Electronic device and character recognition method using same

Abstract

According to various embodiments, an electronic device may comprise: a touch screen display; a processor; and a memory for storing instructions. The instructions, when executed by the processor, may cause the electronic device to: detect at least two reference points for a user input on the basis of the user input through the touch screen display; determine a plurality of candidate lines on the basis of the detected at least two reference points; determine an optimal candidate line satisfying a candidate line selection condition among the plurality of candidate lines; divide at least two character regions with reference to a division point included in the optimal candidate line; and identify a first character corresponding to a first character region and a second character corresponding to a second character region among the at least two character regions. Various other embodiments may be possible.

Description

Electronic device and method for recognizing characters using the same

[0001] An embodiment of the present disclosure relates to an electronic device and a character recognition method using the same.

[0002] With the recent advancement of digital technology, various types of electronic devices (user devices) capable of communication and personal information processing (e.g., mobile terminals, personal digital assistants (PDAs), electronic organizers, smartphones, tablets, personal computers (PCs), etc.) are being released. As the functions provided by electronic devices diversify and their widespread use in daily life increases, the amount of time spent using them is gradually increasing. Electronic devices can be designed to be easily portable, with a certain size and weight, and one side of the device can be implemented as a touchscreen display.

[0003] An electronic device can detect user input (e.g., touch input, pen input, stylus pen input, finger input, gesture input, and / or segment input) through a touchscreen display, and can perform an input command based on the detected user input. For example, when a drawing input using a pen is detected, the electronic device can generate points, lines, and images corresponding to the drawing input, and display the generated points, lines, and images through the touchscreen display. The electronic device can generate a drawing object based on the drawing input.

[0004] According to one embodiment, when a segment input occurs, the electronic device can monitor a start point when the segment input starts, an end point when the segment input ends, and / or a movement path (e.g., movement, movement gesture) from the start point to the end point of the segment input. The electronic device can determine whether the segment input corresponds to a set character (e.g., letter, text), and if the segment input corresponds to the set input, the electronic device can generate characters and letters corresponding to the segment input. The electronic device can extract characters corresponding to the segment input and provide them to the user.

[0005] The above information may be provided as background art to aid in understanding the present disclosure. No claim or determination is made as to whether any of the above-described matters constitute prior art related to the present disclosure.

[0006] Electronic devices can recognize characters (e.g., letters, characters) based on segments according to a user's touch input (e.g., finger input, pen input, stylus pen input, gesture input). However, since each user has a different handwriting style (e.g., handwriting shape, handwriting form), it may be difficult to recognize a specific character corresponding to a specific segment. Because there is a high degree of freedom in handwriting, it may be difficult to recognize a specific character according to the user's intention. For example, if multiple characters are written with a single stroke, it may be difficult to distinguish and recognize each of the multiple characters as a single character.

[0007] According to one embodiment, when recognizing multiple characters written with a single stroke, the electronic device can identify a connecting line connecting each character and determine a dividing point included in the connecting line. Based on the determined dividing point, the electronic device can provide a method for recognizing multiple characters by dividing them into individual characters.

[0008] The technical tasks to be achieved in this document are not limited to the technical tasks mentioned above, and other technical tasks not mentioned will be clearly understood by those with ordinary skill in the technical field to which this document pertains from the description below.

[0009] According to one embodiment, an electronic device may include a touchscreen display, a processor, and a memory storing instructions. When the instructions are executed by the processor, the electronic device may detect at least two reference points (e.g., points satisfying reference point conditions among a plurality of inflection points) for a user input through the touchscreen display based on the user input, determine a plurality of candidate lines based on the detected at least two reference points, determine an optimal candidate line (e.g., an optimal segment) satisfying a candidate line selection condition (e.g., a length greater than or equal to a certain length, satisfying AR of a character, and verifying reliability) among the plurality of candidate lines, divide at least two character areas based on a dividing point included in the optimal candidate line, and identify a first character corresponding to a first character area and a second character corresponding to a second character area among the at least two character areas.

[0010] According to one embodiment, a method for recognizing characters in an electronic device may include an operation of detecting at least two reference points for a user input through a touch screen display, an operation of determining a plurality of candidate lines based on the detected at least two reference points, an operation of determining an optimal candidate line satisfying a candidate line selection condition among the plurality of candidate lines, an operation of dividing at least two character areas based on a dividing point included in the optimal candidate line, and an operation of confirming a first character corresponding to a first character area and a second character corresponding to a second character area among the at least two character areas.

[0011] According to one embodiment, a non-transitory computer-readable storage medium (or, computer program product) storing one or more programs for performing a character recognition method of an electronic device may be described. According to one embodiment, the one or more programs may include instructions that, when executed by a processor of the electronic device, perform an operation of detecting at least two reference points for a user input through a touchscreen display (160), an operation of determining a plurality of candidate lines based on the detected at least two reference points, an operation of determining an optimal candidate line satisfying a candidate line selection condition among the plurality of candidate lines, an operation of dividing at least two character areas based on a dividing point included in the optimal candidate line, and an operation of identifying a first character corresponding to a first character area and a second character corresponding to a second character area among the at least two character areas.

[0012] According to one embodiment, an electronic device can detect a user input (e.g., touch input, pen input, stylus pen input, finger input, gesture input, and / or segment input) via a touchscreen display, and recognize at least one letter based on the detected user input. For example, the electronic device can recognize a connecting line connecting each letter among a plurality of letters written with a single stroke (e.g., stroke), and can effectively extract a dividing point for distinguishing each letter based on the connecting line. According to one embodiment, the electronic device can determine an optimal dividing point for distinguishing each letter among a plurality of dividing points included in the connecting line, and can recognize a first letter and a second letter based on the optimal dividing point.

[0013] According to one embodiment, an electronic device may determine at least one word using a first letter and a second letter recognized based on an optimal segmentation point. Based on the determined at least one word, the electronic device may identify a first word written before the at least one word and a second word written after the at least one word. Based on a combination of the first word, the at least one word, and the second word, the electronic device may determine a first candidate word corresponding to the at least one word. According to one embodiment, when recognizing a letter according to a user input, the electronic device may identify a first word located before a specific word and a second word located after the specific word, and may provide a method for recognizing the specific word by considering a combination among the first word, the specific word, and / or the second word. By considering the first word located before the specific word and the second word located after the specific word based on the specific word, the recognition accuracy for the specific word may be improved. According to one embodiment, when a user inputs text using an electronic device, the accuracy of character recognition can be improved, and the user's convenience in using the electronic device can be enhanced. By identifying the preceding and following words of a specific word and then recognizing the specific word, the recognition accuracy for the specific word can be improved.

[0014] The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and other effects that are not mentioned can be clearly understood by a person having ordinary skill in the art to which the present disclosure belongs from the description below.

[0015] In connection with the description of the drawings, the same or similar reference numerals may be used for the same or similar components.

[0016] FIG. 1 is a block diagram of an electronic device within a network environment according to one embodiment of the present disclosure.

[0017] FIG. 2 is a diagram illustrating an embodiment of recognizing letters corresponding to user input according to one embodiment of the present disclosure.

[0018] FIG. 3 is a block diagram of an electronic device according to one embodiment of the present disclosure.

[0019] FIG. 4 is a flowchart illustrating a character recognition method according to one embodiment of the present disclosure.

[0020] FIG. 5A is an example diagram in which at least two reference points are detected based on user input according to one embodiment of the present disclosure.

[0021] FIG. 5b is an exemplary diagram illustrating various pattern shapes for detecting a candidate line according to one embodiment of the present disclosure.

[0022] FIG. 5c is an example diagram of detecting a set pattern shape based on a sentence according to a user input according to one embodiment of the present disclosure and confirming a candidate line corresponding to the detected pattern shape.

[0023] FIG. 5d is a first graph showing a length condition of a candidate line according to a user input according to one embodiment of the present disclosure.

[0024] FIG. 5e is a second graph showing a condition of a horizontal-vertical ratio (e.g., aspect ratio) for a character area divided based on a dividing point included in a candidate line according to one embodiment of the present disclosure.

[0025] FIG. 5f is an exemplary diagram showing size conditions for a letter area divided based on a dividing point included in a candidate line according to one embodiment of the present disclosure.

[0026] FIG. 6 is an exemplary diagram showing an optimal candidate line satisfying a candidate line selection condition according to one embodiment of the present disclosure, and dividing at least two character areas based on a dividing point included in the optimal candidate line.

[0027] FIG. 7 is an example diagram of calculating a reliability corresponding to a user input according to one embodiment of the present disclosure and recognizing a character based on the calculated reliability.

[0028] FIG. 8 is an example diagram showing different letters recognized based on segmentation points included in an optimal candidate line according to one embodiment of the present disclosure.

[0029] FIG. 9A is an example diagram for determining a cluster based on coordinate information (e.g., xy coordinate information) corresponding to a user input according to one embodiment of the present disclosure.

[0030] FIG. 9b is an example diagram for distinguishing a first cluster and a second cluster based on coordinate information (e.g., xz coordinate information) corresponding to a user input according to one embodiment of the present disclosure.

[0031] FIG. 9c is an example diagram for recognizing a first letter corresponding to a first cluster and a second letter corresponding to a second cluster according to one embodiment of the present disclosure.

[0032] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings so that those skilled in the art can easily implement the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In connection with 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 conciseness.

