Device and method for automatically editing document by using artificial intelligence

Abstract

Provided are a device and a method for automatically editing a document by using artificial intelligence. The method may comprise the steps of: receiving a request for uploading a document from a terminal of a first user who is an uploader; providing an editing guide including a first edit of the document on the basis of characteristics of the document by using an artificial intelligence-based first model; and detecting an input of the terminal of the first user and determining whether to proceed with the first edit.

Description

Device and method for automatically editing documents using artificial intelligence

[0001] The present disclosure relates to a device and method for automatically editing documents using artificial intelligence.

[0002] PDF stands for Portable Document Format, a file format that displays documents consistently across different platforms, regardless of software, hardware, or operating system. Its primary purpose is to facilitate the seamless exchange of electronic documents between users while preserving their visual appearance and format.

[0003] Currently, PDF is widely used as a means of information sharing in various fields, including business environments, government, and legal fields, where contracts, reports, and presentations are created and distributed. However, sharing PDF documents poses a challenge: regardless of the characteristics of the users distributing or using them, they must be shared in a consistent format.

[0004] The purpose of the embodiments disclosed in this disclosure is to provide a document automatic editing device and method using artificial intelligence.

[0005] The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

[0006] A method for automatically editing a document using artificial intelligence according to one aspect of the present disclosure for achieving the above-described technical task may include a step of receiving a request for uploading a document from a terminal of a first user who is an uploader, a step of providing an editing guide including a first editing of the document based on characteristics of the document using an artificial intelligence-based first model, and a step of detecting an input of the terminal of the first user to determine whether to proceed with the first editing.

[0007] In addition, the method further includes a step of requesting access to the document from a terminal of a second user who is a downloader, a step of editing the document a second time based on characteristics of the second user, and a step of providing the second edited document to the terminal of the second user, wherein the first editing and the second editing may be adding specific content to a specific location of the document.

[0008] In addition, the specific location may be selected through artificial intelligence-based document analysis or analysis of the document viewing behavior pattern of the second user, and the specific content may be generated in the form of content inserted into one page or a page included in the document.

[0009] In addition, the first editing may include, if the document is a document requiring security, a step of extracting a highly confidential page within the document by utilizing the first model and a step of inserting a security page notifying a security warning in front of the extracted page.

[0010] In addition, a page within the document having a view rate higher than a preset value can be specified, and security content including at least one of a security warning, personal information of the second user, and a watermark can be inserted into the specified page.

[0011] In addition, the second editing step may include a step of analyzing a document viewing behavior pattern of the second user, a step of extracting a page of interest of the second user based on the analysis result, a step of selecting a location to insert security content within the page of interest based on the analysis result, and a step of inserting the security content at the selected location.

[0012] Additionally, the security content may include at least one of a security warning, personal information of the second user, and a watermark.

[0013] In addition, the first editing may include a step of extracting a plurality of documents of the same type as the type of the document requested for upload from among all documents already uploaded, a step of analyzing a document viewing behavior pattern of a plurality of second users for each of the plurality of documents, a step of extracting a page expected to have a high bounce rate from among the documents requested for upload through the analysis, a step of extracting content related to the bounce rate from among the pages expected to have a high bounce rate, and a step of recommending alternative content to be inserted into the content related to the bounce rate using an artificial intelligence-based second model.

[0014] In addition, the document is divided into at least one area, and a mouse pointer heatmap is generated that overlaps at least partly with the at least one area, and the second model can learn the number of clicks for the at least one area, the mouse hovering time for the at least one area, the mouse pointer heatmap, the content viewing time, and the number of repeated viewings for each type of the document.

[0015] Additionally, after the decision on whether to proceed with the first editing is made, the document can be set to private mode for a preset period of time at the request of the first user.

[0016] In addition, in another aspect of the present disclosure for achieving the above-described technical task, a method for automatically editing a document using artificial intelligence includes a step of receiving a request for uploading a document from a terminal of a first user who is an uploader, a step of receiving a request for access to the document from a terminal of a second user who is a downloader, a step of editing the document based on characteristics of the second user, and a step of providing the edited document to the terminal of the second user, wherein the editing may be adding specific content to a specific location of the document.

