Electronic device, method, and non-transitory computer-readable storage medium for filtering spam message

Abstract

According to an embodiment, an electronic device may comprise: a communication circuit; a memory for storing instructions, and including one or more storage media; and at least one processor including a processing circuit. The instructions, when executed individually or collectively by the at least one processor, may cause the electronic device to: receive a message from an external electronic device by using the communication circuit; identify the message as an allowed message by using content of the message and a calling number of the message; identify a category related to the message and a filtering level set according to the category; obtain information on a probability that the message is a spam message; identify the message as the spam message on the basis of identifying that the probability is within a probability range according to the filtering level; and maintain the message as the allowed message on the basis of identifying that the probability is outside the probability range according to the filtering level.

Description

Electronic device, method, and non-transient computer-readable storage medium for filtering spam messages

[0001] The following descriptions relate to an electronic device, a method, and a non-transient computer-readable storage medium for filtering spam messages.

[0002] Spam messages are advertising messages sent indiscriminately to an unspecified number of people. To filter spam messages, electronic devices may be configured with blocked words and blocked sender numbers. Spam messages may be filtered if they contain blocked words or if the sender number of the spam message corresponds to a blocked sender number.

[0003] The information described above may be provided as related art for the purpose of aiding understanding of the present disclosure. No claim or determination is made as to whether any of the foregoing may be applied as prior art related to the present disclosure.

[0004] According to one embodiment, the electronic device may include a communication circuit, a memory including one or more storage media for storing instructions, and at least one processor including a processing circuit. When the instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to receive a message from an external electronic device using the communication circuit, identify the message as an allowed message using the content of the message and the sender number of the message, identify a category of the message and a filtering level set according to the category based on the content of the message identified as the allowed message, obtain information regarding the probability that the message is a spam message distinct from the allowed message, identify the message as the spam message based on identifying that the probability is within the probability range according to the filtering level, and maintain the message as the allowed message based on identifying that the probability is outside the probability range according to the filtering level.

[0005] According to one embodiment, a method performed in an electronic device may include: receiving a message from an external electronic device using a communication circuit of the electronic device; identifying the message as an allowed message using the content of the message and the sender number of the message; identifying a category of the message and a filtering level set according to the category based on the content of the message identified as the allowed message, and obtaining information regarding the probability that the message is a spam message that is distinguished from the allowed message; identifying the message as the spam message based on identifying that the probability is within a probability range according to the filtering level; and maintaining the message as the allowed message based on identifying that the probability is outside the probability range according to the filtering level.

[0006] According to one embodiment, a non-transient computer-readable storage medium may store one or more programs. The one or more programs may include instructions that, when executed by at least one processor of an electronic device having a communication circuit, receive a message from an external electronic device, identify the message as an allowed message using the content of the message and the sender number of the message, identify a category of the message and a filtering level set according to the category based on the content of the message identified as the allowed message, obtain information regarding the probability that the message is a spam message distinct from the allowed message, identify the message as the spam message based on identifying that the probability is within the probability range according to the filtering level, and cause the electronic device to maintain the message as the allowed message based on identifying that the probability is outside the probability range according to the filtering level.

[0007] According to one embodiment, the electronic device may include a communication circuit, a memory comprising one or more storage media for storing instructions, and at least one processor comprising a processing circuit. When the instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to receive a message from an external electronic device using the communication circuit, identify the message as an allowed message using the content of the message and the sender number of the message, identify whether the sender address of the message corresponds to one of the registered sender addresses, perform spam message filtering using an artificial intelligence model on the message based on the sender address of the message which is distinct from the registered sender addresses, and maintain the message as an allowed message based on the sender address of the message which corresponds to one of the registered sender addresses.

[0008] FIG. 1 is a block diagram of an electronic device in a network environment according to one embodiment.

[0009] FIG. 2 illustrates an example of the operation of an electronic device for filtering a received message according to one embodiment.

[0010] FIG. 3 illustrates an example of a simplified block diagram of an electronic device according to one embodiment.

[0011] FIG. 4 illustrates an example of the operation of an electronic device for identifying spam messages according to one embodiment.

[0012] FIG. 5 is a flowchart relating to the operation of an electronic device for identifying whether a message is a spam message, according to one embodiment.

[0013] FIG. 6 is a flowchart relating to the operation of an electronic device for identifying whether a message is a spam message, according to one embodiment.

[0014] FIG. 7 illustrates examples of messages identified as allowed messages according to one embodiment.

[0015] FIG. 8 illustrates examples of messages identified as allowed messages according to one embodiment.

[0016] FIG. 9 illustrates a flowchart regarding the operation of an electronic device for determining an artificial intelligence model for identifying spam messages according to one embodiment.

[0017] FIG. 10 illustrates a flowchart of the operation of an electronic device for obtaining information regarding the probability that a message is a spam message, according to one embodiment.

[0018] FIG. 11 illustrates an example of a screen of an electronic device for displaying spam messages according to one embodiment.

[0019] FIG. 12 illustrates a flowchart regarding the operation of an electronic device for providing information to guide changing the filtering level, according to one embodiment.

[0020] FIG. 13a illustrates a flowchart relating to the operation of an electronic device for providing information to guide changing a filtering level, according to one embodiment.

[0021] FIG. 13b illustrates an example of an input for changing a message identified as a spam message into an allowed message, according to one embodiment.

[0022] FIG. 14a illustrates a flowchart relating to the operation of an electronic device for providing information to guide changing a filtering level, according to one embodiment.

[0023] FIG. 14b illustrates an example of an input for changing a message identified as an allowed message into a spam message, according to one embodiment.

[0024] FIG. 15 illustrates a flowchart regarding the operation of an electronic device for providing information to guide changing a filtering level, according to one embodiment.

[0025] Hereinafter, embodiments of the present disclosure are described in detail with reference to the drawings so that those skilled in the art can easily practice them. However, the present disclosure may be embodied in various different forms and is not limited to the embodiments described herein. In relation to the description of the drawings, the same or similar reference numerals may be used for identical or similar components. Furthermore, in the drawings and related descriptions, descriptions of well-known functions and configurations may be omitted for clarity and brevity.

[0026] FIG. 1 is a block diagram of an electronic device in a network environment according to one embodiment.

[0027] Referring to FIG. 1, in a network environment (100), an electronic device (101) may communicate with an electronic device (102) through a first network (198) (e.g., a short-range wireless communication network) or with at least one of an electronic device (104) or a server (108) through a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) through a server (108). According to one embodiment, the electronic device (101) may include a processor (120), memory (130), input module (150), sound output module (155), display module (160), audio module (170), sensor module (176), interface (177), connection terminal (178), haptic module (179), camera module (180), power management module (188), battery (189), communication module (190), subscriber identification module (196), or antenna module (197). In some embodiments, at least one of these components (e.g., connection terminal (178)) may be omitted from the electronic device (101), or one or more other components may be added. In some embodiments, some of these components (e.g., sensor module (176), camera module (180), or antenna module (197)) may be integrated into a single component (e.g., display module (160)).

[0028] The processor (120) can control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) by executing software (e.g., a program (140)), and can perform various data processing or operations. According to one embodiment, as at least part of the data processing or operations, the processor (120) can store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in volatile memory (132), process the commands or data stored in volatile memory (132), and store the resulting data in non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or an auxiliary processor (123) that can operate independently or together with it (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor). For example, if the electronic device (101) includes a main processor (121) and an auxiliary processor (123), the auxiliary processor (123) may be configured to use lower power than the main processor (121) or to be specialized for a designated function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as part thereof.

[0029] The auxiliary processor (123) may control at least some of the functions or states associated with at least one component of the electronic device (101) (e.g., display module (160), sensor module (176), or communication module (190)) on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. According to one embodiment, the auxiliary processor (123) (e.g., image signal processor or communication processor) may be implemented as part of another functionally related component (e.g., camera module (180) or communication module (190)). According to one embodiment, the auxiliary processor (123) (e.g., neural network processing unit) may include a hardware structure specialized for processing an artificial intelligence model. The artificial intelligence model may be generated through machine learning. Such learning may be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or through a separate server (e.g., server (108)). The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model may include a plurality of artificial neural network layers.An artificial neural network may be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to the hardware structure, the artificial intelligence model may include a software structure, either additionally or substantially.

[0030] The memory (130) can store various data used by at least one component of the electronic device (101) (e.g., processor (120) or sensor module (176)). The data may include, for example, input data or output data for software (e.g., program (140)) and related commands. The memory (130) may include volatile memory (132) or non-volatile memory (134).

[0031] The program (140) may be stored as software in memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0032] The input module (150) can receive commands or data to be used for a component of the electronic device (101) (e.g., processor (120)) from outside the electronic device (101) (e.g., user). The input module (150) may include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0033] The sound output module (155) can output a sound signal to the outside of the electronic device (101). The sound output module (155) may include, for example, a speaker or a receiver. The speaker may be used for general purposes, such as multimedia playback or recording playback. The receiver may be used to receive incoming calls. According to one embodiment, the receiver may be implemented separately from the speaker or as part thereof.

[0034] The display module (160) can visually provide information to an external (e.g., user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling said device. According to one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of the force generated by said touch.

[0035] The audio module (170) can convert sound into an electrical signal or, conversely, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150) or output sound through the sound output module (155) or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphones) connected directly or wirelessly to the electronic device (101).

[0036] The sensor module (176) can detect the operating state of the electronic device (101) (e.g., power or temperature) or the external environmental state (e.g., user state) and generate an electrical signal or data value corresponding to the detected state. According to one embodiment, the sensor module (176) may include, for example, a gesture sensor, a gyroscope sensor, a barometric pressure sensor, a magnetic sensor, an accelerometer sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biosensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0037] The interface (177) may support one or more specified protocols that can be used for the electronic device (101) to be connected directly or wirelessly to an external electronic device (e.g., electronic device (102)). According to one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0038] The connection terminal (178) may include a connector through which the electronic device (101) can be physically connected to an external electronic device (e.g., electronic device (102)). According to one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0039] The haptic module (179) can convert an electrical signal into a mechanical stimulus (e.g., vibration or movement) or an electrical stimulus that the user can perceive through tactile or kinesthetic senses. According to one embodiment, the haptic module (179) may include, for example, a motor, a piezoelectric element, or an electric stimulation device.

[0040] The camera module (180) can capture still images and video. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0041] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented, for example, as at least part of a power management integrated circuit (PMIC).

[0042] The battery (189) can supply power to at least one component of the electronic device (101). According to one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0043] The communication module (190) can support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between an electronic device (101) and an external electronic device (e.g., electronic device (102), electronic device (104), or server (108)), and the performance of communication through the established communication channel. The communication module (190) may include one or more communication processors that operate independently of the processor (120) (e.g., application processor) and support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) may include a wireless communication module (192) (e.g., cellular communication module, short-range wireless communication module, or GNSS (global navigation satellite system) communication module) or a wired communication module (194) (e.g., LAN (local area network) communication module, or power line communication module). The corresponding communication module among these communication modules can communicate with an external electronic device (104) through a first network (198) (e.g., a short-range communication network such as Bluetooth, WiFi (wireless fidelity) direct, or IrDA (infrared data association)) or a second network (199) (e.g., a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN). These various types of communication modules may be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can identify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) using subscriber information (e.g., International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module (196).