[0033] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100) according to various embodiments. Referring to FIG. 1, in the network environment (100), the electronic device (101) may communicate with the electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of the electronic device (104) or the server (108) via 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) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

[0034] The processor (120) may, for example, execute software (e.g., a program (140)) to control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) and perform various data processing or calculations. According to one embodiment, as at least a part of the data processing or calculations, the processor (120) may store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in a volatile memory (132), process the commands or data stored in the volatile memory (132), and store result data in a 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 a secondary processor (123) (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor)) that can operate independently or together therewith. For example, if the electronic device (101) includes a main processor (121) and a secondary processor (123), the secondary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a specified function. The secondary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0035] The auxiliary processor (123) may control at least a portion of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), for example, 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. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, in the electronic device (101) itself where artificial intelligence is performed, or can be performed through a separate server (e.g., server (108)). The learning algorithm can 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 can include multiple artificial neural network layers.The artificial neural network may be one of 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, or alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

[0036] The memory (130) can store various data used by at least one component (e.g., processor (120) or sensor module (176)) of the electronic device (101). The data can include, for example, software (e.g., program (140)) and input data or output data for commands related thereto. The memory (130) can include volatile memory (132) or non-volatile memory (134).

[0037] The program (140) may be stored as software in the memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0038] The input module (150) can receive commands or data to be used in a component of the electronic device (101) (e.g., a processor (120)) from an external source (e.g., a user) of the electronic device (101). The input module (150) can include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0039] The audio output module (155) can output audio signals to the outside of the electronic device (101). The audio output module (155) can include, for example, a speaker or a receiver. The speaker can be used for general purposes, such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. In one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0040] The display module (160) can visually provide information to an external party (e.g., a 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 the device. In 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 a force generated by the touch.

[0041] The audio module (170) can convert sound into an electrical signal, or vice versa, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150), output sound through the sound output module (155), or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (101).

[0042] The sensor module (176) can detect the operating status (e.g., power or temperature) of the electronic device (101) or the external environmental status (e.g., user status) and generate an electrical signal or data value corresponding to the detected status. According to one embodiment, the sensor module (176) can include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0043] The interface (177) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (101) with an external electronic device (e.g., the electronic device (102)). In 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.

[0044] The connection terminal (178) may include a connector through which the electronic device (101) may 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).

[0045] A haptic module (179) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. In one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0046] The camera module (180) can capture still images and videos. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0047] 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 a part of a power management integrated circuit (PMIC).

[0048] A battery (189) may power at least one component of the electronic device (101). In one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0049] The communication module (190) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the 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 operate independently from the processor (120) (e.g., application processor) and may include one or more communication processors that 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., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (194) (e.g., a local area network (LAN) communication module, or a power line communication module). Among these communication modules, the corresponding communication module can communicate with an external electronic device (104) via a first network (198) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (199) (e.g., a long-range communication network such as 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 can 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 verify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) by using subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (196).

[0050] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) can support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), 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), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the 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 eMBB realization, a loss coverage (e.g., 164 dB or less) for mMTC realization, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for URLLC realization.

[0051] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (197) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In 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 the first network (198) or the second network (199), may be selected from the plurality of antennas by, for example, the 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. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (197).

[0052] In one embodiment, the antenna module (197) may form a mmWave antenna module. In one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high-frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) disposed on or adjacent a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high-frequency band.

[0053] At least some of the above components can be interconnected and exchange signals (e.g., commands or data) with each other via a communication method between peripheral devices (e.g., a bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)).

[0054] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) via 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 executed in the electronic device (101) may be executed in one or more of the external electronic devices (102, 104, or 108). For example, when the electronic device (101) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (101) may, instead of or in addition to executing the function or service itself, request one or more external electronic devices to perform the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or an 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 process the result as is or additionally and provide it as at least a portion of a response to the request. For this purpose, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used, for example. The electronic device (101) may provide an ultra-low latency service by using distributed computing or mobile edge computing, for example. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server utilizing machine learning and / or a neural network. According to one embodiment, the external electronic device (104) or the server (108) may be included in 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.

[0055] FIG. 2 is a diagram illustrating an embodiment of recognizing letters corresponding to user input according to one embodiment of the present disclosure.

[0056] The electronic device (101) of FIG. 2 may be at least partially similar to the electronic device (101) of FIG. 1, or may further include other embodiments of the electronic device (101). In one embodiment, the electronic device (101) may include at least partially similar components to the electronic device (101) of FIG. 1.

[0057] According to one embodiment, the electronic device (101) can detect a user input (e.g., touch input, pen input, stylus pen input, finger input, gesture input, and / or segment input) through a display (e.g., the display module (160) of FIG. 1, a touchscreen display) and generate a drawing object (201) corresponding to the user input. For example, the drawing object (201) can include a point, a line, and a specific shape drawn with the line (e.g., a letter, a character, a text). The drawing object (201) can be composed of one stroke, and one stroke can be composed of multiple points. For example, a stroke can be divided into multiple sub-regions based on an inflection point (e.g., a point where the direction of curvature changes according to a user input) among the multiple points. The divided sub-regions can be defined as segments.

[0058] Referring to FIG. 2, the electronic device (101) can recognize an input of a stylus pen (210) corresponding to a user input through a touchscreen display (160), and display a drawing object (201) generated based on the input of the stylus pen (210). For example, when a user inputs “Take a note on the off screen!” on the touchscreen display (160) using a stylus pen (210), the electronic device (101) can generate a drawing object (201) implemented as “Take a note on the off screen!”, and display the drawing object (201) through the touchscreen display (160). According to one embodiment, the electronic device (101) can recognize at least one character included in the drawing object (201). For example, the electronic device (101) can determine the “off screen” included in the drawing object (201) as a character input corresponding to each character (e.g., “off”, “true”, “fire”, “plane”).

[0059] According to one embodiment, when a drawing object (201) is input according to a user input, the electronic device (101) can recognize the drawing object (201) by converting it into a character (e.g., text) input in real time (e.g., within a set time (e.g., n seconds)). According to one embodiment, after the drawing object (201) is input, if a trigger condition is met, the electronic device (101) can recognize the drawing object (201) as a character (e.g., text) input. For example, after the drawing object (201) is input, when the drawing object (201) is additionally selected (e.g., long press input), the electronic device (101) can determine that the trigger condition is met and recognize the selected drawing object (201) as a character (e.g., text) input. The electronic device (101) may determine that a trigger condition is met when, after inputting a drawing object (201), an additional selection is confirmed for a separate menu (e.g., a text conversion menu, a conversion menu provided by an application), and may recognize the drawing object (201) as a text input. According to another embodiment, the electronic device (101) may convert the drawing object (201) into a text input when a set conversion time has elapsed after inputting the drawing object (201).

[0060] According to one embodiment, in response to fulfillment of a trigger condition, the electronic device (101) may recognize a drawing object (201) as a character input and display the recognized character input through the display (160). For example, the electronic device (101) may display the recognized character input in a pop-up form. As another example, the electronic device (101) may input text corresponding to the character input based on the cursor position for handwriting input.

[0061] According to one embodiment, the electronic device (101) can determine whether at least one character is included in the drawing object (201) based on the drawing object (201). For example, if it is confirmed that at least one character is included in the drawing object (201), the electronic device (101) can extract and recognize the at least one character. According to one embodiment, the electronic device (101) can determine whether at least two characters (e.g., a first character and / or a second character) are included in the drawing object (201) and can extract each character individually. For example, the electronic device (101) can determine whether a plurality of characters (e.g., a first character and / or a second character) are included in the drawing object (201) drawn with a single stroke (e.g., a stroke), and if the plurality of characters are confirmed, the electronic device (101) can divide the drawing object (201) into the first character and the second character and extract them. The electronic device (101) can distinguish between a first letter and a second letter based on a drawing object (201), and can recognize the first letter and the second letter.

[0062] According to one embodiment, the electronic device (101) can execute a program (e.g., an application) that provides a function for recognizing a user input, and can recognize the user input based on the program. For example, the electronic device (101) can recognize a user input inputted through the touchscreen display (160) in response to the execution of the program. When the program is executed, the electronic device (101) can at least partially activate a portion of the touchscreen display (160), and can obtain a user input based on the activated portion of the area.

[0063] FIG. 3 is a block diagram of an electronic device according to one embodiment of the present disclosure.

[0064] The electronic device (101) of FIG. 3 may be at least partially similar to the electronic device (101) of FIG. 1 or may further include other embodiments of the electronic device (101). According to one embodiment, the electronic device (101) may include at least partially similar components to the electronic device (101) of FIG. 1.

[0065] Referring to FIG. 3, the electronic device (101) may include a processor (120) (e.g., the processor (120) of FIG. 1), a memory (130) (e.g., the memory (130) of FIG. 1), a touchscreen display (360) (e.g., the display module (160) of FIG. 1), and / or a communication circuit (390) (e.g., the communication module (190) of FIG. 1). The memory (130) of the electronic device (101) may store reference point information (331), candidate line information (332), and / or character area information (333) related to user input.

