In-institution takeover processing device using artificial intelligence and control method thereof

Abstract

The present disclosure relates to a device for document search personalization and new document generation using artificial intelligence and a control method thereof. The device for document search personalization and new document generation using artificial intelligence may comprise: an input module for acquiring data; a communication module for transmitting and receiving the data to and from an external device; a memory storing at least one process for performing an operation and storing user input and data; a display for displaying a graphic image; and a processor for performing a control method according to the process, wherein the processor acquires first data including a first electronic document produced by each department and a second electronic document produced by an individual user through the input module, preprocesses the first data, learns the preprocessed first data, generates a takeover processing model by using a learning result, acquires a request message through the input module, and generates a takeover result corresponding to the request message by using the takeover processing model, and the display may display the takeover result.

Description

Institutional handover processing device using artificial intelligence and control method thereof

[0001] The present disclosure relates to a handover processing device. More specifically, it relates to an in-institutional handover processing device using artificial intelligence and a method for controlling the same.

[0002] With the recent advancement of information technology, many companies have adopted numerous solutions to improve information efficiency, and this trend of change is showing a recent tendency toward integration. Each company has established groupware and intranets for internal information sharing, and has enabled users to perform centrally managed tasks by allowing them to access thin servers built within the company using thin clients.

[0003] Furthermore, each company established systems such as Enterprise Resource Planning, Customer Relation Management, and Supply Chain Management with the goal of managing various types of information. In addition, with the rise of the Internet, they built websites and implemented B2C (Business-to-Consumer) or B2B (Business-to-Business) systems for e-commerce.

[0004] And because it was still difficult to find necessary information amidst such a flood of systems, enterprise portals began to spread rapidly. These portals integrate various types of complexly intertwined internal and external information—such as intranets, groupware, enterprise resource management, customer relationship management, supply chain management, electronic document management systems, and knowledge management systems—into a single interface for efficient business processing, thereby increasing not only convenience but also business productivity by providing services tailored to user needs.

[0005] However, in the case of conventional technology, when one of the organization's members resigns, it is difficult to determine which of multiple documents to hand over to the next employee, and since management must be done manually, it is difficult to proceed with the handover of duties systematically, causing inconvenience to the user.

[0006] The embodiment disclosed in this disclosure aims to provide a handover processing device that automatically generates and provides summary data to the person taking over tasks and automatically links and provides related documents in order to resolve situations where the handover of tasks is not performed properly.

[0007] The embodiments disclosed in this disclosure aim to provide a handover processing device capable of delivering weekly, monthly, and annual plans through the analysis of production documents by department and user.

[0008] The embodiment disclosed in this disclosure aims to provide a handover processing device capable of analyzing production documents by department and user and reminding the successor of the analysis results.

[0009] The embodiment disclosed in this disclosure aims to provide a handover processing device capable of automatically transmitting handover details using analysis data and user input patterns when a user moves to a different department.

[0010] The problems that this disclosure aims to solve are not limited to those mentioned above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below.

[0011] An in-institutional handover processing device using artificial intelligence according to the present disclosure for achieving the aforementioned technical problem comprises: an input module for acquiring data; a communication module for transmitting and receiving said data with an external device; a memory for storing at least one process for performing an operation and storing user input and data; and a display for displaying a graphic image. and includes a processor that performs a control method according to the above process, wherein the processor acquires first data including a first electronic document produced by each department and a second electronic document produced by an individual user through an input module, preprocesses the first data, learns the preprocessed first data, generates a handover processing model using the learning result, acquires a request message through the input module, generates a handover result corresponding to the request message using the handover processing model, the display displays the handover result, evaluates the importance of past documents to set priorities, displays the set priorities through the display, generates future documents and work plans that have elapsed a preset time from the current point in time based on the past documents, displays the future documents and work plans through the display, automatically identifies past documents among the past documents that the user has accessed or modified more than a specific number of times within a preset period, selects the identified past documents as handover results, analyzes the correlation and collaboration patterns between documents, and visualizes a work network based on the analysis result It can generate and display the generated visualized business network through the display.

[0012] According to one embodiment, the processor can analyze a document creation cycle and pattern through time series analysis and control the display to display the document creation cycle and pattern.

[0013] According to one embodiment, the processor can classify documents based on the subject of the documents to identify a work area, and control the display to display the identified work area.

[0014] According to one embodiment, the processor can automatically extract due date information from the contents of the past documents, set reminder information based on the extracted due date information, and control the display to display the set reminder information.

[0015] According to one embodiment, the processor may analyze the creation order of related documents among the past documents and execute a reminder based on the analyzed result.