[0044] The wireless communication module (192) can support 5G networks and next-generation communication technologies following 4G networks, for example, new radio access technology. NR access technology can support high-speed transmission of high-capacity data (enhanced mobile broadband (eMBB)), minimization of terminal power and connection of multiple terminals (massive machine type communications (mMTC)), or high reliability and low latency (ultra-reliable and low-latency communications (URLLC)). The wireless communication module (192) can support a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate, for example. The wireless communication module (192) can support various technologies for securing performance in the high-frequency band, such as beamforming, massive MIMO (multiple-input and multiple-output), full-dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large-scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), external electronic device (e.g., electronic device (104)), or network system (e.g., second network (199)). According to one embodiment, the wireless communication module (192) can support a Peak data rate (e.g., 20 Gbps or more) for realizing eMBB, loss coverage (e.g., 164 dB or less) for realizing mMTC, or U-plane latency (e.g., downlink (DL) and uplink (UL) each 0.5 ms or less, or round trip 1 ms or less) for realizing URLLC.

[0045] An antenna module (197) can transmit a signal or power to or from an external source (e.g., an external electronic device). According to one embodiment, the antenna module (197) may include an antenna comprising a radiator made of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). According to one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as a first network (198) or a second network (199), may be selected from the plurality of antennas, for example, by a communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through the selected at least one antenna. According to some embodiments, in addition to the radiator, other components (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as part of the antenna module (197).

[0046] According to various embodiments, the antenna module (197) may form a mmWave antenna module. According to one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent to a first surface (e.g., bottom surface) of the printed circuit board and capable of supporting a specified high frequency band (e.g., mmWave band), and a plurality of antennas (e.g., array antennas) disposed on or adjacent to a second surface (e.g., top surface or side surface) of the printed circuit board and capable of transmitting or receiving a signal of the specified high frequency band.

[0047] At least some of the above components can be connected to each other via a communication method between peripheral devices (e.g., bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)) and exchange signals (e.g., commands or data) with each other.

[0048] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) through a server (108) connected to a second network (199). Each of the external electronic devices (102, or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations performed on the electronic device (101) may be performed on one or more of the external electronic devices (102, 104, or 108). For example, if the electronic device (101) needs to perform a function or service automatically or in response to a request from a user or another device, the electronic device (101) may request one or more external electronic devices to perform at least part of the function or service instead of performing the function or service itself or additionally. One or more external electronic devices that receive the above request may execute at least part of the requested function or service, or additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may provide the result as is or additionally processed as at least part of the response to the request. For this purpose, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used. The electronic device (101) may provide ultra-low latency services using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server using machine learning and / or neural networks. According to one embodiment, the external electronic device (104) or the server (108) may be included within the second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0049] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) can receive a message (e.g., a text message). The electronic device can determine whether the received message is a spam message. The electronic device can identify the received message as a spam message if the received message contains a specified word (or phrase). The electronic device can identify the received message as a spam message if the sender number of the received message is a blocked sender number. However, if the spam message does not contain the specified word (or phrase) or if the sender number is an unknown sender number, the received message may be identified as an allowed message. Accordingly, the following specification will describe technical features for identifying a received message as either a spam message or an allowed message using an artificial intelligence model.

[0050] FIG. 2 illustrates an example of the operation of an electronic device for filtering a received message according to one embodiment.

[0051] Referring to FIG. 2, an electronic device (200) may receive a message (290) from an external electronic device. The electronic device (200) may identify the message (290) as either an allowed message or a spam message. For example, an allowed message may be displayed (or provided) in the message box of the electronic device (200). A spam message may be displayed (or provided) in the blocked message box of the electronic device (200). The electronic device (200) may provide an allowed message in the message box so as not to expose spam messages to the user. The electronic device (200) may provide a filtered spam message in the blocked message box.

[0052] For example, spam messages may include unsolicited messages, unwanted messages, irrelevant messages, and malicious messages. Spam messages may be referred to as any of unsolicited messages, unwanted messages, irrelevant messages, and malicious messages.

[0053] For example, allowed messages may include solicited messages, authorized messages, relevant messages, personalized messages, and trusted messages. Allowed messages may be referred to as one of solicited messages, authorized messages, relevant messages, personalized messages, and trusted messages.

[0054] According to one embodiment, the electronic device (200) can identify the content of the message (290) and the sender number of the message (290). For example, the electronic device (200) can store one or more blocked sender numbers (271) and one or more blocked words (272) (or one or more blocked phrases).

[0055] For example, the electronic device (200) can identify whether the sender number of the message (290) is included in one or more blocked sender numbers (271). Based on identifying that the sender number of the message (290) is included in one or more blocked sender numbers (271), the electronic device (200) can identify the message (290) as a spam message.

[0056] For example, the electronic device (200) can identify whether the content of the message (290) contains at least one of one or more blocked words (272). Based on identifying that the content of the message (290) contains at least one of one or more blocked words (272), the electronic device (200) can identify the message (290) as a spam message.

[0057] According to one embodiment, an electronic device (200) can identify a message (290) as either an allowed message or a spam message by using an artificial intelligence model (280). The electronic device (200) can set the message (290) (or the content of the message (290)) as input data for the artificial intelligence model (280). The electronic device (200) can input the message (290) (or the content of the message (290)) into the artificial intelligence model (280). The electronic device (200) can obtain information regarding the category of the message (290) and the probability that the message (290) is a spam message from the output data of the artificial intelligence model (280). For example, the electronic device (200) can set multiple categories of spam messages. The multiple categories of spam messages may include at least one of smishing / phishing, illegal gambling / gaming, illegal loans, adult content, illegal pharmaceuticals, and / or illegal investments. This is exemplary and is not limited to this.

[0058] According to one embodiment, the electronic device (200) can determine the category of a message (290) as one of a plurality of categories using an artificial intelligence model (280). The electronic device (200) can obtain information regarding the probability that the message (290) is a spam message using the artificial intelligence model (280). Based on the category of the message (290) and the information regarding the probability that the message (290) is a spam message, the electronic device (200) can identify (or determine) the message (290) as either an allowed message or a spam message. In the specification below, specific operations of the electronic device (200) for identifying whether a received message is a received message will be described.

[0059] FIG. 3 illustrates an example of a simplified block diagram of an electronic device according to one embodiment.

[0060] Referring to FIG. 3, the electronic device (200) may include at least some or all of the components of the electronic device (101) of FIG. 1. For example, the electronic device (200) may correspond to the electronic device (101) of FIG. 1.

[0061] According to one embodiment, the electronic device (200) may include at least one of a processor (210), a memory (220), a communication circuit (230), and / or a display (240). For example, at least some of the processor (210), the memory (220), the communication circuit (230), and / or the display (240) may be omitted according to the embodiment.

[0062] According to one embodiment, the processor (210) may include at least a portion of the processor (120) of FIG. 1 or correspond to at least a portion of the processor (120). For example, the processor (210) may include one or more processors including an application processor (AP) and / or a communication processor (CP). For example, the processor (210) may be implemented as a single chip, such as a system on chip (SoC), or as multiple chips. For example, the processor (210) may be implemented as a single integrated circuit or as multiple integrated circuits. For example, the processor (210) may be distributedly arranged within an electronic device (200).

[0063] The processor (210) may be operatively coupled with or connected with the memory (220), the communication circuit (230), and the display (240). For example, the processor (210) being operatively coupled with other components may mean that the processor (210) can control other components. The processor (210) can control the memory (220), the communication circuit (230), and / or the display (240).

[0064] According to one embodiment, the memory (220) of the electronic device (200) may include a circuit and / or a storage medium for storing data and / or instructions that are input and / or output to the processor (210). The memory (220) may include, for example, volatile memory such as random-access memory (RAM) and / or non-volatile memory such as read-only memory (ROM). Non-volatile memory may be referred to as storage. Volatile memory may include, for example, at least one of dynamic RAM (DRAM), static RAM (SRAM), cache RAM, and pseudo SRAM (PSRAM). Non-volatile memory may include, for example, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), flash memory, hard disk, compact disk, solid state drive (SSD), and embedded multi-media card (eMMC).

[0065] According to one embodiment, the memory (220) may include at least a portion of the memory (130) of FIG. 1 or correspond to at least a portion of the memory (130) of FIG. 1. For example, the memory (220) may be implemented as a single chip or as a plurality of chips. For example, the memory (220) may be implemented as a single integrated circuit or as a plurality of integrated circuits. For example, the memory (220) may be distributedly arranged within an electronic device (200).

[0066] According to one embodiment, a processor (210) of an electronic device (200) may execute instructions in a memory (220) within the electronic device (200) to perform a function and / or operation indicated by said instructions. For example, if the electronic device (200) includes at least one processor, said at least one processor may be configured to execute said instructions collectively or individually.

[0067] For example, memory (220) may include an artificial intelligence model (280). The artificial intelligence model (280) may include at least one artificial intelligence model. Memory (220) may store instructions regarding at least one artificial intelligence model. Memory (220) may include (or store) at least one of a first artificial intelligence model (e.g., the first artificial intelligence model (281) of FIG. 4) and / or a second artificial intelligence model (e.g., the second artificial intelligence model (282) of FIG. 4), which will be described below. According to one embodiment, at least one of the first artificial intelligence model and / or the second artificial intelligence model may be configured based on a language-based artificial intelligence model. According to one embodiment, at least one of the first artificial intelligence model and / or the second artificial intelligence model may be configured based on at least one of a rule model and / or a deep model. According to one embodiment, at least one of the first artificial intelligence model and / or the second artificial intelligence model may be configured based on a generative model (or generative artificial intelligence model). However, it is not limited thereto.

[0068] According to an embodiment, the artificial intelligence model (280) may be contained in a chip (e.g., NPU) distinct from the memory (220). For example, at least one of the first artificial intelligence model and / or the second artificial intelligence model contained in the artificial intelligence model (280) may be implemented in hardware (e.g., an artificial intelligence chip) contained within the electronic device (200). According to an embodiment, the first artificial intelligence model may be implemented in hardware (e.g., an artificial intelligence chip) contained within the electronic device (200). The second artificial intelligence model may be contained in an external server.

[0069] According to one embodiment, the communication circuit (230) can be used for various radio access technologies (RAT). For example, the communication circuit (230) can be used to perform Bluetooth communication, wireless local area network (WLAN) communication, or ultra-wideband (UWB) communication. For example, the communication circuit (230) can be used to perform cellular communication. For example, the processor (210) can exchange messages with an external electronic device through the communication circuit (230). For example, the processor (110) can receive messages from an external electronic device or send messages to an external electronic device using at least one of SMS (short message service), MMS (multimedia messaging service), RCS (rich communication services), OTT (over-the-top) messaging, USSD (unstructured supplementary service data), and / or IoT (internet of things) messaging.

[0070] According to one embodiment, a display (240) of an electronic device (200) can output visualized information (e.g., a screen) to a user. For example, the display (240) can be controlled by a controller, such as a GPU (graphic processing unit), to output visualized information to a user. The display (240) may include a liquid crystal display (LCD), a plasma display panel (PDP), and / or one or more light emitting diodes (LEDs). The LEDs may include organic LEDs (OLEDs). The display (240) may include a flat panel display (FPD) and / or electronic paper. The embodiments are not limited thereto, and the display (240) may have at least a partially curved shape or a deformable shape. A display (240) having a deformable shape may be referred to as a flexible display. According to an embodiment, when the electronic device (200) operates as a server, the electronic device (200) may not include a display (240).

[0071] FIG. 4 illustrates an example of the operation of an electronic device for identifying spam messages according to one embodiment.