[0017] In addition, in another aspect of the present disclosure for achieving the above-described technical problem, an automatic document editing device using artificial intelligence includes a communication unit, a memory storing at least one process for providing an automatic document editing service using artificial intelligence, and a processor configured to receive a request for uploading a document from a terminal of a first user who is an uploader through the communication unit, perform a first edit on the document based on a characteristic of the document, receive a request for downloading the document from a terminal of a second user who is a downloader through the communication unit, perform a second edit on the first edited document based on a characteristic of the second user, and provide the second edited document to the terminal of the second user through the communication unit, wherein the first edit and the second edit may be adding specific content to a specific location of the document.

[0018] In addition, a computer program stored in a computer-readable recording medium for executing a method for implementing the present disclosure may be further provided.

[0019] In addition, a computer-readable recording medium recording a computer program for executing a method for implementing the present disclosure may be further provided.

[0020] According to the aforementioned problem solving means of the present disclosure, the efficiency and security of document sharing can be improved by editing the document by taking into account the characteristics of the person uploading the document and the person downloading the document, respectively.

[0021] The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

[0022] FIG. 1 is a schematic diagram illustrating a system for automatically editing a document using artificial intelligence according to one embodiment of the present disclosure.

[0023] FIG. 2 is a block diagram of an automatic document editing device using artificial intelligence according to one embodiment of the present disclosure.

[0024] FIG. 3 is a flowchart of a method for automatically editing a document using artificial intelligence according to one embodiment of the present disclosure.

[0025] FIG. 4 is a flowchart of a content recommendation-based editing method based on a churn rate according to one embodiment of the present disclosure.

[0026] FIG. 5A and FIG. 5B are diagrams illustrating page and content insertion according to one embodiment of the present disclosure.

[0027] FIG. 6 is a flowchart of a method for automatically editing a document using artificial intelligence according to another embodiment of the present disclosure.

[0028] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and any content that is common in the technical field to which this disclosure belongs or that overlaps between embodiments is omitted. The terms "part, module, element, block" used in the specification may be implemented in software or hardware, and depending on the embodiment, multiple "parts, modules, elements, blocks" may be implemented as a single component, or a single "part, module, element, block" may include multiple components. Throughout the specification, when a part is said to be "connected" to another part, this includes not only cases where it is directly connected, but also cases where it is indirectly connected, and an indirect connection includes a connection via a wireless communication network.

[0029] Additionally, when a part is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise specifically stated.

[0030] Throughout the specification, when we say that an element is "on" another element, this includes not only cases where the element is in contact with the other element, but also cases where another element exists between the two elements.

[0031] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0032] Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0033] The identification codes for each step are used for convenience of explanation and do not describe the order of each step. Each step may be performed in a different order than specified unless the context clearly indicates a specific order.

[0034] The operating principle and embodiments of the present disclosure are described below with reference to the attached drawings.

[0035] Before proceeding, the meanings of terms used in this specification will be briefly explained. However, it should be noted that the explanation of terms is intended to aid understanding of this specification, and therefore, unless explicitly stated to limit the disclosure, they are not intended to limit the technical concepts of this disclosure.

[0036] In this specification, the term "device" encompasses a variety of devices capable of performing computational processing and providing results to a user. For example, a device may include a computer, a server, or a portable terminal, or may be any one of these.

[0037] Here, the computer may include, for example, a notebook, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser.

[0038] The above server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

[0039] The above portable terminal may include, for example, a wireless communication device that ensures portability and mobility, and may include all kinds of handheld-based wireless communication devices such as a PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminal, a smart phone, and a wearable device such as a watch, a ring, a bracelet, an anklet, a necklace, glasses, contact lenses, or a head-mounted device (HMD).

[0040] The artificial intelligence-related functions according to the present disclosure are operated through a processor and memory. The processor may be composed of one or more processors. In this case, one or more processors may be a general-purpose processor such as a CPU, an AP, a DSP (Digital Signal Processor), a graphics-only processor such as a GPU or a VPU (Vision Processing Unit), or an artificial intelligence-only processor such as an NPU. One or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in memory. Alternatively, if one or more processors are artificial intelligence-only processors, the artificial intelligence-only processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0041] The predefined operation rules or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that the basic artificial intelligence model is learned by a learning algorithm using a plurality of learning data, thereby creating a predefined operation rules or artificial intelligence model set to perform a desired characteristic (or purpose). This learning may be performed on the device itself on which the artificial intelligence according to the present disclosure is performed, or may be performed through a separate server and / or system. Examples of the learning algorithm include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0042] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values, and performs neural network operations through operations between the operation results of the previous layer and the multiple weights. The multiple weights of the multiple neural network layers may be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model is reduced or minimized during the learning process. The artificial neural network may include a deep neural network (DNN), and examples thereof include, but are not limited to, a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or deep Q-networks.

