Specialized document sharing platform providing method and system therefor

Abstract

To provide a specialized document sharing platform providing method and a system therefor for generating question-and-answer content regarding specialized documents using a predetermined deep learning neural network and for providing public relation content based on the generated question-and-answer content.SOLUTION: A method according to the present invention has a step of acquiring a predetermined specialized document, a step of generating question-and-answer content as to the specialized document based on a question-and-answer language model, a step of generating public relation content as an on-line publicly available subject as to the specialized document based on the question-and-answer content, a step of providing the public relation content based on a publicly-available subject creation work space, a step of, based on the publicly-available subject creation work space, determining publicity starting content as the public relation content to be registered on a specialized document sharing platform, and a step of providing the publicity starting content based on the specialized document sharing platform.SELECTED DRAWING: Figure 6

Description

Technical Field

[0001] The present invention relates to a method for providing a specialized document sharing platform and its system. More specifically, the present invention relates to a method for providing a specialized document sharing platform and its system that generates question-and-answer content for specialized documents using a predetermined deep-learning neural network and provides publicity content based on the generated question-and-answer content.

Background Art

[0002] Generally, existing technical information providing services using the Internet simply display a list of information provided by an operator when a user connects to a technical information providing site via the Internet, or provide simple html materials in an abstract form when a user clicks a bookmark.

[0003] In addition, various companies, research institutes, public institutions, and / or universities have accumulated data on industrial technology knowledge information and research results. However, the fact that such data cannot be appropriately utilized is actually acting as one factor inhibiting the development of national industrial technology.

[0004] Therefore, various companies, research institutes, public institutions, and / or universities, etc. need to appropriately compensate and distribute the accumulated data on industrial technology knowledge information and research results, and provide reliable data to those who request industrial technology knowledge information, so as to promote the circulation and transaction activation of industrial technology knowledge information. A system and service method are required.

[0005] Therefore, currently, various sharing platforms for specialized documents (such as papers and / or reports, etc.) have been realized and provided.

[0006] Such platforms can share various data to widely publicize specialized documents, enabling more research to be conducted through this. Through sharing data, codes, and / or drafts derived during the research process, etc., more transparent research can be carried out.

[0007] Furthermore, by recording the research process, in the future, when there are discussions about research ideas, it can hold a preemptive position, and it is also possible to recommend the research works of scholars at various stages in various fields according to the research fields and research topics, leading to the effect of breaking the polarization citation trend where only the papers of scholars already well-known in the academic community are mainly cited.

[0008] Exemplarily, such platforms include Arxiv, Open science framework (OSF), Dataverse, Figshare, and / or Github, etc.

[0009] However, most of the conventional specialized document sharing platforms as described above have the problem that they simply summarize or list at least one specialized document related to the content desired by the user, providing search results at such a level that additional efforts are required to familiarize oneself in detail with the content of the documents corresponding to the search results.

[0010] Also, in the case of conventional specialized document sharing platforms, for documents that require innovation in knowledge processing and inference, such as specialized documents related to in-depth technical information (e.g., scientific and technical papers, etc.), they have the limitation that the accuracy and quality of their search results are low.

[0011] Furthermore, most of the conventional specialized document sharing platforms are realized as paid services that pay appropriate compensation to the providers of the specialized documents so that a large number of specialized documents on the platform can be subscribed to. However, in the case of most information providers, they lack knowledge about publicity methods and content production methods for increasing their sharing volume, etc., and thus experience difficulties in actively publicizing and circulating the specialized documents they have created.

Prior Art Documents

Patent Documents

[0012] Patent Document 1: KR10-1341948 B1

Summary of the Invention

Problems to be Solved by the Invention

[0013] One embodiment of the present invention was devised to solve the problems of the prior art as described above, and aims to realize a method for providing a specialized document sharing platform and its system that generates question-and-answer content for specialized documents using a predetermined deep-learning neural network and provides publicity content based on the generated question-and-answer content.

[0014] At this time, one embodiment of the present invention attempts to realize a method for providing a specialized document sharing platform and its system that generates question-and-answer content using a language model specialized for specialized documents.

[0015] Also, one embodiment of the present invention attempts to realize a method for providing a specialized document sharing platform and its system that provides publicity content based on a user interface (UI) that allows the freely editable generated question-and-answer content.

[0016] However, the technical problems that the present invention and the embodiments of the present invention seek to solve are not limited to the technical problems as described above, and there may be other technical problems.

Means for Solving the Problems

[0017] A method for providing a professional document sharing platform according to an embodiment of the present invention is a method in which a platform application executed by at least one processor of a terminal provides a professional document sharing platform, the method including: a step of acquiring a first professional document; a step of generating question-and-answer content for the first professional document based on a Question and Answer Language Model; a step of generating publicity content, which is an online publicity material, for the first professional document based on the question-and-answer content; a step of providing the publicity content based on a publicity material production workspace; a step of determining publicity start content, which is the publicity content registered on the professional document sharing platform based on the publicity material production workspace; and a step of providing the publicity start content based on the professional document sharing platform.

[0018] In another aspect, the step of generating the question-and-answer content includes: a step of inputting the first professional document into the question-and-answer language model; a step of acquiring at least one question-and-answer data including question data and answer data based on the first professional document from the question-and-answer language model; and a step of generating the question-and-answer content based on the at least one question-and-answer data.

[0019] On the other hand, the step of obtaining the Q&A data includes the step of obtaining the at least one question data based on a question deep - learning model included in the question - answering language model, and the step of obtaining the at least one answer data corresponding to each of the at least one question data based on an answer deep - learning model included in the question - answering language model.

[0020] On the other hand, the answer deep - learning model is a deep - learning model that outputs the answer data based on a multi - step inference process. The multi - step inference process includes an associative selection process for determining an evidence paragraph, which is a paragraph associated with the question data on the first specialized document, a rationale generation process for obtaining at least one piece of basis data corresponding to the question data based on the evidence paragraph, and a systematic composition process for performing data processing based on the basis data.

[0021] On the other hand, the publicity content is content data configured based on a predetermined data volume condition.

[0022] On the other hand, the step of determining the publicity start content includes the step of generating publicity - edited content, which is the publicity content edited by user input based on the publicity production workspace.

[0023] On the other hand, the step of generating the publicity-edited content includes at least one of the step of generating the publicity-edited content by user input for editing the composition of the Q&A content in the publicity content and the step of generating the publicity-edited content by user input for editing the content of the Q&A content in the publicity content.

[0024] On the other hand, the step of generating the publicity-edited content includes the step of providing an Editing Assistant Tools which is a user interface for providing at least one of the predetermined images, tables, and mathematical formula data related to the first specialized document in a form insertable onto the Q&A content in the publicity content.

[0025] On the other hand, the step of generating the publicity-edited content includes the step of providing a related document search function which is a function for automatically detecting and providing at least one other specialized document related to the Q&A content in the publicity content.

[0026] On the other hand, the step of determining the publicity start content further includes the step of determining, as the publicity start content, either one of the publicity content or the publicity-edited content by user input based on the publicity production workspace.

[0027] On the other hand, the method for providing a specialized document sharing platform according to an embodiment of the present invention further includes the step of providing a specialized document search function based on the publicity start content based on the specialized document sharing platform.

[0028] On the other hand, the method for providing a specialized document sharing platform according to an embodiment of the present invention further includes the step of providing a specialized document sharing and citation function based on the publicity start content based on the specialized document sharing platform.

[0029] On the other hand, the step of providing the professional document sharing and citation function includes at least one of the steps of providing a publicity material identification code including a connection URL (Uniform Resource Locator) corresponding to the publicity start content and a time stamp, and providing a question-and-answer identification code including a connection URL and a time stamp corresponding to the question-and-answer content in the publicity start content.

[0030] On the other hand, the method for providing a professional document sharing platform according to an embodiment of the present invention further includes the step of providing a reader question recommendation function, which is a function of acquiring and providing question data created on the user side provided with the first professional document based on the professional document sharing platform.

[0031] On the one hand, a professional document sharing platform providing system according to an embodiment of the present invention includes at least one memory storing a platform application, and at least one processor for reading out the platform application stored in the memory to provide a professional document sharing platform. The instruction words of the platform application include instructions for performing steps of acquiring a first professional document, generating question-and-answer content for the first professional document based on a question and answer language model, generating publicity content which is an online publicity material for the first professional document based on the question-and-answer content, providing the publicity content based on a publicity material production workspace, determining publicity start content which is the publicity content registered on the professional document sharing platform based on the publicity material production workspace, and providing the publicity start content based on the professional document sharing platform.

Advantages of the Invention

[0032] The method and system for providing a specialized document sharing platform according to an embodiment of the present invention generate question-and-answer content for a specialized document using a predetermined deep-learning neural network, and provide publicity content based on the generated question-and-answer content, so that users can automatically obtain question-and-answer-formatted data that efficiently encompasses the content of the specialized document without additional effort, and can utilize the publicity content based on the obtained data.

[0033] At this time, the method and system for providing a specialized document sharing platform according to an embodiment of the present invention generate question-and-answer content using a language model specialized for the specialized document, thereby providing question-and-answer content that eliminates the hallucination and ambiguous answering problems that are limitations of existing general-purpose language models (e.g., OpenAI GPT, etc.).

[0034] Through this, the method and system for providing a specialized document sharing platform according to an embodiment of the present invention can provide question-and-answer content that is faithful to the question, fact-based (hallucination-controlled), and presents clear evidence based on an advanced inference / estimation function realized in a process similar to human cognitive inference.

