KR102619086B1 - Control method of electronic apparatus for providing evaluation information of essay - Google Patents

Abstract

A method for controlling an electronic device is disclosed. This control method includes the steps of receiving an essay written by a student for at least one question, analyzing the text constituting the essay and identifying attribute values of the essay for each parameter, displaying the text constituting the essay, and displaying the displayed text. and displaying an indicator highlighting at least one subtext related to an attribute value for each parameter of the essay.

Description

CONTROL METHOD OF ELECTRONIC APPARATUS FOR PROVIDING EVALUATION INFORMATION OF ESSAY }

This disclosure relates to an electronic device that provides evaluation information about an essay, and more specifically, to a method of controlling an electronic device that analyzes an essay written by a student and provides evaluation information about attribute values for each parameter.

In the case of conventional college admissions consulting, it provided editing functions for essays focusing on grammar and vocabulary, but in most cases, it failed to evaluate factors that admissions officers pay attention to, such as the essay's theme, relevance to each question, and level of interest to each university.

In particular, in some countries, such as the United States, the need for holistic analysis solutions has increased due to changes in SAT test policies, and a solution that can provide more professional analysis of essays is needed.

The present disclosure discloses a method of controlling an electronic device that recognizes the key elements of a story, such as characters, background, and conflict entities, and supports analysis of the intent and comparative analysis of successful student essay patterns and questions.

The present disclosure provides a control method for an electronic device that visually/intuitively provides attribute values of an essay for each parameter on text.

A method of controlling an electronic device according to an embodiment of the present disclosure includes receiving an essay written by a student for at least one question, analyzing text constituting the essay, and identifying attribute values of the essay for each parameter. , displaying text constituting the essay, and displaying an indicator highlighting at least one subtext related to an attribute value for each parameter of the essay within the displayed text.

The step of displaying the indicator may include, when at least one parameter is selected, displaying an indicator that highlights subtext related to the attribute value of the selected parameter.

In this case, the control method of the electronic device may include, when the indicator is selected, displaying attribute information of the subtext related to the attribute value of the selected parameter.

Additionally, in the step of displaying the indicator, a plurality of indicators that emphasize each of the plurality of subtexts may be displayed separately according to attribute information.

The control method of the electronic device includes the steps of receiving a school and a major to which the student wishes to apply, analyzing the essays of each successful applicant for the major at the school, and providing an attribute value for each parameter for each essay of the successful applicants. Identifying, when at least one parameter is selected, displaying a graphic user interface (GUI) visualizing ratio information of successful applicants for each attribute value related to the selected parameter, on the GUI, written by the student It may include the step of displaying an indicator indicating a point that matches the attribute value of the essay.

In this case, the method of providing evaluation of the electronic device includes the steps of receiving attribute values for each parameter according to the student's intention for the essay, and, on the GUI, an indicator indicating a point matching the attribute value according to the student's intention. It may include a step of displaying, and a step of displaying comparison information that compares the attribute value of the essay written by the student with the attribute value according to the student's intention.

Meanwhile, a method of controlling an electronic device according to an embodiment of the present disclosure includes receiving a school and a major to which a student wishes to apply, providing a plurality of questions matching the major of the school, and answering the plurality of questions. receiving an essay written by the student for at least one question, identifying a type of the at least one question, and identifying a plurality of parameters matching the identified type, each of the identified plurality of parameters For this, the method includes obtaining evaluation information on an essay written by the student and generating a feedback text according to the evaluation information obtained for each of the plurality of parameters.

In this case, the step of obtaining evaluation information on the essay written by the student includes extracting a plurality of keywords from the text constituting the essay written by the student in obtaining evaluation information about the Originality parameter, the plurality of keywords It may include converting each keyword into a vector form, identifying a degree of association between the plurality of keywords according to the distance between the converted vectors, and obtaining evaluation information according to the identified degree of association.

In addition, the step of obtaining evaluation information on the essay written by the student includes extracting a plurality of keywords from the text constituting the essay written by the student, in obtaining evaluation information about the Topic Uniqueness parameter, the plurality of keywords Performing a search on the web for each keyword, selecting at least one unique keyword among the plurality of keywords according to the search frequency of each of the plurality of keywords, and determining the frequency of the unique keyword in the essay written by the student. It may include a step of obtaining evaluation information based on the evaluation information.

The control method of an electronic device according to the present disclosure can provide evaluation information on attribute values for various parameters for an essay written by a student.

The control method of an electronic device according to the present disclosure provides evaluation information by comparing the attribute values of the essay written by the student with the attribute values of the essays of successful applicants and the attribute values intended by the student for each parameter.

In addition, the method of controlling an electronic device according to the present disclosure provides an indicator that highlights subtext related to the attribute value for each parameter within the essay written by the student, thereby providing intuitive feedback on parts of the essay written by the student. You can.

1 is a block diagram for explaining the configuration of an electronic device according to an embodiment of the present disclosure;
2 is a flowchart illustrating a control method of an electronic device according to an embodiment of the present disclosure;
FIG. 3 is a diagram illustrating a UI (User Interface) provided by an electronic device according to an embodiment of the present disclosure to receive an essay written by a student and an attribute value intended by the student;
FIG. 4A is a diagram illustrating a UI in which an electronic device provides evaluation information on attribute values of an essay for a Theme parameter according to an embodiment of the present disclosure;
FIG. 4B is a diagram illustrating a UI in which an electronic device provides evaluation information on attribute values of an essay for character parameters according to an embodiment of the present disclosure;
FIG. 4C is a diagram illustrating a UI in which an electronic device provides evaluation information on attribute values of an essay for setting parameters according to an embodiment of the present disclosure;
FIG. 4D is a diagram illustrating a UI in which an electronic device provides evaluation information on attribute values of an essay for Plot & Conflict parameters according to an embodiment of the present disclosure;
5 is a flowchart illustrating an operation in which an electronic device provides evaluation information of an essay on a plurality of parameters identified according to the school and major for support, according to an embodiment of the present disclosure; and
FIG. 6 is a diagram illustrating a UI provided by an electronic device according to the embodiment of FIG. 5.