[0072] Referring to FIG. 4, the memory (220) of the electronic device (200) can store a message application (410), a contact application (420), and an artificial intelligence model (280). For example, the memory (220) can store instructions for the message application (410). The memory (220) can store instructions for the contact application (420). The memory (220) can store instructions for the artificial intelligence model (280). The message application (410), the contact application (420), and the artificial intelligence model (280) can be operated by the processor (210).

[0073] According to one embodiment, an electronic device (200) can receive a message (290) from an external electronic device using a message application (410). For example, the electronic device (200) can use the message application (410) to identify whether the message (290) is a spam message. A database (e.g., memory (220)) of the message application (410) can store one or more blocked words. A processor (210) can identify one or more blocked words within the message application (410). The processor (210) can identify whether at least one of the one or more blocked words is included in the content of the message (290). Based on identifying that at least one of the one or more blocked words is included in the content of the message (290), the processor (210) can identify the message (290) as a spam message.

[0074] For example, the processor (210) can identify the sender number of the message (290) through the message application (410). The processor (210) can provide the sender number of the message (290) to the contact application (420). The processor (210) can use the contact application (420) to identify whether the sender number of the message (290) is registered as a contact and / or tag. For example, the processor (210) can identify whether the sender number is registered as a contact. For example, the processor (210) can identify whether the sender number is registered as a tag. The processor (210) can use the contact application (420) to provide the message application (410) with information regarding whether the sender number of the message (290) is registered as a contact and / or tag.

[0075] For example, the processor (210) may provide the message (290) to the artificial intelligence model (280) to identify whether the message (290) is a spam message using the artificial intelligence model (280). The processor (210) may identify whether the message (290) is a spam message using at least one of the first artificial intelligence model (281) and / or the second artificial intelligence model (282). The processor (210) may provide information regarding whether the message (290) is a spam message to the message application (410) using the artificial intelligence model (280).

[0076] According to one embodiment, the first artificial intelligence model (281) and / or the second artificial intelligence model (282) may be implemented as hardware (e.g., an artificial intelligence chip) included inside the electronic device (200).

[0077] For example, the first artificial intelligence model (281) may be configured to identify whether a message is a spam message regardless of the message transmission and reception history. For example, the first artificial intelligence model (281) may be trained based on messages classified according to multiple categories of spam messages that are distinguished from messages transmitted and received in the electronic device (200). The first artificial intelligence model (281) may be converted based on the ONNX (open neural network exchange) format and then quantized. The first artificial intelligence model (281) may be configured to run as an ORT (ONNX runtime) within the electronic device (200).

[0078] For example, the second artificial intelligence model (282) can learn the transmission and reception history of messages. The second artificial intelligence model (282) can be trained based on multiple messages stored in memory (220). The second artificial intelligence model (282) can be configured to identify whether a message is a spam message based on the transmission and reception history of messages. For example, the first artificial intelligence model (281) can be configured to provide objective results. The second artificial intelligence model (282) can be configured to provide user-customized results. However, it is not limited thereto.

[0079] According to an embodiment, the first artificial intelligence model (281) and the second artificial intelligence model (282) may be configured based on different artificial intelligence models. The first artificial intelligence model (281) and the second artificial intelligence model (282) may be trained based on a plurality of messages stored in memory (220). The processor (210) may identify whether a message is a spam message based on both the output of the first artificial intelligence model (281) and the output of the second artificial intelligence model (282).

[0080] According to one embodiment, the processor (210) can identify whether a message (290) is a spam message by using at least one of a contact application (410) and / or an artificial intelligence model (280). For example, if the message (290) is identified as a spam message, the processor (210) can store the message (290) in a blocked message box. If the message (290) is identified as a spam message, the processor (210) can provide (or display) the message (290) through the blocked message box using the user interface of the message application (410). For example, if the message (290) is identified as an allowed message, the processor (210) can store the message (290) in a message box (or normal message box) for providing incoming messages and outgoing messages. If the processor (210) identifies the message (290) as an allowed message, it can provide (or display) the message (290) through a message box (or normal message box) using the user interface of the message application (410).

[0081] At least some or all of the operations of FIG. 4 may be performed by the processor (210). In FIG. 5 below, specific operations of the processor (210) for identifying whether a message is a spam message using an artificial intelligence model (280) (e.g., a first artificial intelligence model (281) and / or a second artificial intelligence model (282)) will be described later.

[0082] FIG. 5 is a flowchart relating to the operation of an electronic device for identifying whether a message is a spam message according to one embodiment. In the following embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel.

[0083] Referring to FIG. 5, in operation 501, the processor (210) may receive a message from an external electronic device. For example, the processor (210) may receive a message from an external electronic device using a communication circuit (230). For example, the message (290) may include an SMS (short message service), an MMS (multimedia messaging service), and / or a chat message. However, it is not limited thereto. The message (290) may also include an email and / or call recording data.

[0084] According to one embodiment, the processor (210) can identify the content of the message and the sender number of the message. The processor (210) can identify the content of the message and the sender number to identify whether the message is a spam message before the message is provided to a user. According to one embodiment, the processor (210) can identify the sender address of the message (e.g., a SIP (session initiation protocol) address).

[0085] In operation 502, the processor (210) can identify a message as an allowed message by using the content of the message and the sender number of the message. For example, the processor (210) can identify a message as an allowed message based on identifying that at least one blocked word is not included in the content of the message. For example, the processor (210) can identify a message as an allowed message based on identifying that the sender number of the message is distinguishable from at least one blocked sender number.

[0086] According to one embodiment, the processor (210) may identify a message as an allowed message based on identifying that the sending address of the message corresponds to one of the registered sending addresses. According to one embodiment, the processor (210) may identify a message as an allowed message based on identifying whether the sending number is a number stored in memory (220).

[0087] The specific operation of operation 502 will be described later in FIG. 6.

[0088] In operation 503, the processor (210) can identify the category of the message. For example, the processor (210) can identify the category of the message based on the content of the message. For example, the processor (210) can identify the category of the message as one of the multiple categories of spam messages based on the content of the message. For example, the processor (210) can input the content of the message (or message) into an artificial intelligence model (280). The processor (210) can identify the category of the message as one of the multiple categories of spam messages based on the output of the artificial intelligence model (280). For example, the output of the artificial intelligence model (280) may be a probability value for each of the multiple categories. The processor (210) can identify the category having the highest probability value among the multiple categories as the category of the message.

[0089] For example, multiple categories of spam messages may include at least one of smishing / phishing, illegal gambling / gaming, illegal loans, adult content, illegal drugs, and / or illegal investments. This is exemplary and is not limited thereto.

[0090] In operation 504, the processor (210) can identify a filtering level set according to the category of the message. For example, the processor (210) can identify a filtering level set according to the category of the message based on the content of the message.

[0091] According to one embodiment, the processor (210) can set a filtering level according to each of a plurality of categories. The filtering level according to each of the plurality of categories can be set by a user of the electronic device (200). For example, the filtering level can be set to one of strong, normal, or weak. However, it is not limited thereto. According to an embodiment, the filtering level can be set to one of a plurality of levels.

[0092] According to one embodiment, the processor (210) may allow the user to set a filtering level for each of the multiple categories of spam messages. For example, the processor (210) may display a screen through the display (240) for setting a filtering level for each of the multiple categories of spam messages. An example of a screen for setting a filtering level for each of the multiple categories will be described later in FIG. 8.

[0093] According to one embodiment, the processor (210) can identify a filtering level set according to a category regarding the message. For example, the processor (210) can identify a category regarding the message as illegal gambling / game. The processor (210) can identify a filtering level set according to illegal gambling / game. The processor (210) can identify the filtering level set according to illegal gambling / game as one of 'strong', 'medium', and 'weak'.

[0094] According to one embodiment, the processor (210) can identify a filtering level set according to a category based on the user's profile information. For example, the processor (210) can set (or change) a filtering level according to a category based on the user's profile information (e.g., occupation, age, gender, hobbies, or interests). For example, the processor (210) can set a low filtering level according to the pharmaceutical (or illegal pharmaceutical) category based on identifying that the user of the electronic device (200) is engaged in the medical field. For example, the processor (210) can set a low filtering level according to the loan (or illegal loan) category based on identifying that the user of the electronic device (200) is engaged in the financial field. For example, the processor (210) can set a high filtering level according to the adult category based on identifying that the user of the electronic device (200) is under a standard age. For example, the processor (210) can set a high filtering level according to the smishing / phishing category based on the age of the user of the electronic device (200) exceeding a standard age.

[0095] In operation 505, the processor (210) can obtain information regarding the probability that a message is a spam message. For example, the processor (210) can obtain information regarding the probability that a message is a spam message based on the content of the message.

[0096] According to one embodiment, the processor (210) may input the content of a message into an artificial intelligence model (280). Based on the output of the artificial intelligence model (280), the processor (210) may obtain information regarding the probability that the message is a spam message. For example, the processor (210) may obtain information regarding the probability that the message is a spam message by using at least one of the first artificial intelligence model (281) and / or the second artificial intelligence model (282). For example, the processor (210) may obtain information regarding the probability that the message is a spam message by using only the first artificial intelligence model (281). For example, the processor (210) may identify a first probability that the message is a spam message by using the first artificial intelligence model (281). The processor (210) may identify a second probability that the message is a spam message by using the second artificial intelligence model (282). The processor (210) can obtain information regarding the probability that a message is a spam message based on the first probability and the second probability. A specific example of obtaining information regarding the probability that a message is a spam message based on the first probability and the second probability will be described later in FIG. 10.

[0097] In operation 506, the processor (210) can identify whether the probability that a message is a spam message is within a probability range according to the filtering level.

[0098] In operation 507, the processor (210) can identify a message as a spam message if the probability that the message is a spam message is within a probability range according to the filtering level. For example, the processor (210) can identify a message as a spam message based on identifying that the probability that the message is a spam message is within a probability range according to the filtering level. For example, the processor (210) can change a message from an allowed message to a spam message based on identifying that the probability that the message is a spam message is within a probability range according to the filtering level.

[0099] In operation 508, the processor (210) may keep the message as an allowed message if the probability that the message is a spam message is outside the probability range according to the filtering level. The processor (210) may keep the message as an allowed message based on identifying that the probability that the message is a spam message is outside the probability range according to the filtering level.

[0100] According to actions 506, 507, and 508, a probability range can be set according to the filtering level. For example, if the filtering level is set to 'Strong', the probability range can be set from 85% to 100%. If the filtering level is set to 'Medium', the probability range can be set from 90% to 100%. If the filtering level is set to 'Weak', the probability range can be set from 95% to 100%.

[0101] For example, if the probability that a message is a spam message falls within a probability range according to a filtering level, the processor (210) can identify the message as a spam message. For example, if the probability that a message is a spam message is 92% and the probability range according to a filtering level (e.g., strong) is from 85% to 100%, the processor (210) can identify the message as a spam message. For example, if the probability that a message is a spam message is 92% and the probability range according to a filtering level (e.g., medium) is from 90% to 100%, the processor (210) can identify the message as a spam message. For example, if the probability that a message is a spam message is 92% and the probability range according to a filtering level (e.g., weak) is from 95% to 100%, the processor (210) can identify the message as an allowed message.

