KR20220142896A - English education method using learning level and service system therefor - Google Patents

Abstract

According to various embodiments of the present invention, the present invention relates to an English education method using a learning level and a service system therefor. According to the present invention, an English education with a method of simply memorizing grammar or words can cause a learner to lose interest and motivation in English education, and a learning effect is not high due to the simplicity of content including only a text. According to various embodiments of a server and an operating method thereof, learning content for each individual is produced based on a preferred category of a user, and an image related to the learning content is also provided for a user device to increase a learning effect. In addition, a hint word can be provided for a user on the basis of the completeness of an English sentence answered by the user.

Description

English education method using learning level and service system therefor

Various embodiments of the present invention relate to a method of teaching English using a learning level and a service system therefor.

Various embodiments of the present invention relate to a server providing an English learning service and an operating method thereof.

Thanks to the influence of the Internet, online education programs using the Internet have been in the spotlight and widely used in the education world. In most online education systems, lectures by lecturers of the subject are produced as video files, uploaded to the Internet through an education server, and then the user downloads and watches the lectures he or she wants regardless of time and place with a PC connected to the Internet. It provides streaming-type Lecture On Demand (LOD) training materials that can be learned.

This online education system enables multimedia Internet home-based learning in which users download and play educational materials (including videos, voices, texts, etc.) from education-related websites such as cyber universities and Internet education companies. Training materials can be repeated through a PC anytime, anywhere, and the user can send and receive questions about training materials or lecture evaluations with an educational service provider through the Internet.

No. 10-2002-0005242 (2002.01.17)

English education by simply memorizing grammar or words may cause learners to lose interest and motivation for English education, and there is a problem in that the learning effect is not high due to the simplicity of the content composed only of text.

A server and an operating method thereof according to various embodiments of the present invention produce individual learning content based on a user's preferred category, and provide an image related to the learning content to a user device in order to increase learning efficiency, and provide an answer by the user A hint word may be provided to the user based on the completeness of an English sentence.

The technical problems to be achieved in the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those of ordinary skill in the art to which the present invention belongs from the description below. will be able

According to various embodiments, a server providing an English learning service includes a communication interface, and a processor, wherein the processor identifies a preference category of a user using the user device, and crawls the web based on the preference category ( web crawling), select learning content including an English sentence corresponding to the learning level of the user and a Korean sentence translated from the English sentence at the same time, and the English sentence included in the learning content and By analyzing the Korean sentence, a pair is formed with an English word corresponding to a predetermined part-of-speech in the English sentence, a Korean word corresponding to the predetermined part-of-speech is selected from the Korean sentence, and using the web crawling, the collecting first images corresponding to a Korean word and collecting second images corresponding to the English word; collect second images, and when the user device is connected to a Wi-Fi network, collect the first images and the second images corresponding to still images or moving images; by determining a first similarity between the second images, and associating a representative image having the highest similarity to the second images among the first images with the Korean word - the predetermined part-of-speech in the Korean sentence An operation of associating representative images is performed for all words corresponding to -, providing the Korean sentence to which the representative images are related to the user device through the communication interface, and from the user device through the communication interface receiving a comparison target English sentence for the Korean sentence, and determining a second degree of similarity between the comparison target English sentence and the English sentence as a correct answer sentence using a doc2vec algorithm, and When the second similarity is less than or equal to the first threshold and greater than or equal to a second threshold lower than the first threshold: 1) Using the word2vec algorithm, the query English word included in the comparison target English sentence and the correct English included in the English sentence Determining the third degree of similarity between the words - The operation of determining the similarity of all the query words included in the English sentence to be compared with all the correct English words included in the English sentence is performed-, 2) the above When the third similarity is less than the third threshold, a word corresponding to the basic form of the correct English word is provided to the user device as a hint word, and 3) when the third similarity exceeds the fourth threshold, providing the antonym of the correct English word as the hint word to the user device, and 4) when the third degree of similarity is greater than or equal to the third threshold and less than or equal to the fourth threshold, a synonym of the correct English word is provided as the hint word may be set to be provided to the user device as

According to various embodiments, when the second similarity exceeds the first threshold, the processor processes the English sentence to be compared as a correct answer, and provides the English sentence to the user device through the communication interface, , and when the second similarity is less than the second threshold, the English sentence to be compared may be treated as an incorrect answer, and the English sentence may be provided to the user device through the communication interface.

According to various embodiments, the processor processes the first images and the second images according to a specific criterion for extracting a texture feature and a shape feature, and converts the processing result into an index according to a criterion for synthesizing the Indexing the first images and the second images, processing the target building design according to the specific criterion, and determining the first similarity using a value converted according to a criterion for synthesizing the processing result and the specific criterion is set below in the first images and the second images to extract the texture feature from the first images and the second images, and calculate a vector of the texture feature. applying Equation 1 of , and the specific criterion is to extract the shape feature from the first images and the second images, and to calculate the shape feature, the first images and the second images Equation 2 below can be applied to

[Equation 1]

[Equation 2]

According to various embodiments, the processor is configured to: the first images and the second images processed according to the specific criterion to calculate the first similarity between the first images and the second images It may be set to calculate the distance value between the two by applying Equation 3 below.

[Equation 3]

According to various embodiments, the processor is configured to calculate the second degree of similarity between the comparison target English sentence and the English sentence by applying Equation 4 below, using the doc2vec algorithm, and the comparison target English sentence doc2vec of English sentence p is [p ₁ , p ₂ , … , p _n ], and doc2vec of the English sentence q is [q ₁ , q ₂ , ... , q _n ].

[Equation 4]

According to various embodiments, the processor vectorizes the query English word and the correct English word using Equation 5 below based on the skip-gram model of the word2vec algorithm, and based on the cosine similarity It may be set to determine the third degree of similarity between the query English word and the correct English word using Equation 6 below.

[Equation 5]

[Equation 6]

According to various embodiments of the present invention, by providing content for learning to the user device based on the user's preferred category and providing hint words to the user based on the completeness of the English sentence answered by the user, the user's English learning is improved. efficiency can be increased.

The effects obtainable in the present invention are not limited to the above-mentioned effects, and other effects not mentioned may be clearly understood by those of ordinary skill in the art from the following description. will be.

Other aspects, features and benefits as described above of certain preferred embodiments of the present invention will become more apparent from the following description taken in conjunction with the accompanying drawings.
1 is a block diagram of an electronic device and a network according to various embodiments of the present disclosure;
2 is a block diagram of an electronic device according to various embodiments of the present disclosure;
3 is a block diagram of a program module according to various embodiments of the present disclosure;
4A to 4C are flowcharts illustrating a method of an electronic device providing an English learning service, according to various embodiments of the present disclosure;
5 is a diagram illustrating query content provided by an electronic device to a user device according to various embodiments of the present disclosure;
6 is an exemplary diagram for explaining a process of converting a sentence into an embedding vector according to various embodiments of the present disclosure;
7 is a diagram illustrating a skip-gram model of a word2vec algorithm, according to various embodiments.

Hereinafter, various embodiments of the present document will be described with reference to the accompanying drawings. The examples and terms used therein are not intended to limit the technology described in this document to specific embodiments, and should be understood to cover various modifications, equivalents, and/or substitutions of the embodiments. In connection with the description of the drawings, like reference numerals may be used for like components. The singular expression may include the plural expression unless the context clearly dictates otherwise. In this document, expressions such as “A or B” or “at least one of A and/or B” may include all possible combinations of items listed together. Expressions such as "first," "second," "first," or "second," can modify the corresponding elements, regardless of order or importance, and to distinguish one element from another element. It is used only and does not limit the corresponding components. When an (eg, first) component is referred to as being “connected (functionally or communicatively)” or “connected” to another (eg, second) component, that component is It may be directly connected to the component or may be connected through another component (eg, a third component).