Before explaining the present disclosure in detail, the description method of the present specification and drawings will be explained.

First, the terms used in the specification and claims are general terms selected in consideration of their functions in various embodiments of the present disclosure. However, these terms may vary depending on the intention of technicians working in the relevant technical field, legal or technical interpretation, and the emergence of new technologies. Additionally, some terms are arbitrarily selected by the applicant. These terms may be interpreted as defined in this specification, and if there is no specific term definition, they may be interpreted based on the overall content of this specification and common technical knowledge in the relevant technical field.

In addition, the same reference numbers or symbols in each drawing attached to this specification indicate parts or components that perform substantially the same function. For convenience of explanation and understanding, the same reference numerals or symbols are used in different embodiments. That is, even if all components having the same reference number are shown in multiple drawings, the multiple drawings do not represent one embodiment.

Additionally, in this specification and claims, terms including ordinal numbers such as “first”, “second”, etc. may be used to distinguish between components. These ordinal numbers are used to distinguish identical or similar components from each other, and the meaning of the term should not be interpreted limitedly due to the use of these ordinal numbers. For example, the order of use or arrangement of components combined with these ordinal numbers should not be limited by the number. If necessary, each ordinal number may be used interchangeably.

In this specification, singular expressions include plural expressions, unless the context clearly dictates otherwise. In this application, terms such as “comprise” or “consist of” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are intended to indicate the presence of one or more other It should be understood that this does not exclude in advance the presence or addition of features, numbers, steps, operations, components, parts, or combinations thereof.

In embodiments of the present disclosure, terms such as “module”, “unit”, “part”, etc. are terms to refer to components that perform at least one function or operation, and these components are either hardware or software. It may be implemented or may be implemented through a combination of hardware and software. In addition, a plurality of "modules", "units", "parts", etc. are integrated into at least one module or chip, except in cases where each needs to be implemented with individual specific hardware, and is integrated into at least one processor. It can be implemented as:

Additionally, in an embodiment of the present disclosure, when a part is connected to another part, this includes not only direct connection but also indirect connection through other media. In addition, the meaning that a part includes a certain component does not mean that other components are excluded, but that it may further include other components, unless specifically stated to the contrary.

Hereinafter, various embodiments of the present invention will be described in detail using the attached drawings.

1 is a block diagram for explaining the configuration of an electronic device according to an embodiment of the present disclosure.

Referring to FIG. 1 , the electronic device 100 may include a memory 110 and a processor 120.

The electronic device 100 may be implemented as a server including at least one computer. In this case, the electronic device 100 can communicate with external devices through various communication methods. Specifically, the electronic device 100 may be connected to various users' terminal devices through at least one application or web page and perform control methods according to various embodiments, which will be described later.

Additionally, the electronic device 100 may correspond to various terminal devices such as a smartphone, tablet PC, laptop PC, desktop PC, PDA, or wearable device.

The memory 110 is configured to store an operating system (OS) for controlling the overall operation of the components of the electronic device 100 and at least one instruction or data related to the components of the electronic device 100. am.

The memory 110 may include non-volatile memory, such as ROM or flash memory, and may include volatile memory, such as DRAM. Additionally, the memory 120 may include a hard disk, solid state drive (SSD), etc.

The memory 110 may include one or more artificial intelligence models used in various embodiments that will be described later, and this artificial intelligence model may be a model trained through supervised learning, unsupervised learning, reinforcement learning, etc. An artificial intelligence model may correspond to a neural network model that is trained in a way that is updated according to the weights between nodes included in different layers.

The processor 120 is a component that controls the overall configuration and operation of the electronic device 100.

The processor 120 is connected to the memory 110 and can control the electronic device 100 by executing at least one instruction stored in the memory 110.

To this end, the processor 120 may be a general-purpose processor such as a Central Processing Unit (CPU), an Application Processor (AP), a graphics-specific processor such as a Graphic Processing Unit (GPU), a Vision Processing Unit (VPU), or a Neural Processing Unit (NPU). It can be implemented with an artificial intelligence-specific processor such as . The processor 120 may include volatile memory such as SRAM.

Meanwhile, although not shown, the electronic device 100 may further include a communication unit for communicating with at least one external device.

The communication unit can be connected to external servers and/or terminal devices through one or more networks, and data can be exchanged through various wired and wireless communication methods.

Depending on the area or size, the network may be a personal area network (PAN), a local area network (LAN), or a wide area network (WAN). Depending on the openness of the network, it may be an intranet, It may be an extranet, or the Internet.

Wireless communications include LTE (long-term evolution), LTE-A (LTE Advance), 5G (5th Generation) mobile communications, CDMA (code division multiple access), WCDMA (wideband CDMA), UMTS (universal mobile telecommunications system), and WiBro. At least one of the following communication methods: (Wireless Broadband), GSM (Global System for Mobile Communications), DMA (Time Division Multiple Access), WiFi (Wi-Fi), WiFi Direct, Bluetooth, NFC (near field communication), and Zigbee. It can be included.

Wired communication may include at least one of communication methods such as Ethernet, optical network, USB (Universal Serial Bus), and Thunderbolt.

Meanwhile, the communication method is not limited to the examples described above and may include newly emerging communication methods as technology develops.

The electronic device 100 can obtain student information according to user input, and can identify the school and major to which the student wishes to apply based on user input.

User input may be received through a user input unit (ex. touch screen, button, microphone, camera (motion recognition unit)) included in the electronic device 100. Alternatively, when the electronic device 100 is a server, user input may be received through at least one terminal device connected to the electronic device 100.

As a specific example, the electronic device 100 may perform membership registration for a platform provided by the electronic device 100 through a process of receiving student information including the student's name, age, contact information, etc. In this case, an ID and password linked to student information may be created.

Additionally, while a specific student is logged in, the school and major to which the student wishes to apply may be entered into the electronic device 100. Alternatively, of course, the school and major to which the student wishes to apply may be entered during the membership registration process.