[0016] In addition, a method for processing an in-institutional handover using artificial intelligence, performed by a processor of a device according to the present disclosure for achieving the aforementioned technical objectives, comprises the steps of: acquiring first data including a first electronic document produced by each department and a second electronic document produced by an individual user through an input module; preprocessing the first data; learning the preprocessed first data; generating a handover processing model using the learning results; acquiring a request message through the input module; and generating a handover result corresponding to the request message using the handover processing model. The method includes the step of controlling the display to display the handover results, wherein the processor evaluates the importance of past documents to set priorities, displays the set priorities through the display, generates future documents and work plans that have elapsed a predetermined time from the present point in time based on the past documents, displays the future documents and work plans through the display, automatically identifies among the past documents that the user has accessed or modified more than a certain number of times within a preset period, selects the identified documents as handover results, analyzes the correlation and collaboration patterns between documents, generates a visualized work network based on the analysis results, and can display the generated work network through the display.

[0017] In addition to this, a computer program stored on a computer-readable recording medium may be further provided to carry out a method for implementing the present disclosure.

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

[0019] According to the present invention, in order to resolve situations where work handover is not performed properly, summary data can be automatically generated and provided to the person taking over the work, and related documents can be automatically linked and provided, thereby offering the advantage of making the handover more efficient.

[0020] According to the present invention, since weekly, monthly, and annual plans can be delivered through the analysis of production documents by department and user, there is an advantage in that the handover can be performed more efficiently.

[0021] According to the present invention, production documents by department and user can be analyzed, and the analysis results can be reminded to the successor, thus providing the advantage of making the handover more efficient.

[0022] According to the present invention, since handover details can be automatically transmitted using analysis data and user input patterns when a user moves to a different department, there is an advantage of making the handover more efficient.

[0023] The effects of the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below.

[0024] FIG. 1 is a configuration diagram of an in-institutional handover processing device using artificial intelligence according to the present disclosure.

[0025] FIG. 2 is a flowchart illustrating a method for handling internal handover within an institution using artificial intelligence according to the present disclosure.

[0026] FIG. 3 is a drawing illustrating an example of a handover processing UX according to the present disclosure.

[0027] FIGS. 4a and FIGS. 4b are drawings illustrating the concept of a handover process according to the present disclosure.

[0028] FIG. 5 is a drawing of an example of document generation pattern analysis according to the present disclosure.

[0029] FIG. 6 is a drawing illustrating an example of document topic modeling according to the present disclosure.

[0030] FIG. 7 is a drawing illustrating an example of future document generation according to the present disclosure.

[0031] FIG. 8 is a drawing illustrating an example of importance based on document analysis according to the present disclosure.

[0032] FIG. 9 is a drawing illustrating an embodiment of extracting a deadline according to the present disclosure.

[0033] FIG. 10 is a drawing illustrating an embodiment showing the order of creation of documents according to the present disclosure.

[0034] FIG. 11 is a drawing illustrating an embodiment for identifying a key document according to the present disclosure.

[0035] FIG. 12 is a drawing illustrating an embodiment for visualizing a business network according to the present disclosure.

[0036] FIG. 13 is a drawing illustrating an embodiment of generating a knowledge map according to the present disclosure.

[0037] FIG. 14 is a drawing illustrating an embodiment of an adaptive handover system according to the present disclosure.

[0038] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and general content in the art to which this disclosure pertains or content that overlaps between embodiments is omitted. The terms 'part, module, component, block' as used in the specification may be implemented in software or hardware, and depending on the embodiments, a plurality of 'parts, modules, components, blocks' may be implemented as a single component, or a single 'part, module, component, block' may include a plurality of components.

[0039] Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are directly connected but also cases where they are indirectly connected, and indirect connections include connections made via a wireless communication network.

[0040] Furthermore, when it is stated that a part "includes" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0041] Throughout the specification, when it is stated that a component is located "on" another component, this includes not only cases where a component is in contact with another component, but also cases where another component exists between the two components.

[0042] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0043] Singular expressions include plural expressions unless there is an obvious exception in the context.

[0044] In each step, identification codes are used for convenience of explanation and do not describe the order of the steps; the steps may be performed differently from the specified order unless a specific order is clearly indicated in the context.

[0045] The operating principles and embodiments of the present disclosure will be described below with reference to the attached drawings.

[0046] In this specification, the present invention may be implemented not only as a server system but also as various devices capable of performing computational processing and providing results to a user. For example, the present invention may include a computer, a server device, and a portable terminal, or may take the form of any one of them.

[0047] Here, the computer may include, for example, a notebook, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser.