[0066] According to one embodiment, the processor (120) of the electronic device (101) may execute a program (e.g., the program (140) of FIG. 1, an application that provides a function of detecting a user input) stored in the memory (130) to control at least one other component (e.g., a hardware or software component) and perform various data processing or operations. For example, the processor (120) may execute a program for detecting a user input, and based on the program, may detect a user input through the touchscreen display (360). The processor (120) may recognize a drawing object (e.g., a drawing object (201) of FIG. 2) according to the user input. For example, the drawing object may include a line drawn with a single stroke (e.g., a stroke), a letter implemented with the line, and / or a shape implemented with the line. According to one embodiment, when a drawing object includes multiple characters, the processor (120) can individually recognize each of the multiple characters and perform a keypad input corresponding to each character. According to one embodiment, when a user performs a memo function using a stylus pen, the processor (120) can recognize a drawing object according to the user input and individually confirm at least two characters included in the drawing object. According to one embodiment, when multiple characters are input using a stylus pen, the multiple characters are recognized separately, so that user convenience for character input can be improved. According to one embodiment, the processor (120) can be operatively, functionally, and / or electrically connected to a memory (130), a touchscreen display (360), and / or a communication circuit (390).

[0067] According to one embodiment, the memory (130) of the electronic device (101) may store reference point information (331) for detecting a reference point included in a drawing object, candidate line information (332) for detecting a candidate line included in the drawing object, and / or character area information (333) for detecting a character area corresponding to a character included in the drawing object. According to another embodiment, the reference point information (331), the candidate line information (332), and / or the character area information (333) of FIG. 3 may also be stored in the memory of an external electronic device (e.g., the server (108) of FIG. 1) operatively connected to the electronic device (101). For example, the electronic device (101) may obtain the reference point information (331), the candidate line information (332), and / or the character area information (333) from an external electronic device (e.g., a server) operatively connected to the electronic device (101).

[0068] For example, the reference point information (331) may include a reference point condition for detecting at least two reference points among a plurality of inflection points included in the drawing object. For example, the inflection point may include a point on a curve indicating a place where the direction of inflection changes according to a user input. The reference point condition may include a condition in which, in a situation where the movement direction of the user input changes, the amount of change in the angle of inflection according to the change in direction exceeds a set value (e.g., a preset reference value). According to one embodiment, the processor (120) may detect at least two reference points that satisfy the reference point condition based on a drawing object corresponding to the user input.

[0069] For example, the candidate line information (332) may include a candidate line selection condition for selecting an optimal candidate line among candidate lines implemented with two reference points. The candidate line may be set as a line (e.g., segment) in which two reference points sequentially detected are connected based on a drawing object corresponding to a user input. For example, the candidate line may be set as a line longer than a certain length. The candidate line may be set based on the size (e.g., area) and ratio (e.g., width-to-height ratio, length-to-width ratio, aspect ratio) of the text area when dividing the text area into two text areas based on the candidate line. When a condition is satisfied that the area of ​​the text area exceeds a certain area and the length-to-width ratio of the text area is within a set range, the processor (120) may set the corresponding line as a candidate line. The processor (120) can compare a first reliability corresponding to a drawing object with a second reliability corresponding to a character area divided based on a specific line, and when the second reliability is relatively greater than the first reliability, the specific line can be set as a candidate line.

[0070] According to one embodiment, the candidate line selection conditions may include a first condition that the length is greater than or equal to a certain length, a second condition that the movement direction of the user input satisfies a preset specific pattern (e.g., a pattern that moves from left-bottom to right-top), a third condition that the area and ratio of the character area divided based on the candidate line are within a preset range, and / or a fourth condition that the reliability corresponding to the character area divided based on the specific line is relatively higher than the reliability corresponding to the drawing object. For example, the preset specific pattern may include a LB2RT (left_bottom to right_top) pattern, which is a pattern that connects from the bottom left to the top right when the character is Korean. The preset specific pattern is not limited to the LB2RT pattern, and may include a LC2RT (left_center to right_top) pattern and / or a LB2RC (left_bottom to right_center) pattern. The preset specific pattern may be set to various types of patterns depending on the type of character. For example, if the character is Korean, a first pattern set corresponding to Korean characters may be applied, and if the character is English, a second pattern set corresponding to English characters may be applied. For another example, if the character is English, the preset specific pattern may include a LC2RC (left_center to right_center) pattern, which is a pattern that connects from the left middle to the right middle. According to one embodiment, the processor (120) may check the type of character (e.g., Korean, English, and / or Chinese characters) according to the drawing object, and may determine a preset specific pattern corresponding to the checked character. When selecting a candidate line, if a preset specific pattern is detected, the processor (120) may select a candidate line according to the preset specific pattern as an optimal candidate line.

[0071] According to one embodiment, the processor (120) may select an optimal candidate line (e.g., an optimal segment) that satisfies a candidate line selection condition from among a plurality of candidate lines. For example, the optimal candidate line may be determined as a candidate line that exhibits the greatest reliability in distinguishing a plurality of character areas from among a plurality of candidate lines included in a drawing object. Based on the optimal candidate line, the processor (120) may individually recognize a first character input before the optimal candidate line and a second character input after the optimal candidate line.

[0072] For example, the text area information (333) may include information related to the area (e.g., size) of the text area and information related to the aspect ratio (e.g., width-to-height ratio) of the text area. When a plurality of text areas are distinguished based on a specific candidate line, each text area may be relatively larger than a set area and may satisfy the aspect ratio included in the text area information (333). The processor (120) may determine that the text area satisfies the aspect ratio when the aspect ratio corresponding to the text area is included in a set range according to the aspect ratio. According to one embodiment, the processor (120) may distinguish a text area having an optimal aspect ratio based on the text area information (333), and may determine a candidate line distinguished by the text area as an optimal candidate line.

[0073] According to one embodiment, the processor (120) of the electronic device (101) may detect at least two reference points that satisfy reference point conditions included in reference point information (331) based on a drawing object corresponding to a user input. The processor (120) may determine a candidate line connecting two reference points based on the detected at least two reference points. The processor (120) may determine an optimal candidate line (e.g., an optimal segment) that satisfies the candidate line selection conditions included in the candidate line information (332). As another example, in determining the optimal candidate line, the processor (120) may distinguish a first character area and a second character area having an optimal aspect ratio based on character area information (333), and determine an optimal candidate line that can be distinguished into the first character area and the second character area. The processor (120) may select an optimal candidate line based on the candidate line information (332) and the character area information (333). According to one embodiment, the processor (120) may divide the first character area and the second character area based on a dividing point included in the selected optimal candidate line. For example, a drawing object corresponding to a user input may be divided into a first drawing object input before the dividing point and a second drawing object input after the dividing point based on the dividing point. The processor (120) may divide the first character area corresponding to the first drawing object and the second character area corresponding to the second drawing object based on the dividing point. According to one embodiment, the processor (120) may identify the first character corresponding to the first character area and the second character corresponding to the second character area.

[0074] According to one embodiment, the touchscreen display (360) of the electronic device (101) can detect a user input (e.g., touch input, pen input, stylus pen input, finger input, gesture input, and / or segment input). The processor (120) can detect a user input through the touchscreen display (360) and generate a drawing object (e.g., a point, a line, and a specific shape drawn with the line (e.g., a letter, a character, a text)) corresponding to the user input. The processor (120) can display the generated drawing object through the touchscreen display (360). According to one embodiment, the processor (120) can detect a user input based on the touchscreen display (360) and display a drawing object corresponding to the user input.

[0075] According to one embodiment, the electronic device (101) may be connected to an external electronic device (e.g., server (108)) based on a communication circuit (390) and may transmit and receive data with the external electronic device. For example, the processor (120) may transmit or receive data to or from the external electronic device when calculating a reliability corresponding to a text area or confirming text corresponding to the text area. The processor (120) may transmit a drawing object corresponding to a distinguished text area to the external electronic device. The external electronic device may apply a character recognition method based on an artificial intelligence model (e.g., an AI-related model) to the drawing object received from the electronic device (101) and confirm the text corresponding to the drawing object. The external electronic device may calculate a reliability (e.g., accuracy) for the confirmed text. The external electronic device may generate analysis result data based on the artificial intelligence model and provide the analysis result data to the electronic device (101). According to one embodiment, the electronic device (101) can identify a letter corresponding to a letter area based on analysis result data obtained from an external electronic device.

[0076] According to one embodiment, when a drawing object corresponding to a user input includes a first letter and a second letter, the electronic device (101) can recognize a word by combining the first letter and the second letter. The electronic device (101) can identify a first word described above and a second word described later in the word, centered on the recognized word. The electronic device (101) can identify at least one combination among a first combination between the first word and the recognized word, a second combination between the recognized word and the second word, and / or a third combination of the first word, the recognized word, and the second word in order, and can determine whether the word has been recognized by considering the preceding / consequential context. The processor (120) of the electronic device (101) can check the contextual interpretation related to the first word and the second word, centered on one recognized word, and determine the one word (e.g., the first candidate word).

[0077] According to one embodiment, the electronic device (101) may provide a method for recognizing a specific word by identifying a first word located in front of a specific word and a second word located behind the specific word when recognizing a character according to a user input, and considering a combination among the first word, the specific word, and / or the second word. According to one embodiment, when a user inputs a character using a stylus pen, the accuracy of character recognition may be improved, and the convenience of the user using the electronic device may be improved. The electronic device (101) may recognize the specific word by considering the context before and after the specific word. The recognition accuracy for the specific word may be improved.

[0078] According to one embodiment, an electronic device (101) may include a touchscreen display (360), a processor (120), and a memory (130) that stores instructions. When the instructions are executed by the processor (120), the electronic device (101) may detect at least two reference points (e.g., points satisfying reference point conditions among a plurality of inflection points) for a user input through the touchscreen display (160) based on the user input, determine a plurality of candidate lines based on the detected at least two reference points, determine an optimal candidate line (e.g., optimal segment) satisfying a candidate line selection condition (e.g., a predetermined length or more, satisfying AR of a character) among the plurality of candidate lines, divide at least two character areas based on a dividing point included in the optimal candidate line, and identify a first character corresponding to a first character area and a second character corresponding to a second character area among the at least two character areas.