[0043] The processor can create a neural network, train (or learn) a neural network, perform computations based on received input data, and generate information signals based on the results of the computations, or retrain the neural network.

[0044] Neural networks include CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), perceptron, multilayer perceptron, FF (Feed Forward), RBF (Radial Basis Network), DFF (Deep Feed Forward), LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit), AE (Auto Encoder), VAE (Variational Auto) Encoder), DAE (Denoising Auto Encoder), SAE (Sparse Auto Encoder), MC (Markov Chain), HN (Hopfield Network), BM (Boltzmann Machine), RBM (Restricted Boltzmann Machine), DBN (Depp Belief Network), DCN (Deep Convolutional Network), DN (Deconvolutional Network), DCIGN (Deep Convolutional Inverse Graphics Network), Generative Adversarial Network (GAN), Liquid State Machine (LSM), Extreme Learning Machine (ELM), It will be understood by those skilled in the art that any neural network may be included, including but not limited to ESN (Echo State Network), DRN (Deep Residual Network), DNC (Differentiable Neural Computer), NTM (Neural Turning Machine), CN (Capsule Network), KN (Kohonen Network), and AN (Attention Network).

[0045] According to an exemplary embodiment of the present disclosure, the processor may be configured to perform a process for generating a CNN (Convolution Neural Network) such as GoogleNet, AlexNet, VGG Network, Region with Convolution Neural Network (R-CNN), Region Proposal Network (RPN), Recurrent Neural Network (RNN), Stacking-based deep Neural Network (S-DNN), State-Space Dynamic Neural Network (S-SDNN), Deconvolution Network, Deep Belief Network (DBN), Restrcted Boltzman Machine (RBM), Fully Convolutional Network, Long Short-Term Memory (LSTM) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT, SP-BERT, MRC / QA for natural language processing, Text Analysis, Dialog System, GPT-3, GPT-4, Visual Analytics for vision processing, Visual Understanding, Video Synthesis, ResNet for data intelligence, Anomaly Detection, Prediction, Time-Series Forecasting, Various artificial intelligence structures and algorithms can be used, including but not limited to Optimization, Recommendation, and Data Creation.

[0046] In this specification, "document" may refer to a document file created to convey information in various fields. Specifically, the document may be a PDF file, but is not limited thereto, and various document file formats may be applied.

[0047] In this specification, "first editing" refers to editing based on the characteristics of the document, while "second editing" refers to editing based on the characteristics of the downloader. The first and second editing may be performed independently. That is, the first editing of the original document may be performed based on the characteristics of the document, and the second editing of the original document may be performed separately based on the characteristics of the downloader.

[0048] However, without limitation thereto, depending on the embodiment, the first and second edits may be performed sequentially. That is, the original document may be first edited according to the characteristics of the document, and then second edited according to the characteristics of the downloader.

[0049] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings.

[0050] FIG. 1 is a schematic diagram illustrating a system for automatically editing a document using artificial intelligence according to one embodiment of the present disclosure.

[0051] Referring to Figure 1, an uploader using the service platform can request the upload of a document he or she has created (or wishes to share) to the service platform via his or her terminal, and a downloader using the service platform can request the download of a document uploaded to the service platform via his or her terminal. Within the service platform, an uploader can be a downloader, and a downloader can be an uploader.

[0052] At this time, the document automatic editing device (10) linked to the service platform can determine whether to provide the original document, the first edited document (first edited version), or the second edited document (second edited version) when providing the document to the downloader according to the uploader's settings.

[0053] If the uploader sets it to 'Provide Original', the document auto-editing device (10) does not perform any editing on the document.

[0054] If the uploader sets it to 'provide first edit', the document automatic editing device (10) can edit the original document for the first time.

[0055] If the uploader sets it to 'provide a second edit', the document automatic editing device (10) can edit the original document a second time.