[0102] According to one embodiment, the processor (210) can identify whether a message is a spam message based on the output of the artificial intelligence model (280). For example, the processor (210) can obtain information regarding whether a message is a spam message by using at least one of the first artificial intelligence model (281) and / or the second artificial intelligence model (282). For example, the processor (210) can obtain information regarding whether a message is a spam message by using only the first artificial intelligence model (281). For example, the processor (210) can identify whether a message is a spam message by using the first artificial intelligence model (281). The processor (210) can identify whether a message is a spam message by using the second artificial intelligence model (282). The processor (210) can obtain information regarding whether a message is a spam message based on at least one of the first artificial intelligence model (281) and / or the second artificial intelligence model (282).

[0103] According to the above-described embodiment, the processor (210) can primarily identify whether a message is a spam message based on operation 502. The processor (210) can secondarily identify whether a message is a spam message based on operation 506. For example, if the processor (210) identifies the message as an allowed message according to operation 502, it can identify whether the message is a spam message according to operation 506. The processor (210) can maintain the message as an allowed message or identify (or change) the message as a spam message according to operation 506. For example, if the processor (210) identifies the message as a spam message according to operation 502, it may not perform operations 503 through 508.

[0104] FIG. 6 is a flowchart relating to the operation of an electronic device for identifying whether a message is a spam message according to one embodiment. In the following embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel.

[0105] In operation 601, the processor (210) can receive a message from an external electronic device. Operation 601 may correspond to operation 501 of FIG. 5.

[0106] In operation 602, the processor (210) can identify whether the sender number of a message is included in one or more blocked sender numbers. For example, one or more blocked sender numbers may be set by the user. The processor (210) can identify messages received from one or more blocked sender numbers as spam messages.

[0107] According to one embodiment, the processor (210) may perform operation 607 if the sender number of a message is included in one or more blocked sender numbers. The processor (210) may identify the message as a spam message based on identifying that the sender number of a message is included in one or more blocked sender numbers.

[0108] In operation 603, if the sender number of the message is not included in one or more blocked sender numbers, the processor (210) can identify whether at least one of one or more blocked words is included in the content of the message. For example, the processor (210) can identify whether at least one of one or more blocked words is included in the content of the message based on identifying that the sender number of the message is not included in one or more blocked sender numbers.

[0109] According to one embodiment, the processor (210) can identify the content of a message. The content of the message may include a title of the message and a body of the message. The processor (210) can identify whether at least one of one or more blocked words is included in the title of the message. The processor (210) can identify whether at least one of one or more blocked words is included in the body of the message. The processor (210) can identify that at least one of one or more blocked words is not included in the content of the message if at least one of one or more blocked words is not included in both the title and the body of the message.

[0110] According to one embodiment, the processor (210) may perform operation 607 if at least one of one or more blocked words is included in the content of the message. The processor (210) may identify the message as a spam message based on identifying that at least one of one or more blocked words is included in the content of the message.

[0111] In the above-described embodiment, it was explained that operation 603 is performed after operation 602 is performed, but this is not limited thereto. Depending on the embodiment, operation 602 may be performed after operation 603 is performed. Depending on the embodiment, operation 602 and operation 603 may be performed simultaneously.

[0112] In operation 604, the processor (210) can identify whether a filtering function is enabled. For example, the processor (210) can identify whether additional filtering functions are enabled. For example, the processor (210) can identify whether a filtering function is enabled based on additional conditions. For example, the processor (210) can identify whether a filtering function is enabled through an artificial intelligence model (280). For example, if at least one of one or more blocked words is not included in the content of the message, the processor (210) can identify whether a filtering function is enabled through an artificial intelligence model (280). For example, the processor (210) can identify whether a filtering function is enabled through an artificial intelligence model (280) based on identifying that at least one of one or more blocked words is not included in the content of the message.

[0113] According to one embodiment, the electronic device (200) may provide a filtering function through an artificial intelligence model (280). The filtering function through the artificial intelligence model (280) may be enabled or disabled by a user. For example, if the filtering function through the artificial intelligence model (280) is disabled, the processor (210) may identify a message as either a spam message or an allowed message based on actions 602 and 603. For example, if the filtering function through the artificial intelligence model (280) is enabled, the processor (210) may again identify whether the message is a spam message through the artificial intelligence model (280), even if the message is identified as an allowed message based on actions 602 and 603.

[0114] According to one embodiment, the processor (210) may perform operation 608 when the filtering function through the artificial intelligence model (280) is not enabled. For example, the processor (210) may identify a message as an allowed message based on identifying that the filtering function through the artificial intelligence model (280) is not enabled. Since the processor (210) identified the message as an allowed message based on operations 602 and 603, it may maintain the message as an allowed message based on identifying that the filtering function through the artificial intelligence model (280) is not enabled.

[0115] In operation 605, the processor (210) can identify whether the sending address of a message corresponds to one of the registered sending addresses when the filtering function through the artificial intelligence model (280) is enabled. For example, the processor (210) can identify whether the sending address of a message corresponds to one of the registered sending addresses based on identifying that the filtering function through the artificial intelligence model (280) is enabled.

[0116] For example, the processor (210) can identify that the message is configured based on rich communication services (RCS). For example, the processor (210) can identify that the message is an RCS chat message. The processor (210) can identify the sender address of the message to identify whether the message received from an external electronic device is a message sent by a registered enterprise. For example, the processor (210) can obtain (or receive) profile information of the enterprise message through an RCS server based on a SIP address. The processor (210) can identify whether the received message was sent by a registered enterprise based on the enterprise message profile information. By identifying whether the received message was sent by a registered enterprise based on the enterprise message profile information, the processor (210) can identify whether the sender address of the message corresponds to one of the registered sender addresses.

[0117] According to one embodiment, the processor (210) can identify that the received message is an RCS-related message. The processor (210) can identify the SIP address of the received message. Based on the SIP address, the processor (210) can obtain (or receive) profile information of the enterprise message through the RCS server. For example, the processor (210) can determine (or identify) whether the received message was sent from a registered enterprise based on the received enterprise message profile information.

[0118] According to one embodiment, the processor (210) may perform operation 608 if the sending address of a message corresponds to one of the registered sending addresses. For example, the processor (210) may identify (or maintain) the message as an allowed message based on identifying that the sending address of the message corresponds to one of the registered sending addresses. The processor (210) may identify that the message is a message sent from a registered enterprise based on identifying that the sending address of the message corresponds to one of the registered sending addresses. The processor (210) may identify a message sent from a registered enterprise as an allowed message. An example of a message sent from a registered enterprise will be described later in FIG. 7.

[0119] In operation 606, if the sending address of the message does not correspond to one of the registered sending addresses, the processor (210) can identify whether the sending number of the message is a number stored in memory (220). For example, the processor (210) can identify whether the sending number of the message is a number stored in memory (220) based on identifying that the sending address of the message does not correspond to one of the registered sending addresses.

[0120] According to one embodiment, the processor (210) can perform operation 608 if the sender number of the message is a number stored in memory (220). The processor (210) can identify the message as an allowed message based on identifying that the sender number of the message is a number stored in memory (220).

[0121] For example, the processor (210) can identify whether the sender number of a message corresponds to a registered contact (or a stored contact). If the sender number of a message corresponds to a registered contact, the processor (210) can identify the message as an allowed message.

[0122] For example, the processor (210) can identify whether the sender number of the message is included in the call history information of the electronic device (200). If the sender number of the message is included in the call history information of the electronic device (200), the processor (210) can identify the message as an allowed message.

[0123] For example, the processor (210) can identify tagged contacts among one or more contacts in the call history information of the electronic device (200). Tagged contacts can be distinguished from contacts registered in the electronic device (200). Tagged contacts may not be registered in the electronic device (200). The tag can function as a memo (or identifier) ​​for each contact. Contacts can be stored in association with tags. Specific examples of tagged contacts will be described later in FIG. 7.

[0124] For example, the processor (210) can identify whether the sender number of a message corresponds to one of the tagged contacts. If the sender number of a message corresponds to one of the tagged contacts, the processor (210) can identify the message as an allowed message.

[0125] In operation 609, the processor (210) can filter the message using an artificial intelligence model (280) if the sender number is not a number assigned in memory (220). The processor (210) can filter the message using an artificial intelligence model (280) based on identifying that the sender number is not a number assigned in memory (220). Specific operations for filtering the message using the artificial intelligence model (280) will be described later in FIGS. 9 and FIGS. 10.

[0126] In the above-described embodiment, it was explained that operation 606 is performed after operation 605 is performed, but this is not limited thereto. Depending on the embodiment, operation 605 may be performed after operation 606 is performed. Depending on the embodiment, operation 605 and operation 606 may be performed simultaneously.

[0127] FIG. 7 illustrates examples of messages identified as allowed messages according to one embodiment.

[0128] Referring to FIG. 7, the processor (210) of the electronic device (200) can display a screen (700) for displaying messages stored in a message box through a display (240). Messages stored in the message box may include not only received messages but also transmitted messages.

[0129] Within the screen (700), messages (710), messages (720), messages (730), and messages (740) may be displayed. The processor (210) may identify messages (710), messages (720), messages (730), and messages (740) as allowed messages and store them in a message box. The processor (210) may display messages (710), messages (720), messages (730), and messages (740) stored in the message box through the screen (700).

[0130] For example, a message (710) may be sent from a registered enterprise. The processor (210) may identify that the sending address (e.g., SIP address) of the message (710) is one of the registered addresses. The processor (210) may identify the message (710) as an allowed message and display it on the screen (700). On the screen (700), the processor (210) may display the name (711) of the enterprise that sent the message (710), some of the content (712) of the message (710), and the date (713) that the message (710) was received.

[0131] For example, a message (720) may be sent from a registered enterprise. The processor (210) may identify that the sending address (e.g., SIP address) of the message (720) is one of the registered addresses. The processor (210) may identify the message (720) as an allowed message and display it on the screen (700). On the screen (700), the processor (210) may display the name (721) of the enterprise that sent the message (720), some of the content (722) of the message (720), and the date (723) on which the message (720) was received.

[0132] For example, a message (730) may be sent from a tagged contact. The processor (210) may identify that the sender number of the message (730) corresponds to one of the tagged contacts. The processor (210) may identify the message (730) as an allowed message and display it on the screen (700). On the screen (700), the processor (210) may display a tag (731) associated with the contact, an object (734) indicating that the contact has been tagged, some of the content (732) of the message (730), and the date (733) that the message (730) was received.

[0133] For example, a message (740) may be sent from a contact registered (or stored) in the electronic device (200). The processor (210) may identify that the sender number of the message (740) corresponds to one of the contacts registered (or stored) in the electronic device (200). The processor (210) may identify the message (740) as an allowed message and display it through the screen (700). Within the screen (700), the processor (210) may display the name (721) registered in the electronic device (200), some of the content (742) of the message (740), and the date (743) when the message (740) was received.

[0134] In the screen (700) of FIG. 7, for convenience of explanation, an example is described in which information regarding a message received for the contact is displayed, but it is not limited thereto. For example, if a message is sent to the contact, information regarding the message sent to the contact (e.g., part of the content and the date sent) may be displayed. According to one embodiment, the processor (210) may display information regarding a conversation with the contact as shown in the screen (700).

[0135] FIG. 8 illustrates examples of messages identified as allowed messages according to one embodiment.

[0136] Referring to FIG. 8, the processor (210) of the electronic device (200) can display (or provide) a screen (810) for setting multiple categories of spam messages through the display (240).

[0137] According to the screen (810), the processor (210) may display multiple categories of spam messages. For example, the multiple categories may include smishing / phishing (812), illegal gambling / gaming (813), illegal loans (814), adult content (815), illegal drugs (816), and illegal investments (817). A filtering level may be set for each of the multiple categories. Based on identifying an input for one of the multiple categories, the processor (210) may display (or provide) a screen (820) for setting a filtering level for the input category.