Additionally, the electronic device 100 can receive an essay written by a specific student while the student is logged in.

In relation to this, FIG. 2 is a flowchart for explaining a method of controlling an electronic device according to an embodiment of the present disclosure.

Referring to FIG. 2, the electronic device 100 can receive an essay written by a student for at least one question (S210).

The electronic device 100 may provide questions through a display/speaker of the electronic device 100 or a display/speaker of at least one terminal device (ex. smartphone, tablet PC) connected to the electronic device 100. .

The questions are questions related to essays for at least one university/major entrance exam, and may correspond to questions asking about the applicant's (student's) motivation for admission, growth background, various experiences, values, etc., but are not limited to this.

The electronic device 100 can receive essay input through a user input unit (ex. keypad, keyboard device, microphone, etc.) provided in the electronic device 100. Alternatively, if the electronic device 100 is implemented as a server, the essay may be uploaded to the electronic device 100 through at least one terminal device connected to the electronic device 100.

Here, the electronic device 100 can receive text that constitutes an essay.

The electronic device 100 may analyze the text constituting the input essay and identify attribute values of the essay for each parameter (S220). The electronic device 100 can analyze text using various natural language processing techniques.

Parameters may include Theme/Mood, Character, Setting, "Plot & Conflict", Writing Quality, "Showing vs Telling", etc., but in addition, various elements to indicate the properties or flow of the essay are set as one or more parameters. It can be utilized.

Theme/Mood parameters are parameters for the overall emotion or atmosphere contained in the essay. Theme/Mood can correspond to various attribute values such as joyful, sad, calm, suspenseful, and depressed. Attribute values that can be set for Theme/Mood may be defined differently depending on the questions already provided.

For example, if the question related to the essay corresponds to a question asking about motivation for applying, the electronic device 100 may determine the attribute value of the essay for the Theme/Mood parameter to be at least one of curiosity, desire, excitement, and pride. there is. On the other hand, if the question related to the essay corresponds to a question asking about growth background, the electronic device 100 may determine the attribute value of the essay for the Theme/Mood parameter as joyful, sad, calm, caring, realization, etc. .

In one embodiment, the electronic device 100 may extract a plurality of keywords related to emotion or atmosphere from text constituting an essay.

In this case, the electronic device 100 may identify each keyword using at least one artificial intelligence model trained to extract keywords corresponding to emotions or mood.

Additionally, the electronic device 100 may classify the emotion/mood of each keyword extracted from the text or the sentence containing each keyword. In this case, when at least one subtext is input, at least one artificial intelligence model (ex. classifier model) trained to classify emotion/mood may be used.

Alternatively, the electronic device 100 may extract topics by analyzing sentences containing each keyword using Latent Dirichlet Allocation (LDA). Here, at least one artificial intelligence model trained to classify a topic (emotion/mood) through sentences corresponding to various emotions or moods may be used.

Additionally, the electronic device 100 may determine an attribute value corresponding to the overall emotion/mood of the essay according to the ratio or frequency of each keyword corresponding to each emotion or atmosphere. In this case, the electronic device 100 may identify the emotion or atmosphere of the essay by analyzing the frequency of each keyword using TF-IDF (Term Frequency - Inverse Document Frequency).

Here, the electronic device 100 may determine the attribute value of the Theme parameter of the essay according to the emotion/mood of the most dominant and frequently appearing keywords.

Character is a parameter for the characters that appear in the essay.

The Character parameter can have an attribute value determined depending on which character the essay is mainly focused on. For example, the attribute value of the Character parameter may be determined as Mostly me, Me some others, other characters, etc. Mostly me refers to a case in which the essay author (you) appears in a relatively high proportion, Other characters refers to a case in which characters other than the essay author appear in a relatively high proportion, and Me some others refers to a case in between the two cases mentioned above. it means. However, the attribute value of the Character parameter is defined as the frequency of appearance of characters classified by simply you (author) and others as described above, as well as the frequency of appearance of characters classified by other criteria such as friends and parents. Of course it can be done.

In one embodiment, the electronic device 100 may extract a plurality of keywords related to characters from text constituting an essay.

In this case, the electronic device 100 may identify each keyword using at least one artificial intelligence model trained to extract keywords corresponding to the characters.

Additionally, the electronic device 100 can classify each keyword extracted from the text or which character (ex. you (author), others) corresponds to each keyword. In this case, when at least one word is input, at least one artificial intelligence model trained to identify the character implied by the input word may be used.

Additionally, the electronic device 100 may determine the overall frequency of appearance of each character in the essay according to the ratio or frequency of each keyword corresponding to each character.

Here, the electronic device 100 may determine the attribute value of the character parameter according to the attribute of the character that appears most frequently.

Setting is a parameter related to the intensity/detail of the description of place, background, time, etc. included in the essay.

Setting parameters may correspond to attribute values such as, for example, Heavy emphasis on setting, Moderate emphasis on setting, Setting is not a big factor, etc., but are not necessarily limited thereto. The attribute value of the setting parameter may be defined separately for location, time, and movement.

In one embodiment, the electronic device 100 may extract a plurality of keywords related to at least one of place, time, and movement from text constituting an essay.

Additionally, the electronic device 100 can identify one or more sentences that modify each keyword related to place, time, and movement.

To this end, the electronic device 100 uses at least one Recurrent Neural Network (RNN) trained to recognize relationships (e.g., parallel relationships, modifying relationships, consecutive relationships, etc.) between subtexts (e.g. words, sentences) that follow sequentially. Network)-based artificial intelligence model can be used.

Here, the electronic device 100 can identify the strength of the setting according to the ratio/frequency of keywords and formula sentences related to place, time, and movement in the essay, and determine the attribute value according to the strength of the identified setting. For example, the electronic device 100 calculates an average value for the intensity of the setting related to place, the intensity of the setting related to time, and the intensity of the setting related to movement, and then calculates an attribute value (strength of setting) according to the calculated average value. ) can be determined.

Plot & Conflict is a parameter for the overall story flow, such as the mood or content being reversed depending on the emotion or plot within the essay.