[0056] That is, the downloader can view the document in one of the following forms: original, first edit, or second edit.

[0057] The document automatic editing device (10) may be a server device of a company providing document editing and document sharing services. The document automatic editing device (10) will be described in detail below with reference to FIG. 2.

[0058] FIG. 2 is a block diagram of an automatic document editing device using artificial intelligence according to one embodiment of the present disclosure.

[0059] Referring to FIG. 2, the document automatic editing device (10) may include a communication unit (11), a memory (12), and a processor (13). The processor (13) may include a first editing module (131) and a second editing module (132). However, in some embodiments, the document automatic editing device (10) and the processor (13) may include fewer or more components than the components illustrated in FIG. 2.

[0060] The communication unit (11) may include one or more modules that enable wireless or wired communication between the automatic document editing device (10) and a user terminal (not shown), between the automatic document editing device (10) and an external server (not shown), and between the automatic document editing device (10) and a communication network. For example, it may include at least one of a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0061] A user terminal (not shown) may be a device used by a user (uploader or downloader), may be applied with an information processing means such as a computer, may include a processor such as a control unit, a photographing means such as a camera, an input / output means including a touch screen, and may mean any device with a communication function. In other words, any device such as a smartphone, tablet, PDA, laptop, or desktop may be applied.

[0062] The external server (not shown) may be, but is not limited to, a service platform server.

[0063] The communication network can use various types of communication networks, for example, wireless communication methods such as WLAN (Wireless LAN), Wi-Fi, Wibro, WiMAX, and HSDPA (High Speed ​​Downlink Packet Access), or wired communication methods such as Ethernet, xDSL (ADSL, VDSL), HFC (Hybrid Fiber Coax), FTTC (Fiber to The Curb), and FTTH (Fiber to The Home) can be used.

[0064] Meanwhile, the communication network is not limited to the communication methods presented above, and may include all other widely known or future-developed communication methods in addition to the above-described communication methods.

[0065] The wired communication module may include various wired communication modules such as a Local Area Network (LAN) module, a Wide Area Network (WAN) module, or a Value Added Network (VAN) module, as well as various cable communication modules such as a Universal Serial Bus (USB), a High Definition Multimedia Interface (HDMI), a Digital Visual Interface (DVI), RS-232 (recommended standard 232), power line communication, or plain old telephone service (POTS).

[0066] The wireless communication module may include a wireless communication module that supports various wireless communication methods such as GSM (global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), 4G, 5G, and 6G, in addition to a WiFi module and a Wireless Broadband module.

[0067] The short-range communication module is for short-range communication, and can support short-range communication using at least one of Bluetooth™, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus) technologies.

[0068] The memory (12) may store at least one process for providing an automatic document editing service using artificial intelligence.

[0069] Memory (12) may store an artificial intelligence-based model used for automatic document editing.

[0070] The memory (12) can store data supporting various functions of the automatic document editing device (10), a program for the operation of the processor (13), can store input / output data (e.g., music files, still images, moving images, etc.), and can store a plurality of application programs (or applications) run by the automatic document editing device (10), data for the operation of the automatic document editing device (10), and commands. At least some of these application programs can be downloaded from an external server via wireless communication.

[0071] The memory (12) may include at least one type of storage medium among a flash memory type, a hard disk type, an SSD (Solid State Disk type), an SDD (Silicon Disk Drive type), a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. In addition, the memory (12) is separate from the document automatic editing device (10), but may be a database connected by wire or wirelessly.

[0072] The processor (13) can perform the aforementioned operations using a memory that stores data regarding an algorithm for controlling the operations of components within the automatic document editing device (10) or a program that reproduces the algorithm, and the data stored in the memory. At this time, the memory (12) and the processor (13) may each be implemented as separate chips. Alternatively, the memory (12) and the processor (13) may be implemented as a single chip.

[0073] The first editing module (131) of the processor (13) can edit a document based on the characteristics of the document requested for upload. At this time, as described above, the first editing can be performed only when the uploader of the document has set the first editing of the document.

[0074] In one embodiment, when a document upload request is made, the first editing module (131) may provide the uploader's terminal with a document editing guide including a first edit based on the characteristics of the document. The uploader may request the first edit based on the document editing guide. When the first edit request is received from the uploader's terminal, the first editing module (131) may perform the first edit on the document based on the uploader's input.