[0079] According to one embodiment, when the instructions are executed by the processor (120), the electronic device (101) can recognize at least one word based on the first letter and the second letter.

[0080] According to one embodiment, when the instructions are executed by the processor (120), the electronic device (101) can identify the first word described above, centered on the at least one recognized word, and determine a first candidate word based on a combination between the identified first word and the at least one recognized word.

[0081] According to one embodiment, when the instructions are executed by the processor (120), the electronic device (101) can identify a second word described below based on the at least one recognized word, and determine a second candidate word based on a combination between the at least one recognized word and the identified second word.

[0082] According to one embodiment, when the instructions are executed by the processor (120), the electronic device (101) may change the division point included in the optimal candidate line if the first candidate word and the second candidate word do not match.

[0083] According to one embodiment, when the instructions are executed by the processor (120), the electronic device (101) can divide the first character area and the second character area based on a dividing point included in the optimal candidate line when the first reliability corresponding to the character input by the user is lower than the second reliability for the first character and the second character.

[0084] According to one embodiment, when the instructions are executed by the processor (120), the electronic device (101) can detect the at least two reference points based on the point where the direction change occurs when the amount of angular change due to the direction change of the user input exceeds a set value.

[0085] According to one embodiment, the candidate line selection conditions may include a first condition in which the candidate line is longer than a set length, a second condition in which the movement direction of the user input satisfies a preset specific pattern (e.g., a pattern in which the movement direction is from left-bottom to right-top), and a third condition in which the width-to-height ratio of a character area determined based on the candidate line is within a preset range.

[0086] According to one embodiment, when the instructions are executed by the processor (120), the electronic device (101) can determine the optimal candidate line that satisfies all of the first condition, the second condition, and the third condition included in the candidate line selection conditions.

[0087] According to one embodiment, when the instructions are executed by the processor (120), the electronic device (101) can, based on the user input through the touchscreen display (360), check first coordinate information and second coordinate information indicating the location of the user input, check third coordinate information indicating the input order of the user input, and, based on the first coordinate information, the second coordinate information, and the third coordinate information, distinguish a first cluster and a second cluster, and check a first letter corresponding to the first cluster and a second letter corresponding to the second cluster.

[0088] According to another embodiment, the electronic device (101) may include a touchscreen display (360), a processor (120), and a memory (130) for storing instructions. When the above instructions are executed by the processor (120), the electronic device (101) may detect at least two reference points (e.g., points satisfying reference point conditions among a plurality of inflection points) for a user input through the touch screen display (160), determine at least one dividing point included in a candidate line determined based on the at least two reference points, identify one word corresponding to the first character area and the second character area based on a first character area and a second character area divided based on the at least one dividing point, identify the first word described above with respect to the one word as the center, identify the second word described below with respect to the one word as the center, determine a first candidate word corresponding to the one word based on a combination between the first word and the one word, determine a second candidate word corresponding to the one word based on a combination between the one word and the second word, and determine the one word when the first candidate word and the second candidate word match.

[0089] According to another embodiment, the electronic device (101) may change the at least one splitting point if the first candidate word and the second candidate word do not match.

[0090] FIG. 4 is a flowchart illustrating a character recognition method according to one embodiment of the present disclosure.

[0091] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0092] According to one embodiment, operations 401 to 409 may be understood to be performed by a processor (e.g., processor (120) of FIG. 3) of an electronic device (e.g., electronic device (101) of FIG. 3). The electronic device of FIG. 4 may be at least partially similar to the electronic device (101) of FIG. 3, or may further include other embodiments of the electronic device (101).

[0093] According to one embodiment, the processor (120) of the electronic device (101) may execute a program for detecting a user input and may detect the user input through a touchscreen display (e.g., the touchscreen display (360) of FIG. 3). For example, the processor (120) may recognize a drawing object (e.g., the drawing object (201) of FIG. 2) according to the user input. For example, the drawing object may include a line drawn with a single stroke (e.g., a stroke), a letter implemented with the line, and / or a shape implemented with the line. The drawing object may be composed of multiple strokes, and a single stroke may be composed of multiple points. For example, a stroke may be divided into multiple sub-regions based on an inflection point (e.g., a point where the direction of curvature changes according to a user input) among the multiple points. The divided sub-regions may be defined as segments. The divided sub-regions may include at least one candidate line.

[0094] In operation 401, the processor (120) can detect at least two reference points based on a user input. For example, the processor (120) can recognize a drawing object (201) according to the user input, and check a plurality of inflection points included in the drawing object (201). The processor (120) can detect at least two reference points that satisfy a reference point condition among the plurality of inflection points based on reference point information (e.g., reference point information (331) of FIG. 3) stored in a memory (e.g., memory (130) of FIG. 3). For example, the inflection point may include a point on a curve indicating a location where the direction of the bending changes according to the user input. For example, the reference point condition may include a condition in which, in a situation where the movement direction of the user input changes, the amount of change in the angle of the bending according to the change in direction exceeds a set value (e.g., a preset reference value). In operation 401, the processor (120) can detect at least two reference points that satisfy the reference point condition based on a plurality of inflection points included in the drawing object (201).

[0095] According to one embodiment, when a drawing object (201) is input, the electronic device (101) can recognize the drawing object (201) by converting it into a character (e.g., text) input in real time (e.g., within a set time (e.g., n seconds)). According to one embodiment, after the drawing object (201) is input, if a trigger condition is met, the electronic device (101) can recognize the drawing object (201) as a character (e.g., text) input. For example, after the drawing object (201) is input, when the drawing object (201) is additionally selected (e.g., long press input), the electronic device (101) can determine that the trigger condition is met and recognize the selected drawing object (201) as a character (e.g., text) input. The electronic device (101) may determine that a trigger condition is met when, after inputting a drawing object (201), an additional selection for a separate menu (e.g., a text conversion menu, a conversion menu provided by an application) is confirmed, and may recognize the drawing object (201) as a character input. According to one embodiment, the electronic device (101) may detect at least two reference points in order to recognize the drawing object (201) as a character input.

[0096] In operation 403, the processor (120) may determine a plurality of candidate lines (e.g., a plurality of segments) based on at least two detected reference points. For example, the candidate line may be set as a line in which two reference points detected sequentially among the at least two detected reference points are connected. The drawing object (201) may include a line drawn with a single stroke by a user input, and may include at least one candidate line at least partially based on the line.

[0097] In operation 405, the processor (120) may determine an optimal candidate line that satisfies a candidate line selection condition among a plurality of candidate lines. For example, the candidate line selection condition may include a first condition that the length is greater than a certain length, a second condition that the movement direction of the user input satisfies a preset specific pattern (e.g., a pattern that moves from left-bottom to right-top), a third condition that when a character area is divided based on the candidate line, the area and ratio of the divided character area are included within a preset range, and / or a fourth condition that a first reliability corresponding to the drawing object (201) is compared with a second reliability corresponding to the divided character area, and the second reliability is relatively higher than the first reliability. For example, the preset specific pattern may be set as a different type of pattern depending on the type of character (e.g., Korean, English, Chinese characters). For example, if the character is Korean, the preset specific pattern may include at least one of a LB2RT (left_bottom to right_top) pattern, a LC2RT (left_center to right_top) pattern, and / or a LB2RC (left_bottom to right_center) pattern. For another example, if the character is English, the preset specific pattern may include a LC2RC (left_center to right_center) pattern. According to one embodiment, the processor (120) may check the type of character (e.g., Korean, English, and / or Chinese characters) according to the drawing object, and determine the preset specific pattern corresponding to the checked character.

[0098] In operation 405, the optimal candidate line that satisfies the candidate line selection conditions may be determined as a candidate line that satisfies all of the first condition, the second condition, the third condition, and / or the fourth condition.

[0099] According to one embodiment, the processor (120) may determine an optimal candidate line that satisfies candidate line selection conditions (e.g., a first condition, a second condition, a third condition, a fourth condition) from among a plurality of candidate lines. According to one embodiment, the processor (120) may recognize a plurality of dividing points included in the optimal candidate line based on the optimal candidate line, and determine one dividing point from among the plurality of dividing points. According to one embodiment, the processor (120) may select a plurality of optimal candidate lines, and recognize a plurality of dividing points included in the selected optimal candidate lines. The processor (120) may divide a plurality of character areas (e.g., a first character area, a second character area) based on at least one dividing point among the plurality of dividing points. For example, the processor (120) may divide a drawing object (201) into a first drawing object input before the at least one dividing point and a second drawing object input after the dividing point based on the determined at least one dividing point. A first drawing object may be contained within a first character area, and a second drawing object may be contained within a second character area.

[0100] In operation 407, the processor (120) may distinguish at least two character areas (e.g., a first character area and a second character area) based on a dividing point included in an optimal candidate line. For example, the processor (120) may distinguish the drawing object (201) into a first drawing object and a second drawing object based on the dividing point. The first drawing object may include an area (e.g., a first character area) input before the dividing point based on the drawing object (201). The second drawing object may include an area (e.g., a second character area) input after the dividing point based on the drawing object (201). The processor (120) may distinguish a first character area corresponding to the first drawing object and a second character area corresponding to the second drawing object.

