determine (or infer) a threshold value for the quality of a signal for switching from short-range wireless communication to cellular wireless communication based on data related to a signal received through short-range wireless communication.

[0052] According to one example, the first model can classify data related to a signal received via short-range wireless communication based on delay time. For example, the first model can classify (or label) data related to a signal received via short-range wireless communication into first data related to a signal with a delay time of less than or equal to a specified size and second data related to a signal with a delay time exceeding a specified size. The first data may be referred to as class 0, and the second data may be referred to as class 1. The first model can infer a threshold value of signal quality based on the number of classified first data and the number of second data. According to one example, the first model can list (or graph) data related to a signal received via short-range wireless communication according to the quality of the signal received via short-range wireless communication (e.g., RSSI).

[0053] The first model can identify a state in which the number of second data increases rapidly due to a change in signal quality, and determine the signal quality corresponding to the state in which the number of second data increases rapidly as a threshold value. The first model can determine the threshold value if the number of first data among data having a quality lower than or equal to the signal quality corresponding to the threshold value is less than or equal to a specified number. A signal received via short-range wireless communication may have the characteristic that as the signal quality decreases, the number of first data decreases rapidly and the number of second data increases rapidly. The signal quality corresponding to the state in which the number of first data decreases rapidly and the number of second data increases rapidly may be substantially the same as the maximum value of the signal quality required for switching from short-range wireless communication to cellular wireless communication. Therefore, the threshold value may refer to an inflection point of the number of data in the distribution of data related to the signal received via short-range wireless communication. The first model, taking into account the above characteristics, can check the quality of a signal corresponding to a rapid increase in the number of second data and a number of first data less than or equal to a specified number, and determine (or infer) the quality of the checked signal as a threshold value.

[0054] The first model can verify (or validate, infer) the validity of a confirmed (or inferred) threshold value. The first model can verify the validity of the threshold value based in part on at least one of the skewness of the data related to a signal with a delay time greater than a specified size among the data related to a signal received via short-range wireless communication, and the skewness of the data related to a signal with a delay time greater than a specified size among the data related to a signal having a quality less than or equal to the confirmed threshold value. The skewness of the data related to a signal received via short-range wireless communication may be a parameter capable of measuring the asymmetry of the distribution of the data related to the signal received via short-range wireless communication (e.g., may be distributed according to the quality of the signal).

[0055] According to one example, the first model can compare the skewness of data related to a signal with a delay time greater than a specified size with the skewness of data related to a signal with a delay time greater than a specified size that has a quality below a identified threshold. The first model can identify (or determine, infer) the threshold as valid if the difference between the skewness of data related to a signal with a delay time greater than a specified size and the skewness of data related to a signal with a delay time greater than a specified size that has a quality below a identified threshold is greater than (or exceeds) the specified size. If the threshold is inferred to be substantially the same as the previously described inflection point, the difference between the skewness of data related to a signal with a delay time greater than a specified size and the skewness of data related to a signal with a delay time greater than a specified size that has a quality below a identified threshold may be large. Conversely, if the threshold value is determined (or inferred) to differ significantly from the previously described inflection point, the difference between the skewness of the data related to the signal with a delay time greater than the specified size and the skewness of the data related to the signal with a delay time greater than the specified size that has a quality below the identified threshold value may be small. Therefore, the first model can confirm (or determine, infer) the threshold value as valid if the difference between the skewness of the data related to the signal with a delay time greater than the specified size and the skewness of the data related to the signal with a delay time greater than the specified size that has a quality below the identified threshold value is greater than (or exceeds) the specified size.The first model can identify (or determine, infer) that the threshold is invalid if the difference between the skewness of data related to a signal with a delay time greater than a specified size and the skewness of data related to a signal with a delay time greater than a specified size and the skewness of data related to a signal having a quality less than or equal to a identified threshold is less than (or less than) the specified size.

[0056] According to one example, the first model can confirm (or determine, infer) that the threshold is valid if the absolute value of the skewness of the data associated with a signal having a quality below a confirmed threshold among the data associated with a signal having a delay time greater than a specified size is greater than or equal to a specified size (e.g., 1).

[0057] According to one example, the first model can identify (or determine, infer) the threshold as valid if the skewness of the data associated with a signal having a quality below a identified threshold among the data associated with a signal having a delay time greater than or equal to a specified size is less than or equal to (or less than) the specified size (e.g., -1).

[0058] According to one example, the first model can identify (or determine, infer) the threshold as valid if the skewness of the data associated with a signal having a quality below a identified threshold among the data associated with a signal with a delay time greater than a specified size is greater than (or exceeds) the specified size (e.g., +1).

[0059] According to one example, the first model can determine that the threshold is valid if the ratio of the number of data related to signals having quality below the confirmed threshold and the number of data with a delay time of longer than the specified time is greater than the specified size.

[0060] According to one example, the processor (320) can control the first communication circuit (310) and the second communication circuit (340) to switch from short-range wireless communication to cellular wireless communication based on a threshold value that the first model has determined (or inferred) to be valid.

[0061] The processor (320) can determine whether the quality of a signal received for a specified period is below a threshold value while short-range wireless communication is enabled. The processor (320) can decide to switch from short-range wireless communication to cellular wireless communication based at least partially on whether the quality of a signal received for a specified period is below a threshold value. The processor (320) can control the second communication circuit (340) to transmit a signal containing data to be transmitted via cellular wireless communication.

[0062] According to one example, the processor (320) may decide to switch from short-range wireless communication to cellular wireless communication if it determines that the quality of the signal received for a specified time is below a threshold value and the delay time of the signal is longer than the specified time. The processor (320) may control the second communication circuit (340) to transmit a signal containing data to be transmitted via cellular wireless communication.

[0063] The processor (320) can switch from short-range wireless communication to cellular wireless communication based on the quality of the signal verified during one designated time (e.g., 231, 232, 233, 234, 235, or 236 in FIG. 2b), unlike the switching method described above in FIG. 2b. Accordingly, the electronic device (100) can prevent a deterioration in the quality of the service performed by the electronic device (100) by switching to cellular wireless communication relatively quickly in response to a deterioration in the quality of the short-range wireless communication.

[0064] According to one example, the processor (320) may switch from cellular wireless communication to short-range wireless communication based at least in part that, after switching to cellular wireless communication, the quality of the signal received via short-range wireless communication exceeds (or is greater than) a threshold value (or another value substantially equal to the threshold value to prevent frequent switching). The processor (320) may switch from cellular wireless communication to short-range wireless communication based on that, after switching to cellular wireless communication, the quality of the signal received via short-range wireless communication exceeds (or is greater than) a threshold value and the delay time of the signal is less than (or less than) a specified time.

[0065] The processor (320) may switch from near-field wireless communication to cellular wireless communication using the switching method described in FIG. 2b when the threshold value confirmed by the first model is determined (or confirmed, inferred) to be invalid. According to one example, the processor (320) may decide to switch from near-field wireless communication to cellular wireless communication when it confirms that the delay time of a signal received during a plurality of specified times is greater than or equal to the specified time. The processor (320) may control the second communication circuit (340) to transmit a signal containing data to be transmitted via cellular wireless communication. According to one example, the plurality of specified times may refer to times greater than the specified time corresponding to the case where the threshold value confirmed by the first model is determined to be valid. The plurality of specified times may be replaced with times greater than the specified time corresponding to the case where the threshold value confirmed by the first model is determined to be valid, instead of a plurality of specified times.

[0066] According to one example, data related to a signal applied (or input) to a first model may be data collected by a second model different from the first model. The processor (320) may store a second model for collecting data related to a signal applied (or input) to the first model in memory included in the processor (320) or in memory (330) existing outside the processor (320). The second model may be an artificial intelligence model learned by the manufacturer of the electronic device (100), and may be an artificial intelligence model learned using various technologies (e.g., machine learning, neural network learning, self-organizing map, hidden Markov model, or convolution neural network learning). The second model may be a model for collecting data related to a signal transmitted and / or received via short-range wireless communication.

[0067] The second model can receive data related to a signal transmitted and / or received via short-range wireless communication from the first communication circuit (310). The second model can classify and / or manage data related to a signal transmitted and / or received via short-range wireless communication according to the quality of the signal. The second model can classify data related to a signal transmitted and / or received via short-range wireless communication according to the quality of the signal and store the classified data in different storage spaces (e.g., queues).