[0138] For example, in response to an input for one of a plurality of categories displayed on a screen (810), the processor (210) may display a screen (820) via a display (240) for selecting a filtering level (or blocking strength) for that category. For example, the filtering level may be set to one of strong (821), medium (822), and weak (823). The processor (210) may display an object (825) on the screen (820) indicating the currently selected filtering level. The processor (210) may set (or change) the filtering level for that category based on an input selecting one of strong (821), medium (822), and weak (823).

[0139] For example, a probability range can be set according to the filtering level. For instance, if the filtering level is set to Strong, the probability range can be set from 85% to 100%. If the filtering level is set to Medium, the probability range can be set from 90% to 100%. If the filtering level is set to Weak, the probability range can be set from 95% to 100%. This is exemplary and subject to change. The higher the filtering level, the more messages can be identified as spam. The lower the filtering level, the fewer messages can be identified as spam.

[0140] For example, the processor (210) can identify the category of a message as one of a plurality of categories by using an artificial intelligence model (280) (e.g., a first artificial intelligence model (281) and / or a second artificial intelligence model (282)). The processor (210) can identify information regarding the probability that a message is a spam message by using the artificial intelligence model (280). The processor (210) can identify whether the probability that the message is a spam message falls within a probability range according to the category of the message. Based on identifying that the probability that the message is a spam message falls within a probability range according to the category of the message, the processor (210) can identify the message as a spam message.

[0141] For example, the category of a message may be identified as smishing / phishing (812). The filtering level set according to smishing / phishing (812) may be set to weak (823). If the probability that the message is a spam message is 88%, and the probability range according to the filtering level set to weak (823) is from 85% to 100%, the processor (210) may identify the message as a spam message.

[0142] For example, the category of the message may be identified as illegal gambling / game (813). The filtering level set according to illegal gambling / game (813) may be set to strong (821). If the probability that the message is a spam message is 94% and the probability range according to the filtering level set to strong (821) is from 95% to 100%, the processor (210) may identify the message as an allowed message.

[0143] In FIG. 8, an example is shown in which there are 6 multiple categories of spam messages, but this is exemplary and is not limited thereto. In FIG. 8, an example is shown in which there are 3 configurable filtering levels, but this is exemplary and is not limited thereto. For example, the number of filtering levels can be set in various ways.

[0144] FIG. 9 illustrates a flowchart regarding the operation of an electronic device for determining an artificial intelligence model for identifying spam messages according to one embodiment. In the following embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel.

[0145] Referring to FIG. 9, in operation 901, the processor (210) can identify whether the number of multiple messages stored in memory (220) is greater than or equal to a reference number. For example, the processor (210) can use the multiple messages stored in memory (220) to train a second artificial intelligence model (282). The processor (210) can identify whether the number of multiple messages is greater than or equal to a reference number in order to determine whether the number of multiple messages used for training the second artificial intelligence model (282) is sufficient.

[0146] According to one embodiment, the artificial intelligence model (280) may include a first artificial intelligence model (281) and a second artificial intelligence model (282). The first artificial intelligence model (281) may be trained based on messages classified according to a plurality of categories of spam messages, which are distinguished from messages transmitted and received by the electronic device (200). The second artificial intelligence model (282) may be trained based on a plurality of messages stored in the memory (220) (or message box) of the electronic device (200). The second artificial intelligence model (282) may be trained based on the message transmission and reception history of the electronic device (200) (or messages transmitted and received by the electronic device (200). As an example, the second artificial intelligence model (282) may be trained based on LIBSVM (library for support vector machines) (or LIBSVM on Android). The processor (210) can train the second artificial intelligence model (282) while the electronic device (200) is idle.

[0147] According to one embodiment, the processor (210) may perform operation 904 when the number of multiple messages stored in memory (220) is less than a reference number. For example, the processor (210) may obtain information regarding the probability that a message is a spam message by using the first artificial intelligence model (281) based on identifying that the number of multiple messages stored in memory (220) is less than a reference number. The processor (210) may determine that there is insufficient data for training the second artificial intelligence model (282) when the number of multiple messages is less than a reference number. Therefore, the processor (210) may use only the first artificial intelligence model (281) to obtain information regarding the probability that a message is a spam message.

[0148] In operation 902, if the number of multiple messages stored in memory (220) is greater than or equal to a reference number, the processor (210) can identify whether the reliability of the second artificial intelligence model (282) is greater than or equal to a reference reliability. For example, the processor (210) can identify the reliability of the second artificial intelligence model (282) to evaluate the performance of the second artificial intelligence model (282).

[0149] For example, the processor (210) may input test messages into the second artificial intelligence model (282). Based on the output of the second artificial intelligence model (282), the processor (210) may identify at least one of the test messages as a spam message. Based on the at least one test message identified as a spam message, the processor (210) may identify information regarding the reliability of the second artificial intelligence model (282). For example, the test messages may include normal messages and spam messages. The processor (210) may identify information regarding the reliability of the second artificial intelligence model (282) based on the similarity between the at least one test message identified through the second artificial intelligence model (282) and the spam messages included in the test messages.

[0150] According to one embodiment, the processor (210) may perform operation 904 when the reliability of the second artificial intelligence model (282) is below the reference reliability. For example, the processor (210) may obtain information regarding the probability that a message is a spam message by using the first artificial intelligence model (281) based on identifying that the reliability of the second artificial intelligence model (282) is below the reference reliability. If the reliability of the second artificial intelligence model (282) is below the reference reliability, the processor (210) may determine that the second artificial intelligence model (282) is not suitable for identifying spam messages. Therefore, the processor (210) may use only the first artificial intelligence model (281) to obtain information regarding the probability that a message is a spam message.

[0151] In operation 903, if the reliability of the second artificial intelligence model is greater than or equal to the reference reliability, the processor (210) can obtain information regarding the probability that the message is a spam message by using the first artificial intelligence model (281) and the second artificial intelligence model (282). For example, the processor (210) can obtain information regarding the probability that the message is a spam message by using both the first artificial intelligence model (281) and the second artificial intelligence model (282) based on identifying that the reliability of the second artificial intelligence model is greater than or equal to the reference reliability. A specific operation of the processor (210) for obtaining information regarding the probability that the message is a spam message by using both the first artificial intelligence model (281) and the second artificial intelligence model (282) will be described later in FIG. 10.

[0152] FIG. 10 illustrates a flowchart of the operation of an electronic device for obtaining information regarding the probability that a message is a spam message, according to one embodiment. In the following embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel.

[0153] Referring to FIG. 10, in operation 1001, the processor (210) can obtain a first probability that a message is a spam message by using a first artificial intelligence model (281). For example, the processor (210) can input a message (or the content of the message) into the first artificial intelligence model (281). The processor (210) can obtain a first probability that a message is a spam message based on the output of the first artificial intelligence model (281).

[0154] In operation 1002, the processor (210) can obtain a second probability that the message is a spam message by using a second artificial intelligence model (282). For example, the processor (210) can input a message (or the content of the message) into the second artificial intelligence model (282). The processor (210) can obtain a second probability that the message is a spam message based on the output of the second artificial intelligence model (282).

[0155] In operations 1001 and 1002, the first artificial intelligence model (281) may be trained based on messages classified according to multiple categories of spam messages (e.g., ground truth). The second artificial intelligence model (282) may be trained based on multiple messages stored in memory (220) (or messages transmitted and received from the electronic device (200)). Accordingly, when the inputs of the first artificial intelligence model (281) and the second artificial intelligence model (282) are set to be the same as messages (or the content of messages), a first probability may be obtained from the first artificial intelligence model (281) and a second probability may be obtained from the second artificial intelligence model (282).

[0156] In operation 1003, the processor (210) can obtain information regarding the probability that a message is a spam message. For example, the processor (210) can obtain information regarding the probability (or final probability) that a message is a spam message based on a first probability and a second probability. For example, the processor (210) can determine a weight for each of the first probability and the second probability. The processor (210) can apply a first weight to the first probability. The processor (210) can apply a second weight to the second probability. The processor (210) can obtain information regarding the probability (or final probability) that a message is a spam message by using the first probability to which the first weight ratio is applied and the second probability to which the second weight is applied.

[0157] For example, the processor (210) may obtain information regarding the reliability of the second artificial intelligence model (282) and, based on the information regarding the reliability of the second artificial intelligence model (282), determine weights for the first probability and the second probability, respectively. The operation for obtaining the reliability of the second artificial intelligence model (282) may correspond to operation 902 of FIG. 9. The processor (210) may set the weight of the second probability higher as the reliability of the second artificial intelligence model (282) increases.

[0158] For example, information regarding the probability that an acquired message is a spam message based on the first and second probabilities can be structured as shown in the table below.

[0159] Confidence of the 2nd Artificial Intelligence Model 1st Probability 2nd Probability Weight Ratio Final Probability 90% 95% 50% 7:38 7.5% 95% 90% 30% 3:75 8%...............

[0160] Referring to Table 1, when the confidence level of the second artificial intelligence model (282) is 90%, the ratio between the first weight for the first probability and the second weight for the second probability can be set to 7:3. Thus, when the first probability is 90% and the second probability is 50%, the final probability can be identified as 87.5%. When the confidence level of the second artificial intelligence model (282) is 95%, the ratio between the first weight for the first probability and the second weight for the second probability can be set to 3:7. Thus, when the first probability is 90% and the second probability is 30%, the final probability can be identified as 58%.

[0161] According to the above-described embodiment, the second artificial intelligence model (282) can be trained based on messages transmitted and received from the electronic device (200). As the second artificial intelligence model (282) is trained, the reliability of the second artificial intelligence model (282) can increase. Accordingly, as the reliability of the second artificial intelligence model (282) increases, the processor (210) can set the second weight for the second artificial intelligence model (282) higher than the first weight for the first artificial intelligence model (281).

[0162] FIG. 11 illustrates an example of a screen of an electronic device for displaying spam messages according to one embodiment.

[0163] Referring to FIG. 11, the processor (210) may display a screen (1110) for indicating a message box through a display (240). The screen (1110) may include an area (1111) indicating information about allowed messages (or conversations). The processor (210) may display a visual object (1112) within the screen (1110) indicating that there are blocked messages for a specified period (e.g., 30 days). The visual object (1112) may include an element (1113) for checking the blocked message box. Based on input for the element (1113), the processor (210) may change the screen displayed through the display (240) from the screen (1110) to the screen (1120).

[0164] According to one embodiment, the processor (210) may display a screen (1120) for indicating a blocked message box through a display (240). The processor (210) may display areas (1121, 1122) within the screen (1120) indicating messages identified as spam messages.

[0165] For example, within the area (1121), information about a message received from a first sender number may be displayed. The processor (210) may include text (1151) indicating a first sender number, text (1152) indicating the number of messages received from the first sender number, text (1153) indicating the date of receipt of the most recent message received from the first sender number, and text (1154) indicating a part (or summary) of the most recent message.

[0166] For example, within the area (1122), information about a message received from a second sender number may be displayed. The processor (210) may include text (1161) indicating a second sender number, text (1162) indicating the number of messages received from the second sender number, text (1163) indicating the date of receipt of the most recent message received from the second sender number, and text (1164) indicating a part (or summary) of the most recent message.