In this document, "configured (or configured to)" means "suitable for," "having the ability to," "modified to, ," "made to," "capable of," or "designed to," may be used interchangeably. In some contexts, the expression “a device configured to” may mean that the device is “capable of” with other devices or components. For example, the phrase “a processor configured (or configured to perform) A, B, and C” refers to a dedicated processor (eg, an embedded processor) for performing the operations, or by executing one or more software programs stored in a memory device. , may refer to a general-purpose processor (eg, a CPU or an application processor) capable of performing corresponding operations.

The electronic device according to various embodiments of the present disclosure may include, for example, a smartphone, a tablet PC, a mobile phone, a video phone, an e-book reader, a desktop PC, a laptop PC, a netbook computer, a workstation, a server, a PDA, and a PMP. It may include at least one of a portable multimedia player, an MP3 player, a medical device, a camera, and a wearable device. A wearable device may be an accessory (e.g., watch, ring, bracelet, anklet, necklace, eyewear, contact lens, or head-mounted-device (HMD)), a textile or clothing integral (e.g. electronic garment); It may include at least one of a body-worn (eg, skin pad or tattoo) or bioimplantable circuit In some embodiments, the electronic device may include, for example, a television, a digital video disk (DVD) player, Audio, refrigerator, air conditioner, vacuum cleaner, oven, microwave oven, washing machine, air purifier, set-top box, home automation control panel, security control panel, media box (e.g. Samsung HomeSync ^TM , Apple TV ^TM , or Google TV ^TM ) , a game console (eg, Xbox ^TM , PlayStation ^TM ), an electronic dictionary, an electronic key, a camcorder, or an electronic picture frame.

In another embodiment, the electronic device may include various medical devices (eg, various portable medical measuring devices (eg, a blood glucose meter, a heart rate monitor, a blood pressure monitor, or a body temperature monitor), magnetic resonance angiography (MRA), magnetic resonance imaging (MRI), Computed tomography (CT), imagers, or ultrasound machines, etc.), navigation devices, global navigation satellite systems (GNSS), event data recorders (EDRs), flight data recorders (FDRs), automotive infotainment devices, marine electronic equipment (e.g. navigation devices for ships, gyro compasses, etc.), avionics, security devices, head units for vehicles, industrial or household robots, drones, ATMs in financial institutions, point of sale (POS) in stores of sales) or IoT devices (eg, light bulbs, various sensors, sprinkler devices, fire alarms, thermostats, street lights, toasters, exercise equipment, hot water tanks, heaters, boilers, etc.). According to some embodiments, the electronic device is a piece of furniture, a building/structure, or a vehicle, an electronic board, an electronic signature receiving device, a projector, or various measuring devices (eg, water, electricity, gas, or a radio wave measuring device). In various embodiments, the electronic device may be flexible or a combination of two or more of the various devices described above. The electronic device according to the embodiment of the present document is not limited to the above-described devices. In this document, the term user may refer to a person who uses an electronic device or a device (eg, an artificial intelligence electronic device) using the electronic device.

1 , an electronic device 101 in a network environment 100 is described, in various embodiments. Meanwhile, the electronic device 101 according to various embodiments will be described later with reference to FIGS. 1 to 3 .

4A to 4C are first flowcharts for explaining a method of providing an English language learning service by an electronic device (eg, the electronic device 101 of FIG. 1 ) according to various embodiments of the present disclosure.

5 is a diagram illustrating query content provided by the electronic device 101 to the user device 102 according to various embodiments of the present disclosure.

6 is an exemplary diagram for explaining a process of converting a sentence into an embedding vector according to various embodiments of the present disclosure;

7 is a diagram illustrating a skip-gram model of a word2vec algorithm, according to various embodiments.

According to various embodiments, the electronic device 101 communicates with a user device (eg, the electronic device 102 of FIG. 1 ) (eg, a smartphone) through a communication network, and displays a plurality of execution screens with the user device 102 . It may be a server that operates an application related to English learning composed of The electronic device 101 may transmit a source code enabling the user device 102 to display each execution screen of a dedicated application or website to the user device 102 , and the user device 102 may send the source code to the user device 102 . may be received, and the requested execution screen may be displayed through the dedicated application or web browser.

In operation 401 , according to various embodiments, the electronic device 101 (eg, the processor 120 of FIG. 1 ) may identify a preference category of a user who uses the user device 102 . The reason for checking the user's preference category is to increase the concentration of the user by studying a foreign language using contents corresponding to the user's interest field when studying a foreign language such as English.

According to an embodiment, the electronic device 101 is configured based on log data of the user device 102 processed for a predetermined previous period (eg, 24 hours) from the point in time when the user device 102 executes the English learning application. A preference category of a user who uses the user device 102 may be identified. In this case, the electronic device 101 is the log data of the user device 102 , based on a web search history, a web access record, an SNS application use record, a media playback record, etc. You can check the category.

According to an embodiment, the electronic device 101 may receive information on the preference category directly selected by the user through the English learning application according to the present invention from the user device 102, and based on the received information, the user A preference category of a user using the device 102 may be identified.

In operation 403 , according to various embodiments, the electronic device 101 (eg, the processor 120 of FIG. 1 ) selects the user from among the contents collected using web crawling based on the user's preference category. It is possible to select content for learning that includes an English sentence corresponding to a learning level of , and a Korean sentence translated from the English sentence at the same time.

According to an embodiment, the electronic device 101 may collect content corresponding to a user's preference category by using web crawling. According to an embodiment, the electronic device 101 may include a crawler, a parser, and an indexer to collect web documents online and access various types of text information included in the web documents. For example, the crawler may collect a list of web addresses of a preference category (ie, an area of interest), check a website, and transmit the text data to the electronic device 101 by tracking a link. At this time, the parser interprets the web document collected during the crawling process to extract text information contained in the page, and the indexer can index the location and meaning. For example, the electronic device 101 uses a word representing a preference category (eg, incident accident) as a key keyword, and uses the word 'domestic issue accident', 'overseas issue accident', 'absurd accident that occurred today', etc. Web crawling may be performed by combining related related keywords with core keywords, and learning contents including both English sentences and Korean sentences may be collected among movie-related news articles published by the news article providing server. According to an embodiment, the electronic device 101 may designate in advance a website that publishes news including both English sentences and Korean sentences for learning English as a target website to perform web crawling.

According to an embodiment, the electronic device 101 translates an English sentence (eg, "The boat crashed into a reef and shot under an arched bridge") corresponding to the user's learning level and the English sentence from the collected content. You can select learning content that contains one Korean sentence at the same time (eg, "The boat galloped under an arched bridge after crashing into a reef"). According to an embodiment, the electronic device 101 may determine the user's learning level based on the user's previous learning data or the learning level directly input by the user. For example, the electronic device 101 may classify the user's learning level into five levels, and select a grammar format (eg, type 1 to type 5) corresponding to the user's learning level (eg, level 1 to level 5). can be checked According to an embodiment, the electronic device 101 may recognize and analyze text data included in the collected content using a natural language understanding module (NLU module), and from the analyzed text data It is possible to select content for learning that includes both an English sentence having a grammar format corresponding to the user's learning level and a Korean sentence translated from the English sentence.

In operation 405 , according to various embodiments, the electronic device 101 (eg, the processor 120 of FIG. 1 ) analyzes the English sentence and the Korean sentence included in the learning content in advance in the English sentence. A pair may be formed with an English word corresponding to a predetermined part-of-speech, and a Korean word corresponding to the predetermined part-of-speech may be selected from the Korean sentence.

According to an embodiment, the electronic device 101 may check the English sentence and the Korean sentence by analyzing the English sentence and the Korean sentence included in the learning content by using the natural language understanding module, and may correspond to a predetermined part of speech. and English words and Korean words that are semantically paired with each other can be selected. For example, the electronic device 101 corresponds to a predetermined part-of-speech (eg, a noun) and semantically pairs English words and Korean words (eg, "boat and boat", "reef and reef", "arched"). bridge and arched bridge"). As another example, the electronic device 101 may use an English word and a Korean word (eg, “crash and collide”, “shot, and run”) that are paired with each other in meaning corresponding to a predetermined part-of-speech (eg, a verb). ") can be selected.