[0101] In operation 409, the processor (120) can identify a first letter corresponding to the first letter area and a second letter corresponding to the second letter area among the above-described letter areas (e.g., a first letter area, a second letter area). For example, a word can be generated based on the first letter and the second letter.

[0102] According to one embodiment, the electronic device (101) can check a plurality of candidate lines based on a drawing object (201) according to a user input, and can determine an optimal candidate line that satisfies a candidate line selection condition among the plurality of candidate lines. The electronic device (101) can divide the drawing object (201) into a first drawing object and a second drawing object based on a dividing point included in the optimal candidate line. The electronic device (101) can divide a first character area corresponding to the first drawing object and a second character area corresponding to the second drawing object. The electronic device (101) can check a first character corresponding to the first character area and a second character corresponding to the second character area, and can recognize a word composed of the first character and the second character.

[0103] According to one embodiment, the electronic device (101) can sequentially identify a first word preceding the word and a second word following the word, based on a single word, and can identify a combination between the first word, the single word, and / or the second word. For example, the electronic device (101) can identify a first combination between the first word and the single word, a second combination between the single word and the second word, and / or a third combination between the first word, the single word, and the second word in that order. The electronic device (101) can determine the single word based on the first combination, the second combination, and / or the third combination.

[0104] According to one embodiment, the electronic device (101) can recognize letters according to user input based on the method disclosed in FIG. 4. According to one embodiment, when a user inputs letters using a stylus pen, the accuracy and user convenience of letter recognition using the electronic device (101) can be improved. According to one embodiment, when determining a single word, the electronic device (101) can determine the single word by considering the context with the first word described above and the context with the second word described below.

[0105] FIG. 5A is an exemplary diagram showing at least two reference points detected based on a user input according to one embodiment of the present disclosure. FIG. 5B is an exemplary diagram showing various pattern shapes for detecting a candidate line according to one embodiment of the present disclosure. FIG. 5C is an exemplary diagram showing detecting a set pattern shape based on a sentence according to a user input according to one embodiment of the present disclosure and determining a candidate line corresponding to the detected pattern shape. FIG. 5D is a first graph showing a length condition of a segment corresponding to a user input according to one embodiment of the present disclosure. FIG. 5E is a second graph showing a width-to-height ratio (e.g., aspect ratio) condition for a character area divided based on a dividing point included in a segment according to one embodiment of the present disclosure. FIG. 5F is an exemplary diagram showing a size condition for a character area divided based on a dividing point included in a segment according to one embodiment of the present disclosure.

[0106] The electronic device (101) of FIGS. 5A to 5F may be at least partially similar to the electronic device (101) of FIGS. 1 and 2, or may further include other embodiments of the electronic device (101). In one embodiment, the electronic device (101) may include at least partially similar components to the electronic device (101) of FIG. 1.

[0107] Referring to FIGS. 5A to 5F, the electronic device (101) may include a processor (120) (e.g., the processor (120) of FIG. 3), a memory (130) (e.g., the memory (130) of FIG. 3), a touchscreen display (360) (e.g., the display module (160) of FIG. 1, the touchscreen display (360) of FIG. 3), and / or a communication circuit (390) (e.g., the communication module (190) of FIG. 1, the communication circuit (390) of FIG. 3).

[0108] According to one embodiment, the processor (120) of the electronic device (101) can recognize a drawing object (501) (e.g., a drawing object (201) of FIG. 2) according to a user input, and select an optimal candidate line (531) from among a plurality of candidate lines included in the drawing object (501). The processor (120) can distinguish at least two character areas (e.g., a first character area and / or a second character area) based on the optimal candidate line (531), and recognize a first character corresponding to the first character area and a second character corresponding to the second character area.

[0109] Referring to FIG. 5A, the processor (120) can confirm a drawing object (501) corresponding to a user input through the touch screen display (360) of the electronic device (101). For example, the drawing object (501) may include a line drawn with a single stroke (e.g., a stroke), a letter implemented with the line, and / or a shape implemented with the line. The processor (120) can confirm a plurality of inflection points (511-521) included in the drawing object (501). For example, an inflection point may include a point on a curve indicating a location where the direction of curvature changes according to the user input. The processor (120) may detect at least two reference points that satisfy a reference point condition among the plurality of inflection points (511-521) based on reference point information (e.g., reference point information (331) of FIG. 3) stored in the memory (130) (e.g., memory (130) of FIG. 3). For example, the reference point condition may include a condition in which, in a situation in which the direction of movement of a user input changes, the amount of change in the angle of inflection due to the change in direction exceeds a set value (e.g., a preset reference value). Referring to FIG. 5A, the first reference point (516) and the second reference point (517) may be reference points that satisfy the reference point condition.

[0110] According to one embodiment, the processor (120) can detect at least two reference points (e.g., a first reference point (516) and / or a second reference point (517)) that satisfy a reference point condition based on a plurality of inflection points (511-521) included in a drawing object (501).

[0111] Referring to FIG. 5A, the processor (120) may determine a plurality of candidate lines based on at least two or more detected reference points. A candidate line may be set as a line (e.g., a segment) in which two reference points detected sequentially are connected among the at least two or more detected reference points. For example, a drawing object (501) may include a line drawn with a single stroke by a user input, and at least a portion of the line may be determined as a candidate line. According to one embodiment, a candidate line may be determined as a line matching a preset pattern shape. For example, the processor (120) may select at least one candidate line matching the preset pattern shape from among a plurality of segments included in the drawing object (501).

[0112] Referring to FIG. 5A, the first candidate line (531) may be included as one of a plurality of candidate lines. According to one embodiment, the processor (120) may determine the candidate line based on the horizontal length (532) of the candidate line (e.g., width), the vertical length (533) of the candidate line (e.g., height), and / or the length of the candidate line. For example, the first candidate line (531) may be determined as one candidate line by satisfying a set condition.

[0113] Referring to FIG. 5A, the processor (120) may determine an optimal candidate line that satisfies a candidate line selection condition from among a plurality of candidate lines. For example, the candidate line selection condition may include a first condition that the length is greater than or equal to a certain length, a second condition that the movement direction of the user input satisfies a preset specific pattern (e.g., a pattern that moves from left-bottom to right-top), a third condition that when a text area is divided based on the candidate line, the area and ratio (e.g., width-to-height ratio, height-to-length ratio) of the divided text area are within a set range, and / or a fourth condition that a first reliability corresponding to the drawing object (201) is compared with a second reliability corresponding to the divided text area, and the second reliability is relatively higher than the first reliability. For example, the processor (120) may determine an optimal candidate line that satisfies all four conditions included in the candidate line selection condition from among a plurality of candidate lines.

[0114] FIG. 5b illustrates various pattern shapes for detecting candidate lines. For example, the processor (120) may select a candidate line that matches a preset pattern shape among multiple segments included in a drawing object (501). Referring to FIG. 5b, approximately four pattern shapes (541, 544, 547, 550) are illustrated, but the present invention is not limited thereto.

[0115] Referring to FIG. 5B, the electronic device (101) can set the LB2RT (LeftBottom to RightTop) pattern, which is a pattern in which the shape of the segment is connected from the left bottom (542) to the right top (543), as a first pattern (541). The electronic device (101) can set the LC2RT (LeftCenter to RightTop) pattern, which is a pattern in which the shape of the segment is connected from the left center (545) to the right top (546), as a second pattern (544). The electronic device (101) can set the LB2RC (LeftBottom to RightCenter) pattern, which is a pattern in which the shape of the segment is connected from the left bottom (548) to the right center (549), as a third pattern (547). The electronic device (101) may set the LC2RC (LeftCenter to RightCenter) pattern, which is a pattern in which the shape of the segment is connected from the left center (551) to the right center (552), as the fourth pattern (550). According to one embodiment, the electronic device (101) may apply a different pattern depending on the language type of the drawing object (501). For example, if the language corresponding to the drawing object (501) is language A, the A pattern may be applied, and if the language corresponding to the drawing object (501) is language B, the B pattern, which is different from the A pattern, may be applied. According to one embodiment, the first pattern (541) to the fourth pattern (550) of FIG. 5B correspond to exemplary patterns. The patterns are not limited to a specific form of pattern.

[0116] According to one embodiment, when the language corresponding to the drawing object (501) is Hangul (e.g., Korean), the electronic device (101) may set at least one pattern among the first pattern (541), the second pattern (544), and / or the third pattern (547), and when the language corresponding to the drawing object (501) is English, the electronic device (101) may set the fourth pattern (550). For example, when applying at least one pattern to the drawing object (501), the electronic device (101) may apply all of the set patterns. For another example, the pattern shape may be set differently depending on the type of language. According to one embodiment, the processor (120) may detect at least one candidate line matching the set pattern shape (541, 544, 547, 550) based on the drawing object (501), and may apply a candidate line selection condition based on the detected at least one candidate line.

[0117] According to one embodiment, the patterns are not limited to the patterns illustrated in FIG. 5b. The patterns may be set in various forms depending on the type of language.

[0118] Figure 5c is an example diagram for identifying at least one candidate line corresponding to a preset pattern shape within a sentence according to user input.