[0035] In addition, the method and system for providing a specialized document sharing platform according to an embodiment of the present invention provide publicity content based on a user interface (UI) that allows the generated question-and-answer content to be freely edited. Beyond simply sharing specialized documents, this can support users in creating customized publicity materials optimized in the form they desire with a high degree of freedom and actively engaging in publicity activities using these materials.

[0036] Furthermore, through this, the method for providing a professional document sharing platform and its system according to an embodiment of the present invention include in-depth and practical question-and-answer content obtained from a deep learning model specialized for professional documents, and have the effect of being able to easily generate and utilize high-quality publicity materials optimized for user needs.

Brief Description of the Drawings

[0037]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Embodiments for Carrying Out the Invention

[0038] The present invention can be subjected to various conversions and can have various embodiments. Specific embodiments are illustrated in the drawings and will be described in detail in the detailed description. The effects and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described in detail below together with the drawings. However, the present invention is not limited to the embodiments disclosed below and can be realized in various forms.

[0039] FIG. 1 is a conceptual diagram of a specialized document sharing platform providing system according to an embodiment of the present invention.

[0040] As shown in FIG. 1, a specialized document sharing platform providing system 1000 according to an embodiment of the present invention can realize a specialized document sharing platform providing service that generates question-and-answer content for specialized documents using a predetermined deep-learning neural network and provides publicity content based on the generated question-and-answer content.

[0041] In an embodiment, the specialized document sharing platform providing system 1000 that realizes the specialized document sharing platform providing service can include a terminal 100, a platform providing server 200, and a network 300 (Network).

[0042] At this time, the terminal 100 and / or the platform providing server 200 can be connected via the network 300.

[0043] Here, the network 300 according to the embodiment means a connection structure in which information can be exchanged between each node such as the terminal 100 and / or the platform providing server 200.

[0044] In an example of the network 300, a 3GPP (3rd Generation Partnership Project) (registered trademark) network, an LTE (Long Term Evolution) network, a WIMAX (World Interoperability for Microwave Access) network, the Internet, a LAN (Local Area Network), a Wireless LAN (Wireless Local Area Network), a WAN (Wide Area Network), a PAN (Personal Area Network), a Bluetooth (registered trademark) network, a satellite broadcast network, an analog broadcast network, and / or a DMB (Digital Multimedia Broadcasting) network are included, but not limited thereto.

[0045] Hereinafter, the terminal 100 and the platform providing server 200 that realize the specialized document sharing platform providing system 1000 will be described in detail with reference to the attached drawings.

[0046] · Terminal 100

[0047] The terminal 100 according to the embodiment of the present invention may be a predetermined computing device provided with a platform application (hereinafter, referred to as an application) that provides a specialized document sharing platform providing service.

[0048] Specifically, from a hardware perspective, the terminal 100 can include a mobile - type computing device 100 - 1 with an application installed and / or a desktop - type computing device 100 - 2, etc.

[0049] Here, the mobile - type computing device 100 - 1 may be a mobile device with an application installed.

[0050] For example, the mobile - type computing device 100 - 1 can include a smart phone, a mobile phone, a digital - broadcast device, a PDA (personal digital assistants), a PMP (portable multimedia player), and / or a tablet PC (tablet PC), etc.

[0051] Also, the desktop - type computing device 100 - 2 may be a wired / wireless communication infrastructure device with an application installed.

[0052] For example, the desktop - type computing device 100 - 2 can include a personal computer such as a fixed - type desktop PC, a laptop computer, and / or an ultrabook.

[0053] Depending on the embodiment, the terminal 100 can further include a predetermined server computing device that provides a specialized document - sharing platform - providing service environment.

[0054] FIG. 2 is an internal block diagram of the terminal 100 according to an embodiment of the present invention.

[0055] As shown in FIG. 2, from a functional perspective, the terminal 100 can include a memory 110, a processor assembly 120, a communication processor 130, an interface unit 140, an input system 150, a sensor system 160, and a display system 170. In an embodiment, the terminal 100 can include the above components within a housing.

[0056] Specifically, the memory 110 can store an application 111.

[0057] At this time, the application 111 can store any one or more of various application programs, data, and instruction words for providing a service environment for a professional document sharing platform.

[0058] That is, the memory 110 can store instructions, data, etc. that can be used to generate a service environment for providing a professional document sharing platform.

[0059] Also, the memory 110 can include a program area and a data area.

[0060] Here, the program area according to the embodiment can be associated between the operating system (OS) for booting the terminal 100 and functional elements.

[0061] Also, the data area according to the embodiment can store data generated by the use of the terminal 100.

[0062] Also, the memory 110 can include at least one or more non - transient computer - readable storage media and a transient computer - readable storage media.

[0063] For example, the memory 110 may be various storage devices such as ROM, EPROM, flash drive, hard drive, etc., and may include web storage that performs the storage function of the memory 110 on the internet.

[0064] The processor assembly 120 can include at least one or more processors capable of executing the instructions of the application 111 stored in the memory 110 to perform various operations for generating a specialized document sharing platform providing service environment.

[0065] In an embodiment, the processor assembly 120 can control the overall operation of the components via the application 111 of the memory 110 to provide a specialized document sharing platform providing service.

[0066] Specifically, the processor assembly 120 may be a system-on-chip SOC suitable for the terminal 100 including a central processing unit CPU and / or a graphics processing unit GPU, etc.

[0067] Also, the processor assembly 120 can execute the operation system OS and / or application programs stored in the memory 110.

[0068] Also, the processor assembly 120 can control each component installed in the terminal 100.

[0069] Also, the processor assembly 120 can communicate internally with each component via a system bus, and can include one or more predetermined bus structures including a local bus.

[0070] In addition, the processor assembly 120 can be implemented with at least one of ASICs (application specific integrated circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (field programmable gate arrays), controllers, micro-controllers, microprocessors, and / or other electrical units for performing functions.

[0071] The communication processor 130 can include one or more devices for communicating with external devices. Such a communication processor 130 can communicate via a wireless network.

[0072] Specifically, the communication processor 130 can communicate with the terminal 100 storing the content source for realizing the specialized document sharing platform providing service environment.

[0073] In addition, the communication processor 130 can communicate with various user input components such as a controller for receiving user input.

[0074] In an embodiment, the communication processor 130 can transmit and receive various data related to the specialized document sharing platform providing service to the other terminal 100 and / or an external server, etc.

[0075] Such a communication processor 130 can wirelessly transmit and receive data with at least one of a base station, an external terminal 100, and any server over a mobile communication network constructed via a communication device capable of performing technical standards or communication methods for mobile communication (e.g., LTE (Long Term Evolution), LTE-A (Long Term Evolution-Advanced), 5G NR (New Radio), WIFI), or a short-range communication method, etc.

[0076] The sensor system 160 can include various sensors such as an image sensor 161, a position sensor (IMU) 163, an audio sensor 165, a distance sensor, a proximity sensor, a contact sensor, etc.

[0077] Here, the image sensor 161 can capture an image (such as an image and / or video, etc.) of the physical space around the terminal 100.

[0078] Specifically, the image sensor 161 can capture a predetermined physical space via a camera arranged facing the outside of the terminal 100.

[0079] In an embodiment, the image sensor 161 is arranged on the front surface and / or the rear surface of the terminal 100 and can capture the physical space on the arranged direction side.

[0080] In an embodiment, the image sensor 161 can capture and obtain various images (such as specialized document images, etc.) related to the specialized document sharing platform providing service.

[0081] Such an image sensor 161 can include an image sensor device and an image processing module.

[0082] Specifically, the image sensor 161 can process a still image or a moving image obtained by an image sensor device (e.g., CMOS or CCD).

[0083] In addition, the image sensor 161 can process a still image or a moving image acquired via the image sensor device using an image processing module to extract necessary information and transmit the extracted information to the processor.

[0084] Such an image sensor 161 may be a camera assembly including at least one or more cameras.

[0085] Here, the camera assembly can include a general camera that captures in the visible light band, and can further include special cameras such as an infrared camera and a stereo camera.

[0086] Also, the image sensor 161 as described above can be included in the terminal 100 and operate according to an embodiment, or can be included in an external device (for example, an external server, etc.) and operate via interlocking based on the communication processor 130 and / or the interface unit 140 described above.

[0087] The position sensor (IMU) 163 can sense at least one or more of the movement and acceleration of the terminal 100. For example, it can be composed of a combination of various position sensors such as an accelerometer, a gyroscope, and / or a magnetometer.

[0088] Also, the position sensor (IMU) 163 interlocks with a position communication processor 130 such as the GPS of the communication processor 130 and can recognize spatial information regarding the physical space around the terminal 100.

[0089] The audio sensor 165 can recognize sounds around the terminal 100.

[0090] Specifically, the audio sensor 165 can include a microphone that can sense the voice input of the user using the terminal 100.

[0091] In an embodiment, the audio sensor 165 can receive voice data necessary for a specialized document sharing platform providing service from the user.

[0092] The interface unit 140 can connect the terminal 100 communicably to one or more other devices.

[0093] Specifically, the interface unit 140 can include wired and / or wireless communication devices that are compatible with one or more different communication protocols.

[0094] Through such an interface unit 140, the terminal 100 can be connected to various input / output devices.

[0095] For example, the interface unit 140 can be connected to an audio output device such as a headset port or a speaker to output audio.