[0167] According to one embodiment, the processor (210) may display a screen (1130) through the display (240) for displaying message(s) received from a first sender number and identified as spam messages, based on input for at least a portion of the area (1121). The processor (210) may display a screen (1140) through the display (240) for displaying message(s) received from a second sender number and identified as spam messages, based on input for at least a portion of the area (1122).

[0168] The screen (1130) may include text (1131) representing a first sender number, an object (1132) representing a message received from the first sender number, text (1133) representing the date the message was received, a category (1134) of the message, and text (1135) representing the time the message was received. For example, the processor (210) may display the category (1134) of the message together with the object (1132) representing the message. The processor (210) may display an object (1136) for deleting all message(s) received from the first sender number within the screen (1130).

[0169] The screen (1140) may include text (1141) representing a second caller number, an object (1142) representing a message received from the second caller number, text (1143) representing the date the message was received, a category (1144) of the message, and text (1145) representing the time the message was received. For example, the processor (210) may display the category (1144) of the message together with the object (1142) representing the message. The processor (210) may display an object (1146) for deleting all message(s) received from the second caller number within the screen (1130).

[0170] In FIG. 11, an example is illustrated in which message(s) identified as spam messages are distinguished by sender number, but is not limited thereto. According to an embodiment, message(s) identified as spam messages may be distinguished by category.

[0171] FIG. 12 illustrates a flowchart regarding the operation of an electronic device for providing information to guide changing a filtering level, according to one embodiment. In the following embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel.

[0172] Referring to FIG. 12, in operation 1201, the processor (210) can identify whether the probability that a message is a spam message is within a probability range according to a filtering level set according to a category. For example, the processor (210) can obtain information regarding the probability that a message is a spam message through operation 1003 of FIG. 10. Based on obtaining information regarding the probability that a message is a spam message, the processor (210) can identify whether the probability that a message is a spam message is within a probability range according to a filtering level set according to a category.

[0173] According to one embodiment, if the probability that a message is a spam message is within a probability range according to a filtering level set according to a category, the processor (210) may perform operation 1204. For example, the processor (210) may maintain a filtering level set according to a category based on identifying that the probability that a message is a spam message is within a probability range according to a filtering level set according to a category. The processor (210) may maintain a filtering level set according to a category and identify the message as a spam message.

[0174] In operation 1202, if the probability that a message is a spam message is outside the probability range according to the filtering level set according to the category, the processor (210) can identify whether the probability that a message is a spam message is within a different probability range according to a different filtering level. For example, the processor (210) can identify whether the probability that a message is a spam message is within a different probability range according to a different filtering level based on identifying that the probability that a message is a spam message is outside the probability range according to the filtering level set according to the category. If the probability that a message is a spam message is identified as being outside the probability range according to the currently set filtering level, the processor (210) can identify whether the probability that a message is a spam message is within a different probability range according to a different filtering level.

[0175] According to one embodiment, the processor (210) may perform operation 1204 if the probability that a message is a spam message is not within a different probability range according to a different filtering level. For example, the processor (210) may maintain a filtering level set according to a category based on identifying that the probability that a message is a spam message is not within a different probability range according to a different filtering level.

[0176] For example, the current filtering level may be set to 'weak'. The processor (210) can identify that a message is outside the probability range according to the filtering level set to 'weak'. The processor (210) can identify the message as an allowed message when the filtering level is set to 'weak'. The processor (210) can identify whether the message is identified as a spam message when the filtering level is changed from 'weak' to 'strong'. The processor (210) can identify the message as an allowed message even when the filtering level is changed from 'weak' to 'strong'. The processor (210) can determine that the filtering level is set appropriately and maintain the filtering level set according to the category.

[0177] In operation 1203, if the probability that a message is a spam message falls within a different probability range according to a different filtering level, the processor (210) may provide information to guide changing the filtering level set according to the category to a different filtering level. For example, the processor (210) may provide information to guide changing the filtering level set according to the category to a different filtering level based on identifying that the probability that a message is a spam message falls within a different probability range according to a different filtering level. As an example, the processor (210) may display a screen through the display (240) to guide changing the filtering level set according to the category to a different filtering level.

[0178] For example, the current filtering level may be set to 'weak'. The processor (210) can identify that a message is outside the probability range according to the filtering level set to 'weak'. The processor (210) can identify the message as an allowed message when the filtering level is set to 'weak'. The processor (210) can identify whether the message is identified as a spam message when the filtering level is changed from 'weak' to 'strong'. The processor (210) can identify the message as a spam message when the filtering level is changed from 'weak' to 'strong'. Since the processor (210) can identify the message as a spam message when the filtering level is changed to 'strong', it can provide information to guide changing the filtering level set according to the category from 'weak' to 'strong'.

[0179] FIG. 13a illustrates a flowchart relating to the operation of an electronic device for providing information to guide changing a filtering level, according to one embodiment.

[0180] FIG. 13b illustrates an example of an input for changing a message identified as a spam message into an allowed message, according to one embodiment.

[0181] In the following embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel.

[0182] Referring to FIGS. 13a and 13b, in operation 1301 of FIG. 13a, the processor (210) can identify an input for changing a message identified as a spam message into an allowed message. For example, the processor (210) can display the screen (1350) of FIG. 13b through the display (240) to indicate a blocked message box. The screen (1350) may include an object (1351) representing a message identified as a spam message and an object (1352) for changing the message identified as a spam message into an allowed message. The processor (210) can identify an input for the object (1352) as an input for changing the message identified as a spam message into an allowed message.

[0183] In operation 1302, the processor (210) can identify whether the category of the message corresponds to one of a plurality of categories of spam messages based on an input for changing a message identified as a spam message into an allowed message. The processor (210) can identify the category of the message using an artificial intelligence model (280). The processor (210) can input the message (or the content of the message) into the artificial intelligence model (280). The processor (210) can identify whether the category of the message corresponds to one of a plurality of categories of spam messages based on the output of the artificial intelligence model (280).

[0184] According to one embodiment, the processor (210) may perform operation 1306 if the category of the message does not correspond to one of the plurality of categories for spam messages. For example, the processor (210) may maintain a first filtering level set according to the category based on identifying that the category of the message does not correspond to one of the plurality of categories for spam messages. The processor (210) may maintain the first filtering level set according to the category and change the message to an allowed message. According to an embodiment, the processor (210) may train a second artificial intelligence model (282) based on the message changed to an allowed message.

[0185] In operation 1303, if the category of the message corresponds to one of a plurality of categories regarding spam messages, the processor (210) can identify whether the probability that the message is a spam message is within a first probability range according to a first filtering level set according to the category. For example, based on identifying that the category of the message corresponds to one of a plurality of categories regarding spam messages, the processor (210) can identify whether the probability that the message is a spam message is within a first probability range according to a first filtering level set according to the category.

[0186] According to one embodiment, the processor (210) can identify the probability that the message is a spam message by using an artificial intelligence model (280). The processor (210) can identify a first filtering level according to the category of the message. The processor (210) can identify a first probability range according to the first filtering level. The processor (210) can identify whether the probability that the message is a spam message is within the first probability range. For example, the processor (210) can identify whether the message is identified as an allowed message based on a first filtering level set according to the current category.

[0187] According to one embodiment, if the probability that the message is a spam message is outside the first probability range, the processor (210) may perform operation 1306. Based on the fact that the probability that the message is a spam message is identified as being outside the second probability range, the processor (210) may maintain a first filtering level set according to the category. The processor (210) may maintain the first filtering level set according to the category and change the message to an allowed message. For example, the processor (210) may maintain the first filtering level set according to the category because the message is identified as an allowed message even when the currently set first filtering level is applied. According to an embodiment, the processor (210) may train a second artificial intelligence model (282) based on the message changed to an allowed message.

[0188] In operation 1304, if the probability that the message is a spam message is within a first probability range, it can identify whether the probability that the message is a spam message is outside a second probability range according to a second filtering level. For example, the processor (210) can identify whether the probability that the message is a spam message is outside a second probability range based on identifying that the probability that the message is a spam message is within a first probability range.

[0189] For example, the first filtering level may be higher than the second filtering level. For example, the first filtering level may be 'moderate' and the second filtering level may be 'weak'. For example, the first filtering level may be 'strong' and the second filtering level may be 'moderate' or 'weak'. The processor (210) may identify whether the probability that the message is a spam message is outside the second probability range in order to identify whether the message is identified as an allowed message when the filtering level is lowered. According to an embodiment, if the first filtering level is the lowest filtering level, the processor (210) may not perform operation 1304.

[0190] According to one embodiment, if the probability that the message is a spam message is within a second probability range, the processor (210) may perform operation 1306. For example, the processor (210) may maintain a first filtering level set according to a category based on identifying that the probability that the message is a spam message is within the second probability range. Since the message is identified as a spam message even when the filtering level is lowered, the processor (210) may maintain the first filtering level set according to a category and change the message from a spam message to an allowed message. The processor (210) may train a second artificial intelligence model (282) based on the message changed to an allowed message.

[0191] In operation 1305, if the probability that the message is a spam message is outside the second probability range, the processor (210) may provide information to guide changing the first filtering level set according to the category to the second filtering level. For example, the processor (210) may provide information to guide changing the first filtering level set according to the category to the second filtering level based on identifying that the probability that the message is a spam message is outside the second probability range. As an example, the processor (210) may display a screen through the display (240) to guide changing the first filtering level set according to the category to the second filtering level.

[0192] For example, if the filtering level is lowered, the message may be identified as an allowed message. Accordingly, the processor (210) may guide the first filtering level set according to the category to be changed to a second filtering level lower than the first filtering level. For example, the processor (210) may provide information to guide the lowering of the filtering level set according to the category so that the message may be identified as an allowed message.

[0193] FIG. 14a illustrates a flowchart relating to the operation of an electronic device for providing information to guide changing a filtering level, according to one embodiment.

[0194] FIG. 14b illustrates an example of an input for changing a message identified as an allowed message into a spam message, according to one embodiment.

[0195] In the following embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel.

[0196] Referring to FIGS. 14a and 14b, in operation 1401 of FIG. 14a, the processor (210) can identify an input for changing a message identified as an allowed message into a spam message. For example, the processor (210) can display the screen (1410) of FIG. 14b through the display (240) to represent a message box (or an allowed message box). The screen (1410) may include an object (1411) representing a message identified as an allowed message. The processor (210) can display the screen (1420) through the display (240) based on an input to the object (1411) (e.g., a long press input, a tap input, a drag input, or a double tap input). The processor (210) can display an object (1421) on the screen (1420) for performing actions related to the message. The object (1421) may include an element (1422) for changing the message, which is an allowed message, into a spam message. The processor (210) may identify the input for the element (1422) as an input for changing the message identified as a spam message into an allowed message.

[0197] In operation 1402, the processor (210) can identify whether the category of the message corresponds to one of a plurality of categories for spam messages based on an input for changing a message identified as an allowed message into a spam message. The processor (210) can identify the category of the message using an artificial intelligence model (280). The processor (210) can input the message (or the content of the message) into the artificial intelligence model (280). Based on the output of the artificial intelligence model (280), the processor (210) can identify whether the category of the message corresponds to one of a plurality of categories for spam messages. Operation 1402 may correspond to operation 1302 of FIG. 13a.

[0198] According to one embodiment, the processor (210) may perform operation 1406 if the category of the message does not correspond to one of the plurality of categories for spam messages. For example, the processor (210) may maintain a first filtering level set according to the category based on identifying that the category of the message does not correspond to one of the plurality of categories for spam messages. The processor (210) may maintain the first filtering level set according to the category and change the message to a spam message. According to an embodiment, the processor (210) may train a second artificial intelligence model (282) based on the message changed to a spam message.