[0119] Referring to FIG. 5c, when a sentence (e.g., phrase, sentence, and / or word) (e.g., “Meeting with reporters and talking about North America”) is input by a user input, the electronic device (101) can check a plurality of segments (e.g., lines connecting two reference points) included in the sentence, and can check at least one candidate line corresponding to a preset pattern shape among the plurality of segments. For example, the processor (120) can extract a plurality of candidate lines (561, 562, 563, 564, 565) from the sentence (e.g., “Meeting with reporters and talking about North America”). For example, the plurality of candidate lines (561, 562, 563, 564, 565) can include a candidate line matching a preset pattern shape (e.g., the first pattern (541), the second pattern (544), and / or the third pattern (547) of FIG. 5b). According to one embodiment, the electronic device (101) can recognize that the language according to the user input is Hangul (e.g., Korean), and can confirm a pattern shape set based on the Hangul (e.g., the first pattern (541), the second pattern (544), and / or the third pattern (547) of FIG. 5B). According to another embodiment, the electronic device (101) can recognize that the language according to the user input is English, and can confirm a pattern shape set based on the English (e.g., the fourth pattern (550) of FIG. 5B). The electronic device (101) can extract at least one candidate line corresponding to the set pattern shape from within a sentence according to the user input.

[0120] According to one embodiment, the electronic device (101) can determine an optimal candidate line that satisfies a candidate line selection condition among a plurality of candidate lines.

[0121] In one embodiment, the candidate selection criteria may be determined based on a fitness score. For example, the processor (120) may calculate a fitness score corresponding to each of multiple candidate lines, and determine the candidate line with the highest fitness score as the optimal candidate line. The fitness score may be calculated using the following equation (Mathematical Formula 1).

[0122]

[0123] FIG. 5d is a first graph representing a length condition of a segment (e.g., a candidate line). The processor (120) can determine whether the length of the candidate line is appropriate (e.g., greater than or equal to a certain length) based on the first graph. Referring to the first graph, if the length of the candidate line is greater than or equal to a certain length, a relatively high score (e.g., length appropriateness score) can be obtained. (x-axis: length information of candidate line, y-axis: length appropriateness score) For example, the candidate line can be set to be greater than or equal to Tmin length, and if it is greater than or equal to Tmax length, the highest score (e.g., approximately 1.0) can be obtained. The length appropriateness score according to the first graph of FIG. 5d can be calculated using the following (Mathematical Formula 2).

[0124]

[0125] FIG. 5E is a second graph showing a condition of a width-to-height ratio (e.g., aspect ratio) for a character area divided based on a dividing point included in a segment (e.g., candidate line). The processor (120) can determine whether the aspect ratio of the character area is appropriate (e.g., whether the width-to-height ratio is within a certain range) based on the second graph. Referring to the second graph, if the aspect ratio of the character shape is within a certain range, a relatively high score (e.g., character shape suitability score) can be obtained. The character shape suitability score can determine whether the ratio of the left character area (e.g., first character area) and the right character area (e.g., second character area) based on the candidate line is an optimal ratio. For example, the character shape suitability score can be calculated as a relatively high score when the aspect ratio (e.g., width-to-height ratio, aspect ratio, left letter AR score, right letter AR score) for the character area is high and the sizes (e.g., area) of the first character area and the second character area are similar. The letter shape suitability score according to the second graph of Fig. 5e can be calculated using (Mathematical Formula 3) below.

[0126]

[0127] The second graph in Figure 5e is a graph regarding the aspect ratio (AR) (e.g., width-to-height ratio, height-to-width ratio) for the letter region. When a certain AR range is satisfied, a relatively high score can be obtained. The AR score for the letter region (e.g., (left / right) letter AR score) can be calculated using the following equation (Mathematical Formula 4).

[0128]

[0129] Referring to FIG. 5e, when the AR score (letter AR score) is in the range of about 0.7 (e.g., Tmin2) to about 1.3 (Tmax1), the corresponding letter area can be judged to have an optimal width-height ratio (e.g., aspect ratio).

[0130] For example, if the first letter ratio corresponding to the left letter area (e.g., the first letter area) and the second letter ratio corresponding to the right letter area (e.g., the second letter area) are similar based on the candidate line, the similarity score (letter similarity) can be calculated to be relatively high. For example, the similarity score can numerically represent the similarity in the sizes of the left / right letters. The similarity score (letter similarity) can be calculated using the following (Mathematical Formula 5).

[0131]

[0132] (Referring to Equation 5), the similarity score can be calculated by comparing the horizontal length (e.g., left width, LW) for the first character region with the horizontal length (e.g., right width, RW) for the second character region. For another example, the similarity score can be calculated by comparing the vertical length (e.g., left height, LH) for the first character region with the vertical length (e.g., right height, RH) for the second character region. In one embodiment, the similarity scores for the first character region and the second character region can be calculated using various comparison methods.

[0133] Referring to FIG. 5F, the processor (120) can set various first character areas (e.g., character areas corresponding to the first drawing object input relatively earlier than the first candidate line (531)) based on the first candidate line (531). The electronic device (101) can set various shapes (571, 572, 573) of the first character areas, as shown in (a), (b), and (c) of FIG. 5F. The processor (120) can calculate a character shape suitability score for each character area and determine an optimal character area. According to one embodiment, the processor (120) can recognize a character corresponding to the optimal character area.

[0134] According to one embodiment, the processor (120) may calculate a segment length score based on (Mathematical Formula 2) and may calculate a letter similarity score based on (Mathematical Formulas 3, 4, and 5). The processor (120) may apply the segment length score and the letter similarity score to (Mathematical Formula 1) and may calculate a suitability score corresponding to the candidate line. The processor (120) may determine an optimal candidate line based on the calculated suitability score among a plurality of candidate lines included in the drawing object (501). The processor (120) may distinguish a first drawing object input before the optimal candidate line and a second drawing object input after the optimal candidate line based on the determined optimal candidate line. The processor (120) can distinguish a first character area corresponding to a first drawing object and a second character area corresponding to a second drawing object, and can recognize a first character corresponding to the first character area and a second character corresponding to the second character area.

[0135] FIG. 6 is an exemplary diagram showing an optimal candidate line satisfying a candidate line selection condition according to one embodiment of the present disclosure, and dividing at least two character areas based on a dividing point included in the optimal candidate line.

[0136] The electronic device (101) of FIG. 6 may be at least partially similar to the electronic device (101) of FIGS. 1 and 2, or may further include other embodiments of the electronic device (101). In one embodiment, the electronic device (101) may include at least partially similar components to the electronic device (101) of FIG. 1.

[0137] According to one embodiment, the processor (120) of the electronic device (101) (e.g., the processor (120) of FIG. 3) can recognize a drawing object (e.g., the drawing object (201) of FIG. 2) according to a user input, and select an optimal candidate line (601) from among a plurality of candidate lines included in the drawing object. For example, the processor (120) can select an optimal candidate line (601) that satisfies a candidate line selection condition based on reference point information (e.g., reference point information (331) of FIG. 3), candidate line information (e.g., candidate line information (332) of FIG. 3), and character area information (e.g., character area information (333) of FIG. 3) stored in the memory (130).

[0138] Referring to FIG. 6, the processor (120) can distinguish a first character area (621) corresponding to a first drawing object input before the optimal candidate line (601) and a second character area (622) corresponding to a second drawing object input after the optimal candidate line (601) based on the optimal candidate line (601). For example, the first character area (621) and the second character area (622) can be distinguished based on a first reference point (611) corresponding to one end of the optimal candidate line (601) and a second reference point (612) corresponding to the other end of the optimal candidate line (601). Referring to FIG. 6, the first reference point (611) and the second reference point (612) can each be set as a dividing point.

[0139] According to one embodiment, the processor (120) can recognize at least one dividing point among a plurality of dividing points (611, 612, 613, 614) included in the optimal candidate line (601), and can divide two character areas based on the at least one dividing point. According to one embodiment, the dividing point is not fixed to a specific position, and can be determined as at least one of the points included in the optimal candidate line (601).

[0140] According to one embodiment, the electronic device (101) can individually recognize a first letter corresponding to the first letter area (621) and a second letter corresponding to the second letter area (622). The electronic device (101) can recognize a single word by combining the first letter and the second letter.

[0141] FIG. 7 is an example diagram of calculating a reliability corresponding to a user input according to one embodiment of the present disclosure and recognizing a character based on the calculated reliability.

[0142] The electronic device (101) of FIG. 7 may be at least partially similar to the electronic device (101) of FIGS. 1 and 2, or may further include other embodiments of the electronic device (101). In one embodiment, the electronic device (101) may include at least partially similar components to the electronic device (101) of FIG. 1.

[0143] Referring to FIG. 7, a processor of an electronic device (101) (e.g., processor (120) of FIG. 3) can calculate a reliability level for a letter when recognizing a letter corresponding to a letter area, and can recognize the letter based on the calculated reliability level.

[0144] For example, the processor (120) can calculate a first reliability (e.g., about 40) for the entire recognized character (e.g., “bone”) based on the entire character area (710) corresponding to the entire drawing object. The processor (120) can select an optimal candidate line included in the drawing object, and can distinguish a first character area (720) and a second character area (730) based on the selected optimal candidate line. The processor (120) can recognize a first character (e.g., “year”) corresponding to the first character area (720) and a second character (e.g., “of”) corresponding to the second character area (730). The processor (120) can calculate a second-first reliability (e.g., about 90) for the first character (e.g., “year”) and a second-second reliability (e.g., about 80) for the second character (e.g., “of”). The processor (120) can calculate an average reliability (e.g., about 85) of the 2-1 reliability (e.g., about 90) and the 2-2 reliability (e.g., about 80), and compare the 1st reliability (e.g., about 40) and the average reliability (e.g., about 85).