For example, the Plot & Conflict parameter may have attribute values defined according to the frequency of words or action verbs related to conflict. In addition, the Plot & Conflict parameter may be defined as an attribute value such as frequent, often, or almost never emotional ups and downs, depending on the changes in emotions or flow. Additionally, the Plot & Conflict parameter may have its attribute value (ex. small/large number of characters) defined depending on the total number of characters in the essay.

As an example, the electronic device 100 may identify the overall complexity of the plot according to the number of characters appearing in the essay, the number/frequency of words related to conflict, and the number/frequency of words/sentences related to setting. In this case, the electronic device 100 may determine the attribute value of the essay for the Plot & Conflict parameter according to the identified complexity.

Additionally, the electronic device 100 may identify the number/frequency of occurrences of words related to conflict within the essay and determine this as an attribute value for the Plot & Conflict parameter.

In addition, the electronic device 100 divides the text constituting the essay into a plurality of sections, recognizes conflict-related words and/or changes in emotions for each section, and determines the attribute value according to how the overall essay development progresses. can be judged.

Writing Quality is a parameter that corresponds to the excellence (clarity, grammar, etc.) of each sentence in an essay.

The attribute values of the Writing Quality parameter (ex. superb, strong, good, mediocre, weak) can be judged for each of Correctness, Writing Diversity, Readability, and Clarity.

For example, the electronic device 100 may determine the grammatical accuracy of each sentence in an essay using at least one grammar checking algorithm/logic, and convert the attribute value for Correctness into a score, etc.

Additionally, the electronic device 100 may convert the attribute value for Writing Diversity into a score, etc. according to the number/frequency of words that are not generally used (ex. TF-IDF based extraction).

Additionally, the electronic device 100 may identify attribute values related to readability using indices such as Gunning fog, Flesch-Kincaid, and Simple Measure of Gobbledygook (SMOG).

Additionally, the electronic device 100 can calculate the attribute value for Clarity according to the number of words for each sentence in the essay, specifically, the number of words corresponding to transitions, nouns, passive voices, etc. for each sentence.

“Showing vs Telling” is a parameter that corresponds to the ratio relationship between emphasized sentences and detailed sentences.

The attribute value of the “Showing vs Telling” parameter can be defined according to the ratio between emphatic or symbolic sentences and explanatory sentences.

In one embodiment, the electronic device 100 may extract emphasizing sentences and explanatory sentences respectively from the text constituting the essay.

Specifically, a sentence containing at least one of a strong verb and an uncommon adjective may be identified as an emphatic sentence, and a sentence containing at least one of a static/stative verb and a common adjective may be identified as an explanatory sentence. Here, whether each verb/adjective is common (static/stative/common) or uncommon (strong/uncommon) is determined through at least one database (ex. It may be predefined depending on the lexicon.

Specifically, the electronic device 100 may input each sentence into an artificial intelligence model trained to determine the properties of the sentence (e.g., a sentence that emphasizes vs. a sentence that explains). In this case, the artificial intelligence model can determine the properties of each sentence by comparing each word included in the pre-stored lexicon with each verb/adjective in the sentence.

Additionally, the electronic device 100 may determine the attribute value for the “Showing vs. Telling” parameter according to the ratio between the emphasized sentence (Showing) and the explaining sentence (telling).

When attribute values related to various parameters are determined as described above, the electronic device 100 may provide a visual UI (User Interface) that highlights at least one subtext related to each attribute value within the text constituting the essay. There is (S230).

The electronic device 100 may provide the above-described text (essay) and indicator through its own display or the display of at least one terminal device connected to the electronic device 100.

Specifically, the electronic device 100 may display text constituting an essay, while displaying an indicator that highlights at least one subtext related to an attribute value for each parameter of the essay within the displayed text. In relation to this, it will be described in more detail later with reference to FIGS. 4A to 4D.

Meanwhile, FIG. 3 is a diagram illustrating a UI (User Interface) provided by an electronic device according to an embodiment of the present disclosure to receive an essay written by a student and an attribute value intended by the student.

Referring to FIG. 3 , the electronic device 100 may provide at least one question 301 related to the university and major to which the student wishes to apply. For example, this question 301 may be a question that has already been asked during the entrance exam for the university and major to which the student wishes to apply, but is not limited to this.

Additionally, the electronic device 100 may display the received essay 302 according to the user input. Specifically, text constituting the essay 302 may be displayed.

Additionally, the electronic device 100 may provide a UI 310 for receiving attribute values for each parameter intended by the student for the essay 302.

Through the corresponding UI 310, attribute values for each parameter (Mood, Character, Setting) intended by the student for the essay 302 can be selected.

Here, the electronic device 100 may analyze the essay 302 written by the student and determine attribute values for each parameter as in the various embodiments described above.

Additionally, the electronic device 100 may analyze the essays of each successful applicant for the school and major to which the student wishes to apply, and identify attribute values for each parameter for each successful applicant's essay.

In addition, the electronic device 100 compares and analyzes the attribute values for each parameter of the essay 302 written by the student, the attribute value for each parameter of the essay written by the successful applicants, and the attribute value for each parameter intended by the student (ex. FIG. 3), Evaluation information may be provided as shown in FIGS. 4A to 4D, which will be described later.

FIG. 4A is a diagram illustrating a UI in which an electronic device provides evaluation information on attribute values of an essay for a Theme parameter, according to an embodiment of the present disclosure.

Referring to FIG. 4A, the electronic device 100 may provide a menu UI 401 for selecting at least one parameter. FIG. 4A shows the Theme parameter 410 of the menu UI 401 according to the user input. Assume that is selected.

When the Theme parameter 410 is selected, the electronic device 100 displays an indicator that highlights the subtext (sentence, word, etc.) related to the attribute value (ex. joyful, suspenseful, disturbed, etc.) of the selected Theme parameter 410. can do.

Here, each subtext emphasized by the indicator may be matched with attribute information (ex. joy, suspense, disturbed) related to the Theme parameter 410.

Attribute information refers to information about the attributes of each subtext used in defining attribute values of an essay related to a specific parameter (ex. Theme parameter).