[0075] In another embodiment, when a document upload is requested, the first editing module (131) can perform a first editing based on the characteristics of the document.

[0076] The second editing module (132) of the processor (13) can edit the requested document based on the characteristics of the downloader. At this time, as described above, the second editing can be performed only if the uploader of the document has set the second editing of the document.

[0077] When a document download is requested, the second editing module (132) can perform a second editing of the original document based on the characteristics of the downloader who requested the download.

[0078] However, without being limited thereto, depending on the embodiment, when a document download is requested, the second editing module (132) may perform a second editing on the document for which the first editing has been performed based on the characteristics of the downloader.

[0079] In addition, the processor (13) can control any one or a combination of the components discussed above to implement various embodiments according to the present disclosure described in FIGS. 3 to 6 below on the automatic document editing device (10).

[0080] Hereinafter, the automatic document editing method will be specifically described with reference to FIGS. 3 to 6.

[0081] FIG. 3 is a flowchart of a method for automatically editing a document using artificial intelligence according to one embodiment of the present disclosure.

[0082] FIG. 4 is a flowchart of a content recommendation-based editing method based on a churn rate according to one embodiment of the present disclosure.

[0083] FIG. 5A and FIG. 5B are diagrams illustrating page and content insertion according to one embodiment of the present disclosure.

[0084] FIG. 6 is a flowchart of a method for automatically editing a document using artificial intelligence according to another embodiment of the present disclosure.

[0085] For convenience of explanation, the following description describes each step as being performed by the processor (13), but it may be understood that each step is performed by one of the first editing module (131), the second editing module (132), and a module not shown in FIG. 2 included in the processor (13).

[0086] Hereinafter, with reference to FIGS. 3, 4, 5a and 5b, an embodiment of performing a first edit on a document will be described.

[0087] Referring to FIG. 3, the processor (13) can receive a request to upload a document from the terminal of the first user, who is an uploader (S211).

[0088] The processor (13) can provide an editing guide including a first editing of a document based on the characteristics of the document using an artificial intelligence-based first model (S212).

[0089] The processor (13) can detect input from the terminal of the first user and perform the first editing of the document (S213).

[0090] Prior to step S211, the processor (13) may request settings regarding the document provision format from the first user's terminal. In response, the processor (13) may receive settings from the first user's terminal regarding whether to provide the document in its original form, a first edited form, or a second edited form. The following describes a case where the first edit is performed.

[0091] The processor (13) can provide an editing guide to the first user by considering the characteristics of the document requested for upload, perform a first editing according to the content entered by the first user according to the editing guide, and provide the first edited document to the second user terminal.

[0092] Here, the characteristics of the document may include, but are not limited to, the type of document, purpose, author, number of pages, composition, and the document viewing behavior patterns of downloaders who viewed the document.

[0093] Additionally, the editing guide may be a guide for the first edit, depending on the characteristics of the document. Depending on the embodiment, the editing guide may provide examples of the parts (which may be one or multiple) that will be changed in the document when the first edit is performed. Depending on the embodiment, the editing guide may provide examples of the parts (which may be one or multiple) that will be changed in the document when the first edit is performed, and may further include questions asking whether to apply these examples.

[0094] When the first user checks the editing guide and requests the first editing process through the terminal, the processor (13) can proceed with the first editing process.

[0095] At this point, the first edit may be to add specific content to a specific location in the document.

[0096] Specific locations can be selected through AI-based document analysis or analysis of document viewing behavior patterns of second-party users.

[0097] Specific content may be created in the form of content inserted into a single page or a page included in the document. The content may be, but is not limited to, text, graphs, tables, photos, drawings, charts, etc.

[0098] That is, the processor (13) can determine a location within the document that requires editing through document analysis and determine which page or which content to add to that location.

[0099] In one embodiment, the first edit may include, if the document is a document requiring security, a step of extracting a highly confidential page within the document using the first model, and a step of inserting a security page notifying a security warning in front of the extracted page.

[0100] The processor (13) can extract highly confidential pages within a document using the AI-based first model. Specifically, among the pages contained in the document, pages containing a greater than preset number of security-related words can be extracted as highly confidential pages. Alternatively, among the pages contained in the document, pages containing information requiring security (text, graphs, tables, photos, drawings, charts, etc.) can be extracted as highly confidential pages.