[0068] For example, the second model can classify signal quality according to a specified unit (e.g., 5 dBm) and store data related to signals having quality included in the classified quality in a storage space corresponding to each classified quality. The second model can collect data related to signals with relatively low quality together with data related to signals with relatively high quality, and can apply (or input) the collected data related to signals to the first model upon confirming that the number of data related to signals with relatively low quality is greater than or equal to a specified number (e.g., 20). If the number of data related to signals with relatively low quality is less than the specified number, the second model may not apply (or input) the collected data related to signals to the first model. Due to the characteristics of short-range wireless communication, the number of data related to signals with relatively low quality may be smaller than the number of data related to signals with relatively high quality. A lack of data related to signals with relatively low quality may cause an over-fitting phenomenon. Overfitting can occur when the first model is trained primarily on data related to signals of relatively high quality, causing it to determine (or infer) a threshold value different from the quality corresponding to a situation where actual conversion is required. Therefore, the second model can prevent the above-mentioned overfitting phenomenon by confirming that the number of data related to signals of relatively low quality is greater than a specified number (e.g., 20) and by applying (or inputting) the collected data related to the signals to the first model.

[0069] In relation to the example described above, the processor (320) may be configured to determine (or infer) a threshold value using the first model for each AP (or external electronic device (210)) that can be connected to the electronic device (100). Accordingly, the processor (320) may be configured to switch from short-range wireless communication to cellular wireless communication according to different threshold values ​​for each AP connected to the electronic device (100).

[0070] In relation to the example described above, the processor (320) may be configured to determine (or infer) a threshold value using a first model for each of the multiple frequency bands (e.g., 2.4 GHz, 5 GHz, and / or 6 GHz) for an AP (or external electronic device (210)) connected to the electronic device (100) via short-range wireless communication. Accordingly, the processor (320) may enable switching from short-range wireless communication to cellular wireless communication based on a threshold value that is set differently depending on the frequency band of the link established between the electronic device (100) and the external electronic device (210).

[0071] In relation to the example described above, the processor (320) may reset the threshold value according to changes in the environment of the link established between the electronic device (100) and the external electronic device (210). According to one example, the processor (320) may determine the ratio of the first data and the second data among the data related to the signal received and / or transmitted from the external electronic device (210), and compare the ratio of the first data and the second data with the existing ratio. Based on the result of comparing the ratio of the first data and the second data with the existing ratio (e.g., the ratio of the first data and the second data has changed significantly), the processor (320) may perform fine-tuning of the first model based on the collected data. The processor (320) may re-determine (or infer) the threshold value using the fine-tuned first model.

[0072] In relation to the example described above, the processor (320) may reset the threshold value according to the state of the electronic device (100). The state of the electronic device (100) may refer to an open state, which refers to a state where the angle of the housing parts included in the foldable housing is greater than or equal to a specified size (e.g., 170 degrees), a folded state, which refers to a state where the angle of the housing parts is less than or equal to a specified size (e.g., 10 degrees), and an intermediate state, which refers to a state where the angle of the housing parts is included within a specified range (e.g., 10 degrees to 170 degrees). When the state of the electronic device (100) changes, the relative position (e.g., distance) between the antennas included in the electronic device (100) may change, and the change in the relative position between the antennas may cause a change in the environment of the link established between the electronic device (100) and the external electronic device (210). According to one example, the processor (320) can determine the ratio of the first data and the second data among the data related to the signal received and / or transmitted from the external electronic device (210) according to a change in the state of the electronic device (100), and compare the ratio of the first data and the second data with an existing ratio. The processor (320) can perform fine-tuning of the first model based on the collected data based on the result of comparing the ratio of the first data and the second data with the existing ratio (e.g., the ratio of the first data and the second data is significantly changed). The processor (320) can redetermine (or infer) the threshold value using the fine-tuned first model.

[0073] In the example described above, the validity of the threshold value is verified by distributing data related to a signal received via short-range wireless communication according to the quality of the signal and then checking the skewness of the distributed data. However, the first model may be implemented to verify the validity of the threshold value by checking the skewness of the distributed data according to other characteristics of the signal (e.g., transmission success rate, reception success rate) in addition to the quality of the signal, and furthermore, the first model may be implemented to verify the validity of the threshold value by checking the skewness of the distributed data according to multiple characteristics among the characteristics of the signal. Specific details will be described later in FIGS. 7a to 7c.

[0074] FIG. 4 is a diagram illustrating a model for inferring a threshold value of signal quality for performing a transition from short-range wireless communication to cellular wireless communication in an electronic device according to one embodiment.

[0075] Referring to FIG. 4, a first model (410) and a second model (420) are illustrated. The first model (410) and the second model (420) may be software components implemented on the processor (310) or hardware components implemented on the processor (310). The first model (410) and the second model (420) may be run on a neural processing unit (NPU) included in the processor (310).

[0076] The second model (420) may include a data collector (421) and a second discriminator (422). The data collector (421) may receive data related to a signal transmitted and / or received via short-range wireless communication from a first communication circuit (e.g., the first communication circuit (310) of FIG. 3). The data collector (421) may classify and / or manage data related to a signal transmitted and / or received via short-range wireless communication according to the quality of the signal. The data collector (421) may classify data related to a signal transmitted and / or received via short-range wireless communication according to the quality of the signal and store the classified data in different storage spaces (e.g., queues).

[0077] For example, the data collector (421) can classify the quality of the signal according to a specified unit (e.g., 5 dBm) and store data related to the signal having a quality included in the classified quality in a storage space corresponding to each of the classified qualities.

[0078] The second discriminator (422) may be an entity that determines whether to authorize data related to a signal transmitted and / or received via short-range wireless communication, which is data collected by the data collector (421), to the first model (410).

[0079] The second model (420) can collect data related to signals of relatively low quality, along with data related to signals of relatively high quality. The second discriminator (422) can apply (or input) the collected data related to signals to the first model (410) as it confirms that the number of data related to signals of relatively low quality is greater than or equal to a specified number (e.g., 20).

[0080] The second discriminator (422) may not apply (or input) the data related to the collected signal to the first model (410) if the number of data related to the signal having relatively low quality is less than the specified number.

[0081] Due to the characteristics of short-range wireless communication, the number of data related to signals of relatively low quality may be smaller than the number of data related to signals of relatively high quality. A lack of data related to signals of relatively low quality can cause an over-fitting phenomenon. Over-fitting can cause the first model (410) to determine (or infer) a threshold value different from the quality corresponding to the situation where actual conversion is required, if the first model (410) is trained mainly on data related to signals of relatively high quality. Therefore, the second model (420) can prevent the above-mentioned over-fitting phenomenon by applying (or inputting) the collected signal-related data to the first model (410) upon confirming that the number of data related to signals of relatively low quality is greater than a specified number (e.g., 20).

[0082] The first model (410) may include a threshold inference model (411) and a first discriminator (412).

[0083] According to one example, the threshold inference model (411) can determine (or infer) the threshold value of the signal quality for switching from short-range wireless communication to cellular wireless communication based on data related to the signal received through short-range wireless communication input by the second model (420).

[0084] According to one example, a threshold inference model (411) can infer a threshold value by integrating data related to the signal, classified according to the quality of the signal, and inputting the integrated data into a machine learning model.

[0085] According to one example, the threshold inference model (411) can classify data related to a signal received via near-field wireless communication based on delay time. For example, the threshold inference model (411) can classify (or label) data related to a signal received via near-field wireless communication into first data related to a signal with a delay time of less than or equal to a specified size and second data related to a signal with a delay time exceeding a specified size. The first data may be referred to as class 0, and the second data may be referred to as class 1. The threshold inference model (411) can infer a threshold value of signal quality based on the number of classified first data and the number of second data. According to one example, the threshold inference model (411) can list (or graph) data related to a signal received via near-field wireless communication according to the quality of the signal received via near-field wireless communication (e.g., RSSI).

[0086] The threshold inference model (411) can identify a state in which the number of second data increases rapidly due to a change in signal quality, and determine the signal quality corresponding to the state in which the number of second data increases rapidly as a threshold value. The threshold inference model (411) can determine the threshold value if the number of first data among data having a quality lower than the signal quality corresponding to the threshold value is less than or equal to a specified number. A signal received via short-range wireless communication may have the characteristic that as the signal quality decreases, the number of first data decreases rapidly and the number of second data increases rapidly. The signal quality corresponding to the state in which the number of first data decreases rapidly and the number of second data increases rapidly may be substantially the same as the maximum value of the signal quality required for switching from short-range wireless communication to cellular wireless communication. Therefore, the threshold value may refer to an inflection point of the number of data in the distribution of data related to the signal received via short-range wireless communication. The threshold inference model (411) can check the quality of a signal in which the number of second data increases rapidly and the number of first data is less than or equal to a specified number, taking into account the above characteristics, and determine (or infer) the quality of the checked signal as a threshold value.

[0087] The first discriminator (412) can verify (or validate, infer) the validity of a threshold value identified (or inferred) by the threshold inference model (411). The first discriminator (412) can verify the validity of the threshold value based in part on at least one of the skewness of the data related to the signal received via near-field wireless communication and the skewness of the data related to the signal having a quality below the identified threshold value among the data related to the signal received via near-field wireless communication. The skewness of the data related to the signal received via near-field wireless communication may be a parameter capable of measuring the asymmetry of the distribution of the data related to the signal received via near-field wireless communication (e.g., may be distributed according to the quality of the signal).