In operation 407, according to various embodiments, the electronic device 101 (eg, the processor 120 of FIG. 1 ) collects first images corresponding to the Korean word using web crawling, and adds the first images to the English word. Corresponding second images may be collected. For example, the electronic device 101 may access a web site providing a search service, search for first images corresponding to “boat”, and search for second images corresponding to “boat”. The technique using the web crawling may use the method described in operation 403 . According to an embodiment, when the user device 102 is in a state of being connected to a cellular network (eg, a 3G network or an LTE network), the electronic device 101 displays first images and second images corresponding only to still images. and, when the user device 102 is connected to the Wi-Fi network, first images and second images corresponding to still images or moving images may be collected. This is to minimize data usage of the user device 102 by providing an image corresponding only to a still image to the user device 102 when the user device 102 is connected to the cellular network.

In operation 409, according to various embodiments, the electronic device 101 (eg, the processor 120 of FIG. 1 ) determines a first similarity between the first images and the second images, A representative image having the highest similarity to the second images among 1 images may be associated with the Korean word.

According to various embodiments, the electronic device 101 (eg, the processor 120 of FIG. 1 ) may display first images corresponding to a Korean word (eg, “boat”) and an English word (eg, “boat”). When the second images corresponding to are collected, the first similarity between the first images and the second images may be determined, and one specific one having the highest similarity to the second images among the first images An image can be selected as a representative image. According to an embodiment, after collecting the first images and the second images, the electronic device 101 may pre-process the first images and the second images for comparison. The pre-processing of the images may change the scale of the images themselves according to a preset format, change the size, or change the resolution. According to an embodiment, the electronic device 101 may convert the first images and the second images to gray scale. The electronic device 101 may extract a texture feature and a shape feature from the first images and the second images, and since the corresponding feature is not dependent on a color value, it is preferable to convert it to a gray scale in which only a saturation value and a contrast value exist. This is because the amount of resources required for subsequent processing can be reduced.

The electronic device 101 may extract a texture feature by applying a Gabor filter to the first images and the second images. More specifically, the electronic device 101 may extract the texture feature by transforming the first images and the second images into a frequency space and Gabor filtering. Texture in an image, that is, texture information, has been studied for a long time as one of the important visual features that characterize the image. This texture feature of the image can be used as a major low-level descriptor in extracting labels from the image, indexing and abstracting the extracted labels. In addition, the texture features of the image can be used as important for content-based searches in tile or textile databases. The Gabor filter is an algorithm used to extract a feature vector from an image and corresponds to a Vander pass filter using a Gaussian function. The gabor filter may extract a 2D vector for a texture feature from the first images and the second images according to Equation 1 below.

[Equation 1]

Also, the electronic device 101 may extract a shape feature from the first images and the second images. For example, the electronic device 101 may extract the shape feature by applying the HOG algorithm. Although various versions of the HOG feature may exist, the main concept is an algorithm for calculating local features of an object and extracting shape features of an object from an image using uniform intensity distribution of the features of the object. The electronic device 101 may extract a low-dimensional vector for a shape feature from the first images and the second images according to Equation 2 below.

[Equation 2]

Thereafter, the electronic device 101 may calculate a first similarity between the first images and the second images by merging vectors for the extracted features. According to an embodiment, the electronic device 101 may compare the sets of feature descriptors of the first images and the second images to determine whether the first images and the second images are identical to each other. Specifically, the electronic device 101 may determine a distance (ie, a first degree of similarity) between the feature descriptor vector value of the first images and the feature descriptor vector value of the second images. According to an embodiment, the electronic device 101 may calculate a distance value between the first images and the second images according to Equation 3 below, and based on this, the second image among the first images A specific image having the highest similarity to the images may be selected as the representative image. That is, as a result of comparing the first images and the second images, the electronic device 101 compares the first images and the second images, and the pair of first specific images (ie, images corresponding to “boat”) and the second specific images determined to be the most similar (ie, an image corresponding to "boat") may be checked, and a first specific image may be selected as a representative image.

[Equation 3]

According to an embodiment, the electronic device 101 may associate a representative image selected from among the first images with a Korean word (eg, “boat”). According to an embodiment, the electronic device 101 may perform an operation of associating representative images with respect to all words corresponding to a predetermined part-of-speech in a Korean sentence included in the learning content. For example, the electronic device 101 may display all Korean words (eg, "boat", "reef", "arch bridge", "collide", "run "), an operation of associating a corresponding representative image may be performed for each.

In operation 411 , according to various embodiments, the electronic device 101 (eg, the processor 120 of FIG. 1 ) associates representative images through a communication interface (eg, the communication interface 170 of FIG. 1 ). Korean sentences may be provided to the user device 102 . For example, referring to FIG. 5 , the electronic device 101 uses an English learning application to display representative images for Korean words corresponding to a predetermined part-of-speech and a Korean sentence 511 (eg: "The boat galloped under the arched bridge after it collided with the reef.") may be included in query content 510 and provided to user device 102 , which user device 102 may provide for querying content 510 . The content 510 may be received from the electronic device 101 and displayed through the display.

In operation 413 , according to various embodiments, the electronic device 101 (eg, the processor 120 of FIG. 1 ) receives information included in the query content 510 from the user device 102 through the communication interface 170 . An English sentence to be compared with respect to the Korean sentence 511 may be received. For example, the user may input into the user device 102 an English translation of a Korean sentence (eg, "The boat galloped under an arched bridge after colliding with a reef") into English. Also, the electronic device 101 may receive the comparison target English sentence input by the user from the user device 102 .

In operation 415 , according to various embodiments, the electronic device 101 (eg, the processor 120 of FIG. 1 ) uses the doc2vec algorithm as a comparison target English sentence and a correct answer sentence received from the user device 102 . A second degree of similarity between English sentences included in the learning content may be determined. For example, referring to FIG. 5 , the electronic device 101 provides a comparison target English sentence input by the user and an English sentence 512 for a correct answer included in the learning content (eg, “The boat crashed into a reef and shot under An arched bridge") can determine a second degree of similarity.

According to various embodiments, the electronic device 101 (eg, the processor 120 of FIG. 1 ) may express the comparison target English sentence and the correct English sentence 512 in the form of a numeric multidimensional vector. Referring to FIG. 6 , the electronic device 101 uses doc2vec, which is an embedding technique for changing a sentence into a numeric vector 501, which is a real value vector, in a multidimensional virtual space 500, so that the comparison target English sentence and the correct English sentence ( 512) can be expressed as a number vector. The electronic device 101 may remove meaningless text information from each of the comparison target English sentence and the correct English sentence 512 using a language preprocessor such as a morpheme analyzer or an index word extractor. For example, after removing unnecessary parts-of-speech words or special symbols (eg, !, ?, /, etc.) from a sentence, and extracting words corresponding to the remaining parts of the sentence, that is, a body language or root, the extracted You can convert a word to a vector of numbers. According to an embodiment, the electronic device 101 calculates the second similarity between the comparison target English sentence and the correct English sentence 512 by using the embedding vectors of each of the comparison target English sentence and the correct English sentence 512 . can In this case, the electronic device 101 may calculate a similarity score between sentences by using a vector set representing words constituting the sentences. For example, the electronic device 101 may calculate the second similarity between the comparison target English sentence and the correct answer English sentence by calculating the Euclidean distance between doc2vec. doc2vec of the English sentence p to be compared is [p1, p2, … , pn], and the doc2vec of the English sentence q for the correct answer is [q1, q2, … , qn], the Euclidean distance representing the similarity between the two sentences p and q may be defined as in Equation 4 below.