[0145] According to one embodiment, if the first reliability (e.g., about 40) for the entire character area (710) is lower than the average reliability (e.g., about 85) for the segmented character areas (e.g., the first character area (720) and the second character area (730)), the electronic device (101) may determine that the drawing object is appropriately segmented. When recognizing characters for the drawing object, if the average reliability is relatively higher than the first reliability, the electronic device (101) may individually recognize the first character corresponding to the first character area (720) and the second character corresponding to the second character area (730), rather than the entire character area (710). According to one embodiment, the electronic device (101) may recognize a single word (e.g., “년”) by combining the individually recognized first character (e.g., “년”) and second character (e.g., “의”).

[0146] According to one embodiment, if the first confidence level for the entire character area (710) is higher than the average confidence level for the separated character areas (e.g., the first character area (720) and the second character area (730)), the electronic device (101) may determine that the two character areas are improperly separated. In this case, the electronic device (101) may change the dividing point that separates the two character areas.

[0147] FIG. 8 is an example diagram showing different letters recognized based on segmentation points included in an optimal candidate line according to one embodiment of the present disclosure.

[0148] The electronic device (101) of FIG. 8 may be at least partially similar to the electronic device (101) of FIGS. 1 and 2, or may further include other embodiments of the electronic device (101). In one embodiment, the electronic device (101) may include at least partially similar components to the electronic device (101) of FIG. 1.

[0149] Referring to FIG. 8, a processor of an electronic device (101) (e.g., processor (120) of FIG. 3) may, when recognizing a word by combining a first letter and a second letter, identify a first word described above based on the word and a second word described later based on the word. The processor (120) may identify at least one combination among a first combination between the first word and the word, a second combination between the word and the second word, and / or a third combination of the first word, the word, and the second word, and determine the word. The processor (120) may identify a contextual interpretation related to the first word and the second word based on the word, and determine the word (e.g., a first candidate word). The processor (120) may consider the context before / after the word and determine the word.

[0150] Referring to FIG. 8, the processor (120) can determine one dividing point from among a plurality of dividing points (810, 820, 830) included in the optimal candidate line, and can confirm the first letter and the second letter based on the determined dividing point.

[0151] For example, when dividing a character area based on the first dividing point (810), the processor (120) can identify “gi” corresponding to the first character and “ja” corresponding to the second character. The processor (120) can recognize the word “gija” (811) by combining the first character (“gi”) and the second character (“ja”). The processor (120) can identify the word “sinmun” (812) described above based on the word “gija” (811), and in response to the word “sinmun” (812) and the word “gija” (811) being sequentially combined, determine whether the word “gija” (811) is contextually appropriate. The processor (120) can determine the word “gija” (811) based on the word “sinmun reporter.” For another example, the processor (120) can identify the word “interview” (813) described later based on the word “reporter” (811), and in response to the sequential combination of the word “reporter” (811) and the word “interview” (813), determine whether the word “reporter” (811) is contextually appropriate. The processor (120) can determine the word “reporter” (811) based on the word “press conference.”

[0152] For example, when dividing a character area based on the second dividing point (820), the processor (120) can identify “가” corresponding to the first character and “자” corresponding to the second character. The processor (120) can recognize the word “가자” (821) by combining the first character (“가”) and the second character (“자”). The processor (120) can identify the word “산에” (822) described above based on the word “가자” (821), and in response to the word “산에” (822) and the word “가자” (821) being sequentially combined, determine whether the word “가자” (821) is appropriate in context. The processor (120) can determine the word “가자” (821) based on the word “산에 가자”.

[0153] For example, when dividing a character area based on the third dividing point (830), the processor (120) can identify “가” corresponding to the first character and “사” corresponding to the second character. The processor (120) can recognize the word “가사” (831) by combining the first character (“가”) and the second character (“사”). The processor (120) can identify the word “송” (832) described above based on the word “가사” (831), and in response to the word “송” (832) and the word “가사” (831) being sequentially combined, determine whether the word “가사” (831) is contextually appropriate. The processor (120) can determine the word “가사” (831) based on the word “송LYRICS”. For another example, the processor (120) can identify the word “lyrics” (831) described later based on the word “lyrics” (831), and in response to the word “lyrics” (831) and the word “lyrics” (833) being sequentially combined, determine whether the word “lyrics” (831) is contextually appropriate. The processor (120) can determine the word “lyrics” (831) based on the word “lyrics writing”.

[0154] According to one embodiment, the electronic device (101) can recognize a word in relation to a character area divided based on a dividing point, and can identify the first word described above and the second word described below based on the recognized word. The processor (120) can identify at least one combination among a first combination between the first word and the one word, a second combination between the one word and the second word, and / or a third combination of the first word, the one word, and the second word, and determine the one word.

[0155] According to one embodiment, when recognizing a word, the electronic device (101) may change a dividing point corresponding to a criterion for distinguishing a letter area if it is determined that the combination with the first letter described above or the combination with the second letter described below is inappropriate.

[0156] FIG. 9A is an exemplary diagram for determining a cluster based on coordinate information (e.g., xy coordinate information) corresponding to a user input according to one embodiment of the present disclosure. FIG. 9B is an exemplary diagram for distinguishing a first cluster and a second cluster based on coordinate information (e.g., xz coordinate information) corresponding to a user input according to one embodiment of the present disclosure. FIG. 9C is an exemplary diagram for recognizing a first letter corresponding to a first cluster and a second letter corresponding to a second cluster according to one embodiment of the present disclosure.

[0157] The electronic device (101) of FIGS. 9A to 9C may be at least partially similar to the electronic device (101) of FIGS. 1 and 2, or may further include other embodiments of the electronic device (101). In one embodiment, the electronic device (101) may include at least partially similar components to the electronic device (101) of FIG. 1.

[0158] According to one embodiment, the processor (120) of the electronic device (101) (e.g., the processor (120) of FIG. 3) can recognize a drawing object (901) (e.g., the drawing object (201) of FIG. 2) according to a user input. Referring to FIG. 9A, the processor (120) can, in response to a user input on a touchscreen display (e.g., the touchscreen display (360) of FIG. 3), identify a drawing object (901) corresponding to the user input based on coordinate information (e.g., xy coordinate information, pixel coordinate information). The processor (120) can obtain x-coordinate information and y-coordinate information corresponding to the drawing object (901), and can obtain z-coordinate information according to the point in time, order, and time at which the drawing object (901) is input. According to one embodiment, the processor (120) may obtain x-coordinate information and y-coordinate information indicating the position of a coordinate point in relation to the drawing object (901), and / or z-coordinate information indicating the input order (e.g., input point, input time) of the drawing object (901).

[0159] Referring to FIG. 9A, the processor (120) may obtain coordinate information corresponding to an image object (901) (e.g., a letter “thing”). For example, the image object (901) may include cluster (e.g., a group, a set, a group) information including a plurality of coordinate points. According to one embodiment, the electronic device (101) may obtain a drawing object (901) corresponding to a user input using a clustering algorithm. For example, the clustering algorithm may include various methods such as K-means and a Gaussian mixture model (GMM).

[0160] Referring to FIG. 9B, the processor (120) can implement an xz graph (902) based on x-coordinate information and z-coordinate information corresponding to a drawing object (901). The processor (120) can implement an xz graph (902) in which coordinate points of the drawing object (901) are listed at regular time intervals. The processor (120) can check first coordinate information (922) corresponding to a first character area and second coordinate information (923) corresponding to a second character area based on the xz graph (902). The first coordinate information (922) can be implemented as a first cluster, and the second coordinate information (923) can be implemented as a second cluster.

[0161] For example, the processor (120) can recognize intermediate coordinate information (921) (e.g., coordinate information corresponding to an optimal candidate line) at which two letters are at least partially connected based on the z-coordinate information, and, based on the intermediate coordinate information (921), can check first coordinate information (922) that is input relatively earlier than the intermediate coordinate information (921) and second coordinate information (923) that is input relatively later than the intermediate coordinate information (921). For example, the processor (120) can recognize a first letter (e.g., “thing”) based on the first coordinate information (922), and can recognize a second letter (e.g., “eul”) based on the second coordinate information (923).

[0162] For another example, a first cluster (e.g., first coordinate information (922)) may include a first center of gravity, and a second cluster (e.g., second coordinate information (923)) may include a second center of gravity. The first cluster may include a plurality of pieces of coordinate information (e.g., first coordinate information (922)) arranged within a certain distance from the first center of gravity. The second cluster may include a plurality of pieces of coordinate information (e.g., second coordinate information (923)) arranged within a certain distance from the second center of gravity. For another example, the intermediate coordinate information (921) may include coordinate information that is not included in the first cluster (922) or the second cluster (923).

[0163] Referring to FIG. 9C, the processor (120) can implement an xy graph (903) based on x-coordinate information and y-coordinate information corresponding to a drawing object (901). The processor (120) can recognize a first character area (932) corresponding to a first cluster (922) and a second character area (933) corresponding to a second cluster (923). The processor (120) can recognize intermediate coordinate information (931) based on the xy graph (903). The processor (120) can recognize a first character (e.g., “thing”) corresponding to the first character area (932) and a second character (e.g., “eul”) corresponding to the second character area (933). The processor (120) can combine the first character (e.g., “thing”) and the second character (e.g., “eul”) to determine one word (e.g., “thing”).

[0164] A method for recognizing characters in an electronic device (101) according to one embodiment may include an operation of detecting at least two reference points for a user input through a touch screen display (360), an operation of determining a plurality of candidate lines based on the detected at least two reference points, an operation of determining an optimal candidate line that satisfies a candidate line selection condition among the plurality of candidate lines, an operation of dividing at least two character areas based on a dividing point included in the optimal candidate line, and an operation of confirming a first character corresponding to a first character area and a second character corresponding to a second character area among the at least two character areas.