[0088] According to one example, the first discriminator (412) can compare the skewness of data related to a signal with a delay time greater than a specified size and the skewness of data related to a signal with a quality below a identified threshold among the data related to a signal with a delay time greater than a specified size. The first discriminator (412) can confirm (or determine, infer) the threshold as valid if the difference between the skewness of data related to a signal with a delay time greater than a specified size and the skewness of data related to a signal with a delay time greater than a specified size and the skewness of data related to a signal with a quality below a identified threshold among the data related to a signal with a delay time greater than a specified size is greater than (or exceeds) the specified size. If the threshold is inferred to be substantially the same as the inflection point described above, the difference between the skewness of data related to a signal with a delay time greater than a specified size and quality below a identified threshold among the data related to a signal with a delay time greater than a specified size may be large. Conversely, if the threshold value is determined (or inferred) to differ significantly from the previously described inflection point, the difference between the skewness of the data related to the signal with a delay time greater than the specified size and the skewness of the data related to the signal with a delay time greater than the specified size that has a quality below the identified threshold value may be small. Accordingly, the first discriminator (412) can confirm (or determine, infer) the threshold value as valid if the difference between the skewness of the data related to the signal with a delay time greater than the specified size and the skewness of the data related to the signal with a delay time greater than the specified size that has a quality below the identified threshold value is greater than (or exceeds) the specified size.The first discriminator (412) can determine (or determine, infer) that the threshold value is invalid if the difference between the skewness of data related to a signal with a delay time greater than the specified size and the skewness of data related to a signal with a delay time greater than the specified size and the skewness of data related to a signal having a quality less than or equal to the identified threshold value is less than (or less than) the specified size.

[0089] According to one example, the first discriminator (412) can confirm (or determine, infer) that the threshold value is valid if the absolute value of the skewness of the data associated with the signal having a quality below the identified threshold value among the data associated with the signal having a delay time greater than the specified size is greater than the specified size (e.g., 1).

[0090] According to one example, the first discriminator (412) can confirm (or determine, infer) that the threshold value is valid if the skewness of the data associated with the signal having a quality below the confirmed threshold value among the data associated with the signal having a delay time greater than the specified size is less than (or less than) the specified size (e.g., -1).

[0091] According to one example, the first discriminator (412) can confirm (or determine, infer) that the threshold is valid if the skewness of the data associated with the signal having a quality below the confirmed threshold among the data associated with the signal having a delay time greater than the specified size is greater than (or exceeds) the specified size (e.g., +1).

[0092] According to one example, the first discriminator (412) can determine that the threshold is valid if the ratio of the number of data related to a signal having a quality below the confirmed threshold and the number of data with a delay time of longer than the specified time is greater than the specified size.

[0093] FIG. 5 is a diagram illustrating an example of collecting data related to a signal received via short-range wireless communication in an electronic device according to one embodiment.

[0094] According to one example, a second model (e.g., the second model (420) of FIG. 4) can receive data related to a signal transmitted and / or received via short-range wireless communication from the first communication circuit (310). The second model (420) can classify and / or manage the data related to the signal transmitted and / or received via short-range wireless communication according to the quality of the signal. The second model (420) can classify the data related to the signal transmitted and / or received via short-range wireless communication according to the quality of the signal and store the classified data in different storage spaces (e.g., queues).

[0095] The second model (420) may include a plurality of storage spaces (510, 520, 530, and 540). The second model (420) may classify the quality of a signal according to a specified unit (e.g., 5 dBm) and store data related to a signal having a quality included in the classified quality in storage spaces (510, 520, 530, and 540) corresponding to each of the classified quality.

[0096] Referring to FIG. 5, the second model (420) may include a first storage space (510) for storing data related to a signal having a quality between -80 dBm and -75 dBm, a second storage space (520) for storing data related to a signal having a quality between -75 dBm and -70 dBm, a third storage space (530) for storing data related to a signal having a quality between -40 dBm and -35 dBm, and a fourth storage space (540) for storing data related to a signal having a quality between -35 dBm and -30 dBm. The second model (420) or the data classifier (421) may store data related to the signal in any one of the first storage space (510), the second storage space (520), the third storage space (530), and / or the fourth storage space (540), depending on the quality of the signal.

[0097] The second model (420) can collect data related to signals of relatively low quality together with data related to signals of relatively high quality, and can apply (or input) the collected data related to signals to the first model (410) by confirming that the number of data related to signals of relatively low quality is greater than or equal to a specified number (e.g., 20). The second model (420) may not apply (or input) the collected data related to signals to the first model (410) if the number of data related to signals of relatively low quality is less than the specified number. Due to the characteristics of short-range wireless communication, the number of data related to signals of relatively low quality may be smaller than the number of data related to signals of relatively high quality. A lack of data related to signals of relatively low quality may cause an over-fitting phenomenon. Overfitting can occur when the first model (410) is trained primarily on data related to signals of relatively high quality, causing it to determine (or infer) a threshold value different from the quality corresponding to the situation where actual conversion is required. Accordingly, the second model (420) can prevent the overfitting phenomenon by applying (or inputting) the collected signal-related data to the first model (410) as it confirms that the number of data related to signals of relatively low quality is greater than a specified number (e.g., 20).

[0098] FIGS. 6a and 6b are drawings illustrating an example of verifying the validity of a threshold value in an electronic device according to one embodiment.

[0099] Referring to FIG. 6a, the first model (e.g., the first model (410) of FIG. 4) can determine (or infer) a threshold value of signal quality for switching from short-range wireless communication to cellular wireless communication based on data related to a signal received via short-range wireless communication.

[0100] According to one example, the first model (410) can classify data related to a signal received via short-range wireless communication based on delay time. For example, the first model (410) can classify (or label) data related to a signal received via short-range wireless communication into first data related to a signal with a delay time of less than or equal to a specified size and second data related to a signal with a delay time exceeding a specified size. The first data may be referred to as class 0, and the second data may be referred to as class 1. The first model (410) can infer a threshold value of signal quality based on the number of classified first data and the number of second data. According to one example, the first model (410) can list (or graph) second data (610) related to a signal with a delay time exceeding a specified size according to the quality of the signal received via short-range wireless communication (e.g., RSSI).

[0101] The first model (410) can identify a state in which the number of second data (610) increases rapidly due to a change in signal quality, and can determine the signal quality corresponding to the state in which the number of second data (610) increases rapidly as a threshold value (612). The first model (410) can determine the threshold value if the number of first data among data having a quality lower than the signal quality corresponding to the threshold value (612) is less than or equal to a specified number. A signal received via short-range wireless communication may have the characteristic that as the signal quality decreases, the number of first data decreases rapidly and the number of second data (620) increases rapidly. The signal quality corresponding to the state in which the number of first data decreases rapidly and the number of second data (620) increases rapidly may be substantially the same as the maximum value of the signal quality required for switching from short-range wireless communication to cellular wireless communication. Accordingly, the threshold value may refer to an inflection point of the number of data in the distribution of data related to a signal received via short-range wireless communication. The first model (410), taking into account the above characteristics, can check the quality of the signal in which the number of the second data (620) increases rapidly and the number of the first data is less than or equal to a specified number, and can determine (or infer) the quality of the confirmed signal as the threshold value.

[0102] The first model (410) can verify (or validate, infer) the validity of a confirmed (or inferred) threshold value. The first model (410) can verify the validity of the threshold value (612) based in part on at least one of the skewness (611) of the second data (610) associated with a signal having a delay time greater than a specified size among the data associated with a signal received via short-range wireless communication, and the skewness (621) of the data (610-1) associated with a signal having a quality less than or equal to the confirmed threshold value (612) among the second data (610) associated with a signal having a delay time greater than a specified size. The skewness of the data associated with a signal received via short-range wireless communication may be a parameter capable of measuring the asymmetry of the distribution of the data associated with a signal received via short-range wireless communication (e.g., may be distributed according to the quality of the signal).