[0096] Exemplarily, although it has been described that an audio output device is connected via the interface unit 140, embodiments provided inside the terminal 100 can also be included.

[0097] Also, for example, the interface unit 140 can be connected to an input device such as a keyboard and / or a mouse to obtain user input.

[0098] Such an interface unit 140 can be configured to include at least one of a wired / wireless headset port, an external charger port, a wired / wireless data port, a memory card port, a port for connecting a device equipped with an identification module, an audio I / O (Input / Output) port, a video I / O (Input / Output) port, an earphone port, a power amplifier, an RF circuit, a transceiver, and other communication circuits.

[0099] The input system 150 can sense user inputs (e.g., gestures, voice commands, button activations, or other types of inputs) related to the professional document sharing platform providing service.

[0100] Specifically, the input system 150 can include a predetermined button, a touch sensor, an image sensor 161 for sensing user motion inputs, and / or an audio sensor 165 for sensing user voice inputs, etc.

[0101] Also, the input system 150 can be connected to an external controller via the interface unit 140 to receive user inputs.

[0102] The display system 170 can output various information related to the professional document sharing platform providing service in graphic images.

[0103] In an embodiment, the display system 170 can display various user interfaces for the professional document sharing platform providing service, professional document data, question-and-answer content, and / or promotional content, etc.

[0104] Such a display can include, but is not limited to, at least one of a liquid crystal display (LCD), a thin film transistor-liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), a flexible display, a 3D display, and / or an e-ink display.

[0105] Also, according to an embodiment, the display system 170 can include a display 171 that outputs an image and a touch sensor 173 that senses a touch input of a user.

[0106] Exemplarily, the display 171 can be realized as a touch screen by forming a mutual layer structure with the touch sensor 173 or being integrally formed.

[0107] Such a touch screen functions as a user input unit that provides an input interface between the terminal 100 and the user, and can also provide an output interface between the terminal 100 and the user.

[0108] On the other hand, the terminal 100 according to an embodiment of the present invention can perform deep learning related to a specialized document sharing platform providing service based on a predetermined deep - learning neural network.

[0109] Here, the deep learning neural network according to the embodiment can include, but is not limited to, OpenAI GPT, Instruct GPT, Bi-LSTM (Bidirectional LSTM), LSTM (Long Short-Term Memory models), MLP (Multi-Layer Perceptron), EfficientNet, ResNet, ARIMA (Autoregressive Integrated Moving Average), VAR (Vector Auto Regression), RNN (Recurrent Neural Networks), GRU (Gated Recurrent Unit), GAN (Generative Adversarial Networks), DualStyleGAN, StyleGAN, Graph Convolution Network (GCN), CNN (Convolution Neural Network, CNN), DPSNet (Deep Plane Sweep Network, DPSNet), AGN (Attention Guided Network, AGN), R-CNN (Regions with CNN features), Fast R-CNN, Faster R-CNN, Mask R-CNN, and / or U-Net network, etc.

[0110] Specifically, in the embodiment, the terminal 100 can cooperate with at least one or more deep learning neural networks capable of realizing the Question and Answer Language Model according to the embodiment of the present invention, and perform the deep learning required for the specialized document sharing platform providing service.

[0111] At this time, in the embodiment, the Question and Answer Language Model can perform deep learning with predetermined specialized document (for example, papers and / or reports, etc.) data as input and output at least one set of question data and response data having an organic flow based on the input specialized document data.

[0112] However, in the embodiments of the present invention, the deep learning algorithm itself for realizing the question-and-answer language model is not limited or restricted, and the question-and-answer language model according to the embodiments of the present invention can be realized based on at least one known deep learning algorithm.

[0113] On the other hand, according to an embodiment, the terminal 100 can further perform at least a part of the functional operations performed by the platform providing server 200 described later.

[0114] · Platform Provision Server 200

[0115] On the other hand, the platform providing server 200 according to the embodiments of the present invention can perform a series of processes for providing a specialized document sharing platform providing service.

[0116] Specifically, in the embodiment, the platform providing server 200 can provide a specialized document sharing platform providing service by exchanging data necessary for driving a specialized document sharing platform providing process with an external device such as the terminal 100.

[0117] More specifically, in the embodiment, the platform providing server 200 can provide an environment in which the application 111 can operate on an external device (in the embodiment, a mobile type computing device 100-1 and / or a desktop type computing device 100-2, etc.).

[0118] For this purpose, the platform providing server 200 can include an application program, data, and / or instruction words for the application 111 to operate, and can transmit and receive various data based on this to and from the external device.

[0119] Also, in the embodiment, the platform providing server 200 can obtain a predetermined specialized document.

[0120] Also, in the embodiment, the platform providing server 200 can generate Q&A content based on the obtained specialized document.

[0121] Here, the Q&A content according to the embodiment can mean content obtained by visualizing at least one question data and response data set obtained via the Q&A language model according to the embodiment of the present invention in a predetermined manner.

[0122] Also, in the embodiment, the platform providing server 200 can generate publicity content based on the generated Q&A content.

[0123] Here, the publicity content according to the embodiment can mean an online publicity material for the purpose of promoting a predetermined specialized document.

[0124] Also, in the embodiment, the platform providing server 200 can provide a publicity material production workspace based on the generated publicity content.

[0125] Here, the publicity material production workspace according to the embodiment can mean a user interface for determining publicity start content.

[0126] At this time, the publicity start content according to the embodiment can mean the publicity content finally registered and shared on the specialized document sharing platform.

[0127] Also, in the embodiment, the platform providing server 200 can determine the publicity start content based on the provided publicity material production workspace.

[0128] Also, in the embodiment, the platform providing server 200 can provide the determined publicity start content.

[0129] Also, in the embodiment, the platform providing server 200 can provide a specialized document search function based on the specialized document sharing platform.

[0130] That is, the platform providing server 200 can provide a specialized document search function that can search for at least one specialized document registered in the specialized document sharing platform.

[0131] Also, in the embodiment, the platform providing server 200 can provide a specialized document sharing and citation function based on the specialized document sharing platform.

[0132] Specifically, the platform providing server 200 can provide a specialized document sharing and citation function that can share and cite publicity start content, question data, and / or response data corresponding to a predetermined specialized document.

[0133] Also, in the embodiment, the platform providing server 200 can provide a reader question recommendation function based on the specialized document sharing platform.

[0134] That is, the platform providing server 200 can provide a reader question recommendation function that can generate and provide proposed question data, which is question data created by the side (in the embodiment, the reader side) to which a predetermined specialized document is provided.

[0135] Also, in the embodiment, the platform providing server 200 can perform deep learning required for the specialized document sharing platform service based on a predetermined deep - learning neural network.

[0136] Specifically, in the embodiment, the platform providing server 200 can perform deep learning required for the specialized document sharing platform providing service in conjunction with at least one or more deep learning neural networks capable of realizing a Question and Answer Language Model according to the embodiment of the present invention.

[0137] More specifically, in the embodiment, the platform providing server 200 can read out a predetermined deep learning neural network driving program constructed for performing the deep learning from the memory module 230.

[0138] Then, the platform providing server 200 can perform deep learning required for the specialized document sharing platform providing service according to the read predetermined deep learning neural network system.

[0139] Here, the deep learning neural network according to the embodiment can include, but is not limited to, OpenAI GPT, Instruct GPT, Bi-LSTM (Bidirectional LSTM), LSTM (Long Short-Term Memory models), MLP (Multi-Layer Perceptron), EfficientNet, ResNet, ARIMA (Autoregressive Integrated Moving Average), VAR (Vector Auto Regression), RNN (Recurrent Neural Networks), GRU (Gated Recurrent Unit), GAN (Generative Adversarial Networks), DualStyleGAN, StyleGAN, Graph Convolution Network (GCN), CNN (Convolution Neural Network, CNN), DPSNet (Deep Plane Sweep Network, DPSNet), AGN (Attention Guided Network, AGN), R-CNN (Regions with CNN features), Fast R-CNN, Faster R-CNN, Mask R-CNN, and / or U-Net network, etc.

[0140] At this time, according to the embodiment, the deep learning neural network can be directly included in the platform providing server 200 or realized as a device and / or server separate from the platform providing server 200.

[0141] In the following description, it is described that the deep learning neural network is included in the platform providing server 200 for realization, but it is not limited thereto.

[0142] In addition, in the embodiment, the platform providing server 200 can store and manage various application programs, instruction words, and / or data for realizing the specialized document sharing platform providing service.

[0143] As an embodiment, the platform providing server 200 can store and manage at least one or more specialized document data, question-and-answer content, publicity content, data processing algorithms, deep learning algorithms, and / or user interfaces.

[0144] However, the functional operations that the platform providing server 200 can perform in the embodiments of the present invention are not limited to those described above, and it can further perform other functional operations.

[0145] On the other hand, as further shown in FIG. 1, in the embodiment, the platform providing server 200 can be realized as a predetermined computing device including at least one or more processor modules 210 (Processor Module) for data processing, at least one or more communication modules 220 (Communication Module) for data exchange with external devices, and at least one or more memory modules 230 (Memory Module) for storing various application programs, data, and / or instruction words for providing the specialized document sharing platform providing service.

[0146] Here, the memory module 230 can store any one or more of the operating system (OS) for providing the specialized document sharing platform providing service, various application programs, data, and instruction words.

[0147] In addition, the memory module 230 can include a program area and a data area.

[0148] At this time, the program area according to the embodiment can be associated between the operating system (OS) for booting the server and the functional elements.