[0101] Referring to Figure 5a, if page 3 is extracted as a highly confidential page within a document, a security page is inserted before page 3, the inserted security page is numbered as page 3, and the page that was previously page 3 is renumbered as page 4.

[0102] In another embodiment, the first edit may include, if the document is a document requiring security, a step of extracting a highly confidential portion (a specific paragraph within a specific page, a specific image, table, graph, chart, etc. within a specific page) within the document by utilizing the first model, and a step of inserting security content notifying a security warning in front of the extracted portion.

[0103] Here, the security content inserted during the first edit may be security warning content. This allows downloaders to preview warnings regarding security-critical sections, allowing them to view the document with security in mind.

[0104] The processor (13) can extract highly confidential portions within a document using the AI-based first model. Specifically, paragraphs containing more than a preset number of security-related words among pages within the document can be extracted as highly confidential portions. Alternatively, information requiring security (graphs, tables, photos, drawings, charts, etc.) can be extracted as highly confidential portions among pages within the document.

[0105] Referring to Figure 5b, if a specific part of page 3 within a document is extracted as a highly confidential part, secure content can be inserted in front of that part.

[0106] In another embodiment, referring to FIG. 4, the first editing may include a step of extracting a plurality of documents of the same type as the type of the document requested for upload from among all documents already uploaded within the platform (S221), a step of analyzing a document viewing behavior pattern of a plurality of second users for each of the plurality of documents (S222), a step of extracting a page expected to have a high bounce rate within the document requested for upload through the analysis (S223), a step of extracting content related to the bounce rate within the page expected to have a high bounce rate, and a step of recommending alternative content to be inserted into the content related to the bounce rate using an artificial intelligence-based second model (S224).

[0107] Specifically, the processor (13) can extract documents of the same type as the document requested for upload, and analyze the document viewing behavior patterns of second users who have downloaded each document based on the download history of each of the documents. In addition, the processor (13) can extract pages expected to have a high bounce rate from the document requested for upload based on the document viewing behavior patterns of the second users for the same type of document, and extract content related to the bounce rate from the pages.

[0108] That is, the processor (13) can predict which page of the currently uploaded document will have a high bounce rate through the user's viewing behavior patterns for documents of the same type, and can also predict the part of the page that is highly correlated with user bounce.

[0109] In addition, the processor (13) can recommend alternative content to be inserted instead of the extracted deviation and the highly correlated portion (content) using the artificial intelligence-based second model.

[0110] Specifically, the processor (13) can divide a document into at least one area and record the number of clicks and mouse hovering time of the second user for each area. In addition, the processor (13) can generate a mouse pointer heat map that overlaps at least a portion of at least one area.

[0111] The processor (13) can utilize various data recorded when second users view documents as learning data for the second model. That is, the second model can learn the number of clicks for at least one area, the mouse hovering time for at least one area, the mouse pointer heat map, the content viewing time, and the number of repeated viewings for each document type.

[0112] The second model, trained in this way, can recommend alternative content to insert in place of the content associated with the aforementioned churn rate. That is, because the second model can predict which content insertions are likely to reduce churn rates through training, it can recommend alternative content to insert in areas highly correlated with churn, thereby increasing the interest of secondary users and reducing churn rates.

[0113] Additionally, the processor (13) can set the document to private mode for a preset period of time at the request of the first user after determining whether the first editing is in progress.

[0114] In some embodiments, the processor (13) may set the document to private mode for a period of time from the time the document is uploaded to the platform until the time the first download is performed, after the first edit of the document is performed.

[0115] In an embodiment, the processor (13) may set the document to private mode after the first edit of the document is performed and uploaded to the platform until the number of downloads of the document exceeds a preset number.

[0116] According to an embodiment, when a request to release the private mode is received from the first user for a document set to the private mode, the processor (13) may release the private mode even if the above time has not elapsed.

[0117] In the above, it was explained that the first edit is determined based on the user's input by providing an editing guide during the first edit. However, if an upload is requested without providing an editing guide, the device may automatically edit based on the characteristics of the document in question.

[0118] Hereinafter, with reference to FIG. 6, an embodiment of performing a second edit on a document will be described.

[0119] Referring to FIG. 6, the processor (13) can receive a request to upload a document from the terminal of the first user, who is the uploader (S231).