[0103] According to one example, the first model (410) can compare the skewness (611) of the second data (610) associated with a signal with a delay time greater than a specified size and the skewness (621) of the data (610-1) associated with a signal having a quality less than or equal to a identified threshold value (612) among the second data (610) associated with a signal with a delay time greater than a specified size. The first model (410) can confirm (or determine, infer) the threshold value (612) as valid if the difference between the skewness (611) of the second data (610) associated with a signal with a delay time greater than a specified size and the skewness (621) of the data (610-1) associated with a signal having a quality less than or equal to a identified threshold value (612) among the second data (610) associated with a signal with a delay time greater than a specified size is greater than (or exceeds) the specified size. If the threshold value (612) is inferred to be substantially the same as the previously described inflection point, the difference between the skewness (611) of the second data (610) associated with a signal with a delay time greater than the specified size and the skewness (621) of the data (610-1) associated with a signal having a quality less than or equal to the identified threshold value (612) among the second data (610) associated with a signal with a delay time greater than the specified size may be large. Conversely, if the threshold value (612) is determined (or inferred) to be significantly different from the previously described inflection point, the difference between the skewness (611) of the second data (610) associated with a signal with a delay time greater than the specified size and the skewness (621) of the data (610-1) associated with a signal having a quality less than or equal to the identified threshold value (612) among the second data (610) associated with a signal with a delay time greater than the specified size may be small.Accordingly, the first model (410) can confirm (or determine, infer) that the threshold value is valid if the difference between the skewness (611) of the second data (610) associated with a signal with a delay time greater than the specified size and the skewness (621) of the data (610-1) associated with a signal having a quality less than or equal to the confirmed threshold value (612) among the second data (610) associated with a delay time greater than the specified size is greater than (or exceeds) the specified size. The first model (410) can determine (or determine, infer) that the threshold value (612) is invalid if the difference between the skewness (611) of the second data (610) associated with a signal with a delay time greater than the specified size and the skewness (621) of the data (610-1) associated with a signal having a quality less than or equal to the identified threshold value (612) among the second data (610) associated with a delay time greater than the specified size is less than (or less than) the specified size.

[0104] FIGS. 7A, 7B, and 7C illustrate an example of verifying the validity of a threshold value based on a plurality of characteristics of a signal in an electronic device according to one embodiment.

[0105] The examples described above verify the validity of the threshold value by distributing data related to a signal received via short-range wireless communication according to the quality of the signal and then checking the skewness of the distributed data. However, the first model (410) may be implemented to verify the validity of the threshold value by checking the skewness of the distributed data according to other characteristics of the signal (e.g., transmission success rate, reception success rate) in addition to the quality of the signal, and furthermore, the first model (410) may be implemented to verify the validity of the threshold value by checking the skewness of the distributed data according to multiple characteristics among the characteristics of the signal.

[0106] According to one example, an electronic device (100) can identify information distributed according to the characteristics of the signal (e.g., signal quality, data transmission rate) of data related to a signal transmitted and / or received via short-range wireless communication.

[0107] Referring to FIG. 7a, a graph is shown in which data (711, 712) related to a signal transmitted and / or received via short-range wireless communication is distributed according to the characteristics of the signal (e.g., signal quality, data transmission rate).

[0108] The electronic device (100) may use a first model (410) to determine threshold values ​​of signal characteristics for switching from short-range wireless communication to cellular wireless communication. According to one example, the threshold values ​​of signal characteristics may refer to a set of threshold values ​​for switching from short-range wireless communication to cellular wireless communication. For example, the threshold values ​​of signal characteristics may include a threshold value of signal quality for switching to cellular wireless communication and a threshold value of data transmission rate for switching to cellular wireless communication.

[0109] The first model (410) may be authorized to transmit and / or receive data via short-range wireless communication, and may determine (or infer) threshold values ​​of signal characteristics for switching from short-range wireless communication to cellular wireless communication based on the data transmitted and / or received via short-range wireless communication.

[0110] According to one example, the first model (410) can classify data related to a signal received via short-range wireless communication based on delay time. For example, the first model (410) can classify (or label) data related to a signal received via short-range wireless communication into first data related to a signal with a delay time of less than or equal to a specified size and second data related to a signal with a delay time exceeding a specified size. The first data may be referred to as class 0, and the second data may be referred to as class 1. The first model (410) can infer a threshold value of signal quality based on the number of classified first data and the number of second data. According to one example, the first model (410) can list (or graph) data related to a signal received via short-range wireless communication according to the quality of the signal received via short-range wireless communication (e.g., RSSI).

[0111] The first model (410) can identify a state in which the number of second data increases rapidly due to a change in the characteristics of the signal, and determine the characteristics of the signal corresponding to the state in which the number of second data increases rapidly as a threshold value.

[0112] The first model (410) can determine (or calculate, verify) the mahalanobis distance of data related to a signal transmitted and / or received via short-range wireless communication in order to determine threshold values ​​of the characteristics of the signal. The mahalanobis distance may refer to the distance between the data (711, 712) and the distribution of the data (713).

[0113] The first model (410) can check the Mahalanobis distance of the data related to the signal and check the distribution of the data according to the Mahalanobis distance.

[0114] FIG. 7b illustrates data (720) related to signals transmitted and / or received via short-range wireless communication, distributed according to the Mahalanobis distance of the data (720).

[0115] The first model (410) can identify a state in which the number of second data (720) increases rapidly according to a change in the Mahalanobis distance, and can determine the characteristic of a signal having a Mahalanobis distance corresponding to the state in which the number of second data (720) increases rapidly as a threshold value (722). The threshold value (722) may refer to an inflection point of the number of data in the distribution of data related to a signal received through short-range wireless communication.

[0116] The first model (410) can verify (or validate, infer) the validity of a confirmed (or inferred) threshold value (722). The first model (410) can verify the validity of the threshold value (722) based in part on at least one of the skewness (721) of the second data (720) associated with a signal having a delay time greater than a specified size among the data associated with a signal received via short-range wireless communication, and the skewness (731) of the data (720-1) associated with a signal having a quality less than or equal to the confirmed threshold value (722) among the second data (720) associated with a signal having a delay time greater than a specified size. The skewness of the data associated with a signal received via short-range wireless communication may be a parameter capable of measuring the asymmetry of the distribution of the data associated with the signal received via short-range wireless communication (e.g., may be distributed according to the quality of the signal).

[0117] According to one example, the first model (410) can compare the skewness (721) of the second data (720) associated with a signal with a delay time greater than a specified size and the skewness (731) of the data (720-1) associated with a signal having a quality less than or equal to a identified threshold value (722) among the second data (720) associated with a signal with a delay time greater than a specified size. The first model (410) can confirm (or determine, infer) the threshold value (722) as valid if the difference between the skewness (721) of the second data (720) associated with a signal with a delay time greater than a specified size and the skewness (731) of the data (720-1) associated with a signal having a quality less than or equal to a identified threshold value (722) among the second data (720) associated with a signal with a delay time greater than a specified size is greater than (or exceeds) the specified size. If the threshold value (722) is inferred to be substantially the same as the previously described inflection point, the difference between the skewness (721) of the second data (720) associated with a signal with a delay time greater than the specified size and the skewness (731) of the data (720-1) associated with a signal having a quality below the identified threshold value among the second data (720) associated with a signal with a delay time greater than the specified size may be large. Conversely, if the threshold value (722) is determined (or inferred) to be significantly different from the previously described inflection point, the difference between the skewness (721) of the second data (720) associated with a signal with a delay time greater than the specified size and the skewness (731) of the data (720-1) associated with a signal having a quality below the identified threshold value (722) among the second data (720) associated with a signal with a delay time greater than the specified size may be small.Accordingly, the first model (410) can confirm (or determine, infer) that the threshold value (722) is valid if the difference between the skewness (721) of the second data (720) associated with a signal with a delay time greater than the specified size and the skewness (731) of the data (720-1) associated with a signal having a quality less than or equal to the confirmed threshold value (722) among the second data (720) associated with a delay time greater than the specified size is greater than (or exceeds) the specified size. The first model (410) can determine (or determine, infer) that the threshold value (722) is invalid if the difference between the skewness (721) of the second data (720) associated with a signal with a delay time greater than the specified size and the skewness (731) of the data (720-1) associated with a signal having a quality less than or equal to the identified threshold value (722) among the second data (720) associated with a delay time greater than the specified size is less than (or less than) the specified size.

[0118] According to one example, the electronic device (100) can control the first communication circuit (310) and the second communication circuit (340) to switch from short-range wireless communication to cellular wireless communication based on a threshold value (722) that the first model (410) determines (or infers) to be valid.

[0119] The electronic device (100) may decide to switch from short-range wireless communication to cellular wireless communication based at least in part on confirming that, while short-range wireless communication is enabled, the quality of the signal received for a specified time is below a threshold value and the data transmission rate for a specified time is below a threshold value. The electronic device (100) may control the second communication circuit (340) to transmit a signal containing data to be transmitted via cellular wireless communication.

[0120] FIG. 8 is a diagram illustrating an example of switching from short-range wireless communication to cellular wireless communication when a threshold value is valid in an electronic device according to one embodiment.

[0121] According to one example, an electronic device (e.g., the electronic device (100) of FIG. 3) can control a first communication circuit (e.g., the first communication circuit (310) of FIG. 3) and a second communication circuit (e.g., the second communication circuit (340) of FIG. 3) to switch from short-range wireless communication to cellular wireless communication based on a threshold value that the first model (e.g., the first model (410) of FIG. 4) determines (or infers) to be valid.