Specifically, referring to FIG. 4A, indicators 411-1 and 2 that emphasize sentences matching joy (: attribute information) may be displayed, respectively, and emphasize sentences matching suspense (: attribute information). An indicator 412-1 that emphasizes a sentence matching disturbed, an indicator 413-1 that emphasizes a sentence matching disturbed, etc. may be displayed on the text of the essay 302, respectively.

Indicators matching different attribute information (ex. joy, suspense, disturbed) can be displayed separately. Specifically, referring to FIG. 4A, indicators matching joy, suspense, and disturbed are displayed in different colors.

Additionally, referring to FIG. 4A, when at least one indicator 411-1 is selected by a user operation such as a mouse click or touch, the electronic device 100 selects the sentence emphasized by the corresponding indicator 411-1. A phrase indicating matching attribute information (: joy) can be additionally displayed.

Referring to FIG. 4A , the electronic device 100 may provide various evaluation information 410', 410'', and 410''' related to the attribute value of the essay 302 for the theme parameter 410.

The evaluation information 410' compares the attribute value intended by the student with the attribute value of the actual essay 302, and includes "vs." in that the attribute value intended by the student is disturbed, while the actual attribute value is joy. It has been done. However, if the attribute value intended by the student is the same as the actual attribute value, "=." can of course be included.

The evaluation information 410'' may include a graphic user interface (GUI) that visualizes information on the ratio of successful applicants for each attribute value related to the selected parameter (Theme). Referring to Figure 4a, a bar-shaped GUI was displayed according to the ratio of successful applicants corresponding to each attribute value (disturbed, suspenseful, sad, joyful, calm).

Additionally, referring to FIG. 4A, the evaluation information 410'' is an indicator (intended) indicating a point on the GUI (bar) that matches the attribute value of the essay intended by the student, and the attribute value of the essay written by the student. Each may include an indicator (detected) indicating a matching point on the GUI.

The evaluation information 410''' includes comparison information that compares various emotions included in the essay 302 written by the student with various emotions included in the essays written by successful applicants. Referring to FIG. 4A, on the left side of the evaluation information 410''', the frequencies of various emotions (e.g. approval, realization, excitement, admiration, optimism, annoyance) included in the essays of successful applicants are displayed in circles matching each emotion. It was shaped by the size of the field. And, on the right side of the evaluation information 410''', the frequency of various emotions included in the essay written by the student is represented by the size of circles matching each emotion.

Meanwhile, although not shown, the electronic device 100 may separately provide an evaluation statement in text form that comprehensively includes the contents of the above-described evaluation information 410', 410'', and 410'''. am. In this case, at least one artificial intelligence model may be used to generate sentences and texts according to given evaluation information.

FIG. 4B is a diagram illustrating a UI in which an electronic device provides evaluation information on attribute values of an essay for character parameters according to an embodiment of the present disclosure.

Figure 4b assumes that the character parameter 420 of the menu UI 401 is selected according to user input.

When the Character parameter 420 is selected, the electronic device 100 displays subtext (sentences, words, etc.) matching each attribute value (e.g. Mostly me, Me some others, other characters) related to the selected Character parameter 420. ) can be displayed.

Here, the attribute information of each subtext related to the attribute value of the character parameter 420 may correspond to you, others, etc., but is not limited thereto.

Specifically, referring to FIG. 4B, the electronic device 100 may display an indicator 421-1 that emphasizes the word "I" (attribute information: you, character indicator) matching the character corresponding to you. there is. Additionally, the electronic device 100 may display an indicator 421-2 that emphasizes a sentence describing “I” (attribute information: you, character descriptor).

If the indicator 421-1 is selected according to user input (mouse click, touch operation, etc.), a phrase such as “character (you)” may be displayed according to attribute information matching “I”. If the indicator 422-2 is selected according to the user input, a phrase such as “Descriptors about (you)” may be displayed according to the attribute information of the sentence.

Additionally, referring to FIG. 4B, the electronic device 100 may display an indicator 422-1 that emphasizes the word “grandmother” (attribute information: others, character indicator) matching the character corresponding to others. . Additionally, the electronic device 100 may display an indicator 422-2 that emphasizes a sentence describing “grandmother” (attribute information: others, character descriptor).

Referring to FIG. 4B, the electronic device 100 provides various evaluation information 420', 420'', 420''', 420'''' related to the attribute value of the essay 302 for the character parameter 420. can be provided.

The evaluation information 420' may include a GUI (bar) indicating the ratio of the attribute values (Mostly me, Me some others, Other characters) of the successful applicants' essays to the character parameter 420.

In addition, the evaluation information 420' is an indicator pointing to a point corresponding to the attribute value (intended by you) intended by the student in the GUI, and an attribute value of the actual essay written by the student in the GUI (detected in essay). Each indicator pointing to a point can be included.

The evaluation information 420'' may include comparison information between the number of sentences describing the characters in the essays of successful applicants and the number of sentences describing the characters in the essays written by the students.

Specifically, the evaluation information 420'' may include graphs representing the number of descriptions for all characters and the number of descriptions for the author (you) in the essays (Admitted Case Avg.) of successful applicants. Additionally, the evaluation information 420'' may include graphs representing the number of descriptions for all characters and the number of descriptions for the author (you) in the essay (Your Essay) written by the student.

The evaluation information 420''' may include comparative information about the appearance ratio of the author (you) to all characters in each of the essays of successful applicants (Admitted Case Avg.) and the essay written by the student (Your Essay). .

Evaluation information (420'''') is provided when each essay is divided into introduction, body (Body 1, Body 2, Body 3), and conclusion, and the essays of successful applicants (Admitted Case Avg.) and student For each of your essays, you can include a comparison graph that compares the number of characters in each section.

FIG. 4C is a diagram illustrating a UI in which an electronic device provides evaluation information on attribute values of an essay for setting parameters according to an embodiment of the present disclosure.

Figure 4c assumes that the setting parameter 430 of the menu UI 401 is selected according to user input.