[0120] The processor (13) may receive a request for access to the document from the terminal of a second user who is a downloader (S232).

[0121] The processor (13) can edit the document a second time based on the characteristics of the second user (S233).

[0122] The processor (13) can provide the second edited document to the terminal of the second user (S234).

[0123] Prior to step S231, the processor (13) may request settings regarding the document provision format from the first user's terminal. In response, the processor (13) may receive settings from the first user's terminal regarding whether to provide the document in its original form, a first edited form, or a second edited form. The following describes the case where the second edit is performed.

[0124] The processor (13) may upload a requested document to the platform, and then, when a download request for the uploaded document is received from a second user, perform a second editing of the document based on the characteristics of the second user who requested the download, and provide the second-edited document to the second user terminal. The characteristics of the second user may include the second user's previous document viewing behavior patterns.

[0125] At this point, the second edit may be to add specific content to a specific location in the document.

[0126] A specific location may be selected through AI-based document analysis or analysis of the document viewing behavior patterns of a second user (more specifically, the second user who requested the download).

[0127] Specific content may be created in the form of content inserted into a single page or a page included in the document. The content may be, but is not limited to, text, graphs, tables, photos, drawings, charts, etc.

[0128] In one embodiment, the second editing step may include a step of analyzing a previous document viewing behavior pattern of a second user who requested a download, a step of extracting a page of interest of the second user based on the analysis result, a step of selecting a location to insert security content within the page of interest based on the analysis result, and a step of inserting the security content at the selected location.

[0129] That is, the processor (13) extracts a page that the second user may be interested in among the documents that the second user has requested to download based on the record of documents that the second user has previously downloaded and viewed, extracts a part containing content that may be of interest within the page of interest, and inserts security content in front of or in the part of the part.

[0130] Here, the security content inserted during the second edit may include at least one of the personal information of the second user who requested the download and a watermark. By inserting the downloader's personal information into the security content, the downloader's illegal leak of the document can be prevented.

[0131] In another embodiment, the processor (13) may specify a page in a document whose view rate is higher than a preset value, and insert secure content including at least one of personal information and a watermark of a second user who requested a download into the specified page.

[0132] That is, based on the viewing behavior patterns of second users who have previously downloaded a document requested by a second user, a page among the documents whose viewing rate is greater than a preset value is identified, and at least one of the personal information of the second user who has currently requested a download and a watermark is inserted into the page, thereby preventing leakage of important parts within the document.

[0133] The second edited document is then transmitted to the second user's terminal, allowing the second user to view the document.

[0134] Below, an embodiment in which the first and second edits are performed sequentially will be described.

[0135] The processor (13) can receive a request to upload a document from the terminal of the first user, who is the uploader.

[0136] The processor (13) can provide an editing guide including a first editing of a document based on the characteristics of the document using an artificial intelligence-based first model.

[0137] The processor (13) can detect input from the terminal of the first user and perform the first editing of the document.

[0138] The processor (13) may receive a request for access (download) to the document from the terminal of a second user who is a downloader.

[0139] The processor (13) can perform a second edit on the document based on the characteristics of the second user.

[0140] The processor (13) can provide the first and second edited documents to the terminal of the second user.

[0141] Here, the first and second edits are the same as those described above, so detailed descriptions are omitted.

[0142] Although FIGS. 3, 4, and 6 describe the steps as being executed sequentially, this is merely an example of the technical idea of ​​the present embodiment, and a person having ordinary skill in the art to which the present embodiment pertains can modify and apply various modifications and variations by changing the order described in FIGS. 3, 4, and 6 or executing them in parallel without departing from the essential characteristics of the present embodiment, and therefore FIGS. 3, 4, and 6 are not limited to a chronological order.

[0143] Meanwhile, in the above description, the steps described in FIGS. 3, 4, and 6 may be further divided into additional steps or combined into fewer steps, depending on the implementation example of the present disclosure. Furthermore, some steps may be omitted as needed, and the order of the steps may be changed.

[0144] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium storing computer-executable instructions. The instructions may be stored in the form of program code, and when executed by a processor, may generate program modules to perform the operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0145] Computer-readable storage media include all types of storage media that store instructions that can be deciphered by a computer. Examples include read-only memory (ROM), random access memory (RAM), magnetic tape, magnetic disks, flash memory, and optical data storage devices.