[0149] In addition, the data area according to the embodiment can store data generated by using the server.

[0150] Also, the memory module 230 may be various storage devices such as ROM, RAM, EPROM, flash drive, hard drive, etc., or may be a web storage that realizes the storage function of the memory module 230 on the Internet.

[0151] Also, the memory module 230 may be a recording medium in a detachable form on the server.

[0152] On the other hand, the processor module 210 can control the overall operations of the aforementioned units in order to realize a specialized document sharing platform providing service.

[0153] Specifically, the processor module 210 may be a system-on-chip (SOC) suitable for a server including a central processing unit (CPU) and / or a graphics processing unit (GPU), etc.

[0154] Also, the processor module 210 can execute the operating system and / or application programs stored in the memory module 230.

[0155] Also, the processor module 210 can control each component mounted on the server.

[0156] Also, the processor module 210 can communicate internally with each component through a system bus, and can include one or more predetermined bus structures including a local bus.

[0157] In addition, the processor module 210 can be implemented using at least one of ASICs (application specific integrated circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (field programmable gate arrays), controllers, micro-controllers, microprocessors, and / or other electrical units for performing functions.

[0158] In the above description, it has been described that the platform providing server 200 according to the embodiment of the present invention performs the functional operations as described above. However, at least a part of the functional operations performed by the platform providing server 200 can be performed by an external device (for example, the terminal 100, etc.), and at least a part of the functional operations performed by the external device can also be further performed by the platform providing server 200. Various embodiments are possible, such as this.

[0159] · Question and Answer Language Model QALM

[0160] FIG. 3 is a conceptual diagram for explaining the Question and Answer Language Model QALM according to an embodiment of the present invention.

[0161] As shown in FIG. 3, the Question and Answer Language Model QALM according to the embodiment of the present invention may be a deep learning model that generates and provides at least one set of question data and response data QA (hereinafter, question-and-answer data) having an organic flow based on a predetermined specialized document SD (for example, a paper and / or a report, etc.).

[0162] That is, the question-and-answer language model QALM according to the embodiment may be a deep learning model that takes predetermined specialized document SD data as input and outputs at least one question-and-answer data QA having an organic flow based on the input specialized document SD data.

[0163] At this time, the question data and answer data according to the embodiment can have a shape connected by a series of organic flows based on the information included in the specialized document SD.

[0164] That is, in the embodiment, the question data and answer data may be question-and-answer data QA in a more cognitive form that deviates from the typical form of question-and-answer data QA in an extraction method that follows the formalized structure of the specialized document SD (for example, introduction, research questions, research methodology, research results, and / or research conclusions, etc. according to the table of contents of a general paper).

[0165] Specifically, as further shown in FIG. 3, in the embodiment, the question-and-answer language model QALM can include a question deep-learning model QDM (Question Deep-learning Model) and an answer deep-learning model ADM (Answer Deep-learning Model).

[0166] Specifically, the question deep-learning model QDM according to the embodiment may be a deep learning model that takes predetermined specialized document SD data as input and outputs at least one question data Q1, Q2, Q3,..., Qn based on the input specialized document SD data.

[0167] In the embodiment, the question deep-learning model QDM can generate 1) question data based on the information included in the specialized document SD, 2) question data based on pre-generated question data, 3) question data based on pre-generated answer data, and / or 4) question data based on other information related to the information included in the specialized document SD, etc.

[0168] At this time, in the embodiment, the question deep learning model QDM can generate at least one or more pieces of question data as described above so as to be connected by an organic flow.

[0169] For example, the question deep learning model QDM can generate first question data based on a predetermined specialized document, obtain first response data which is response data for the generated first question data, and generate second question data based on the obtained first response data and / or the first question data.

[0170] Therefore, the question deep learning model QDM can provide deeper and higher-quality question data compared to the question data generated only based on the individuals and / or the relationships between individuals disclosed in the specialized document SD.

[0171] On the other hand, the response deep learning model ADM according to the embodiment may be a deep learning model that takes predetermined specialized document SD data and question data as inputs and outputs at least one response data A1, A2, A3,..., An based on the input specialized document SD data and question data.

[0172] FIG. 4 and FIG. 5 are examples of diagrams for explaining the multi-step inference process of the response deep learning model ADM according to an embodiment of the present invention.

[0173] Specifically, as shown in FIGS. 4 and 5, in the embodiment, the response deep learning model ADM can generate response data according to a multi-step inference process (Multi-step Inference Process).

[0174] Here, the multi-step inference process according to the embodiment can mean a structured process that uses deep learning to generate response data based on predetermined specialized document SD data and question data.

[0175] Such a multi-step inference process can include an Associative Selection Process, a Rationale Generation Process, and a Systematic Composition Process.

[0176] More specifically, in an embodiment, the response deep learning model ADM can: 1) determine paragraphs (hereinafter referred to as evidence paragraphs) in the specialized document SD associated with the query data. (Associative Selection Process)

[0177] Specifically, the response deep learning model ADM can extract at least one evidence paragraph that is a paragraph containing an answer and / or rationale for the query data among the K (K>=1) paragraphs included in the specialized document SD.

[0178] Through this, the response deep learning model ADM can generate response data based on more extensive evidence data compared to the conventional method of extracting short answer responses for a given query data.

[0179] Also, in an embodiment, the response deep learning model ADM can: 2) obtain evidence data for the query data based on the determined evidence paragraphs. (Rationale Generation Process)

[0180] Here, the evidence data according to the embodiment can be meant to be data that serves as a basis for generating response data for the query data.

[0181] That is, in an embodiment, the evidence data may be a set of various data utilized when generating response data.

[0182] Specifically, in an embodiment, the response deep learning model ADM can detect main response data which is data including a direct response to the question data based on at least one evidence paragraph, explanatory text data which is data for elaborating on the direct response, and / or auxiliary information data which is data including relevant background knowledge, etc.

[0183] Then, the response deep learning model ADM can obtain the evidence data as described above based on the detected data.

[0184] Also, in an embodiment, the response deep learning model ADM can generate response data based on the obtained evidence data. (Systematic Composition Process)

[0185] Specifically, in an embodiment, the response deep learning model ADM can perform data processing based on the obtained evidence data to generate response data.

[0186] In an embodiment, the response deep learning model ADM can perform predetermined data processing (such as removing duplicate text, etc.) to enhance the conciseness and readability of the response based on the evidence data, and generate response data.

[0187] As described above, in an embodiment, the response deep learning model ADM can extract an evidence paragraph that can answer the question data from the specialized document SD, generate evidential basis based on the content of the extracted evidence paragraph, and provide response data that provides a deeper response based on the generated evidential basis.

[0188] That is, in an embodiment, the response deep learning model ADM can be realized as a language model specialized for the specialized document SD that resolves the hallucination and ambiguous response problems which are limitations of existing general-purpose language models (such as OpenAI GPT, etc.) in performing the question-and-answer task for the specialized document SD.

[0189] Through this, the professional document SD sharing platform providing system 1000 according to the embodiment of the present invention can provide response data that is faithful to the question, hallucination-controlled, and evidential based on an advanced inference / estimation function realized in a process similar to human cognitive inference.

[0190] Furthermore, going back, the question-and-answer language model QALM including the above-mentioned question deep learning model QDM and response deep learning model ADM matches each of at least one question data Q1, Q2, Q3,..., Qn obtained through the question deep learning model QDM with each of at least one response data A1, A2, A3,..., An obtained through the response deep learning model ADM based on each question data, and can generate at least one question-and-answer data QA ((Q1, A1), (Q2, A2),..., (Qn, An)).

[0191] At this time, in the embodiment, the question-and-answer language model QALM can generate at least one question-and-answer data QA arranged in the order according to the organic flow.

[0192] And, in the embodiment, the question-and-answer language model QALM can provide the generated at least one question-and-answer data QA externally.

[0193] · Method for providing a professional document sharing platform

[0194] Hereinafter, an application 111 executed by at least one or more processors of the terminal 100 according to an embodiment of the present invention uses a predetermined deep - learning neural network to generate question - and - answer content for the specialized document SD, and a method of providing publicity content based on the generated question - and - answer content (that is, a method of realizing a specialized document SD sharing platform providing service) will be described in detail with reference to the attached drawings.

[0195] At this time, hereinafter, for the sake of effective explanation, the method of providing a specialized document SD sharing platform will be separately described as a method of providing a specialized document SD sharing platform on the author side and a method of providing a specialized document SD sharing platform on the reader side. However, various embodiments are possible, such as at least some of the embodiments included in the providing methods and the like classified as above can also operate by being organically combined with each other.

[0196] Going back further, in an embodiment of the present invention, at least one or more processors of the terminal 100 can execute at least one or more applications 111 stored in at least one or more memories 110 or operate in the background state.

[0197] In the following embodiments, the operation of at least one or more processors of the terminal 100 to execute the instruction words of the application 111 to perform the method of providing a specialized document SD sharing platform will be abbreviated and described as being performed by the application 111.

[0198] [Method of providing a specialized document sharing platform on the author side]

[0199] FIG. 6 is a flowchart for explaining a method of providing a specialized document SD sharing platform on the author side according to an embodiment of the present invention.

[0200] As shown in FIG. 6, in an embodiment, an application 111 that is executed by at least one or more processors of the terminal 100 or operates in a background state can acquire a predetermined specialized document SD. (S101)

[0201] Specifically, in an embodiment, the application 111 can acquire a predetermined specialized document SD (for example, a paper and / or a report, etc.) based on the specialized document SD sharing platform according to the embodiment of the present invention.