[0199] In operation 1403, if the category of the message corresponds to one of a plurality of categories regarding spam messages, the processor (210) can identify whether the probability that the message is a spam message is within a first probability range according to a first filtering level set according to the category. For example, based on identifying that the category of the message corresponds to one of a plurality of categories regarding spam messages, the processor (210) can identify whether the probability that the message is a spam message is within a first probability range according to a first filtering level set according to the category. Operation 1403 may correspond to operation 1303 of FIG. 13a.

[0200] According to one embodiment, the processor (210) can identify the probability that the message is a spam message by using an artificial intelligence model (280). The processor (210) can identify a first filtering level according to the category of the message. The processor (210) can identify a first probability range according to the first filtering level. The processor (210) can identify whether the probability that the message is a spam message is within the first probability range. For example, the processor (210) can identify whether the message is identified as a spam message based on a first filtering level set according to the current category.

[0201] According to one embodiment, if the probability that the message is a spam message is within a first probability range, the processor (210) may perform operation 1406. Based on the fact that the probability that the message is a spam message is identified as being within the first probability range, the processor (210) may maintain a first filtering level set according to a category. The processor (210) may maintain the first filtering level set according to a category and change the message to a spam message. For example, the processor (210) may maintain the first filtering level set according to a category because the message is identified as a spam message even when the currently set first filtering level is applied. According to an embodiment, the processor (210) may train a second artificial intelligence model (282) based on the message changed to a spam message.

[0202] In operation 1404, if the probability that the message is a spam message is outside the first probability range, it can identify whether the probability that the message is a spam message is within the third probability range according to the third filtering level. For example, the processor (210) can identify whether the probability that the message is a spam message is within the third probability range based on identifying that the probability that the message is a spam message is outside the first probability range.

[0203] For example, the first filtering level may be lower than the third filtering level. For example, the first filtering level may be 'moderate' and the third filtering level may be 'strong'. For example, the first filtering level may be 'weak' and the third filtering level may be 'moderate' or 'strong'. The processor (210) may identify whether the probability that the message is a spam message is within the third probability range in order to identify whether the message is identified as a spam message when the filtering level increases. According to an embodiment, if the first filtering level is the highest filtering level, the processor (210) may not perform operation 1404.

[0204] According to one embodiment, if the probability that the message is a spam message is outside the third probability range, the processor (210) may perform operation 1406. For example, the processor (210) may maintain a first filtering level set according to the category based on identifying that the probability that the message is a spam message is outside the third probability range. Since the message is identified as an allowed message even when the filtering level is raised, the processor (210) may maintain the first filtering level set according to the category and change the message from an allowed message to a spam message. The processor (210) may train a second artificial intelligence model (282) based on the message changed to a spam message.

[0205] In operation 1405, if the probability that the message is a spam message is within a third probability range, the processor (210) may provide information to guide changing the first filtering level set according to the category to the third filtering level. For example, the processor (210) may provide information to guide changing the first filtering level set according to the category to the third filtering level based on identifying that the probability that the message is a spam message is within the third probability range. As an example, the processor (210) may display a screen through the display (240) to guide changing the first filtering level set according to the category to the third filtering level.

[0206] For example, if the filtering level is increased, the message may be identified as a spam message. Therefore, the processor (210) may guide the change of the first filtering level set according to the category to a third filtering level higher than the first filtering level. For example, the processor (210) may provide information to guide the increase of the filtering level set according to the category so that the message may be identified as a spam message.

[0207] FIG. 15 illustrates a flowchart regarding the operation of an electronic device for providing information to guide changing a filtering level according to one embodiment. In the following embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel.

[0208] Referring to FIG. 15, in operation 1501, the processor (210) can obtain a first probability that the message is a spam message using a first artificial intelligence model (281). Operation 1501 may correspond to operation 1001 of FIG. 10.

[0209] In operation 1502, the processor (210) can obtain a second probability that the message is a spam message using a second artificial intelligence model (282). Operation 1502 may correspond to operation 1002 of FIG. 10.

[0210] In operation 1503, the processor (210) can obtain information regarding the probability (or final probability) that the message is a spam message. Operation 1503 may correspond to operation 1003 of FIG. 10.

[0211] In operation 1504, the processor (210) can identify whether the second probability is within the probability range according to the filtering level and whether the probability (or final probability) that the message is a spam message is outside the probability range according to the filtering level.

[0212] In operation 1506, if the second probability is within the probability range according to the filtering level and the probability (or final probability) that the message is a spam message is outside the probability range according to the filtering level, the processor (210) may provide information to guide increasing the filtering level. For example, the processor (210) may provide information to guide increasing the filtering level based on identifying that the second probability is within the probability range according to the filtering level and the probability (or final probability) that the message is a spam message is outside the probability range according to the filtering level.

[0213] The processor (210) can identify that the second probability obtained through the second artificial intelligence model (282) is within the probability range according to the filtering level. The processor (210) can identify the message as a spam message using the second artificial intelligence model (282). The processor (210) can identify that the probability (or final probability) that the message is a spam message, obtained through the first artificial intelligence model (281) and the second artificial intelligence model (282), is outside the probability range according to the filtering level. The processor (210) can identify the message as an allowed message using the first artificial intelligence model (281) and the second artificial intelligence model (282).

[0214] The processor (210) can provide information to guide increasing the filtering level when the second artificial intelligence model (282) is used, because the message is identified as a spam message. For example, the processor (210) can display a screen through the display (240) to guide increasing the filtering level.

[0215] In operation 1505, if the second probability is within the probability range according to the filtering level and the probability that the message is a spam message (or final probability) is not outside the probability range according to the filtering level, the processor (210) can identify whether the second probability is outside the probability range according to the filtering level and the probability that the message is a spam message (or final probability) is within the probability range according to the filtering level. For example, based on identifying that the second probability is within the probability range according to the filtering level and the probability that the message is a spam message (or final probability) is not outside the probability range according to the filtering level, the processor (210) can identify whether the second probability is outside the probability range according to the filtering level and the probability that the message is a spam message (or final probability) is within the probability range according to the filtering level.

[0216] In operation 1507, if the second probability is outside the probability range according to the filtering level and the probability that the message is a spam message (or final probability) is within the probability range according to the filtering level, the processor (210) may provide information to guide reducing the filtering level. For example, the processor (210) may provide information to guide reducing the filtering level based on identifying that the second probability is outside the probability range according to the filtering level and the probability that the message is a spam message (or final probability) is within the probability range according to the filtering level.

[0217] The processor (210) can identify that the second probability obtained through the second artificial intelligence model (282) is outside the probability range according to the filtering level. The processor (210) can identify the message as an allowed message using the second artificial intelligence model (282). The processor (210) can identify that the probability (or final probability) that the message is a spam message, obtained through the first artificial intelligence model (281) and the second artificial intelligence model (282), is within the probability range according to the filtering level. The processor (210) can identify the message as a spam message using the first artificial intelligence model (281) and the second artificial intelligence model (282).

[0218] The processor (210) can provide information to guide reducing the filtering level because the message is identified as an allowed message when the second artificial intelligence model (282) is used. For example, the processor (210) can display a screen through the display (240) to guide reducing the filtering level.

[0219] In operation 1508, if the second probability is outside the probability range according to the filtering level and the probability (or final probability) that the message is a spam message is not within the probability range according to the filtering level, the processor (210) may maintain the filtering level. For example, the processor (210) may identify that the first result regarding whether the message is a spam message, identified using both the first artificial intelligence model (281) and the second artificial intelligence model (282), and the second result regarding whether the message is a spam message, identified using the second artificial intelligence model (282), are identical. Based on identifying that the first result and the second result are identical, the processor (210) may maintain the currently set filtering level for the corresponding category.

[0220] According to one embodiment, the electronic device may include a communication circuit, a memory including one or more storage media for storing instructions, and at least one processor including a processing circuit. When the instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to receive a message from an external electronic device using the communication circuit, identify the message as an allowed message using the content of the message and the sender number of the message, identify a category of the message and a filtering level set according to the category based on the content of the message identified as the allowed message, obtain information regarding the probability that the message is a spam message distinct from the allowed message, identify the message as the spam message based on identifying that the probability is within the probability range according to the filtering level, and maintain the message as the allowed message based on identifying that the probability is outside the probability range according to the filtering level.

[0221] For example, the electronic device may include a display. The instructions may cause the electronic device to display a screen through the display to guide changing the filtering level set according to the category to the other filtering level, based on identifying that the probability is within a different probability range according to the other filtering level that is distinct from the filtering level, when executed individually or collectively by the at least one processor.

[0222] For example, the memory may include a first artificial intelligence model for obtaining a first probability that the message is the spam message, and a second artificial intelligence model for obtaining a second probability that the message is the spam message. The second artificial intelligence model may be trained based on a plurality of messages stored in the memory.

[0223] For example, the above instructions may cause the electronic device to obtain information regarding the probability that the message is the spam message, based on at least one of the first probability and the second probability, when executed individually or collectively by the at least one processor.

[0224] For example, the above instructions may cause the electronic device to identify the first probability as the probability that the message is the spam message, based on identifying that the number of the plurality of messages stored in the memory is less than a reference number when executed individually or collectively by the at least one processor.

[0225] For example, the above instructions may cause the electronic device to obtain information regarding the reliability of the second artificial intelligence model based on identifying that the number of the plurality of messages stored in the memory is greater than or equal to a reference number when executed individually or collectively by the at least one processor, and to determine weights for each of the first probability and the second probability based on the information regarding the reliability of the second artificial intelligence model.

[0226] For example, when the instructions are executed individually or collectively by the at least one processor, the electronic device may obtain information regarding the probability that the message is the spam message based on the first probability corrected according to a first weight and the second probability corrected according to a second weight.

[0227] For example, the above instructions may cause the electronic device to input test messages into the second artificial intelligence model when executed individually or collectively by the at least one processor, identify at least one of the test messages as the spam message based on the output of the second artificial intelligence model, and identify the information regarding the reliability of the second artificial intelligence model based on the at least one test message identified as the spam message.

[0228] For example, the above instructions may cause the electronic device to provide information to guide increasing the filtering level based on identifying that the second probability is within the probability range according to the filtering level and that the probability is outside the probability range according to the filtering level when executed individually or collectively by the at least one processor.

[0229] For example, the above instructions may cause the electronic device to provide information to guide reducing the filtering level based on identifying that the second probability is outside the probability range according to the filtering level and the probability is within the probability range according to the filtering level when executed individually or collectively by the at least one processor.

[0230] For example, when the above instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to identify an input for changing the message identified as the spam message from the spam message to the allowed message, and to train the second artificial intelligence model based on the message changed to the allowed message.

[0231] For example, when the above instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to identify an input for changing the message identified as the allowed message from the allowed message to the spam message, and to train the second artificial intelligence model based on the message changed to the spam message.

[0232] For example, the above instructions may cause the electronic device to identify the message as the allowed message based on identifying that, when executed individually or collectively by the at least one processor, at least one blocked word is not included in the content of the message and the sender number of the message is distinguishable from at least one blocked sender number.

[0233] For example, the above instructions may cause the electronic device to identify the message as the allowed message based on identifying the transmission address of the message and identifying that the transmission address of the message corresponds to one of the registered transmission addresses when executed individually or collectively by the at least one processor.