[0122] The electronic device (100) can determine whether the quality of a signal received during a specified time (233) is below a threshold value while short-range wireless communication is enabled. The electronic device (100) can decide to switch from short-range wireless communication to cellular wireless communication (831) based at least partially on whether the quality of a signal received during the specified time (233) is below a threshold value. The electronic device (100) can control a second communication circuit (340) to transmit a signal containing data to be transmitted via cellular wireless communication.

[0123] According to one example, the electronic device (100) may decide to switch from short-range wireless communication to cellular wireless communication if it determines that the quality of the signal received during a specified time (233) is below a threshold value and the delay time of the signal is longer than the specified time. The electronic device (100) may control the second communication circuit (340) to transmit a signal containing data to be transmitted via cellular wireless communication.

[0124] The electronic device (100) can switch from short-range wireless communication to cellular wireless communication based on the quality of the signal checked during one designated time (233). On the other hand, the electronic device (100) can switch from short-range wireless communication to cellular wireless communication based on the quality of the signal checked during a plurality of designated times (233, 234, 235, and 236) when using the switching method shown in FIG. 2b.

[0125] Accordingly, the electronic device (100) can prevent a decrease in the quality of the service performed by the electronic device (100) by switching to cellular wireless communication relatively quickly as the quality of short-range wireless communication deteriorates.

[0126] FIG. 9 is an operation flowchart (900) illustrating the operation method of an electronic device according to one embodiment.

[0127] The electronic device (100) can collect data related to signals transmitted and / or received via short-range wireless communication in operation 910.

[0128] The electronic device (100) can collect (or verify, monitor) data related to a signal transmitted and / or received via the short-range wireless communication while performing short-range wireless communication. Data related to a signal transmitted and / or received via the short-range wireless communication may refer to data related to the quality of the link established between the electronic device (100) and an external electronic device (210). For example, data related to the signal may include at least one parameter among the quality of the signal (e.g., RSSI (received signal strength indicator)), the delay time of the signal, the success rate of receiving the signal, or the success rate of transmitting the signal. The electronic device (100) may control a first communication circuit (310) to acquire data related to a signal transmitted and / or received via the short-range wireless communication. The first communication circuit (310) may acquire data related to a signal transmitted and / or received via the short-range wireless communication and transmit it to the electronic device (100).

[0129] The electronic device (100) can apply the collected data in operation 920 to a first model that infers a threshold value.

[0130] The electronic device (100) may store a first model (410) for verifying (or inferring) a threshold value of signal quality for switching from short-range wireless communication to cellular wireless communication on memory included in the processor (320) or on memory (330) existing outside the processor (320). The first model (410) may be an artificial intelligence model learned based on data related to a signal transmitted via short-range wireless communication and data related to a signal received via short-range wireless communication. The first model (410) may be an artificial intelligence model learned by the manufacturer of the electronic device (100) using various technologies (e.g., machine learning, neural network learning, self-organizing map, hidden Markov model, or convolution neural network learning). The first model (410) may be authorized to have data transmitted and / or received via short-range wireless communication, and may determine (or infer) a threshold value of signal quality for transitioning from short-range wireless communication to cellular wireless communication based on the data transmitted and / or received via short-range wireless communication. The first model (410) may determine (or verify, determine, infer) whether the determined (or inferred) threshold value is a valid value. According to one example, the first model (410) may be referred to as a model for link transition decision.

[0131] According to one example, the first model (410) can determine (or infer) a threshold value of signal quality for switching from short-range wireless communication to cellular wireless communication based on data related to a signal received via short-range wireless communication.

[0132] According to one example, the first model (410) can classify data related to a signal received via short-range wireless communication based on delay time. For example, the first model (410) can classify (or label) data related to a signal received via short-range wireless communication into first data related to a signal with a delay time of less than or equal to a specified size and second data related to a signal with a delay time exceeding a specified size. The first data may be referred to as class 0, and the second data may be referred to as class 1. The first model (410) can infer a threshold value of signal quality based on the number of classified first data and the number of second data. According to one example, the first model (410) can list (or graph) data related to a signal received via short-range wireless communication according to the quality of the signal received via short-range wireless communication (e.g., RSSI).

[0133] The first model (410) can identify a state in which the number of second data increases rapidly due to a change in signal quality, and can determine the signal quality corresponding to the state in which the number of second data increases rapidly as a threshold value. The first model (410) can determine the threshold value if the number of first data among data having a quality lower than the signal quality corresponding to the threshold value is less than or equal to a specified number. A signal received via short-range wireless communication may have the characteristic that the number of first data decreases rapidly and the number of second data increases rapidly as the signal quality decreases. The signal quality corresponding to the state in which the number of first data decreases rapidly and the number of second data increases rapidly may be substantially the same as the maximum value of the signal quality required for switching from short-range wireless communication to cellular wireless communication. Therefore, the threshold value may refer to an inflection point of the number of data in the distribution of data related to the signal received via short-range wireless communication. The first model (410), taking into account the above characteristics, can check the quality of a signal in which the number of second data increases rapidly and the number of first data is less than or equal to a specified number, and can determine (or infer) the quality of the checked signal as a threshold value.

[0134] The electronic device (100) can determine whether a threshold value is valid in operation 930 based on at least one of the skewness of the collected data and the skewness of the data associated with a signal having a quality lower than the threshold value among the collected data.

[0135] The first model (410) can verify (or validate, infer) the validity of a confirmed (or inferred) threshold value. The first model (410) can verify the validity of the threshold value based in part on at least one of the skewness of the data related to a signal with a delay time greater than a specified size among the data related to a signal received via short-range wireless communication, and the skewness of the data related to a signal with a delay time greater than a specified size among the data related to a signal having a quality less than or equal to the confirmed threshold value. The skewness of the data related to a signal received via short-range wireless communication may be a parameter capable of measuring the asymmetry of the distribution of the data related to the signal received via short-range wireless communication (e.g., may be distributed according to the quality of the signal).

[0136] According to one example, the first model (410) can compare the skewness of data related to a signal with a delay time greater than a specified size and the skewness of data related to a signal with a delay time greater than a specified size that has a quality below a identified threshold. The first model (410) can confirm (or determine, infer) the threshold as valid if the difference between the skewness of data related to a signal with a delay time greater than a specified size and the skewness of data related to a signal with a delay time greater than a specified size that has a quality below a identified threshold is greater than (or exceeds) the specified size. If the threshold is inferred to be substantially the same as the inflection point described above, the difference between the skewness of data related to a signal with a delay time greater than a specified size and the skewness of data related to a signal with a delay time greater than a specified size that has a quality below a identified threshold may be large. Conversely, if the threshold value is determined (or inferred) to differ significantly from the previously described inflection point, the difference between the skewness of the data related to the signal with a delay time greater than the specified size and the skewness of the data related to the signal with a delay time greater than the specified size that has a quality below the identified threshold value may be small. Accordingly, the first model (410) can confirm (or determine, infer) the threshold value as valid if the difference between the skewness of the data related to the signal with a delay time greater than the specified size and the skewness of the data related to the signal with a delay time greater than the specified size that has a quality below the identified threshold value is greater than (or exceeds) the specified size.The first model (410) can determine (or determine, infer) that the threshold is invalid if the difference between the skewness of data related to a signal with a delay time greater than a specified size and the skewness of data related to a signal with a delay time greater than a specified size and the skewness of data related to a signal with a delay time greater than a specified size that has a quality below a identified threshold is less than (or below) the specified size.

[0137] According to one example, the first model (410) can confirm (or determine, infer) that the threshold value is valid if the absolute value (or size) of the skewness of the data associated with the signal having a quality below the confirmed threshold value among the data associated with the signal having a delay time greater than the specified size is greater than (or exceeds) the specified size (e.g., 1).

[0138] According to one example, the first model (410) can confirm (or determine, infer) that the threshold is valid if the skewness of the data associated with the signal having a quality below the confirmed threshold among the data associated with the signal having a delay time greater than the specified size is less than (or less than) the specified size (e.g., -1).

[0139] According to one example, the first model (410) can confirm (or determine, infer) that the threshold is valid if the skewness of the data associated with the signal having a quality below the confirmed threshold among the data associated with the signal having a delay time greater than the specified size is greater than (or exceeds) the specified size (e.g., +1).

[0140] According to one example, the first model (410) can determine that the threshold is valid if the ratio of the number of data related to a signal having a quality below the confirmed threshold and the number of data with a delay time of longer than the specified time is greater than the specified size.

[0141] The electronic device (100) can switch from short-range wireless communication to cellular wireless communication, at least in part, based on the fact that, in operation 940, when the threshold value is valid, the quality of the signal received for a specified time is below the threshold value.