[0202] As an embodiment, the application 111 can acquire the specialized document SD uploaded onto the specialized document SD sharing platform via user input.

[0203] Also, in an embodiment, the application 111 can generate question-and-answer content based on the acquired specialized document SD. (S103)

[0204] FIG. 7 is an example of question-and-answer content according to an embodiment of the present invention.

[0205] Here, the question-and-answer content QAC according to the embodiment can mean content in which at least one question-and-answer data QA acquired via the question-and-answer language model QALM according to the embodiment of the present invention is visualized according to a predetermined method.

[0206] Specifically, in an embodiment, the application 111 can generate the question-and-answer content QAC in conjunction with the question-and-answer language model QALM.

[0207] More specifically, in an embodiment, the application 111 can input the specialized document SD data acquired as described above into the question-and-answer language model QALM.

[0208] In this way, in the embodiment, the Question Answering Language Model QALM can obtain at least one piece of question data Q1, Q2, Q3, ..., Qn based on the input specialized document SD data based on the Question Deep Learning Model QDM.

[0209] Also, in the embodiment, the Question Answering Language Model QALM can obtain at least one piece of response data A1, A2, A3, ..., An based on the input specialized document SD data and the question data based on the Response Deep Learning Model ADM.

[0210] Then, in the embodiment, the Question Answering Language Model QALM can mutually match each of the at least one piece of question data Q1, Q2, Q3, ..., Qn obtained with each of the at least one piece of response data A1, A2, A3, ..., An corresponding to each piece of question data to generate at least one piece of Q&A data QA ((Q1, A1), (Q2, A2), ..., (Qn, An)).

[0211] Also, in the embodiment, the Question Answering Language Model QALM can provide the generated at least one piece of Q&A data QA to the application 111.

[0212] Thus, in the embodiment, the application 111 can obtain at least one piece of Q&A data QA for the specialized document SD from the Question Answering Language Model QALM.

[0213] Also, in the embodiment, the application 111 can generate question answering content QAC based on the obtained at least one piece of Q&A data QA.

[0214] In the embodiment, the application 111 can visualize at least one piece of Q&A data QA in a predetermined graphic image to generate question answering content QAC.

[0215] At this time, according to the embodiment, the application 111 can generate question-and-answer content QAC including a predetermined evidence paragraph identification code.

[0216] Here, the evidence paragraph identification code according to the embodiment can mean an identification code corresponding to a predetermined evidence paragraph among the identification codes (for example, a series of numbers in a preset format, etc.) assigned to each paragraph on the specialized document SD.

[0217] Specifically, in the embodiment, the application 111 can detect at least one evidence paragraph corresponding to each response data in the question-and-answer content QAC.

[0218] Also, the application 111 can extract the identification code corresponding to the detected evidence paragraph (that is, the evidence paragraph identification code).

[0219] Then, the application 111 can generate question-and-answer content QAC that matches and displays at least one extracted evidence paragraph identification code with the corresponding response data.

[0220] Through this, the application 111 can clearly present the paragraph and its position in the specialized document SD that discloses the content on which each response data is based, and can make this easily confirmable.

[0221] Also, according to the embodiment, the application 111 can generate question-and-answer content QAC including predetermined down-feature data.

[0222] Here, the down-feature data according to the embodiment can mean data obtained by reducing the information amount of predetermined core data (for example, images, tables, and / or mathematical formulas, etc.) in the specialized document SD.

[0223] That is, in the embodiment, the down-feature data may be data obtained by transforming and reducing the characteristic feature values included in the predetermined core data in the specialized document SD according to a preset method.

[0224] Specifically, in the embodiment, when the application 111 generates the question-and-answer content QAC based on the question-and-answer data QA obtained from the question-and-answer language model QALM, it can determine whether the core data in the predetermined response data can be included.

[0225] At this time, if the application 111 determines that the core data exists in the predetermined response data, it can generate the down-feature data corresponding to the core data.

[0226] As an embodiment, the application 111 can generate the down-feature data by performing data processing including data type conversion, data value removal, and / or data volume compression based on the core data.

[0227] Exemplarily, when the core data is a table, the application 111 can generate the down-feature data obtained by transforming the table into a simple bar graph.

[0228] Also, in the embodiment, the application 111 can replace the generated down-feature data with the core data corresponding to the down-feature data.

[0229] That is, the application 111 can replace the core data in the question-and-answer data QA obtained from the question-and-answer language model QALM with the down-feature data.

[0230] Then, in the embodiment, the application 111 can generate the question-and-answer content QAC based on the question-and-answer data QA in which the core data is replaced with the down-feature data.

[0231] In this way, the application 111 can assist in reducing the amount of information and exposing the data determined to be the core data of the specialized document SD.

[0232] Through this, the application 111 can prevent the situation where the core content in the specialized document SD is overly disclosed by the publicity content provided in the future, and can also prevent in advance the problem that the subscription and / or citation of the specialized document SD itself may be reduced due to the publicity content.

[0233] At this time, according to the embodiment, the application 111 can transform the core data into down-feature data based on user input.

[0234] In the embodiment, the application 111 can obtain user input for setting the degree of transformation, transformation method, and / or transformation content for the core data.

[0235] Then, the application 111 can generate down-feature data according to the obtained user input.

[0236] That is, the application 111 can generate question-and-answer content QAC based on the down-feature data edited in a form optimized for the user's needs.

[0237] Also, in the embodiment, the application 111 can generate publicity content based on the generated question-and-answer content QAC. (S105)

[0238] FIG. 8 is an example of publicity content according to an embodiment of the present invention.

[0239] Here, the publicity content PMC according to the embodiment can mean an online publicity material for the purpose of promoting a predetermined specialized document SD.

[0240] At this time, in the embodiment, the publicity content PMC may be content data composed of a preset data amount (as an embodiment, one page, etc.).

[0241] In the embodiment, such publicity content PMC can include summary data SMD for a predetermined specialized document SD and / or question-and-answer content QAC, etc.

[0242] Specifically, in the embodiment, the application 111 can obtain summary data SMD for the specialized document SD in conjunction with a predetermined deep learning neural network.

[0243] Here, the specific method for the application 111 according to the embodiment of the present invention to obtain the summary data SMD can be realized based on various disclosed algorithms and / or processes. In the embodiment of the present invention, such algorithms and / or processes themselves are not limited or restricted.

[0244] Also, in the embodiment, the application 111 can generate publicity content PMC including the obtained summary data SMD and / or the above-mentioned question-and-answer content QAC.

[0245] Also, in the embodiment, the application 111 can provide a publicity material production workspace based on the generated publicity content PMC. (S107)

[0246] Here, the publicity material production workspace according to the embodiment can mean a user interface for determining publicity start content.

[0247] At this time, the publicity start content according to the embodiment can mean the publicity content PMC finally registered and shared on the specialized document SD sharing platform.

[0248] Specifically, in the embodiment, the application 111 can provide a publicity material production workspace that displays the publicity content PMC generated as described above and can determine the publicity start content by selecting and / or editing the displayed publicity content PMC through user input.

[0249] At this time, according to the embodiment, the application 111 can also provide a publicity material production workspace that can determine the publicity start content based on the inputs of multiple users.

[0250] Therefore, when there are multiple authors of the specialized document SD, the application 111 can support a collaborative process in which the corresponding multiple authors can edit and / or select one publicity content PMC together.

[0251] Also, in the embodiment, the application 111 can determine the publicity start content based on the provided publicity material production workspace. (S109)

[0252] Here, in other words, the publicity start content according to the embodiment can mean the publicity content PMC that is finally registered and shared on the specialized document SD sharing platform through user input based on the publicity material production workspace.

[0253] Specifically, in the embodiment, if the application 111 obtains user input for selecting (i.e., approving) the publicity content PMC based on the provided publicity material production workspace, it can determine the publicity content PMC as the publicity start content.

[0254] On the other hand, in the embodiment, if the application 111 obtains user input for editing the publicity content PMC based on the provided publicity material production workspace, it can generate publicity edited content, which is the publicity content PMC edited by the obtained user input.

[0255] Specifically, in an embodiment, the application 111 can obtain user input for editing the configuration of the question-and-answer content QAC within the publicity content PMC.

[0256] As an embodiment, the application 111 can obtain user input for selecting at least one question-and-answer data QA (i.e., a set of question data and response data) within the question-and-answer content QAC, user input for deleting it, and / or user input for specifying an order, etc.

[0257] Also, as an embodiment, the application 111 can obtain user input for adding at least one question-and-answer data QA onto the question-and-answer content QAC.

[0258] FIG. 9 and FIG. 10 are examples of diagrams for explaining a method of adding question-and-answer data QA based on user input according to an embodiment of the present invention.

[0259] Specifically, as shown in FIG. 9, in an embodiment, the application 111 can generate at least one creative question-and-answer data CD based on user input.

[0260] Here, the creative question-and-answer data CD according to the embodiment can mean a data set composed of question data directly created by the user and response data for the question data.

[0261] More specifically, in an embodiment, the application 111 can obtain question data CQD (hereinafter, creative question data) directly created by the user through user input.

[0262] Also, in an embodiment, the application 111 can obtain response data (hereinafter, additional response data) for the creative question data CQD in conjunction with the question-and-answer language model QALM.