[Equation 4]

The electronic device 101 may determine the similarity between sentences from the Euclidean distance between embedding vectors, and in this case, the closer the Euclidean distance is, the higher the sentence similarity may be.

In operation 417, according to various embodiments, the electronic device 101 (eg, the processor 120 of FIG. 1 ) processes the comparison target English sentence as a correct answer when the second similarity exceeds a first threshold, and , the English sentence 512 for the correct answer may be provided to the user device 102 through the communication interface 170 . For example, when the second similarity between the comparison target English sentence and the correct English sentence 512 exceeds a first threshold (eg, 90%), the electronic device 101 processes the comparison target English sentence as the correct answer and , an English sentence 512 for the correct answer may be provided to the user device 102 . This is because, since the user entered a sentence close to the correct answer, it is more helpful in learning to inform the user of the correct answer immediately for the convenience of the user in case of a simple mistake.

In operation 419, according to various embodiments, the electronic device 101 (eg, the processor 120 of FIG. 1 ) performs the comparison target English sentence when the second similarity is less than a second threshold that is lower than the first threshold. The wrong answer may be processed, and the English sentence 512 for the correct answer may be provided to the user device 102 through the communication interface 170 . For example, when the second similarity between the comparison target English sentence and the correct English sentence 512 is less than a second threshold (eg, 40%), the electronic device 101 processes the comparison target English sentence as an incorrect answer, English sentences 512 for use may be provided to the user device 102 . This is to inform the correct answer immediately by determining that the user's learning level is not suitable for the sentence because the user has input a sentence that is almost different from the correct answer.

In operation 421 , according to various embodiments, the electronic device 101 (eg, the processor 120 of FIG. 1 ) performs a word2vec (W2V) algorithm when the second similarity is less than or equal to the first threshold and greater than or equal to the second threshold. , D2V (doc2vec) algorithm, Sent2Vec algorithm, using at least any one of, a third similarity between the query English word included in the comparison target English sentence and the correct English word included in the correct English sentence 512 is determined can do. For example, in the electronic device 101 , the second similarity between the comparison target English sentence and the correct English sentence 512 is less than or equal to a first threshold (eg, 90%) and greater than or equal to a second threshold (eg, 40%). case, using at least one of the W2V (word2vec) algorithm, the D2V (doc2vec) algorithm, and the Sent2Vec algorithm, the query English word included in the comparison target English sentence and the correct English word included in the correct English sentence 512 A third degree of similarity may be determined. This is to provide hints for words incorrectly entered by the user so that the user can directly complete the English sentence for the correct answer.

According to various embodiments, the electronic device 101 (eg, the processor 120 of FIG. 1 ) configures all query English words included in the comparison English target sentence and all correct English words included in the correct English sentence 512 for the correct answer. Words can be vectorized through a language processing algorithm. Here, the language processing algorithm may refer to a word embedding algorithm used in the field of natural language processing. Word embedding is to express words existing in a corpus as vectors having continuous values, and the vectorized word vectors are learned by an algorithm so that other words and contextual meanings can be preserved as much as possible. The word embedding algorithm may include a Neural Network Language Model (NNLM), a Recurrent Neural Net Language Model (RNNLM), and Word2Vec, but the present invention is not limited thereto, and word embedding may be performed by applying various algorithms. Hereinafter, an embodiment based on the Word2Vec algorithm will be described. Word2Vec is a word embedding algorithm using a language model based on a feedforward neural network. It compensates for the problem of NNLM, which takes a lot of time to calculate in the hidden layer and output layer, so that the word learned compared to the simplicity of the neural network configuration. It shows excellent performance for vector representation of Word2Vec learns the meaning of words by using the relationship between words in the sentences of the input corpus and adjacent words, assuming that words with the same context have close meanings. Since words with related meanings are more likely to appear close to each other in the document, the two words can have closer vector values in the process of repeating learning. Word2Vec has two models, continuous bag-of-words (CBOW) and skip-gram model. CBOW is a model that predicts a central word when given a surrounding word, and skip-gram is a model that receives a central word and predicts the surrounding words as opposed to CBOW. Referring to FIG. 7 , a hierarchical diagram of the skip-gram model in the Word2Vec algorithm that can be applied to the present invention is that the words included in the English sentence for comparison and the correct English sentence 512 to be vectorized in the input layer are one- Vectorized by hot-encoding. In the hidden layer, the one-hot-encoding vectorized data is multiplied by weight matrices W and W` and exported to the output layer. Both the input data and the correct answer data of the skip-gram model are one-hot encoded vectors with a size of 1*|V| (= the size of the vocabulary set). W and W' are |V| * It is a matrix with size d (= number of embedding dimensions). In the output layer, SoftMax calculation is performed, and the calculation result is compared with the calculation result of the correct word and backpropagated. Here, the SoftMax calculation may be performed by the following [Equation 5].

[Equation 5]

Here, P(o|c) is the conditional probability that the context word (c) will appear when the target word (o) is given, v _c is the vector value of the target word, and u _o is the vector value of the context word. do. That is, Word2Vec performs learning while updating the weight matrices W and W` in the direction of maximizing the conditional probability P(o|c) according to Equation 5 above, so that vector values corresponding to related words are N They should be located in similar places in the dimensional space. As described above, the electronic device 101 may vectorize the words included in the sentence parsed through learning to generate vectors for each word. The electronic device 101 uses the following [Equation 6] to obtain a cosine similarity (cosine) between the word vectors (a) included in the comparison target English sentence and the word vectors (b) included in the English sentence for the correct answer. similarity) can be calculated. Here, R(a,b) means cosine similarity.

[Equation 6]

According to an embodiment, when there are a plurality of words to be compared, the electronic device 101 may calculate the degree of similarity by assigning a weight to each item. According to an embodiment, the electronic device 101 performs an operation of determining a similarity with all correct English words included in the correct English sentence 512 with respect to all query word words included in the comparison target English sentence. can do.

In operation 423, according to various embodiments, the electronic device 101 (eg, the processor 120 of FIG. 1 ) hints at a word corresponding to the basic form of the correct English word when the third similarity is less than the third threshold. It may be provided to the user device 102 as a hint word. For example, the electronic device 101 determines that the similarity between the first query word included in the comparison target English sentence and the first correct answer English word (eg, “under”) included in the English sentence for the correct answer is a third threshold (eg, “under”). : 50%), a word (eg, "under") corresponding to the basic form of the first correct English word may be provided to the user device 102 as a hint word. According to an embodiment, in order to select a hint word, the electronic device 101 may search for a first correct English word from a website providing a language dictionary service, and may extract the hint word from the search result. .

In operation 425 , according to various embodiments, the electronic device 101 (eg, the processor 120 of FIG. 1 ) performs a word corresponding to the antonym of the correct English word when the third degree of similarity exceeds a fourth threshold. may be provided to the user device 102 as a hint word. For example, the electronic device 101 determines that the degree of similarity between the first query word included in the comparison target English sentence and the first correct answer English word (eg, “under”) included in the correct English sentence is a fourth threshold (eg, “under”). : 80%), an antonym (eg, "above") of the first correct English word may be provided to the user device 102 as a hint word.

In operation 427, according to various embodiments, the electronic device 101 (eg, the processor 120 of FIG. 1 ) determines that when the third similarity is greater than or equal to the third threshold and less than or equal to the fourth threshold, the synonym of the correct English word A word corresponding to may be provided to the user device 102 as a hint word. For example, the electronic device 101 determines that the similarity between the first query word included in the comparison target English sentence and the first correct answer English word (eg, “under”) included in the English sentence for the correct answer is a third threshold (eg, “under”). : 50%) and less than the fourth threshold (80%), a synonym (eg, "below") of the first correct English word may be provided to the user device 102 as a hint word. According to an embodiment, the reason for providing the basic form, antonym, and synonym of the correct English word as the hint word in operations 423 to 427 is to allow the user to easily associate the correct word by looking at the hint word.

An electronic device 101 according to various embodiments will be described with reference to FIGS. 1 to 3 .