[0142] According to one example, the electronic device (100) can control the first communication circuit (310) and the second communication circuit (340) to switch from short-range wireless communication to cellular wireless communication based on a threshold value that the first model (410) determines (or infers) to be valid.

[0143] The electronic device (100) can determine whether the quality of a signal received for a specified period is below a threshold value while short-range wireless communication is enabled. The electronic device (100) can decide to switch from short-range wireless communication to cellular wireless communication based at least partially on whether the quality of a signal received for a specified period is below a threshold value. The electronic device (100) can control the second communication circuit (340) to transmit a signal containing data to be transmitted via cellular wireless communication.

[0144] According to one example, the electronic device (100) may decide to switch from short-range wireless communication to cellular wireless communication if it determines that the quality of the signal received for a specified time is below a threshold value and the delay time of the signal is longer than the specified time. The electronic device (100) may control the second communication circuit (340) to transmit a signal containing data to be transmitted via cellular wireless communication.

[0145] The electronic device (100) may switch from short-range wireless communication to cellular wireless communication using the switching method described in FIG. 2b when the threshold value confirmed by the first model (410) is determined (or confirmed, inferred) to be invalid. According to one example, the electronic device (100) may decide to switch from short-range wireless communication to cellular wireless communication when it confirms that the delay time of a signal received during a plurality of specified times is longer than the specified time. The electronic device (100) may control the second communication circuit (340) to transmit a signal containing data to be transmitted via cellular wireless communication.

[0146] FIG. 10 is an operation flowchart (1000) illustrating the operation method of an electronic device according to one embodiment.

[0147] The electronic device (100) can collect data related to signals transmitted and / or received via short-range wireless communication in operation 1010.

[0148] The electronic device (100) can collect (or verify, monitor) data related to a signal transmitted and / or received via the short-range wireless communication while performing short-range wireless communication. Data related to a signal transmitted and / or received via the short-range wireless communication may refer to data related to the quality of the link established between the electronic device (100) and an external electronic device (210). For example, data related to the signal may include at least one parameter among the quality of the signal (e.g., RSSI (received signal strength indicator)), the delay time of the signal, the success rate of receiving the signal, or the success rate of transmitting the signal. The electronic device (100) may control a first communication circuit (310) to acquire data related to a signal transmitted and / or received via the short-range wireless communication. The first communication circuit (310) may acquire data related to a signal transmitted and / or received via the short-range wireless communication and transmit it to the electronic device (100).

[0149] The electronic device (100) can determine whether, in operation 1020, there are more than a specified number of data related to a signal having a quality of less than or equal to a specified size.

[0150] According to one example, data related to a signal applied (or input) to the first model (410) may be data collected by a second model (420) different from the first model (410). The electronic device (100) may store the second model (420) for collecting data related to a signal applied (or input) to the first model (410) on memory included in the electronic device (100) or on memory (330) existing outside the electronic device (100). The second model (420) may be an artificial intelligence model learned by the manufacturer of the electronic device (100), and may be an artificial intelligence model learned using various technologies (e.g., machine learning, neural network learning, self-organizing map, hidden Markov model, or convolution neural network learning). The second model (420) may be a model for collecting data related to signals transmitted and / or received via short-range wireless communication.

[0151] The second model (420) can receive data related to a signal transmitted and / or received via short-range wireless communication from the first communication circuit (310). The second model (420) can classify and / or manage data related to a signal transmitted and / or received via short-range wireless communication according to the quality of the signal. The second model (420) can classify data related to a signal transmitted and / or received via short-range wireless communication according to the quality of the signal and store the classified data in different storage spaces (e.g., queues).

[0152] For example, the second model (420) can classify the quality of a signal according to a specified unit (e.g., 5 dBm) and store data related to a signal having a quality included in the classified quality in a storage space corresponding to each of the classified qualities. The second model (420) can collect data related to a signal having a relatively low quality together with data related to a signal having a relatively high quality, and can apply (or input) the collected data related to the signal to the first model (410) by confirming that the number of data related to a signal having a relatively low quality is greater than or equal to a specified number (e.g., 20). If the number of data related to a signal having a relatively low quality is less than the specified number, the second model (420) may not apply (or input) the collected data related to the signal to the first model (410). Due to the characteristics of short-range wireless communication, the number of data related to a signal having a relatively low quality may be smaller than the number of data related to a signal having a relatively high quality. A lack of data related to signals of relatively low quality can cause overfitting. Overfitting can cause the first model (410), when trained primarily on data related to signals of relatively high quality, to determine (or infer) a threshold value different from the quality corresponding to the situation where actual conversion is required. Therefore, the second model (420) can prevent the overfitting phenomenon by applying (or inputting) the collected data related to signals to the first model (410) as it confirms that the number of data related to signals of relatively low quality is greater than a specified number (e.g., 20).

[0153] The electronic device (100) can collect data related to signals transmitted and / or received via short-range wireless communication until the number of data related to signals having a quality of less than or equal to a specified size is less than the specified number (operation 1020-N).

[0154] The electronic device (100) can determine a threshold value by applying the collected data to a model that infers a threshold value when, in operation 1030, the number of data related to a signal having a quality of less than or equal to a specified size is greater than or equal to a specified number (operation 1020-Y).

[0155] The electronic device (100) may store a first model (410) for verifying (or inferring) a threshold value of signal quality for switching from short-range wireless communication to cellular wireless communication on memory included in the processor (320) or on memory (330) existing outside the processor (320). The first model (410) may be an artificial intelligence model learned based on data related to a signal transmitted via short-range wireless communication and data related to a signal received via short-range wireless communication. The first model (410) may be an artificial intelligence model learned by the manufacturer of the electronic device (100) using various technologies (e.g., machine learning, neural network learning, self-organizing map, hidden Markov model, or convolution neural network learning). The first model (410) may be authorized to have data transmitted and / or received via short-range wireless communication, and may determine (or infer) a threshold value of signal quality for transitioning from short-range wireless communication to cellular wireless communication based on the data transmitted and / or received via short-range wireless communication. The first model (410) may determine (or verify, determine, infer) whether the determined (or inferred) threshold value is a valid value. According to one example, the first model (410) may be referred to as a model for link transition decision.

[0156] According to one example, the first model (410) can determine (or infer) a threshold value of signal quality for switching from short-range wireless communication to cellular wireless communication based on data related to a signal received via short-range wireless communication.

[0157] According to one example, the first model (410) can classify data related to a signal received via short-range wireless communication based on delay time. For example, the first model (410) can classify (or label) data related to a signal received via short-range wireless communication into first data related to a signal with a delay time of less than or equal to a specified size and second data related to a signal with a delay time exceeding a specified size. The first data may be referred to as class 0, and the second data may be referred to as class 1. The first model (410) can infer a threshold value of signal quality based on the number of classified first data and the number of second data. According to one example, the first model (410) can list (or graph) data related to a signal received via short-range wireless communication according to the quality of the signal received via short-range wireless communication (e.g., RSSI).

[0158] The first model (410) can identify a state in which the number of second data increases rapidly due to a change in signal quality, and can determine the signal quality corresponding to the state in which the number of second data increases rapidly as a threshold value. The first model (410) can determine the threshold value if the number of first data among data having a quality lower than the signal quality corresponding to the threshold value is less than or equal to a specified number. A signal received via short-range wireless communication may have the characteristic that the number of first data decreases rapidly and the number of second data increases rapidly as the signal quality decreases. The signal quality corresponding to the state in which the number of first data decreases rapidly and the number of second data increases rapidly may be substantially the same as the maximum value of the signal quality required for switching from short-range wireless communication to cellular wireless communication. Therefore, the threshold value may refer to an inflection point of the number of data in the distribution of data related to the signal received via short-range wireless communication. The first model (410), taking into account the above characteristics, can check the quality of a signal in which the number of second data increases rapidly and the number of first data is less than or equal to a specified number, and can determine (or infer) the quality of the checked signal as a threshold value.

[0159] The electronic device (100) can determine whether the threshold value is valid in operation 1040.

[0160] The electronic device (100) can determine whether a threshold value is valid based on at least one of the skewness of the collected data and the skewness of the data associated with a signal having a quality lower than the threshold value among the collected data.

[0161] The first model (410) can verify (or validate, infer) the validity of a confirmed (or inferred) threshold value. The first model (410) can verify the validity of the threshold value based in part on at least one of the skewness of the data related to a signal with a delay time greater than a specified size among the data related to a signal received via short-range wireless communication, and the skewness of the data related to a signal with a delay time greater than a specified size among the data related to a signal having a quality less than or equal to the confirmed threshold value. The skewness of the data related to a signal received via short-range wireless communication may be a parameter capable of measuring the asymmetry of the distribution of the data related to the signal received via short-range wireless communication (e.g., may be distributed according to the quality of the signal).