[0263] Specifically, in an embodiment, the application 111 can input the creation query data CQD into the question-and-answer language model QALM.

[0264] Then, in the embodiment, the question-and-answer language model QALM can obtain response data based on the specialized document SD data and the creation query data CQD input as described above based on the response deep learning model ADM.

[0265] And the question-and-answer language model QALM can provide the obtained response data (i.e., additional response data) to the application 111.

[0266] Thus, in the embodiment, the application 111 can obtain additional response data from the question-and-answer language model QALM.

[0267] And in the embodiment, the application 111 can generate creation Q&A data CD including the obtained additional response data and the creation query data CQD corresponding to the additional response data.

[0268] Also, in the embodiment, the application 111 can obtain user input to add the generated creation Q&A data CD to the question-and-answer content QAC.

[0269] According to the embodiment, the application 111 can obtain response data directly created by the user (hereinafter, creation response data) through user input.

[0270] And the application 111 can generate creation Q&A data CD including the obtained creation response data and the creation query data CQD corresponding to the creation response data.

[0271] Also, in the embodiment, the application 111 can obtain user input to add the generated creation Q&A data CD to the question-and-answer content QAC.

[0272] As described above, the application 111 can provide question-and-answer content QAC that is generated with a high degree of freedom and incorporates cognitive elements by utilizing questions directly created by the user and the responses thereto.

[0273] On the other hand, as shown in FIG. 10, in the embodiment, the application 111 can generate at least one recommended Q&A data SD based on user input.

[0274] Here, the recommended Q&A data SD according to the embodiment can mean a data set composed of question data additionally provided based on the question-and-answer language model QALM and response data for the question data.

[0275] More specifically, in the embodiment, the application 111 can obtain question data SQD (hereinafter, recommended question data) additionally provided in conjunction with the question-and-answer language model QALM.

[0276] As an embodiment, the application 111 can obtain, for example, 1) recommended question data SQD based on the information included in the specialized document SD, 2) recommended question data SQD based on pre-generated question data, 3) recommended question data SQD based on pre-generated response data, and / or 4) recommended question data SQD based on other information related to the information included in the specialized document SD.

[0277] Also, in the embodiment, the application 111 can obtain response data (hereinafter, recommended response data) for the recommended question data SQD in conjunction with the question-and-answer language model QALM.

[0278] Specifically, in the embodiment, the application 111 can input the recommended question data SQD into the question-and-answer language model QALM.

[0279] In this way, in the embodiment, the Question Answering Language Model (QALM) can obtain response data based on the specialized document SD data and the recommended question data SQD input as described above based on the response deep learning model (ADM).

[0280] Then, the Question Answering Language Model (QALM) can provide the obtained response data (i.e., the recommended response data) to the application 111.

[0281] Thus, in the embodiment, the application 111 can obtain the recommended response data from the Question Answering Language Model (QALM).

[0282] Then, in the embodiment, the application 111 can generate recommended Q&A data SD including the obtained recommended response data and the recommended question data SQD corresponding to the recommended response data.

[0283] Also, in the embodiment, the application 111 can obtain user input to add the generated recommended Q&A data SD to the question answering content QAC.

[0284] According to the embodiment, the application 111 can obtain response data directly created by the user (i.e., creative response data) through user input.

[0285] Then, the application 111 can generate recommended Q&A data SD including the obtained creative response data and the recommended question data SQD corresponding to the creative response data.

[0286] Also, in the embodiment, the application 111 can obtain user input to add the generated recommended Q&A data SD to the question answering content QAC.

[0287] As described above, the application 111 can generate question-and-answer content QAC based on at least one question-and-answer data QA additionally recommended via the question-and-answer language model QALM, thereby minimizing the difficulty of question creation for the publicity of the specialized document SD and providing question-and-answer content QAC based on more extended various options.

[0288] On the other hand, as further shown in FIG. 10, in an embodiment, the application 111 can generate at least one proposed question-and-answer data PD based on the input of other users.

[0289] Here, the proposed question-and-answer data PD according to the embodiment can be meant to be a data set composed of question data directly created by other users (in the embodiment, readers, etc.) and response data for the question data.

[0290] Specifically, in an embodiment, the application 111 can obtain question data PQD (hereinafter, proposed question data) directly created by other users in conjunction with the terminal 100 of other users.

[0291] Also, in an embodiment, the application 111 can obtain response data for the proposed question data PQD (hereinafter, proposed response data) in conjunction with the question-and-answer language model QALM.

[0292] Specifically, in an embodiment, the application 111 can input the proposed question data PQD into the question-and-answer language model QALM.

[0293] In this way, in the embodiment, the question-and-answer language model QALM can obtain response data based on the specialized document SD data and the proposed question data PQD input as described above based on the response deep learning model ADM.

[0294] And the question-and-answer language model QALM can provide the obtained response data (that is, proposed response data) to the application 111.

[0295] Thus, in an embodiment, the application 111 can obtain proposed response data from the question-and-answer language model QALM.

[0296] And in an embodiment, the application 111 can generate proposed question-and-answer data PD including the obtained proposed response data and proposed question data PQD corresponding to the proposed response data.

[0297] Also, in an embodiment, the application 111 can obtain user input to add the generated proposed question-and-answer data PD to the question-and-answer content QAC.

[0298] According to an embodiment, the application 111 can obtain response data directly created by the user (i.e., creative response data) through user input.

[0299] And the application 111 can generate proposed question-and-answer data PD including the obtained creative response data and proposed question data PQD corresponding to the creative response data.

[0300] Also, in an embodiment, the application 111 can obtain user input to add the generated proposed question-and-answer data PD to the question-and-answer content QAC.

[0301] In this way, the application 111 can generate question-and-answer content QAC including question data generated by other users including reader users who have subscribed to the specialized document SD, in addition to the author user who created the specialized document SD, and response data thereto.

[0302] Through this, the application 111 can actively accommodate questions that are of concern and of interest to the demand side for the specialized document, and provide promotional content PMC including question-and-answer content QAC reflecting this.

[0303] In summary, in the embodiment, the application 111 can obtain user input for adding the creative Q&A data CD, recommended Q&A data SD, and / or proposed Q&A data PD as described above to the Q&A content QAC.

[0304] Going back further, thus, in the embodiment, the application 111 can edit the configuration of the Q&A content QAC in the publicity content PMC according to the user input obtained as described above (i.e., user input for selecting at least one Q&A data QA in the Q&A content QAC, deleting, specifying the order, and / or adding, etc.).

[0305] On the other hand, in the embodiment, the application 111 can obtain user input for editing the content of the Q&A content QAC in the publicity content PMC.

[0306] As an embodiment, the application 111 can obtain user input for modifying (e.g., correcting, deleting, and / or adding, etc.) the content included in the predetermined question data and / or answer data in the Q&A content QAC.

[0307] And in the embodiment, the application 111 can edit the content of the Q&A content QAC in the publicity content PMC based on the obtained user input.

[0308] At this time, according to the embodiment, the application 111 can provide a function for automatically updating the content related to the modification.

[0309] Here, the function for automatically updating the content related to the modification according to the embodiment can be meant to be a function for automatically detecting and modifying the content (hereinafter referred to as associated data) associated with the modified content (hereinafter referred to as modification data).

[0310] Specifically, as an embodiment, the application 111 can detect at least one associated data related to the predetermined modification data in the Q&A content QAC.

[0311] As an embodiment, the application 111 can detect at least one associated data including information (such as text, image, table, and / or mathematical formula, etc.) included in the correction data and information having a similarity degree equal to or higher than a predetermined standard.

[0312] And in the embodiment, the application 111 can collectively correct each of the at least one detected associated data by applying mutatis mutandis the correction history applied to the correction data.

[0313] For example, when the correction history applied to the first correction data in the technical document SD is the correction history of changing "main contribution" to "key contribution", the application 111 can change all "main contribution" existing on the technical document SD to "key contribution".

[0314] That is, in the embodiment, the application 111 can provide a function (i.e., an automatic update function for correction-related content) of automatically correcting the content associated with a specific content in the Q&A content QAC according to the correction when the user corrects the specific content in the Q&A content QAC.

[0315] Therefore, the application 111 can improve the convenience and usability for the user in editing the Q&A content QAC and improve the satisfaction degree thereof.

[0316] FIG. 11 is an example of a diagram for explaining an editing assistant tool (Editing Assistant Tools) according to an embodiment of the present invention and / or a method of providing a related document search function.

[0317] Also, as shown in FIG. 11, in the embodiment, the application 111 can provide an editing assistant tool EAT (Editing Assistant Tools).

[0318] Here, the editing assistance tool EAT according to the embodiment can be meant to be a user interface that provides a form in which a predetermined image, table, and / or formula, etc. related to a predetermined specialized document can be easily inserted onto the question-and-answer content QAC.

[0319] Exemplarily, the editing assistance tool EAT can include a Markdown Editor or the like.

[0320] In the embodiment, the application 111 can provide an editing assistance tool EAT that configures and provides in a form that can be utilized on the question-and-answer content QAC a predetermined image, table, and / or formula data, etc. included in the specialized document SD.

[0321] That is, in the embodiment, when the user edits the question-and-answer content QAC, the application 111 can easily and simply utilize various images, tables, and / or formulas, etc. related to the specialized document SD by using the above-described editing assistance tool EAT.

[0322] Therefore, the application 111 can provide a question-and-answer content QAC editing process in which richer data can be easily utilized.