When the Setting parameter 430 is selected, the electronic device 100 displays a subtext (sentence) related to the attribute value (ex. heavy emphasis on setting, moderate emphasis on setting, setting is not a big factor) of the selected Setting parameter 430. , words, etc.) can be displayed.

Here, the attribute information of each subtext may correspond to a setting indicator, setting descriptor, etc.

Specifically, referring to FIG. 4C, the electronic device 100 may display an indicator 431-1 that emphasizes “in front of” corresponding to the “setting indicator.” Additionally, the electronic device 100 may display an indicator 431-2 that emphasizes a sentence corresponding to a 'setting descriptor' that explains the background in more detail.

If the indicator 431-1 is selected according to user input (mouse click, touch operation, etc.), the phrase “setting indicator” may be displayed. If the indicator 432-2 is selected according to user input, the phrase “Setting Descriptor” may be displayed.

Additionally, referring to FIG. 4C, the electronic device 100 may display an indicator 431-2 that emphasizes “placed in” corresponding to the “setting indicator.” Additionally, the electronic device 100 may display an indicator 432-2 that emphasizes the sentence corresponding to the 'setting descriptor' (: my hometown as I have lived there for ten years from birth).

Referring to FIG. 4C, the electronic device 100 may provide various evaluation information 430', 430'', and 430''' related to the attribute value of the essay 302 for the setting parameter 430.

The evaluation information 430' may include a GUI indicating ratio information of the essays of successful applicants to the attribute values of the setting parameter 430. In addition, the evaluation information 430' includes an indicator (intended by you) indicating a point corresponding to the attribute value intended by the student on the GUI, and an indicator indicating a point corresponding to the attribute value of the essay written by the student on the GUI (detected in Each essay can be included.

The evaluation information 430'' may include comparative information comparing the number of 'setting indicator' and 'setting descriptor' in the essays of successful applicants with the number of 'setting indicator' and 'setting descriptor' in the essay written by the student. You can.

Specifically, the evaluation information 430'' may include graphs showing the numbers of each 'setting indicator' and 'setting descriptor' in the essays (Admitted Case Avg.) of successful applicants. Additionally, the evaluation information 430'' may include graphs representing the numbers of each 'setting indicator' and 'setting descriptor' in the essay (Your Essay) written by the student.

Evaluation information (430''') includes the essays of successful applicants (Admitted Case Avg.) and the student's essay when each essay is divided into Introduction, Body 2, Body 3, and Conclusion. For each written essay (Your Essay), you can include a comparison graph that compares the strength of the setting for each section (e.g., the number/frequency of setting indicators/descriptors within the section).

FIG. 4D is a diagram illustrating a UI in which an electronic device provides evaluation information on attribute values of an essay for Plot & Conflict parameters according to an embodiment of the present disclosure.

Figure 4d assumes that the Plot & Conflict parameter 440 is selected from the menu UI 401 according to user input.

When the Plot & Conflict parameter 440 is selected, the electronic device 100 displays an indicator that highlights subtext (sentences, words, etc.) related to the attribute value (e.g. sparse, frequent) of the selected Plot & Conflict parameter 440. It can be displayed.

Here, the attribute information of each subtext may correspond to conflict word, action verb, positive sentiment, negative sentiment, etc.

Specifically, referring to FIG. 4D, the electronic device 100 may display indicators 441-1 and 2 that respectively highlight subtexts corresponding to 'action verb'.

Additionally, the electronic device 100 may display an indicator 442-1 that emphasizes the subtext (ex. however) corresponding to the 'conflict word'. Additionally, the electronic device 100 may display an indicator 442-2 that emphasizes subtext corresponding to 'negative sentiment'.

Referring to FIG. 4D, the electronic device 100 may provide various evaluation information (440', 440'', 440''') related to the attribute value of the essay 302 for the Plot & Conflict parameter 440. there is.

The evaluation information 440' may include comparative information that compares the number of 'conflict words' and 'action verbs' in the essays of successful applicants with the number of 'conflict words' and 'action verbs' in the essays written by the students. there is.

Specifically, the evaluation information 440' may include graphs showing the numbers of each 'conflict word' and 'action verb' in the essays (Admitted Case Avg.) of successful applicants. Additionally, the evaluation information 440' may include graphs showing the numbers of each 'conflict word' and 'action verb' in the essay (Your Essay) written by the student.

The evaluation information 430'' consists of comparative information including a graph showing the frequency of emotional ups and downs in the essays of successful applicants (Admitted Case Avg.) and a graph showing the frequency of emotional ups and downs in the essay written by the student (Your Essay). It can be.

Evaluation information (440''') includes the essays of successful applicants (Admitted Case Avg.) and the student's essay when each essay is divided into introduction, body 2, body 3, and conclusion. For each written essay (Your Essay), you can include a comparison graph that compares the intensity of tension (e.g., emotional ups and downs within the section, or the number/frequency of conflict words/action verbs within the section) for each section.

Meanwhile, when “Overall” is selected on the above-described menu UI 401, the electronic device 100 can summarize and comprehensively provide various evaluation information provided in FIGS. 4A to 4D.

Meanwhile, according to one embodiment, the electronic device 100 may provide questions according to the school and major to which the student wishes to apply, and may generate different parameters for evaluating the essay depending on the school and major.

In relation to this, FIG. 5 is a flowchart illustrating an operation in which an electronic device provides evaluation information of an essay on a plurality of parameters identified according to the school and major being supported, according to an embodiment of the present disclosure.

Referring to FIG. 5, the electronic device 100 can receive input of the school and major to which the student wishes to apply (S510).

Additionally, the electronic device 100 may provide a plurality of questions matching the input school and major (S520). Multiple questions may be questions from past entrance exams related to the relevant school and major.

Additionally, the electronic device 100 may receive an essay written by the student for at least one question among the plurality of provided questions (S530).

Here, the electronic device 100 may identify the type of question in which the essay is input and identify a plurality of parameters matching the identified type (S540).