[0162] According to one example, the first model (410) can compare the skewness of data related to a signal with a delay time greater than a specified size and the skewness of data related to a signal with a delay time greater than a specified size that has a quality below a identified threshold. The first model (410) can confirm (or determine, infer) the threshold as valid if the difference between the skewness of data related to a signal with a delay time greater than a specified size and the skewness of data related to a signal with a delay time greater than a specified size that has a quality below a identified threshold is greater than (or exceeds) the specified size. If the threshold is inferred to be substantially the same as the inflection point described above, the difference between the skewness of data related to a signal with a delay time greater than a specified size and the skewness of data related to a signal with a delay time greater than a specified size that has a quality below a identified threshold may be large. Conversely, if the threshold value is determined (or inferred) to differ significantly from the previously described inflection point, the difference between the skewness of the data related to the signal with a delay time greater than the specified size and the skewness of the data related to the signal with a delay time greater than the specified size that has a quality below the identified threshold value may be small. Accordingly, the first model (410) can confirm (or determine, infer) the threshold value as valid if the difference between the skewness of the data related to the signal with a delay time greater than the specified size and the skewness of the data related to the signal with a delay time greater than the specified size that has a quality below the identified threshold value is greater than (or exceeds) the specified size.The first model (410) can determine (or determine, infer) that the threshold is invalid if the difference between the skewness of data related to a signal with a delay time greater than a specified size and the skewness of data related to a signal with a delay time greater than a specified size and the skewness of data related to a signal with a delay time greater than a specified size that has a quality below a identified threshold is less than (or below) the specified size.

[0163] According to one example, the first model (410) can confirm (or determine, infer) that the threshold value is valid if the absolute value (or size) of the skewness of the data associated with the signal having a quality below the confirmed threshold value among the data associated with the signal having a delay time greater than the specified size is greater than (or exceeds) the specified size (e.g., 1).

[0164] According to one example, the first model (410) can confirm (or determine, infer) that the threshold is valid if the skewness of the data associated with the signal having a quality below the confirmed threshold among the data associated with the signal having a delay time greater than the specified size is less than (or less than) the specified size (e.g., -1).

[0165] According to one example, the first model (410) can confirm (or determine, infer) that the threshold is valid if the skewness of the data associated with the signal having a quality below the confirmed threshold among the data associated with the signal having a delay time greater than the specified size is greater than (or exceeds) the specified size (e.g., +1).

[0166] According to one example, the first model (410) can determine that the threshold is valid if the ratio of the number of data related to a signal having a quality below the confirmed threshold and the number of data with a delay time of longer than the specified time is greater than the specified size.

[0167] The electronic device (100) can switch from short-range wireless communication to cellular wireless communication based at least in part on the fact that the quality of the signal received during a specified time is below the threshold value when the threshold value is valid in operation 1050 (operation 1040-Y).

[0168] According to one example, the electronic device (100) can control the first communication circuit (310) and the second communication circuit (340) to switch from short-range wireless communication to cellular wireless communication based on a threshold value that the first model (410) determines (or infers) to be valid.

[0169] The electronic device (100) can determine whether the quality of a signal received for a specified period is below a threshold value while short-range wireless communication is enabled. The electronic device (100) can decide to switch from short-range wireless communication to cellular wireless communication based at least partially on whether the quality of a signal received for a specified period is below a threshold value. The electronic device (100) can control the second communication circuit (340) to transmit a signal containing data to be transmitted via cellular wireless communication.

[0170] According to one example, the electronic device (100) may decide to switch from short-range wireless communication to cellular wireless communication if it determines that the quality of the signal received for a specified time is below a threshold value and the delay time of the signal is longer than the specified time. The electronic device (100) may control the second communication circuit (340) to transmit a signal containing data to be transmitted via cellular wireless communication.

[0171] The electronic device (100) can switch from short-range wireless communication to cellular wireless communication based at least in part on the quality of the signal received during a plurality of specified times when the threshold value is invalid in operation 1060 (operation 1040-N).

[0172] The electronic device (100) may switch from short-range wireless communication to cellular wireless communication using the switching method described in FIG. 2b when the threshold value confirmed by the first model (410) is determined (or confirmed, inferred) to be invalid. According to one example, the electronic device (100) may decide to switch from short-range wireless communication to cellular wireless communication when it confirms that the delay time of a signal received during a plurality of specified times is longer than the specified time. The electronic device (100) may control the second communication circuit (340) to transmit a signal containing data to be transmitted via cellular wireless communication.

[0173] An electronic device according to one example may include a first communication circuit that supports short-range wireless communication. The electronic device may include a second communication circuit that supports cellular wireless communication. The electronic device may include a memory that stores computer programs including instructions. The electronic device may include at least one processor. When the instructions are executed individually or collectively by the at least one processor, the electronic device may control the first communication circuit to collect data related to a signal transmitted and / or received to an external electronic device via the short-range wireless communication. When the instructions are executed individually or collectively by the at least one processor, the electronic device may apply the collected data to a model that infers the threshold value to determine the threshold value of the signal quality for switching from the short-range wireless communication to the cellular wireless communication. When the above instructions are executed individually or collectively by the at least one processor, the electronic device may determine whether the threshold value is valid based, in part, on at least one of the skewness of the collected data and the skewness of a portion of the collected data corresponding to the quality of a signal lower than the identified threshold value among the collected data. When the above instructions are executed individually or collectively by the at least one processor, the electronic device may switch from the short-range wireless communication to the cellular wireless communication based, in part, on whether the quality of a signal received for a specified time is below the identified threshold value when the identified threshold value is valid.

[0174] In an electronic device according to one example, when the instructions are executed individually or collectively by at least one processor, the electronic device may determine the threshold value to be valid if the difference between the skewness of the collected data and the skewness of a portion of the collected data corresponding to a signal quality lower than the identified threshold value among the collected data is greater than or equal to a specified size.

[0175] In an electronic device according to one example, when the instructions are executed individually or collectively by at least one processor, the electronic device may determine the threshold value to be valid if the skewness of a portion of the collected data corresponding to a signal quality lower than the identified threshold value among the collected data is less than or equal to a specified size.

[0176] In an electronic device according to one example, the instructions, when executed individually or collectively by the at least one processor, may cause the electronic device to classify the collected data into first data associated with a signal having a delay time less than or equal to a specified size and second data associated with a signal having a delay time exceeding the specified size. The instructions, when executed individually or collectively by the at least one processor, may cause the electronic device to determine the threshold value based on the number of the second data and the number of the first data.

[0177] In an electronic device according to one example, when the instructions are executed individually or collectively by at least one processor, the electronic device may apply the collected data to the model if there is more than a specified number of data related to signals having a quality of less than or equal to a specified size among the collected data.

[0178] In an electronic device according to one example, when the instructions are executed individually or collectively by at least one processor, the electronic device may collect data related to the signal until the number of data related to the signal having a quality of less than or equal to the specified size is greater than or equal to the specified number, when the number of data related to the signal having a quality of less than or equal to the specified size among the collected data is less than the specified number.

[0179] In an electronic device according to one example, when the instructions are executed individually or collectively by at least one processor, the electronic device may be able to switch from the short-range wireless communication to the cellular wireless communication based on the fact that, if the identified threshold value is valid, the quality of the signal received during the specified time is less than or equal to the identified threshold value and the delay time of the signal received during the specified time is greater than or equal to a specified size.

[0180] In an electronic device according to one example, when the instructions are executed individually or collectively by at least one processor, the electronic device may switch from the short-range wireless communication to the cellular wireless communication based at least in part on the quality of the signal received for a plurality of specified times when the identified threshold value is invalid.

[0181] In a recording medium storing at least one program comprising instructions that cause the electronic device to perform operations when executed individually or collectively by at least one processor of the electronic device according to one example, the instructions may cause the electronic device to collect data related to a signal received and / or transmitted from an external electronic device via near-field wireless communication when executed individually or collectively by the at least one processor. The instructions may cause the electronic device to input the collected data to a model that infers the threshold value in order to determine the threshold value of the signal quality for switching from near-field wireless communication to cellular wireless communication when executed individually or collectively by the at least one processor. The instructions may cause the electronic device to determine whether the threshold value is valid based in part on at least one of the skewness of the collected data and the skewness of a portion of the collected data corresponding to a signal quality lower than the determined threshold value among the collected data when executed individually or collectively by the at least one processor. When the above instructions are executed individually or collectively by the at least one processor, the electronic device may switch from the short-range wireless communication to the cellular wireless communication based at least in part on whether the quality of the signal received for a specified time is below the identified threshold value when the identified threshold value is confirmed to be valid.