[0323] Also, as further shown in FIG. 11, in the embodiment, the application 111 can provide a related document search function.

[0324] Here, the related document search function according to the embodiment can be meant to be a function that automatically detects and provides a specialized document SD (RD: hereinafter, related document) associated with predetermined question data and / or response data.

[0325] Specifically, in the embodiment, the application 111 can obtain a user input for selecting predetermined question data and / or response data within the question-and-answer content QAC.

[0326] Also, in the embodiment, the application 111 can detect at least one specialized document SD related to the interrogation data and / or response data (hereinafter referred to as selected data) selected by the acquired user input.

[0327] Here, the specific method for the application 111 according to the embodiment of the present invention to detect the related document RD can be realized based on various disclosed algorithms and / or processes. In the embodiment of the present invention, such algorithms and / or processes themselves are not limited or restricted.

[0328] Also, in the embodiment, the application 111 can match and provide at least one detected related document RD with the selected data.

[0329] Therefore, when the user edits the question-and-answer content QAC, the application 111 can easily reference and utilize the specialized document SD related to the corresponding interrogation data and / or response data without performing another search.

[0330] Also, through this, the application 111 can assist the user in easily comparing their own specialized document SD with other specialized documents SD and easily highlighting the differences based on the additional related document RD information provided as described above.

[0331] As described above, the application 111 that has acquired the user input for editing the configuration and / or content of the question-and-answer content QAC within the publicity content PMC in the embodiment can generate publicity editing content based on the acquired editing input.

[0332] Also, in the embodiment, if the application 111 acquires the user input for selecting (i.e., approving) the publicity editing content based on the publicity production workspace, the publicity editing content can be determined as the publicity start content.

[0333] Therefore, the application 111 can enable the user to produce customized publicity start content optimized in the form desired by the user with a high degree of freedom.

[0334] At this time, according to the embodiment, the application 111 can provide a question-and-answer content QAC component adjustment function.

[0335] Here, the question-and-answer content QAC component adjustment function according to the embodiment means a function of compressing or increasing the question-and-answer content QAC in the publicity start content according to a predetermined method when the determined publicity start content does not meet the preset data volume (as an embodiment, one page, etc.) condition.

[0336] Specifically, in the embodiment, if the publicity start content exceeds the preset data volume (for example, if the publicity start content has a component exceeding one page), the application 111 can reduce the component of at least one response data in the publicity start content.

[0337] In the embodiment, the application 111 can obtain reduction data for each of at least one response data in the publicity start content in conjunction with a predetermined deep learning neural network.

[0338] Here, the reduction data according to the embodiment can mean data obtained by reducing the data volume of a predetermined response data according to a predetermined method (for example, summarization, etc.).

[0339] Here, the specific method for the application 111 according to the embodiment of the present invention to obtain reduction data can be realized based on various disclosed algorithms and / or processes. In the embodiment of the present invention, such algorithms and / or processes themselves are not limited or restricted.

[0340] Alternatively, as an embodiment, the application 111 can obtain reduction data for each of at least one response data in the publicity start content based on user input.

[0341] That is, according to the embodiment, the application 111 can obtain reduction data based on the content directly input by the user.

[0342] Also, in the embodiment, the application 111 can replace the obtained reduction data with the response data corresponding to the reduction data.

[0343] That is, the application 111 can replace the response data in the publicity start content with reduction data.

[0344] At this time, in the embodiment, if the application 111 obtains user input (such as selection input, etc.) for the reduction data in the publicity start content, it can provide the response data (hereinafter, original data) corresponding to the reduction data.

[0345] On the other hand, in the embodiment, if the publicity start content is less than or equal to a preset data volume (for example, if the publicity start content has a component of less than or equal to one page), the application 111 can additionally provide at least one recommended Q&A data SD as described above.

[0346] And the application 111 can further include the recommended Q&A data SD (hereinafter, added Q&A data) selected by user input from among the at least one recommended Q&A data SD additionally provided in the question-and-answer content QAC in the publicity start content.

[0347] At this time, in the embodiment, when the application 111 includes the added Q&A data in the question-and-answer content QAC, it can determine whether the preset data volume condition is satisfied.

[0348] In addition, when the application 111 meets the preset data volume condition, the added Q&A data can be inserted into the Q&A content QAC in the publicity start content.

[0349] On the contrary, when the preset data volume condition is not met, the application 111 can repeatedly perform the above-described Q&A content QAC component adjustment function.

[0350] In this way, the application 111 can provide a function of easily processing the determined publicity start content into a form that meets the preset component conditions.

[0351] In addition, in the embodiment, the application 111 can provide the determined publicity start content. (S111)

[0352] Specifically, in the embodiment, the application 111 can provide the publicity start content based on the specialized document SD sharing platform.

[0353] More specifically, in the embodiment, the application 111 can register the publicity start content determined as above on the specialized document SD sharing platform, and share and provide it to users (in the embodiment, authors and / or readers, etc.) who use the specialized document SD sharing platform.

[0354] As described above, in the embodiment, the application 111 generates Q&A content QAC for a predetermined specialized document SD using the Q&A language model QALM according to the embodiment of the present invention, provides an interface for freely editing the generated Q&A content QAC, and can provide publicity content PMC based on this.

[0355] Through this, Application 111 can easily provide high-quality publicity materials optimized for user needs, while including in-depth and practical question-and-answer content obtained from a deep learning model specialized for the specialized document SD.

[0356] [Method for providing a reader-side specialized document sharing platform]

[0357] FIG. 12 is a block diagram for explaining a method for providing a reader-side specialized document SD sharing platform according to an embodiment of the present invention.

[0358] On the other hand, as shown in FIG. 12, in the embodiment of the present invention, Application 111 can provide a specialized document SD search function based on a specialized document SD sharing platform. (S201)

[0359] Specifically, in the embodiment, Application 111 can provide a specialized document SD search function capable of searching for at least one specialized document SD (hereinafter, registered document) registered on the specialized document SD sharing platform.

[0360] More specifically, in the embodiment, Application 111 can provide a specialized document SD search function based on the publicity start content corresponding to each registered document.

[0361] Specifically, in the embodiment, Application 111 can obtain at least one search keyword based on user input.

[0362] In addition, Application 111 can detect at least one publicity start content including the obtained search keyword.

[0363] That is, Application 111 can detect at least one publicity start content based on summary data SMD and / or question-and-answer content QAC including a predetermined search keyword.

[0364] Then, the application 111 can provide at least one detected advertising start content via the professional document SD sharing platform.

[0365] In other words, the application 111 can provide at least one advertising start content corresponding to the search keyword by user input as a search result.

[0366] In this way, the application 111 can significantly improve the search speed and / or performance by performing the professional document SD search process by utilizing the content (i.e., advertising start content) that efficiently and specifically implies and represents the content of the professional document SD.

[0367] Furthermore, the application 111 can provide a professional document SD search service that allows users to more easily and efficiently recognize the professional document SD related to the content they desire by providing the search results in the form of advertising start content.

[0368] Also, in an embodiment, the application 111 can provide a professional document SD sharing and citation function based on the professional document SD sharing platform. (S203)

[0369] FIG. 13 is an example of a diagram for explaining a method for providing a professional document SD sharing and citation function according to an embodiment of the present invention.

[0370] Specifically, as shown in FIG. 13, in an embodiment, the application 111 can provide a professional document SD sharing and citation function that can share and cite advertising start content corresponding to a predetermined registered document.

[0371] More specifically, in an embodiment, the application 111 can assign an identification code (PIC: hereinafter, advertising material identification code) corresponding to each advertising start content.

[0372] Here, the publicity material identification code PIC according to the embodiment can include a URL (Uniform Resource Locator) connectable to predetermined publicity start content and / or a time stamp (Time Stamp) for specifying the citation time, etc.

[0373] Also, in the embodiment, the application 111 can provide a sharing and citation function for the predetermined publicity start content based on the publicity material identification code PIC as described above.

[0374] As an embodiment, the application 111 can obtain user input requesting sharing and / or citation for the predetermined publicity start content.

[0375] In that case, the application 111 can detect the publicity material identification code PIC that matches the publicity start content.

[0376] And the application 111 can output and provide the detected publicity material identification code PIC in a predetermined manner (for example, in the form of a post draft that can be posted on a specific service, etc.).

[0377] Also, in the embodiment, the application 111 can provide a specialized document SD sharing and citation function for sharing and citing each question-and-answer data QA included in the question-and-answer content QAC within the predetermined publicity start content.

[0378] Specifically, in the embodiment, the application 111 can assign an identification code DIC (hereinafter referred to as a question-and-answer identification code) corresponding to each question-and-answer data QA.

[0379] Here, the question-and-answer identification code DIC according to the embodiment can include a URL (Uniform Resource Locator) connectable to the publicity start content including the corresponding question-and-answer data QA and / or a time stamp (Time Stamp) for specifying the citation time, etc.

[0380] Also, in the embodiment, the application 111 can provide a sharing and citation function for predetermined Q&A data QA based on the Q&A identification code DIC as described above.

[0381] As an embodiment, the application 111 can obtain user input requesting sharing and / or citation for predetermined Q&A data QA.

[0382] Then, the application 111 can detect a Q&A identification code DIC that matches the Q&A data QA.

[0383] And the application 111 can output and provide the detected Q&A identification code DIC in a predetermined manner (for example, in the form of a post draft that can be posted on a specific service, etc.).