[0234] For example, the above instructions may cause the electronic device to identify the message as the allowed message based on identifying that the sender number of the message is included in the call history information of the electronic device when executed individually or collectively by the at least one processor.

[0235] According to one embodiment, a method performed in an electronic device may include: receiving a message from an external electronic device using a communication circuit of the electronic device; identifying the message as an allowed message using the content of the message and the sender number of the message; identifying a category of the message and a filtering level set according to the category based on the content of the message identified as the allowed message, and obtaining information regarding the probability that the message is a spam message that is distinguished from the allowed message; identifying the message as the spam message based on identifying that the probability is within a probability range according to the filtering level; and maintaining the message as the allowed message based on identifying that the probability is outside the probability range according to the filtering level.

[0236] For example, the above method may include an operation of displaying a screen through the display of the electronic device to guide changing the filtering level set according to the category to the other filtering level, based on identifying that the probability is within a different probability range according to another filtering level distinct from the filtering level.

[0237] For example, the above method may include the operation of obtaining a first probability that the message is the spam message using a first artificial intelligence model, the operation of obtaining a second probability that the message is the spam message using a second artificial intelligence model trained based on a plurality of messages stored in the memory of the electronic device, and the operation of obtaining information regarding the probability that the message is the spam message based on at least one of the first probability and the second probability.

[0238] For example, the above method may include an operation of identifying the message as the allowed message based on identifying that at least one of one or more blocked words is not included in the content of the message and that the sender number of the message is distinguishable from one or more blocked sender numbers.

[0239] According to one embodiment, a non-transient computer-readable storage medium may store one or more programs. The one or more programs may include instructions that, when executed by at least one processor of an electronic device having a communication circuit, receive a message from an external electronic device, identify the message as an allowed message using the content of the message and the sender number of the message, identify a category of the message and a filtering level set according to the category based on the content of the message, obtain information regarding the probability that the message is a spam message that is distinguished from the allowed message, identify the message as the spam message based on identifying that the probability is within the probability range according to the filtering level, and cause the electronic device to maintain the message as the allowed message based on identifying that the probability is outside the probability range according to the filtering level.

[0240] According to one embodiment, the electronic device may include a communication circuit, a memory comprising one or more storage media for storing instructions, and at least one processor comprising a processing circuit. When the instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to receive a message from an external electronic device using the communication circuit, identify the message as an allowed message using the content of the message and the sender number of the message, identify whether the sender address of the message identified as the allowed message corresponds to one of the registered sender addresses, perform spam message filtering using an artificial intelligence model on the message based on the sender address of the message which is distinct from the registered sender addresses, and maintain the message as the allowed message based on the sender address of the message which corresponds to one of the registered sender addresses.

[0241] For example, when the above instructions are executed individually or collectively by the at least one processor, the electronic device may obtain profile information through a server based on the transmission address and identify whether the transmission address of the message corresponds to one of the registered transmission addresses based on the profile information.

[0242] For example, when the above instructions are executed individually or collectively by the at least one processor, they may cause the electronic device to identify a category of the message and a filtering level set according to the category, and to perform the filtering of spam messages through the artificial intelligence model for the message according to the category and the filtering level.

[0243] According to the embodiments described above, the electronic device may perform primary filtering of spam messages based on blocked words and / or blocked sender numbers. If, based on the primary filtering, the electronic device identifies a message as an allowed message, it may perform secondary filtering using an artificial intelligence model (e.g., artificial intelligence model (280)). Based on the primary and secondary filtering, spam messages may be accurately determined. According to the embodiments described above, the electronic device may identify the category of a message and set a filtering level (or blocking strength) according to the category. The electronic device may identify whether a message is a spam message based on the set category. According to the embodiments described above, the electronic device may identify a message as either a spam message or an allowed message by using at least one of the first artificial intelligence model and the second artificial intelligence model. The electronic device may provide more accurate results by training the second artificial intelligence model based on the transmission and reception history of the message.

[0244] The electronic device according to the embodiments disclosed in this document may be of various forms. The electronic device may include, for example, a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a consumer electronics device. The electronic device according to the embodiments of this document is not limited to the aforementioned devices.

[0245] The embodiments of this document and the terms used therein are not intended to limit the technical features described in this document to specific embodiments, and should be understood to include various modifications, equivalents, or substitutions of said embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of said items unless the relevant context clearly indicates otherwise. In this document, each of phrases such as "A or B," "at least one of A and B," "at least one of A or B," "A, B or C," "at least one of A, B and C," and "at least one of A, B, or C" may include any one of the items listed together in the corresponding phrase, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used simply to distinguish a component from another component and do not limit the components in any other aspect (e.g., importance or order). Where any component (e.g., the first) is referred to as "coupled" or "connected" to another component (e.g., the second), with or without the terms "functionally" or "communicationally," it means that said component may be connected to said other component directly (e.g., via a wire), wirelessly, or through a third component.

[0246] In one embodiment of this document, the term “module” used may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit, for example. A module may be a component formed integrally, or a minimum unit of said component or a part thereof that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0247] One embodiment of the present document may be implemented as software (e.g., program (140)) comprising one or more instructions stored in a storage medium (e.g., internal memory (136) or external memory (138)) readable by a machine (e.g., electronic device (101)). For example, a processor (e.g., processor (120)) of the machine (e.g., electronic device (101)) may call at least one of the one or more instructions stored in the storage medium and execute it. This enables the machine to be operated to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code that can be executed by an interpreter. The storage medium readable by the machine may be provided in the form of a non-transitory storage medium. Here, 'non-temporary' simply means that the storage medium is a tangible device and does not contain a signal (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily.

[0248] According to one embodiment, the method according to the embodiments disclosed herein may be provided by being included in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., CD-ROM (compact disc read-only memory)), or distributed online (e.g., download or upload) through an application store (e.g., Play Store™) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0249] According to one embodiment, each component (e.g., module or program) of the components described above may include a singular or multiple entities, and some of the multiple entities may be separated and placed in other components. According to one embodiment, one or more of the components or operations among the aforementioned components may be omitted, or one or more other components or operations may be added. Generally or additionally, multiple components (e.g., module or program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the multiple components in the same or similar manner as those performed by the corresponding component among the multiple components prior to integration. According to one embodiment, operations performed by the module, program, or other components may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. In an electronic device, Communication circuit; Memory for storing instructions and including one or more storage media; and It includes at least one processor including a processing circuit, and When the above instructions are executed individually or collectively by the at least one processor, Using the above communication circuit, a message is received from an external electronic device, and Using the content of the above message and the sender number of the above message, the above message is identified as an allowed message, and Based on the content of the message identified as the allowed message: Identify the category regarding the above message and the filtering level set according to the above category, and Information regarding the probability that the above message is a spam message distinguishable from the above allowed message is obtained, and Based on identifying that the above probability is within the probability range according to the filtering level, the message is identified as the spam message, and Causing the electronic device to maintain the message as the allowed message based on identifying that the above probability is outside the probability range according to the filtering level, Electronic device.

2. In claim 1, the electronic device is, Includes more displays, When the above instructions are executed individually or collectively by the at least one processor, The electronic device causes to display, through the display, a screen to guide changing the filtering level set according to the category to the other filtering level, based on identifying that the above probability is within a different probability range according to another filtering level distinct from the above filtering level. Electronic device.

3. In claim 1, the memory is, A first artificial intelligence model for obtaining a first probability that the above message is the above spam message; It includes a second artificial intelligence model for obtaining a second probability that the above message is the spam message, and The above second artificial intelligence model is, Training based on a plurality of messages stored in the above memory, Electronic device.

4. In claim 3, when the instructions are executed individually or collectively by the at least one processor, Causing the electronic device to obtain information regarding the probability that the message is the spam message based on at least one of the first probability and the second probability. Electronic device.

5. In claim 4, when the instructions are executed individually or collectively by the at least one processor, Based on identifying that the number of the plurality of messages stored in the memory is less than a reference number, the electronic device causes the first probability to be identified as the probability that the message is the spam message. Electronic device.

6. In claim 5, when the instructions are executed individually or collectively by the at least one processor, Based on identifying that the number of the plurality of messages stored in the memory is greater than or equal to a reference number, information regarding the reliability of the second artificial intelligence model is obtained, and Causing the electronic device to determine weights for each of the first probability and the second probability based on the information regarding the reliability of the second artificial intelligence model. Electronic device.

7. In claim 6, when the instructions are executed individually or collectively by the at least one processor, An electronic device that causes to obtain information regarding the probability that the message is the spam message based on the first probability corrected according to the first weight and the second probability corrected according to the second weight, Electronic device.

8. In claim 6, when the instructions are executed individually or collectively by the at least one processor, Input test messages into the above-mentioned second artificial intelligence model, and Based on the output of the second artificial intelligence model, at least one of the test messages is identified as the spam message, and Causing the electronic device to identify the information regarding the reliability of the second artificial intelligence model based on at least one test message identified as the spam message, Electronic device.

9. In claim 4, when the instructions are executed individually or collectively by the at least one processor, Causing the electronic device to provide information for guiding to increase the filtering level based on identifying that the second probability is within the probability range according to the filtering level and that the probability is outside the probability range according to the filtering level. Electronic device.

10. In claim 9, when the instructions are executed individually or collectively by the at least one processor, Causing the electronic device to provide information for guiding to reduce the filtering level based on identifying that the second probability is outside the probability range according to the filtering level and the probability is within the probability range according to the filtering level. Electronic device.

11. In claim 3, when the instructions are executed individually or collectively by the at least one processor, Identifying an input for changing the message identified as the spam message from the spam message to the allowed message, Causing the electronic device to train the second artificial intelligence model based on the message changed to the above allowed message, Electronic device.

12. In claim 3, when the instructions are executed individually or collectively by the at least one processor, Identifying an input for changing the message identified as the allowed message from the allowed message to the spam message, and Causing the electronic device to train the second artificial intelligence model based on the message changed to the spam message, Electronic device.

13. In claim 1, when the instructions are executed individually or collectively by the at least one processor, An electronic device that causes the message to be identified as the allowed message based on identifying that at least one blocked word is not included in the content of the message and that the sender number of the message is distinguishable from at least one blocked sender number. Electronic device.

14. In a method performed in an electronic device, The operation of receiving a message from an external electronic device using the communication circuit of the above electronic device; An operation to identify the message as an allowed message using the content of the message and the sender number of the message; Based on the content of the message identified as the allowed message: Identify the category regarding the above message and the filtering level set according to the above category, and An operation to obtain information regarding the probability that the above message is a spam message distinguishable from the above allowed message; An operation of identifying the message as the spam message based on identifying that the probability is within the probability range according to the filtering level; and The operation of maintaining the message as the allowed message based on identifying that the probability is outside the probability range according to the filtering level, method.

15. A non-transient computer-readable storage medium storing one or more programs, wherein the one or more programs, when executed by at least one processor of an electronic device having a communication circuit, Receive a message from an external electronic device, and Using the content of the above message and the sender number of the above message, the above message is identified as an allowed message, and Based on the content of the message identified as the allowed message: Identify the category regarding the above message and the filtering level set according to the above category, and Information regarding the probability that the above message is a spam message distinguishable from the above allowed message is obtained, and Based on identifying that the above probability is within the probability range according to the filtering level, the message is identified as the spam message, and Instructions comprising causing the electronic device to maintain the message as the allowed message based on identifying that the probability is outside the probability range according to the filtering level, Non-transient computer-readable storage media.

Images