The electronic device 101 may include a bus 110 , a processor 120 , a memory 130 , an input/output interface 150 , a display 160 , and a communication interface 170 . In some embodiments, the electronic device 101 may omit at least one of the components or may additionally include other components. The bus 110 may include a circuit that connects the components 110 - 170 to each other and transmits communication (eg, a control message or data) between the components. The processor 120 may include one or more of a central processing unit, an application processor, and a communication processor (CP). The processor 120 may, for example, execute an operation or data processing related to control and/or communication of at least one other component of the electronic device 101 .

The memory 130 may include volatile and/or non-volatile memory. The memory 130 may store, for example, commands or data related to at least one other component of the electronic device 101 . According to one embodiment, the memory 130 may store software and/or a program 140 . Program 140 may include, for example, kernel 141 , middleware 143 , application programming interface (API) 145 , and/or application program (or “application”) 147 , etc. . At least a portion of the kernel 141 , the middleware 143 , or the API 145 may be referred to as an operating system. The kernel 141 is, for example, system resources (eg, middleware 143, API 145, or application program 147) used to execute an operation or function implemented in other programs (eg, middleware 143, API 145, or the application program 147). : The bus 110, the processor 120, the memory 130, etc.) can be controlled or managed. In addition, the kernel 141 may provide an interface capable of controlling or managing system resources by accessing individual components of the electronic device 101 from the middleware 143 , the API 145 , or the application program 147 . can

The middleware 143 may, for example, play an intermediary role so that the API 145 or the application program 147 communicates with the kernel 141 to send and receive data. Also, the middleware 143 may process one or more work requests received from the application program 147 according to priority. For example, the middleware 143 may use a system resource (eg, the bus 110 , the processor 120 , or the memory 130 ) of the electronic device 101 for at least one of the application programs 147 . It can give priority and process the one or more work requests. The API 145 is an interface for the application 147 to control a function provided by the kernel 141 or the middleware 143, for example, at least for file control, window control, image processing, or character control. It can contain one interface or function (eg command). The input/output interface 150 transmits, for example, a command or data input from a user or other external device to other component(s) of the electronic device 101 , or another component ( ) can output a command or data received from the user or other external device.

Display 160 may include, for example, a liquid crystal display (LCD), a light emitting diode (LED) display, an organic light emitting diode (OLED) display, or a microelectromechanical system (MEMS) display, or an electronic paper display. may include The display 160 may, for example, display various contents (eg, text, images, videos, icons, and/or symbols, etc.) to the user. The display 160 may include a touch screen, and may receive, for example, a touch, gesture, proximity, or hovering input using an electronic pen or a part of the user's body. The communication interface 170, for example, sets up communication between the electronic device 101 and an external device (eg, the first external electronic device 102, the second external electronic device 104, or the server 106). can For example, the communication interface 170 may be connected to the network 162 through wireless communication or wired communication to communicate with an external device (eg, the second external electronic device 104 or the server 106 ).

Wireless communication, for example, LTE, LTE Advance (LTE-A), CDMA (code division multiple access), WCDMA (wideband CDMA), UMTS (universal mobile telecommunications system), WiBro (Wireless Broadband), or GSM (Global System for Mobile Communications) may include cellular communication using at least one of. According to one embodiment, the wireless communication is, for example, WiFi (wireless fidelity), Bluetooth, Bluetooth low energy (BLE), Zigbee (Zigbee), NFC (near field communication), magnetic secure transmission (Magnetic Secure Transmission), radio It may include at least one of a frequency (RF) or a body area network (BAN). According to one embodiment, the wireless communication may include GNSS. The GNSS may be, for example, a Global Positioning System (GPS), a Global Navigation Satellite System (Glonass), a Beidou Navigation Satellite System (hereinafter, “Beidou”) or Galileo, the European global satellite-based navigation system. Hereinafter, in this document, "GPS" may be used interchangeably with "GNSS". Wired communication may include, for example, at least one of universal serial bus (USB), high definition multimedia interface (HDMI), recommended standard232 (RS-232), power line communication, or plain old telephone service (POTS). have. The network 162 may include at least one of a telecommunications network, for example, a computer network (eg, a LAN or WAN), the Internet, or a telephone network.

Each of the first and second external electronic devices 102 and 104 may be the same as or different from the electronic device 101 . According to various embodiments, all or part of the operations executed by the electronic device 101 may be executed by one or a plurality of other electronic devices (eg, the electronic devices 102 and 104 , or the server 106 ). Accordingly, when the electronic device 101 is to perform a function or service automatically or upon request, the electronic device 101 performs at least some functions related thereto instead of or in addition to executing the function or service itself. may request from another device (eg, electronic device 102, 104, or server 106) The other electronic device (eg, electronic device 102, 104, or server 106) may request the requested function or The additional function may be executed and the result may be transmitted to the electronic device 101. The electronic device 101 may provide the requested function or service by processing the received result as it is or additionally. For example, cloud computing, distributed computing, or client-server computing technology may be used.

2 is a block diagram of an electronic device 201 according to various embodiments. The electronic device 201 may include, for example, all or a part of the electronic device 101 illustrated in FIG. 1 . The electronic device 201 includes one or more processors (eg, AP) 210 , a communication module 220 , a subscriber identification module 224 , a memory 230 , a sensor module 240 , an input device 250 , a display ( 260 ), an interface 270 , an audio module 280 , a camera module 291 , a power management module 295 , a battery 296 , an indicator 297 , and a motor 298 . The processor 210 may control a plurality of hardware or software components connected to the processor 210 by, for example, driving an operating system or an application program, and may perform various data processing and operations. The processor 210 may be implemented as, for example, a system on chip (SoC). According to an embodiment, the processor 210 may further include a graphic processing unit (GPU) and/or an image signal processor. The processor 210 may include at least some of the components shown in FIG. 2 (eg, the cellular module 221 ). The processor 210 may load a command or data received from at least one of other components (eg, a non-volatile memory) into a volatile memory for processing, and store the result data in the non-volatile memory.

The communication module 220 (eg, the communication interface 170) may have the same or similar configuration. The communication module 220 may include, for example, a cellular module 221 , a WiFi module 223 , a Bluetooth module 225 , a GNSS module 227 , an NFC module 228 , and an RF module 229 . have. The cellular module 221 may provide, for example, a voice call, a video call, a text service, or an Internet service through a communication network. According to an embodiment, the cellular module 221 may use a subscriber identification module (eg, a SIM card) 224 to identify and authenticate the electronic device 201 within a communication network. According to an embodiment, the cellular module 221 may perform at least some of the functions that the processor 210 may provide. According to one embodiment, the cellular module 221 may include a communication processor (CP). According to some embodiments, at least some (eg, two or more) of the cellular module 221 , the WiFi module 223 , the Bluetooth module 225 , the GNSS module 227 , or the NFC module 228 is one integrated chip. (IC) or contained within an IC package. The RF module 229 may transmit/receive a communication signal (eg, an RF signal), for example. The RF module 229 may include, for example, a transceiver, a power amp module (PAM), a frequency filter, a low noise amplifier (LNA), or an antenna. According to another embodiment, at least one of the cellular module 221 , the WiFi module 223 , the Bluetooth module 225 , the GNSS module 227 or the NFC module 228 transmits and receives an RF signal through a separate RF module. can The subscriber identification module 224 may include, for example, a card including a subscriber identification module or an embedded SIM, and may include unique identification information (eg, integrated circuit card identifier (ICCID)) or subscriber information (eg, IMSI). (international mobile subscriber identity)).