The types of questions include the “why us” type, which asks about motivation for applying, the “Intelectual interest” type, the “Meaningful experience & lesson learned” type, the “Achievement” type related to achievement experiences, the “contribution & solution” type related to social activities, “activity” type asking about vacation or seasonal activities, “unique quality, passion, talent” type, “extracurricular activity or work experience” type, “role and contribution in community” type, “role, involvement, and contributing in college community” " Type, "Overcoming challenge or ethical dilemma" type, "culture & diversity" type, "collaboration & teamwork" type, "Creativity" type, "Leadership experience" type, "values, perspectives, or beliefs" type, ㅇinfluence The received person may be of various types, such as "person who influence you" type, "favorite book/movie/quote" type, "diversity" type, "future goals" type, and "hobby" type, but various other types are also possible. Information on the type of question matching each university/major may be pre-stored and utilized on the electronic device 100 or at least one server connected to the electronic device 100.

Additionally, for each type of question, information on a plurality of parameters can be pre-stored and utilized.

For example, for the “why us” type, parameters such as “College & Department Fit”, “Major Fit”, and “Prompt Oriented Sentiments” may be preset, respectively.

For example, for the “intellectual intereset” type, parameters such as “Major Fit”, “General Knowledge”, “Prompt Oriented Sentiments”, and “Originality” may be preset, respectively.

For example, for the “Contribution & solution” type, parameters such as “Social awareness”, “prompt oriented sentiments”, “initiative, engagement, and contribution”, and “Topic Uniqueness” may be preset, respectively.

Additionally, the electronic device 100 may obtain evaluation information on the essay written by the student for each of a plurality of parameters identified according to the type of question (S550).

The evaluation information may include the absolute evaluation content for each parameter of the essay written by the student, and may also include comparative information with the evaluation content for each parameter of the essays of successful applicants to the university/major to which the student wishes to apply.

For example, if the type of question is the “intellectual interest” type, the electronic device 100 may acquire evaluation information related to the “Originality” parameter by analyzing the essay written by the student.

Specifically, the electronic device 100 may extract a plurality of keywords from text constituting an essay written by a student. Here, the extracted keywords may correspond to pre-stored words related to 'intellectual interest', or words matching a vector whose distance from the vector into which 'intellectual interest' is converted is within a certain distance.

In this case, the electronic device 100 may convert each of the extracted keywords into vector form and identify the degree of association between the plurality of keywords according to the distance between the converted vectors. In this case, if the correlation between keywords is too close, it may be interpreted as a relatively one-dimensional essay, and if the correlation between keywords is too far, it may be interpreted as an essay that is difficult to understand.

The electronic device 100 may obtain evaluation information according to the identified degree of relevance. For example, the closer the degree of association between keywords is to the critical degree of association corresponding to an appropriate value, the higher the electronic device 100 can calculate the evaluation score of the essay for the “Originality” parameter.

Additionally, as an example, if the type of question is the “Contribution & solution” type, the electronic device 100 may acquire evaluation information related to the “Topic Uniqueness” parameter by analyzing the essay written by the student.

Specifically, the electronic device 100 may extract a plurality of keywords from text constituting an essay written by a student. Here, the extracted keywords may be keywords that are relatively highly related to words such as 'social', 'issue', 'contribution', and 'solution', and may be keywords that correspond to the topic of at least one sentence in the essay. .

In this case, the electronic device 100 may perform a search on the web for each of the plurality of extracted keywords.

At this time, according to the search frequency of each of the plurality of keywords, the electronic device 100 may select at least one unique keyword from the plurality of keywords. In this case, the electronic device 100 may use the TF-IDF technique to identify unique keywords that appear in the essay even though they do not appear in general.

Additionally, the electronic device 100 may obtain evaluation information based on the frequency of unique keywords in the essay written by the student. For example, as the frequency of unique keywords approaches a certain value that is neither too high nor too low, the evaluation score may be calculated higher, but is not limited to this.

When evaluation information is obtained for each of a plurality of parameters according to the various embodiments described above, the electronic device 100 may generate feedback text according to the evaluation information obtained for each of the plurality of parameters (S560).

The feedback text may correspond to text generated as a result of summarizing/synthesizing evaluation information for each of a plurality of parameters.

FIG. 6 is a diagram illustrating a UI provided by an electronic device according to the embodiment of FIG. 5.

Referring to FIG. 6, the university and major to which the student wishes to apply may be selected and/or information about the university and major to which the student wishes to apply may be displayed through the UI 610.

The electronic device 100 can provide a question 601 of a type related to the university and major to which the student wishes to apply, and can receive an essay 602 written by the user for the question 601.

Referring to FIG. 6, the electronic device 100 sets a plurality of parameters (“College & Department Fit” (660), “Major Fit” (670), “Prompt Oriented Sentiments” that match the “why us” type of the question. A menu UI (651) including "(680), etc.) may be provided. Prompt oriented sentiments (680) corresponds to a parameter that indicates the degree of expression of emotions related to the type of question (: why us).

In relation to this, the electronic device 100 may provide a UI 651' that includes information on keywords related to the school and major and information on emotions related to the type of question (why us). In this case, the student can supplement the essay writing method by comparing the expressions in the essay 602 written by the student with the keywords and emotions in the UI 651'.

Referring to FIG. 6, in relation to the College & Department Fit parameter 660, the electronic device 100 displays indicators 660-1 and 2 to highlight subtexts related to 'Brown University', the university to be supported. It can be displayed. Additionally, in relation to the Major Fit parameter 670, the electronic device 100 may display indicators 670-1 and 2 to emphasize subtexts related to 'sociology', the major to be supported.

Here, when at least one of the indicators 660-1 and 2 is selected according to a mouse click or touch, the electronic device 100 may display attribute information such as “College & Dept.” Additionally, when at least one of the indicators 670-1 and 2 is selected according to a mouse click or touch, the electronic device 100 may display attribute information such as “Major Fit.”

Additionally, referring to FIG. 6 , the electronic device 100 may provide feedback text 651'' that comprehensively reflects evaluation information on parameters within the menu UI 651.