[0146] The disclosed embodiments have been described with reference to the attached drawings as described above. Those skilled in the art will understand that the present disclosure can be implemented in forms other than the disclosed embodiments without altering the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be construed as limiting.

Claims

1. In a method performed by a device, A step of receiving a request for uploading a document from a terminal of a first user who is an uploader; A step of providing an editing guide including a first edit of the document based on the characteristics of the document using an artificial intelligence-based first model; and A method for automatically editing a document using artificial intelligence, comprising: a step of detecting an input from a terminal of the first user and determining whether to proceed with the first editing.

2. In paragraph 1, A step of requesting access to the document from a terminal of a second user who is a downloader; a step of editing the document a second time based on the characteristics of the second user; and Further comprising a step of providing the second edited document to the terminal of the second user; The above first editing and the above second editing are an automatic document editing method using artificial intelligence, wherein specific content is added to a specific location of the document.

3. In paragraph 2, The above specific location is selected through artificial intelligence-based document analysis or analysis of the document viewing behavior pattern of the second user, The above specific content is a method for automatically editing a document using artificial intelligence, which is generated in the form of content inserted into a single page or a page included in the document.

4. In paragraph 1, The above first edit is, If the above document is a document requiring security, a step of extracting highly confidential pages within the document by utilizing the first model; and A method for automatically editing a document using artificial intelligence, comprising the step of inserting a security page notifying a security warning in front of the extracted page.

5. In paragraph 2, Identify the pages in the above document whose view rate is higher than the preset value, An automatic document editing method using artificial intelligence, which inserts security content including at least one of a security warning, personal information of the second user, and a watermark into a specified page.

6. In paragraph 3, The second editing step is as follows: A step of analyzing the document viewing behavior pattern of the second user; A step of extracting pages of interest of the second user based on the analysis results; A step of selecting a location to insert security content within the page of interest based on the analysis results; and A method for automatically editing a document using artificial intelligence, comprising the step of inserting the security content into the selected location.

7. In paragraph 6, A method for automatically editing a document using artificial intelligence, wherein the above security content includes at least one of a security warning, personal information of the second user, and a watermark.

8. In paragraph 1, The above first edit is, A step of extracting multiple documents of the same type as the document requested for upload from among all documents already uploaded; A step of analyzing document viewing behavior patterns of multiple second users for each of the multiple documents; A step of extracting pages expected to have a high bounce rate within the uploaded document through the above analysis; A step of extracting content related to the bounce rate within a page expected to have a high bounce rate; and A method for automatically editing a document using artificial intelligence, comprising: a step of recommending alternative content to be inserted into content related to the above-mentioned churn rate using an artificial intelligence-based second model; 9. In paragraph 8, Divide the above document into at least one area, Generate a mouse pointer heatmap that overlaps at least a portion of at least one of the above areas, The second model is an artificial intelligence-based automatic document editing method that learns the number of clicks per at least one area, the mouse hovering time per at least one area, the mouse pointer heat map, the content viewing time, and the number of repeated viewings for each type of document.

10. In paragraph 1, An automatic document editing method using artificial intelligence, which sets the document to private mode for a preset period of time at the request of the first user after determining whether to proceed with the above first editing.

11. A computer program stored in a computer-readable recording medium for performing any one of the methods of claims 1 to 10 in combination with a computer.

12. In a method performed by a device, A step of receiving a request for uploading a document from a terminal of a first user who is an uploader; A step of requesting access to the document from a terminal of a second user who is a downloader; A step of editing the document based on the characteristics of the second user; and A step of providing the above-mentioned edited document to the terminal of the second user; The above editing is an automatic document editing method using artificial intelligence, which adds specific content to a specific location in the above document.

13. Ministry of Communications; A memory storing at least one process for providing an automatic document editing service using artificial intelligence; and A processor that receives a request for uploading a document from a terminal of a first user who is an uploader through the communication unit, performs a first edit on the document based on the characteristics of the document, receives a request for downloading the document from a terminal of a second user who is a downloader through the communication unit, performs a second edit on the first edited document based on the characteristics of the second user, and provides the second edited document to the terminal of the second user through the communication unit; An automatic document editing device using artificial intelligence, wherein the first editing and the second editing add specific content to a specific location of the document.

Images