[0182] In a recording medium according to one example, the instructions, when executed individually or collectively by at least one processor, may enable the electronic device to determine the threshold value as valid if the difference between the skewness of the collected data and the skewness of a portion of the collected data corresponding to a signal quality lower than the identified threshold value among the collected data is greater than or equal to a specified size.

[0183] In a recording medium according to one example, when the instructions are executed individually or collectively by at least one processor, the electronic device may determine the threshold value to be valid if the skewness of a portion of the collected data corresponding to a signal quality lower than the identified threshold value among the collected data is less than or equal to a specified size.

[0184] In a recording medium according to one example, the instructions may, when executed individually or collectively by the at least one processor, cause the electronic device to classify the collected data into first data associated with a signal having a delay time less than or equal to a specified size and second data associated with a signal having a delay time exceeding the specified size. The instructions may, when executed individually or collectively by the at least one processor, cause the electronic device to determine the threshold value based on the number of the second data and the number of the first data.

[0185] In a recording medium according to one example, when the instructions are executed individually or collectively by at least one processor, the electronic device may apply the collected data to the model if there is more than a specified number of data related to signals having a quality of less than or equal to a specified size among the collected data.

[0186] In a recording medium according to one example, when the instructions are executed individually or collectively by at least one processor, the electronic device may collect data related to the signal until the number of data related to the signal having a quality of less than or equal to the specified size becomes greater than or equal to the specified number, when the number of data related to the signal having a quality of less than or equal to the specified size among the collected data is less than the specified number.

[0187] In a recording medium according to one example, the instructions, when executed individually or collectively by at least one processor, may cause the electronic device to switch from the short-range wireless communication to the cellular wireless communication based on the fact that, when the identified threshold value is valid, the quality of the signal received during the specified time is less than or equal to the identified threshold value and the delay time of the signal received during the specified time is greater than or equal to the specified size.

[0188] In a recording medium according to one example, the instructions, when executed individually or collectively by at least one processor, may cause the electronic device to switch from the short-range wireless communication to the cellular wireless communication based at least in part on the quality of the signal received for a plurality of specified times when the identified threshold value is invalid.

[0189] A method of operation of an electronic device according to one example may include an operation of collecting data related to a signal received and / or transmitted from an external electronic device via near-field wireless communication. A method of operation of an electronic device may include an operation of applying the collected data to a model that infers the threshold value in order to check the threshold value of the signal quality for switching from the near-field wireless communication to cellular wireless communication. A method of operation of an electronic device may include an operation of checking whether the threshold value is valid based, in part, on at least one of the skewness of the collected data and the skewness of a portion of the collected data corresponding to the signal quality of the collected data that is lower than the confirmed threshold value. If the confirmed threshold value is confirmed to be valid, a method of operation of an electronic device may include an operation of switching from the near-field wireless communication to the cellular wireless communication based, in at least part, on whether the quality of the signal received during a specified time is below the confirmed threshold value.

[0190] In a method of operating an electronic device according to one example, the operation of checking whether the threshold value is valid may include an operation of determining the threshold value as valid when the difference between the skewness of the collected data and the skewness of a portion of the collected data corresponding to the quality of a signal lower than the confirmed threshold value among the collected data is greater than or equal to a specified size.

[0191] In a method of operating an electronic device according to one example, the operation of checking whether the threshold value is valid may include the operation of determining the threshold value as valid when the skewness of a portion of the collected data corresponding to a signal quality lower than the checked threshold value among the collected data is less than or equal to a specified size.

[0192] In a method of operating an electronic device according to one example, the operation of applying the collected data may include applying the collected data to the model when the number of data related to signals having a quality of less than or equal to a specified size among the collected data is greater than or equal to a specified number.

Claims

1. In an electronic device, A first communication circuit supporting short-range wireless communication; A second communication circuit supporting cellular wireless communication; Memory for storing computer programs including instructions; and It includes at least one processor, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, Control the first communication circuit to collect data related to a signal transmitted and / or received to an external electronic device via the above short-range wireless communication, and In order to determine the threshold value of the signal quality for switching from the above short-range wireless communication to the above cellular wireless communication, the collected data is applied to a model that infers the threshold value, and Whether the above threshold value is valid is determined based in part on at least one of the skewness of the collected data and the skewness of a portion of the collected data corresponding to the quality of a signal lower than the confirmed threshold value among the collected data, and An electronic device that switches from the short-range wireless communication to the cellular wireless communication, based at least in part on whether the quality of the signal received during a specified time is below the confirmed threshold value when the confirmed threshold value is valid.

2. In Paragraph 1, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, An electronic device that determines a threshold value as valid when the difference between the skewness of the collected data and the skewness of a portion of the collected data corresponding to the quality of a signal lower than the identified threshold value among the collected data is greater than or equal to a specified size.

3. In paragraphs 1 and 2, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, An electronic device that determines the threshold value as valid when the skewness of a portion of the collected data corresponding to the quality of a signal lower than the confirmed threshold value among the collected data is less than or equal to a specified size.

4. In paragraphs 1 to 3, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, The collected data is classified into first data related to a signal with a delay time less than or equal to a specified size and second data related to a signal with a delay time exceeding the specified size, and An electronic device for determining the threshold value based on the number of the second data and the number of the first data.

5. In paragraphs 1 through 4, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, An electronic device that applies the collected data to the model when the number of data related to signals having a quality of less than or equal to a specified size among the collected data is greater than or equal to a specified number.

6. In paragraphs 1 through 5, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, An electronic device that collects data related to signals having a quality of less than or equal to the specified size among the collected data, until the number of data related to signals having a quality of less than or equal to the specified size becomes greater than or equal to the specified number.

7. In paragraphs 1 through 6, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, An electronic device that switches from the short-range wireless communication to the cellular wireless communication based on the fact that, when the above-mentioned threshold value is valid, the quality of the signal received during the above-mentioned specified time is less than or equal to the above-mentioned threshold value and the delay time of the signal received during the above-mentioned specified time is greater than or equal to the specified size.

8. In paragraphs 1 through 7, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, An electronic device that switches from the short-range wireless communication to the cellular wireless communication based at least in part on the quality of the signal received during a plurality of specified times when the above-mentioned threshold value is invalid.

9. A recording medium storing at least one program comprising instructions that cause the electronic device to perform operations when executed individually or collectively by at least one processor of the electronic device, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, Collecting data related to signals received and / or transmitted from an external electronic device via short-range wireless communication, and In order to determine the threshold value of the signal quality for switching from the above short-range wireless communication to cellular wireless communication, the collected data is applied to a model that infers the threshold value, and Whether the above threshold value is valid is determined based in part on at least one of the skewness of the collected data and the skewness of a portion of the collected data corresponding to the quality of a signal lower than the confirmed threshold value among the collected data, and A recording medium that switches from the short-range wireless communication to the cellular wireless communication, based at least in part on whether the quality of the signal received during a specified time is below the confirmed threshold value when the confirmed threshold value is confirmed to be valid.

10. In Paragraph 9, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, A recording medium that determines the threshold value as valid when the difference between the skewness of the collected data and the skewness of a portion of the collected data corresponding to the quality of a signal lower than the identified threshold value among the collected data is greater than or equal to a specified size.

11. In Articles 9 and 10, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, A recording medium that determines the threshold value as valid when the skewness of a portion of the collected data corresponding to the quality of a signal lower than the confirmed threshold value among the collected data is less than or equal to a specified size.

12. In paragraphs 9 through 11, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, The collected data is classified into first data related to a signal with a delay time less than or equal to a specified size and second data related to a signal with a delay time exceeding the specified size, and A recording medium that determines the threshold value based on the number of the second data and the number of the first data.

13. In Paragraphs 9 through 12, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, A recording medium that applies the collected data to the model when the number of data related to signals having a quality of less than or equal to a specified size among the collected data is greater than or equal to a specified number.

14. In Paragraphs 9 through 13, When the above instructions are executed individually or collectively by the at least one processor, the electronic device, A recording medium that collects data related to signals having a quality of less than or equal to the specified size among the collected data, until the number of data related to signals having a quality of less than or equal to the specified size becomes greater than or equal to the specified number.

15. In a method of operating an electronic device, The operation of collecting data related to signals received and / or transmitted from an external electronic device via short-range wireless communication; An operation of applying the collected data to a model that infers the threshold value in order to determine the threshold value of the signal quality for switching from the above short-range wireless communication to cellular wireless communication; An operation to determine whether the above threshold value is valid, based in part on at least one of the skewness of the collected data and the skewness of a portion of the collected data corresponding to the quality of a signal lower than the confirmed threshold value among the collected data; and A method of operation of an electronic device comprising switching from the short-range wireless communication to the cellular wireless communication, based at least in part on whether the quality of the signal received during a specified time is below the confirmed threshold value when the confirmed threshold value is confirmed to be valid.

Images