The feedback text 651'' may be generated as a result of comprehensively applying the attribute values and/or evaluation information of the essay 602 identified in relation to each of the parameters 660, 670, and 680. In relation to this, the electronic device 100 may use an artificial intelligence model that generates one or more sentences by sequentially reflecting the attribute value and/or evaluation information of each parameter.

Meanwhile, two or more of the various embodiments described above may be implemented together as long as they do not conflict with each other.

Meanwhile, the various embodiments described above may be implemented in a recording medium that can be read by a computer or similar device using software, hardware, or a combination thereof.

According to hardware implementation, the embodiments described in this disclosure include application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), and field programmable gate arrays (FPGAs). ), processor, controller, micro-controllers, microprocessor, and other electrical units for performing functions.

In some cases, embodiments described herein may be implemented in the processor itself. According to software implementation, embodiments such as procedures and functions described in this specification may be implemented as separate software modules. Each of the software modules described above may perform one or more functions and operations described herein.

Meanwhile, computer instructions for performing processing operations of a server or terminal according to various embodiments of the present disclosure described above may be stored in a non-transitory computer-readable medium. Computer instructions stored in such a non-transitory computer-readable medium, when executed by a processor of a specific device, cause the device to perform processing operations of the electronic device according to the various embodiments described above.

A non-transitory readable medium refers to a medium that stores data semi-permanently and can be read by a device, rather than a medium that stores data for a short period of time, such as registers, caches, and memories. Specifically, the various applications or programs described above may be stored and provided on non-transitory readable media such as CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM, etc.

In addition, although preferred embodiments of the present invention have been shown and described above, the present invention is not limited to the specific embodiments described above, and the technical field to which the invention pertains without departing from the gist of the present invention as claimed in the claims. Of course, various modifications can be made by those skilled in the art, and these modifications should not be understood individually from the technical idea or perspective of the present invention.

100: electronic device 110: memory
120: processor

Claims (9)

In a method of controlling an electronic device,
Receiving an essay written by a student for at least one question;
Analyzing the text constituting the essay to identify attribute values of the essay for each parameter; and
Displaying text constituting the essay, and displaying an indicator highlighting at least one subtext related to an attribute value for each parameter of the essay within the displayed text,
The attribute value of the first parameter extracts emotion/mood keywords corresponding to emotions or moods from the essay and is classified based on the frequency of the emotion/mood keywords,
The attribute value of the second parameter is specified by extracting character keywords from the essay, identifying characters appearing in the essay according to the character keywords, and classifying the characters according to their frequency,
The attribute value of the third parameter extracts a setting keyword related to at least one place, time, or movement included in the essay, identifies the strength of the setting keyword according to the ratio of the setting keyword, and relates to the strength of the identified setting keyword. Characterized in that the average value is calculated and identified and designated according to the calculated average value,
Control methods for electronic devices. According to paragraph 1,
The step of displaying the indicator is,
A method of controlling an electronic device, wherein when at least one parameter is selected, an indicator is displayed highlighting subtext related to an attribute value of the selected parameter. According to paragraph 2,
The control method of the electronic device is,
When the indicator is selected, displaying attribute information of the subtext related to the attribute value of the selected parameter. According to paragraph 1,
The step of displaying the indicator is,
A control method for an electronic device, wherein a plurality of indicators that emphasize each of a plurality of subtexts are distinguished and displayed according to attribute information. According to paragraph 1,
The control method of the electronic device is,
Entering the school and major to which the student wishes to apply;
Analyzing the essays of each successful applicant for the major at the school, and identifying attribute values for each parameter for each successful applicant's essay;
When at least one parameter is selected, displaying a graphic user interface (GUI) visualizing ratio information of successful candidates for each attribute value related to the selected parameter; and
Displaying, on the GUI, an indicator indicating a point matching an attribute value of an essay written by the student. According to clause 5,
The control method of the electronic device is,
receiving attribute values for each parameter according to the student's intention for the essay;
On the GUI, displaying an indicator indicating a point matching an attribute value according to the student's intention; and
A method of controlling an electronic device comprising: displaying comparison information comparing an attribute value of an essay written by the student with an attribute value according to the student's intention. In a method of controlling an electronic device,
Step of inputting the school and major to which the student wishes to apply;
Providing a plurality of questions matching the major of the school;
Receiving an essay written by the student for at least one question among the plurality of questions;
Identifying a type of the at least one item and identifying a plurality of parameters matching the identified type;
Obtaining evaluation information of the essay written by the student for each of the identified plurality of parameters; and
A step of generating feedback text according to evaluation information obtained for each of the plurality of parameters,
The step of identifying the plurality of parameters includes:
extracting emotion/mood keywords corresponding to emotions or moods from the essay as attribute values of the first parameter and classifying them based on the frequency of the emotion/mood keywords;
Extracting character keywords from the essay, identifying characters appearing in the essay according to the character keywords, and classifying and specifying the characters according to their frequencies as the attribute value of the second parameter;
The attribute value of the third parameter extracts a setting keyword related to at least one place, time, or movement included in the essay, identifies the intensity of the setting keyword according to the ratio of the setting keyword, and relates to the intensity of the identified setting keyword. Calculating an average value and identifying and designating it according to the calculated average value;
A control method of an electronic device further comprising. In clause 7,
The step of obtaining evaluation information on the essay written by the student includes obtaining evaluation information on the Originality parameter,
Extracting a plurality of keywords from the text constituting the essay written by the student;
Converting each of the plurality of keywords into vector form and identifying a degree of association between the plurality of keywords according to the distance between the converted vectors; and
A method of controlling an electronic device, comprising: acquiring evaluation information according to the identified correlation. In clause 7,
The step of obtaining evaluation information on the essay written by the student includes obtaining evaluation information on the Topic Uniqueness parameter,
Extracting a plurality of keywords from the text constituting the essay written by the student;
performing a search on the web for each of the plurality of keywords;
selecting at least one unique keyword among the plurality of keywords according to the search frequency of each of the plurality of keywords; and
Obtaining evaluation information based on the frequency of the unique keyword in the essay written by the student.