The memory 230 (eg, the memory 130 ) may include, for example, an internal memory 232 or an external memory 234 . The internal memory 232 may include, for example, a volatile memory (eg, DRAM, SRAM, or SDRAM, etc.), a non-volatile memory (eg, one time programmable ROM (OTPROM), PROM, EPROM, EEPROM, mask ROM, flash ROM). , a flash memory, a hard drive, or a solid state drive (SSD), etc. The external memory 234 may include a flash drive, for example, a compact flash (CF) or secure digital (SD). ), Micro-SD, Mini-SD, xD (extreme digital), MMC (multi-media card), memory stick, etc. The external memory 234 is functional with the electronic device 201 through various interfaces. may be physically or physically connected.

The sensor module 240 may, for example, measure a physical quantity or sense an operating state of the electronic device 201 , and convert the measured or sensed information into an electrical signal. The sensor module 240 is, for example, a gesture sensor 240A, a gyro sensor 240B, a barometric pressure sensor 240C, a magnetic sensor 240D, an acceleration sensor 240E, a grip sensor 240F, a proximity sensor ( 240G), color sensor (240H) (e.g. RGB (red, green, blue) sensor), biometric sensor (240I), temperature/humidity sensor (240J), illuminance sensor (240K), or UV (ultra violet) sensor ) may include at least one of the sensors 240M. Additionally or alternatively, the sensor module 240 may include, for example, an olfactory (e-nose) sensor, an electromyography (EMG) sensor, an electroencephalogram (EEG) sensor, an electrocardiogram (ECG) sensor, It may include an infrared (IR) sensor, an iris sensor, and/or a fingerprint sensor. The sensor module 240 may further include a control circuit for controlling at least one or more sensors included therein. In some embodiments, the electronic device 201 further comprises a processor configured to control the sensor module 240 , either as part of the processor 210 or separately, while the processor 210 is in a sleep state; The sensor module 240 may be controlled.

The input device 250 may include, for example, a touch panel 252 , a (digital) pen sensor 254 , a key 256 , or an ultrasonic input device 258 . The touch panel 252 may use, for example, at least one of a capacitive type, a pressure sensitive type, an infrared type, and an ultrasonic type. Also, the touch panel 252 may further include a control circuit. The touch panel 252 may further include a tactile layer to provide a tactile response to the user. The (digital) pen sensor 254 may be, for example, a part of a touch panel or may include a separate recognition sheet. Key 256 may include, for example, a hardware button, an optical key, or a keypad. The ultrasonic input device 258 may detect an ultrasonic wave generated by an input tool through a microphone (eg, the microphone 288 ), and check data corresponding to the sensed ultrasonic wave.

Display 260 (eg, display 160 ) may include panel 262 , hologram device 264 , projector 266 , and/or control circuitry for controlling them. Panel 262 may be implemented, for example, to be flexible, transparent, or wearable. The panel 262 may include the touch panel 252 and one or more modules. According to an embodiment, the panel 262 may include a pressure sensor (or a force sensor) capable of measuring the intensity of the user's touch. The pressure sensor may be implemented integrally with the touch panel 252 or as one or more sensors separate from the touch panel 252 . The hologram device 264 may display a stereoscopic image in the air by using light interference. The projector 266 may display an image by projecting light onto the screen. The screen may be located inside or outside the electronic device 201 , for example. Interface 270 may include, for example, HDMI 272 , USB 274 , optical interface 276 , or D-subminiature (D-sub) 278 . The interface 270 may be included in, for example, the communication interface 170 shown in FIG. 1 . Additionally or alternatively, the interface 270 may include, for example, a mobile high-definition link (MHL) interface, an SD card/multi-media card (MMC) interface, or an infrared data association (IrDA) standard interface. have.

The audio module 280 may interactively convert a sound and an electrical signal, for example. At least some components of the audio module 280 may be included in, for example, the input/output interface 145 illustrated in FIG. 1 . The audio module 280 may process sound information input or output through, for example, the speaker 282 , the receiver 284 , the earphone 286 , or the microphone 288 . The camera module 291 is, for example, a device capable of photographing still images and moving images, and according to an embodiment, one or more image sensors (eg, a front sensor or a rear sensor), a lens, and an image signal processor (ISP). , or a flash (eg, an LED or xenon lamp, etc.). The power management module 295 may manage power of the electronic device 201 , for example. According to an embodiment, the power management module 295 may include a power management integrated circuit (PMIC), a charger IC, or a battery or fuel gauge. The PMIC may have a wired and/or wireless charging method. The wireless charging method includes, for example, a magnetic resonance method, a magnetic induction method, or an electromagnetic wave method, and may further include an additional circuit for wireless charging, for example, a coil loop, a resonance circuit, or a rectifier. have. The battery gauge may measure, for example, the remaining amount of the battery 296 , voltage, current, or temperature during charging. Battery 296 may include, for example, rechargeable cells and/or solar cells.

The indicator 297 may display a specific state of the electronic device 201 or a part thereof (eg, the processor 210 ), for example, a booting state, a message state, or a charging state. The motor 298 may convert an electrical signal into mechanical vibration, and may generate vibration, a haptic effect, or the like. The electronic device 201 is, for example, a mobile TV support device capable of processing media data according to standards such as digital multimedia broadcasting (DMB), digital video broadcasting (DVB), or mediaFlo ^TM (eg, digital multimedia broadcasting). : GPU). Each of the components described in this document may be composed of one or more components, and the name of the component may vary depending on the type of the electronic device. In various embodiments, the electronic device (eg, the electronic device 201 ) is configured as a single entity by omitting some components, further including additional components, or combining some of the components. The functions of the previous corresponding components may be performed identically.

In various embodiments of the present disclosure, the electronic device 201 (or the electronic device 101 ) may include a housing including a front surface, a rear surface, and side surfaces surrounding a space between the front surface and the rear surface. A touch screen display (eg, the display 260 ) may be disposed in the housing and exposed through the front surface. A microphone 288 is disposed within the housing and may be exposed through a portion of the housing. At least one speaker 282 is disposed in the housing, and may be exposed through another portion of the housing. A hardware button (eg, key 256 ) may be disposed on another portion of the housing or configured to be displayed on the touchscreen display. A wireless communication circuit (eg, the communication module 220) may be located in the housing. The processor 210 (or processor 120 ) may be located in the housing and may be electrically connected to the touch screen display, the microphone 288 , the speaker 282 , and the wireless communication circuitry. The memory 230 (or the memory 130 ) may be located in the housing and may be electrically connected to the processor 210 .

In various embodiments of the present disclosure, the memory 230 is configured to store a first application program including a first user interface for receiving a text input, and the memory 230, when executed, Stores instructions causing the processor 210 to perform a first operation and a second operation, wherein the first operation is performed through the button while the first user interface is not displayed on the touch screen display. receiving a first type of user input, and after receiving the first type of user input, Receives a first user utterance through the microphone 288 and provides first data for the first user utterance to an external server including an automatic speech recognition (ASR) and an intelligence system and, after providing the first data, receiving from the external server at least one command to perform a task generated by the intelligent system in response to the first user utterance, the second operation comprising: The first user input is received through the button while the first user interface is displayed on the touch screen display, and after receiving the first type of user input, the second user input is received through the microphone 288 . receiving a user utterance, providing second data for the second user utterance to the external server, and after providing the second data, from the server, by the automatic speech recognition from the second user utterance The data for the generated text may be received, but the command generated by the intelligent system may not be received, and the text may be entered into the first user interface.

In various embodiments of the present invention, the button may include a physical key located on the side of the housing.

In various embodiments of the present disclosure, the first type of user input may be performed after pressing the button once, pressing the button twice, pressing the button 3 times, and pressing the button once. It may be one of a press and hold, or a double press and hold press of the button.

In various embodiments of the present disclosure, the instructions may further cause the processor to display the first user interface with a virtual keyboard. The button may not be part of the virtual keyboard.

In various embodiments of the present disclosure, the instructions further cause the processor 210 to receive, from the external server, data for text generated by ASR from the first user utterance within the first operation. can cause

In various embodiments of the present disclosure, the first application program may include at least one of a note application program, an email application program, a web browser application program, and a calendar application program.