[0165] The method according to one embodiment may further include an operation of recognizing at least one word based on the first letter and the second letter.

[0166] The method according to one embodiment may further include an operation of identifying the first word described above, centered on the at least one recognized word, and an operation of determining a first candidate word based on a combination between the identified first word and the at least one recognized word.

[0167] The method according to one embodiment may further include an operation of identifying a second word described below based on the at least one recognized word, and an operation of determining a second candidate word based on a combination between the at least one recognized word and the identified second word.

[0168] The method according to one embodiment may further include an operation of changing the splitting point included in the optimal candidate line when the first candidate word and the second candidate word do not match.

[0169] The operation of distinguishing at least two character areas according to one embodiment may include an operation of distinguishing the first character area and the second character area based on a dividing point included in the optimal candidate line when the first reliability corresponding to the character input by the user is lower than the second reliability for the first character and the second character.

[0170] The operation of detecting at least two reference points according to one embodiment may include an operation of detecting the at least two reference points based on a point at which the direction change occurs, when an angle change amount due to a change in direction of the user input exceeds a set value.

[0171] According to one embodiment, the candidate line selection conditions may include a first condition that the candidate line is longer than a set length, a second condition that the movement direction of the user input satisfies a preset specific pattern (e.g., a pattern that moves from left-bottom to right-top), and a third condition that the width-to-height ratio of a character area determined based on the candidate line is included within a set range. The operation of determining the optimal candidate line according to one embodiment may include an operation of determining the optimal candidate line that satisfies all of the first condition, the second condition, and the third condition included in the candidate line selection conditions.

[0172] According to one embodiment, the method may further include an operation of confirming first coordinate information and second coordinate information indicating a location of the user input based on the user input through the touch screen display, an operation of confirming third coordinate information indicating an input order of the user input, an operation of distinguishing a first cluster and a second cluster based on the first coordinate information, the second coordinate information, and the third coordinate information, and an operation of confirming a first letter corresponding to the first cluster and a second letter corresponding to the second cluster.

[0173] According to one embodiment, a non-transitory computer-readable storage medium (or, computer program product) storing one or more programs for performing a character recognition method of an electronic device (101) may be described. According to one embodiment, the one or more programs may include instructions that, when executed by a processor (120) of the electronic device (101), perform the following operations: detecting at least two reference points for a user input through a touchscreen display (160), determining a plurality of candidate lines based on the detected at least two reference points, determining an optimal candidate line satisfying a candidate line selection condition among the plurality of candidate lines, dividing at least two character areas based on a dividing point included in the optimal candidate line, and identifying a first character corresponding to a first character area and a second character corresponding to a second character area among the at least two character areas.

[0174] According to another embodiment, a method for recognizing characters in an electronic device (101) may include an operation of detecting at least two reference points for a user input through a touch screen display (360), an operation of determining at least one dividing point included in a candidate line determined based on the at least two reference points, an operation of confirming one word corresponding to the first character area and the second character area based on a first character area and a second character area divided based on the at least one dividing point, an operation of confirming the first word described above based on the one word, an operation of confirming the second word described below based on the one word, an operation of determining a first candidate word corresponding to the one word based on a combination between the first word and the one word, an operation of determining a second candidate word corresponding to the one word based on a combination between the one word and the second word, and an operation of determining the one word when the first candidate word and the second candidate word match.

[0175] A method according to another embodiment may further include an operation of changing the at least one splitting point if the first candidate word and the second candidate word do not match.

[0176] Electronic devices according to the various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to the embodiments of this document are not limited to the aforementioned devices.

[0177] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the 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 the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0178] The term "module" used in various embodiments of this document 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. A module may be an integral component, or a minimum unit or part of such a component 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).

[0179] Various embodiments of the present document may be implemented as software (e.g., a program (140)) including one or more instructions stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120)) of the machine (e.g., an electronic device (101)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate 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 executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0180] According to one embodiment, the method according to various embodiments disclosed in the present document may be provided as included in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) via an application store (e.g., Play Store™) or directly between two user devices (e.g., smart phones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0181] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and placed in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component 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 (101), Touchscreen display (360); processor (120); and A memory (130) for storing instructions; When the above instructions are executed by the processor (120), the electronic device (101) causes: Based on the user input through the touch screen display (160), at least two reference points for the user input are detected, Determine multiple candidate lines based on at least two reference points detected above, Among the above multiple candidate lines, the optimal candidate line that satisfies the candidate line selection conditions is determined, At least two character areas are separated based on the split points included in the above optimal candidate line, An electronic device that identifies a first letter corresponding to a first letter area and a second letter corresponding to a second letter area among at least two letter areas.

2. In paragraph 1, When the above instructions are executed by the processor (120), the electronic device (101) causes: An electronic device that recognizes at least one word based on the first letter and the second letter.

3. In paragraph 2, When the above instructions are executed by the processor (120), the electronic device (101) causes: Identify the first word described above, centering on at least one word recognized above, Determine a first candidate word based on a combination between the first word identified above and at least one word recognized above, Based on at least one of the above recognized words, the second word described below is identified, An electronic device that determines a second candidate word based on a combination between at least one recognized word and the identified second word.

4. In paragraph 3, When the above instructions are executed by the processor (120), the electronic device (101) causes: An electronic device that changes the division point included in the optimal candidate line when the first candidate word and the second candidate word do not match.

5. In paragraph 1, When the above instructions are executed by the processor (120), the electronic device (101) causes: An electronic device that divides the first character area and the second character area based on a dividing point included in the optimal candidate line when the first reliability corresponding to the character input by the user is lower than the second reliability for the first character and the second character.

6. In paragraph 1, When the above instructions are executed by the processor (120), the electronic device (101) causes: An electronic device that detects at least two reference points based on the point at which the direction change occurs when the amount of angular change due to the change in direction of the user input exceeds a set value.

7. In paragraph 1, The above candidate line selection conditions include a first condition in which the candidate line is longer than a set length, a second condition in which the movement direction of the user input satisfies a preset specific pattern, and a third condition in which the width-height ratio of the character area determined based on the candidate line is within a preset range. When the above instructions are executed by the processor (120), the electronic device (101) causes: An electronic device that determines the optimal candidate line that satisfies all of the first condition, the second condition, and the third condition included in the candidate line selection conditions.

8. In paragraph 1, When the above instructions are executed by the processor (120), the electronic device (101) causes: Based on the user input through the touch screen display (360), first coordinate information and second coordinate information indicating the location of the user input are confirmed, Check the third coordinate information indicating the input order of the above user input, Based on the first coordinate information, the second coordinate information, and the third coordinate information, the first cluster and the second cluster are distinguished, An electronic device that verifies a first letter corresponding to the first cluster and a second letter corresponding to the second cluster.

9. In a method for recognizing characters in an electronic device (101), An operation of detecting at least two reference points for a user input based on a user input via a touch screen display (360); An operation of determining a plurality of candidate lines based on at least two reference points detected above; An operation of determining an optimal candidate line that satisfies a candidate line selection condition among the above multiple candidate lines; An operation of dividing at least two character areas based on a dividing point included in the above optimal candidate line; and A method comprising: an operation of identifying a first character corresponding to a first character area and a second character corresponding to a second character area among at least two character areas; 10. In paragraph 9, A method further comprising: an operation of recognizing at least one word based on the first letter and the second letter; 11. In paragraph 10, An operation of confirming the first word described above, centered on at least one word recognized above; An operation of determining a first candidate word based on a combination between the first word identified above and at least one word recognized above; An operation of confirming a second word described below, centered on at least one word recognized above; An operation of determining a second candidate word based on a combination between at least one recognized word and the identified second word; and A method further comprising: an operation of changing the division point included in the optimal candidate line when the first candidate word and the second candidate word do not match; 12. In paragraph 9, The above action of separating at least two character areas is, A method comprising: an operation of dividing the first character area and the second character area based on a dividing point included in the optimal candidate line when the first reliability corresponding to the character input by the user is lower than the second reliability for the first character and the second character; 13. In paragraph 9, The operation of detecting at least two reference points above is: A method comprising: an operation of detecting at least two reference points based on a point where the direction change occurs, when the amount of angular change due to a change in direction of the user input exceeds a set value; 14. In paragraph 9, The above candidate line selection conditions include a first condition in which the candidate line is longer than a set length, a second condition in which the movement direction of the user input satisfies a preset specific pattern, and a third condition in which the width-height ratio of the character area determined based on the candidate line is within a preset range. The operation of determining the above optimal candidate line is: A method comprising: an operation of determining the optimal candidate line that satisfies all of the first condition, the second condition, and the third condition included in the candidate line selection conditions; 15. In a non-transitory computer-readable storage medium storing one or more programs for performing a character recognition method of an electronic device (101), When the above one or more programs are executed by the processor (120) of the electronic device (101), An operation of detecting at least two reference points for a user input based on a user input via a touch screen display (160); An operation of determining a plurality of candidate lines based on at least two reference points detected above; An operation of determining an optimal candidate line that satisfies a candidate line selection condition among the above multiple candidate lines; An operation of dividing at least two character areas based on a dividing point included in the above optimal candidate line; and A computer-readable storage medium including commands for performing an operation of identifying a first character corresponding to a first character area and a second character corresponding to a second character area among at least two character areas.

Images