[0384] At this time, in the embodiment, the application 111 can provide, as a pop-up, the notation format (i.e., the citation notation method) proposed when citing the publicity document identification code PIC and / or the Q&A identification code DIC as a reference.

[0385] Exemplarily, the application 111 can provide, as a pop-up, a citation notation method based on the APA version, MLA version, or Bibtex version, etc.

[0386] In this way, in the embodiment, the application 111 can provide a technical configuration that can share and cite the publicity start content itself for the specialized document SD registered on the specialized document SD sharing platform, or share and cite the Q&A data QA itself within the Q&A content QAC included in the publicity start content.

[0387] Therefore, the application 111 can significantly enhance the accessibility to the registered documents on the specialized document SD sharing platform, and can also further improve the influence of the author insights related to the registered documents.

[0388] On the other hand, according to an embodiment, when the application 111 quotes predetermined publicity start content and / or Q&A data QA based on a publicity material identification code PIC and / or a Q&A identification code DIC, it can also provide information (such as citation credit, etc.) indicating this to the author who created the registration document.

[0389] Thus, the application 111 can enable the author side to grasp in real time the situation where their own professional document SD is shared and cited.

[0390] Also, in an embodiment, the application 111 can provide a reader question recommendation function based on a professional document SD sharing platform. (S205)

[0391] Specifically, in an embodiment, the application 111 can provide a reader question recommendation function that can acquire and provide proposal question data PQD for a predetermined registration document.

[0392] More specifically, in an embodiment, the application 111 can provide a user interface (hereinafter, a proposal question input interface) that can acquire and provide proposal question data PQD as described above based on a professional document SD sharing platform.

[0393] In other words, the application 111 can provide a proposal question input interface that can acquire and provide proposal question data PQD, which is question data directly created by other users (such as readers in an embodiment) other than the author user who created the registration document.

[0394] Then, the application 111 can acquire proposal question data PQD for a predetermined registration document based on the input of a user (such as a reader in an embodiment) based on the provided proposal question input interface.

[0395] In addition, the application 111 can provide the obtained proposal query data PQD to the terminal 100 of the author who created the registered document.

[0396] Therefore, the application 111 can generate question-and-answer content QAC based on the proposal question data PD as described above.

[0397] Therefore, the application 111 can realize publicity start content that actively reflects questions that readers are concerned about and interested in regarding a specific registered document.

[0398] At this time, in the embodiment, the application 111 can set the disclosure range for the proposal query data PQD based on the input of the user (in the embodiment, a reader, etc.) based on the proposal query input interface and / or the input of the user (in the embodiment, an author, etc.) based on the publicity material production workspace.

[0399] As an embodiment, the application 111 can set the disclosure range by user input that sets either "public disclosure to all users using the specialized document SD disclosure platform" or "author disclosure where the proposal query data PQD is disclosed only to the author who created the corresponding specialized document SD".

[0400] In addition, in the embodiment, the application 111 can provide the proposal query data PQD to all users or the author according to the set disclosure range.

[0401] That is, the application 111 can more effectively protect the intellectual rights of readers and / or authors by selectively determining the disclosure range of the question data proposed by the readers.

[0402] As described above, the method and system for providing a professional document SD sharing platform according to an embodiment of the present invention generate question-and-answer content QAC for the professional document SD using a predetermined deep-learning neural network, and provide promotional content PMC based on the generated question-and-answer content QAC. As a result, users can obtain question-and-answer-formatted data that efficiently encompasses the content of the professional document SD automatically without additional effort, and can utilize the promotional content PMC based on the obtained data.

[0403] At this time, the method and system for providing a professional document SD sharing platform according to an embodiment of the present invention generate question-and-answer content QAC using a language model specialized for the professional document SD, thereby providing question-and-answer content QAC that eliminates the hallucination and ambiguous answering problems that are limitations of existing general-purpose language models (e.g., OpenAI GPT, etc.).

[0404] Through this, the method and system for providing a professional document SD sharing platform according to an embodiment of the present invention can provide question-and-answer content QAC that is faithful to the question, fact-based (hallucination-controlled), and presents clear evidence based on an advanced inference / estimation function realized in a process similar to human cognitive inference.

[0405] In addition, the method and system for providing a professional document SD sharing platform according to an embodiment of the present invention provide promotional content PMC based on a user interface (UI) that allows the generated question-and-answer content QAC to be freely edited. This enables users to create customized promotional materials optimized in the form they desire with a high degree of freedom beyond simply sharing the professional document SD, and effectively supports users in actively conducting promotional activities using these materials.

[0406] Furthermore, the method for providing a professional document SD sharing platform and its system according to an embodiment of the present invention through this can include in-depth and practical question-and-answer content obtained from a deep learning model specialized for professional document SD, and has the effect of being able to easily generate and utilize high-quality publicity materials optimized for user needs.

[0407] On the other hand, the embodiments according to the present invention described above can be realized in the form of program instruction words that can be executed through various computer components, and can be recorded on a computer-readable recording medium. The computer-readable recording medium can include program instruction words, data files, data structures, etc. alone or in combination. The program instruction words recorded on the computer-readable recording medium can be those specially designed and configured for the present invention, or those known to those skilled in the computer software field and can be used. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices such as ROMs, RAMs, flash memories, etc., which are specially configured to store and execute program instruction words. Examples of program instruction words include not only machine language codes such as those made by compilers, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device can be changed into one or more software modules for performing the processing according to the present invention, and vice versa.

Claims

1. 1. A method for providing a professional document sharing platform, comprising: obtaining a first technical document; generating a question and answer content for the first specialized document based on a question and answer language model; generating promotional content, which is an online promotional material for the first technical document, based on the question and answer content; Providing the promotional content based on a promotional material production workspace; determining a promotion start content, which is the promotion content to be registered on the professional document sharing platform, based on the promotional material production workspace; providing the promotion start content based on the professional document sharing platform; A method for providing a professional document sharing platform including:

2. The step of generating the question and answer content includes: inputting the first technical document into the question and answer language model; acquiring at least one question and answer data including question data and answer data of the first technical document from the question and answer language model; generating the question and answer content based on the at least one question and answer data; The method for providing a platform for sharing professional documents according to claim 1 , comprising:

3. The step of acquiring question and answer data includes: Obtaining the at least one question data according to a question deep-learning model included in the question and answer language model; Obtaining at least one answer data corresponding to each of the at least one question data based on an answer deep-learning model included in the question and answer language model; The method for providing a platform for sharing professional documents according to claim 2 , further comprising:

4. The response deep learning model is A deep learning model that outputs the response data based on a multi-step inference process, The multi-step inference process comprises: an associative selection process for determining an evidence paragraph, which is a paragraph associated with the question data in the first expert document; a rationale generation process for obtaining at least one rationale data corresponding to the query data according to the evidence paragraph; A systematic composition process for processing data based on the evidence data; The method for providing a platform for sharing professional documents according to claim 3 , comprising:

5. The public relations content is:

2. The method for providing a platform for sharing specialized documents according to claim 1, wherein the content data is configured based on a predetermined data amount condition.

6. The step of determining the publicity start content includes: The method for providing a platform for sharing professional documents according to claim 1, further comprising the step of generating edited publicity content, the publicity content being edited by a user input based on the publicity production workspace.

7. The step of generating the public relations editorial content includes: generating the publicity edited content according to a user input for editing a configuration of the question and answer content in the publicity content; and The method for providing a platform for sharing professional documents according to claim 6, further comprising at least one step of generating the public relations edited content according to a user input for editing the content of the question and answer session in the public relations content.

8. The step of generating the public relations editorial content includes:

7. The method of claim 6, further comprising providing an editing assistant tool, which is a user interface that provides at least one of predetermined image, table, and formula data related to the first professional document in a form that can be inserted into a question and answer content in the promotional content.

9. The step of generating the public relations editorial content includes: The method for providing a professional document sharing platform according to claim 6, further comprising a step of providing a related document search function which is a function of automatically detecting and providing at least one other professional document related to the question and answer content in the public relations content.

10. The step of determining the publicity start content includes: The method of claim 6, further comprising determining one of the promotion content or the promotion editing content as the promotion start content according to a user input based on the promotion production workspace.

11. The method of claim 1 , further comprising providing a professional document search function based on the publicity-initiated content based on the professional document sharing platform.

12. The method of claim 1 , further comprising providing a professional document sharing and citation function based on the publicity-initiated content based on the professional document sharing platform.

13. The step of providing a specialized document sharing and citation function includes: providing a promotion identification code including a connection uniform resource locator (URL) and a time stamp corresponding to the promotion start content; and The method of claim 12, further comprising at least one of providing a question and answer identification code including a connection URL and a time stamp corresponding to the question and answer content in the promotion start content.

14. The method for providing a professional document sharing platform as described in claim 1, further comprising a step of providing a reader question recommendation function, which is a function of acquiring and providing question data created by a user who is provided with the first professional document based on the professional document sharing platform.

15. at least one memory having a platform application stored therein; at least one processor that reads a platform application stored in the memory to provide a professional document sharing platform; Equipped with The platform application command: obtaining a first technical document; generating a question and answer content for the first specialized document based on a question and answer language model; generating promotional content, which is an online promotional material for the first technical document, based on the question and answer content; Providing the promotional content based on a promotional material production workspace; determining a promotion start content, which is the promotion content to be registered on the professional document sharing platform, based on the promotional material production workspace; providing the promotion start content based on the professional document sharing platform; A system providing a platform for sharing specialized documents including commands to do the above.

Images