In various embodiments of the present disclosure, the first application program includes a message application, and the instructions include, when the processor 210 exceeds a selected time period after inputting the text, the wireless communication circuit It may further cause to transmit the text entered automatically through .

In various embodiments of the present disclosure, the instructions further cause the processor 210 to perform a third operation, wherein the third operation is performed while displaying the first user interface on the touch screen display. , receives a second type of user input through the button, and after receiving the second type of user input, receives a third user utterance through the microphone, and receives the third user utterance through the external server. may receive from the external server at least one command for performing a task generated by the intelligent system in response to the third user utterance after providing the third data for have.

In various embodiments of the present disclosure, the instructions further cause the processor 210 to perform a fourth operation, wherein the fourth operation is performed when the first user interface is not displayed on the touch screen display. On the way, the second type of user input is received through the button, and after receiving the second type of user input, a fourth user utterance is received through the microphone 288, and the fourth user utterance is received. provide fourth data for , to the external server, and after providing the fourth data, in response to the fourth user utterance, at least one command for performing the task generated by the intelligent system, the After receiving from an external server, receiving a fifth user utterance through the microphone, providing fifth data for the fifth user utterance to the external server, and providing the fifth data, the second 5 at least one command for performing the task generated by the intelligent system in response to the user's utterance may be received from the external server.

In various embodiments of the present invention, the first type of user input and the second type of user input are different from each other, and one press on the button, two presses on the button, three presses on the button , one of pressing and holding the button after pressing it once, or pressing and holding the press twice on the button.

In various embodiments of the present disclosure, the memory 230 is further configured to store a second application program including a second user interface for receiving a text input, and the instructions, when executed, include the processor ( 210) further causes a third operation to be performed, the third operation comprising: receiving the first type of user input through the button while displaying the second user interface; After the first type of user input is received, a third user utterance is received through the microphone, and third data for the third user utterance is provided to the external server, and the third data is provided. After receiving the data for the text generated by the ASR from the third user utterance from the external server, the command generated by the intelligent system is not received, and the text is displayed on the second user interface. input, and input the text, and automatically transmit the entered text through the wireless communication circuit when the selected time period is exceeded.

In various embodiments of the present disclosure, the memory 230 is configured to store a first application program including a first user interface for receiving a text input, and the memory 230, when executed, Stores instructions causing the processor 210 to perform a first operation and a second operation, the first operation comprising: Receive a first type of user input through the button, and after receiving the first type of user input, receive a first user utterance through the microphone 288, automatic speech recognition (ASR) recognition) and an external server comprising an intelligence system, providing first data for the first user utterance, and after providing the first data, in response to the first user utterance, the Receiving at least one command for performing a task generated by an intelligent system from the external server, The second operation includes receiving a second type of user input through the button, and after receiving the second type of user input, receiving a second user utterance through the microphone 288, and providing second data for the second user utterance to a server, and after providing the second data, receiving, from the server, data for a text generated by ASR from the second user utterance, Commands generated by the intelligent system are not received, and the text can be entered into the first user interface.

In various embodiments of the present disclosure, the instructions may further cause the processor 210 to display the first user interface together with a virtual keyboard, wherein the button may not be part of the virtual keyboard.

In various embodiments of the present invention, the instructions further cause the processor 210 to receive data for the text generated by the ASR from the first user utterance within the first operation from the external server. can do.

In various embodiments of the present disclosure, the first application program may include at least one of a note application program, an email application program, a web browser application program, and a calendar application program.

In various embodiments of the present disclosure, the first application program includes a message application, and the instructions include, when the processor 210 exceeds a selected time period after inputting the text, the wireless communication circuit It may further cause to transmit the text entered automatically through .

In various embodiments of the present disclosure, the instructions may further cause the processor 210 to perform the first operation independently of displaying on the display of the first user interface.

In various embodiments of the present disclosure, the instructions perform the second operation when the processor 210 is at least one of a locked state of the electronic device or a turned off of the touch screen display. may cause more

In various embodiments of the present disclosure, the instructions may further cause the processor 210 to perform the second operation while displaying the first user interface on the touch screen display.

In various embodiments of the present invention, the memory 230, when executed, causes the processor 210 to receive a user utterance through the microphone 288, perform automatic speech recognition (ASR) or It is an external server that performs at least one of natural language understanding (NLU), and performs the ASR on the data for the user's utterance together with the data on the user's utterance, and performs the ASR on the data obtained for the natural language understanding. send information associated with whether to perform the natural language understanding , it is possible to store an instruction for causing to receive a command obtained as a result of performing the natural language understanding on the text from the external server.

3 is a block diagram of a program module according to various embodiments of the present disclosure; According to one embodiment, the program module 310 (eg, the program 140) is an operating system that controls resources related to the electronic device (eg, the electronic device 101) and/or various applications ( For example, the application program 147) may be included. The operating system may include, for example, Android ^TM , iOS ^TM , Windows ^TM , Symbian ^TM , Tizen ^TM , or Bada ^TM . Referring to FIG. 3 , the program module 310 includes a kernel 320 (eg, kernel 141), middleware 330 (eg, middleware 143), (API 360) (eg, API 145). ), and/or an application 370 (eg, an application program 147). At least a portion of the program module 310 is preloaded on the electronic device, or an external electronic device (eg, the electronic device ( 102, 104), server 106, etc.).

The kernel 320 may include, for example, a system resource manager 321 and/or a device driver 323 . The system resource manager 321 may control, allocate, or recover system resources. According to an embodiment, the system resource manager 321 may include a process manager, a memory manager, or a file system manager. The device driver 323 may include, for example, a display driver, a camera driver, a Bluetooth driver, a shared memory driver, a USB driver, a keypad driver, a WiFi driver, an audio driver, or an inter-process communication (IPC) driver. . The middleware 330 provides, for example, functions commonly required by the applications 370 or provides various functions through the API 360 so that the applications 370 can use limited system resources inside the electronic device. It may be provided as an application 370 . According to one embodiment, the middleware 330 includes a runtime library 335 , an application manager 341 , a window manager 342 , a multimedia manager 343 , a resource manager 344 , a power manager 345 , and a database manager ( 346 ), a package manager 347 , a connectivity manager 348 , a notification manager 349 , a location manager 350 , a graphic manager 351 , or a security manager 352 .

The runtime library 335 may include, for example, a library module used by the compiler to add a new function through a programming language while the application 370 is being executed. The runtime library 335 may perform input/output management, memory management, or arithmetic function processing. The application manager 341 may, for example, manage the life cycle of the application 370 . The window manager 342 may manage GUI resources used in the screen. The multimedia manager 343 may identify a format required to reproduce the media files, and may encode or decode the media files using a codec suitable for the format. The resource manager 344 may manage the space of the source code or memory of the application 370 . The power manager 345 may, for example, manage a capacity or power of a battery and provide power information required for an operation of an electronic device. According to an embodiment, the power manager 345 may interwork with a basic input/output system (BIOS). The database manager 346 may create, search, or change a database to be used in the application 370 , for example. The package manager 347 may manage installation or update of an application distributed in the form of a package file.

The connectivity manager 348 may manage wireless connections, for example. The notification manager 349 may provide the user with events such as, for example, arrival messages, appointments, and proximity notifications. The location manager 350 may manage location information of the electronic device, for example. The graphic manager 351 may manage a graphic effect to be provided to a user or a user interface related thereto, for example. Security manager 352 may provide, for example, system security or user authentication. According to an embodiment, the middleware 330 may include a telephony manager for managing the voice or video call function of the electronic device or a middleware module capable of forming a combination of functions of the aforementioned components. . According to an embodiment, the middleware 330 may provide a specialized module for each type of operating system. The middleware 330 may dynamically delete some existing components or add new components. The API 360 is, for example, a set of API programming functions, and may be provided in different configurations depending on the operating system. For example, in the case of Android or iOS, one API set may be provided for each platform, and in the case of Tizen, two or more API sets may be provided for each platform.

The application 370 is, for example, home 371 , dialer 372 , SMS/MMS 373 , instant message (IM) 374 , browser 375 , camera 376 , alarm 377 . , contact (378), voice dial (379), email (380), calendar (381), media player (382), album (383), watch (384), health care (e.g., measuring exercise or blood sugar) , or an application for providing environmental information (eg, barometric pressure, humidity, or temperature information). According to an embodiment, the application 370 may include an information exchange application capable of supporting information exchange between the electronic device and an external electronic device. The information exchange application may include, for example, a notification relay application for transmitting specific information to an external electronic device, or a device management application for managing the external electronic device. For example, the notification delivery application may transmit notification information generated by another application of the electronic device to the external electronic device or may receive notification information from the external electronic device and provide the notification information to the user. The device management application is, for example, a function of the external electronic device communicating with the electronic device (eg, turn-on/turn-off of the external electronic device itself (or some component) or the brightness (or resolution) of the display. adjustment), or an application running in an external electronic device may be installed, deleted, or updated. According to an embodiment, the application 370 may include an application designated according to the property of the external electronic device (eg, a health management application of a mobile medical device). According to an embodiment, the application 370 may include an application received from an external electronic device. At least a portion of the program module 310 may be implemented (eg, executed) in software, firmware, hardware (eg, processor 210), or a combination of at least two or more thereof, a module for performing one or more functions; It may include a program, routine, instruction set, or process.

According to various embodiments, a server providing an English learning service includes a communication interface, and a processor, wherein the processor identifies a preference category of a user using the user device, and crawls the web based on the preference category ( web crawling), select learning content including an English sentence corresponding to the learning level of the user and a Korean sentence translated from the English sentence at the same time, and the English sentence included in the learning content and By analyzing the Korean sentence, a pair is formed with an English word corresponding to a predetermined part-of-speech in the English sentence, a Korean word corresponding to the predetermined part-of-speech is selected from the Korean sentence, and using the web crawling, the collecting first images corresponding to a Korean word and collecting second images corresponding to the English word; collect second images, and when the user device is connected to a Wi-Fi network, collect the first images and the second images corresponding to still images or moving images; by determining a first similarity between the second images, and associating a representative image having the highest similarity to the second images among the first images with the Korean word - the predetermined part-of-speech in the Korean sentence An operation of associating representative images is performed for all words corresponding to -, providing the Korean sentence to which the representative images are related to the user device through the communication interface, and from the user device through the communication interface receiving a comparison target English sentence for the Korean sentence, and determining a second degree of similarity between the comparison target English sentence and the English sentence as a correct answer sentence using a doc2vec algorithm, and When the second similarity is less than or equal to the first threshold and greater than or equal to a second threshold lower than the first threshold: 1) Using the word2vec algorithm, the query English word included in the comparison target English sentence and the correct English included in the English sentence A third degree of similarity between words is determined, and an operation of determining a degree of similarity with all correct English words included in the English sentence for all query word words included in the comparison target English sentence is performed-, 2) the above When the third similarity is less than the third threshold, a word corresponding to the basic form of the correct English word is provided to the user device as a hint word, 3) When the third similarity exceeds the fourth threshold, providing the antonym of the correct English word as the hint word to the user device, and 4) when the third degree of similarity is greater than or equal to the third threshold and less than or equal to the fourth threshold, a synonym of the correct English word is provided as the hint word may be set to be provided to the user device as

According to various embodiments, when the second similarity exceeds the first threshold, the processor processes the English sentence to be compared as a correct answer, and provides the English sentence to the user device through the communication interface, , and when the second similarity is less than the second threshold, the English sentence to be compared may be treated as an incorrect answer, and the English sentence may be provided to the user device through the communication interface.

According to various embodiments, the processor processes the first images and the second images according to a specific criterion for extracting a texture feature and a shape feature, and converts the processing result into an index according to a criterion for synthesizing the Indexing the first images and the second images, processing the target building design according to the specific criterion, and determining the first similarity using a value converted according to a criterion for synthesizing the processing result and the specific criterion is set below in the first images and the second images to extract the texture feature from the first images and the second images, and calculate a vector of the texture feature. applying Equation 1 of , and the specific criterion is to extract the shape feature from the first images and the second images, and to calculate the shape feature, the first images and the second images Equation 2 below can be applied to

[Equation 1]

[Equation 2]

According to various embodiments, the processor is configured to: the first images and the second images processed according to the specific criterion to calculate the first similarity between the first images and the second images It may be set to calculate the distance value between the two by applying Equation 3 below.

[Equation 3]

According to various embodiments, the processor is configured to calculate the second degree of similarity between the comparison target English sentence and the English sentence by applying Equation 4 below, using the doc2vec algorithm, and the comparison target English sentence doc2vec of English sentence p is [p1, p2, … , pn], and doc2vec of the English sentence q is [q1, q2, ... , qn].

[Equation 4]

According to various embodiments, the processor vectorizes the query English word and the correct English word using Equation 5 below based on the skip-gram model of the word2vec algorithm, and based on the cosine similarity It may be set to determine the third degree of similarity between the query English word and the correct English word using Equation 6 below.

[Equation 5]

[Equation 6]

As used herein, the term “module” includes a unit composed of hardware, software, or firmware, and may be used interchangeably with terms such as, for example, logic, logic block, component, or circuit. A “module” may be an integrally formed component or a minimum unit or a part of performing one or more functions. A “module” may be implemented mechanically or electronically, for example, known or to be developed, application-specific integrated circuit (ASIC) chips, field-programmable gate arrays (FPGAs), or It may include a programmable logic device. At least a portion of an apparatus (eg, modules or functions thereof) or a method (eg, operations) according to various embodiments includes instructions stored in a computer-readable storage medium (eg, memory 130 ) in the form of a program module can be implemented as When the instruction is executed by a processor (eg, the processor 120), the processor may perform a function corresponding to the instruction. Computer-readable recording media include hard disks, floppy disks, magnetic media (eg, magnetic tape), optical recording media (eg, CD-ROM, DVD, magneto-optical media (eg, floppy disks), built-in memory, etc.) An instruction may include a code generated by a compiler or a code that can be executed by an interpreter A module or program module according to various embodiments may include at least one or more of the above-described components or , some may be omitted, or may further include other components According to various embodiments, operations performed by a module, a program module, or other components are sequentially, parallelly, repetitively or heuristically executed, or at least Some operations may be executed in a different order, omitted, or other operations may be added.

In addition, the embodiments disclosed in this document are provided for description and understanding of the disclosed, technical content, and do not limit the scope of the present disclosure. Accordingly, the scope of the present disclosure should be construed to include all modifications or various other embodiments based on the technical spirit of the present disclosure.

Claims (1)

In the server providing an English learning service,
communication interface; and a processor; including,
The processor is
Check the preferred category of the user who uses the user device,
Selecting, from among the contents collected using web crawling based on the preference category, learning contents that simultaneously include an English sentence corresponding to the learning level of the user and a Korean sentence translated from the English sentence,
By analyzing the English sentence and the Korean sentence included in the learning content, a pair is formed with an English word corresponding to a predetermined part-of-speech in the English sentence, and a Korean word corresponding to the predetermined part-of-speech is selected from the Korean sentence. do,
Using the web crawling, first images corresponding to the Korean word are collected and second images corresponding to the English word are collected, but only for still images when the user device is connected to a cellular network collecting the first images and the second images, and when the user device is in a state of being connected to a Wi-Fi network, collecting the first images and the second images corresponding to still images or moving images, ,
By determining a first similarity between the first images and the second images, a representative image having the highest similarity with respect to the second images among the first images is associated with the Korean word, wherein the Korean word An operation of associating representative images with respect to all words corresponding to the predetermined part-of-speech in a sentence is performed,
A server that provides the Korean sentence to which the representative images are related to the user device through the communication interface.

Images