[0048] The above server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

[0049] The above portable terminal may include, for example, all types of handheld-based wireless communication devices such as PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminals, smartphones, etc., as well as wearable devices such as watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted devices (HMDs).

[0050] Functions related to artificial intelligence according to the present disclosure are operated through a processor and memory. The processor may be composed of one or more processors. In this case, the one or more processors may be general-purpose processors such as CPUs, APs, and DSPs (Digital Signal Processors), graphics-dedicated processors such as GPUs and VPUs (Vision Processing Units), or artificial intelligence-dedicated processors such as NPUs. The one or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in memory. Alternatively, if the one or more processors are artificial intelligence-dedicated processors, the artificial intelligence-dedicated processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0051] The predefined operation rules or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that a predefined operation rules or artificial intelligence models configured to perform a desired characteristic (or objective) are created by a basic artificial intelligence model being trained using a number of training data by a learning algorithm. Such learning may be performed on the device itself where the artificial intelligence according to the present disclosure is executed, or it may be performed through a separate server and / or system. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the examples described above.

[0052] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values ​​and performs neural network operations through operations between the results of previous layers and the multiple weights. The multiple weights possessed by the multiple neural network layers can be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model during the learning process is reduced or minimized. The artificial neural network may include a Deep Neural Network (DNN), such as a Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), Bidirectional Recurrent Deep Neural Network (BRDNN), or Deep Q-Networks, but is not limited to the examples mentioned above.

[0053] The processor can create a neural network, train (or learn) the neural network, perform operations based on received input data, generate an information signal based on the results of the operation, or retrain the neural network.

[0054] Neural networks include CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), perceptron, multilayer perceptron, FF (Feed Forward), RBF (Radial Basis Network), DFF (Deep Feed Forward), LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit), AE (Auto Encoder), VAE (Variational Auto) Encoder), DAE (Denoising Auto Encoder), SAE (Sparse Auto Encoder), MC (Markov Chain), HN (Hopfield Network), BM (Boltzmann Machine), RBM (Restricted Boltzmann Machine), DBN (Depp Belief Network), DCN (Deep Convolutional Network), DN (Deconvolutional Network), DCIGN (Deep Convolutional Inverse Graphics Network), GAN (Generative Adversarial Network), LSM (Liquid State Machine), ELM (Extreme Learning Machine), ESN (Echo It will be understood by a person skilled in the art that any neural network may be included, but is not limited to, State Network, Deep Residual Network, Differential Neural Computer, Neural Turning Machine, Capsule Network, Kohonen Network, and Attention Network.

[0055] According to an exemplary embodiment of the present disclosure, the processor comprises a Convolutional Neural Network (CNN) such as GoogleNet, AlexNet, VGG Network, Region with Convolutional Neural Network (R-CNN), Region Proposal Network (RPN), Recurrent Neural Network (RNN), Stacking-based Deep Neural Network (S-DNN), State-Space Dynamic Neural Network (S-SDNN), Deconvolution Network, Deep Belief Network (DBN), Restricted Boltzmann Machine (RBM), Fully Convolutional Network, Long Short-Term Memory (LSTM) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT, SP-BERT, MRC / QA, Text Analysis, Dialog System, GPT-3, GPT-4 for Natural Language Processing, Visual Analytics, Visual Understanding, Video Synthesis for Vision Processing, Anomaly Detection, Prediction, Time-Series Forecasting, Optimization, Recommendation for ResNet Data Intelligence, Various artificial intelligence structures and algorithms, such as data creation, may be used, but are not limited thereto. Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings.

[0056] FIG. 1 is a configuration diagram of an in-institutional handover processing device using artificial intelligence according to the present disclosure.

[0057] Referring to FIG. 1, the handover processing device (100) includes an input module (110), a sensor module (120), a processor (130), a display module (140), a memory (150), a communication module (160), and a camera module (170).

[0058] The input module (110) acquires data.

[0059] The sensor module (120) senses data.

[0060] The processor (130) performs a control method according to the process.

[0061] The processor (130) obtains first data including a first electronic document produced by each department and a second electronic document produced by an individual user through an input module (110), preprocesses the first data, learns the preprocessed first data, creates a handover processing model using the learning result, obtains a request message through the input module (110), creates a handover result corresponding to the request message using the handover processing model, and controls the display (140) to display the handover result.

[0062] The processor (130) converts unstructured data into text through OCR, speech-to-text conversion, etc., and performs preprocessing by performing text normalization, stop word removal, and morphological analysis.

[0063] The display module (140) displays a graphic image according to a control command from the processor (130).

[0064] The memory (150) stores at least one process for performing operations and stores user input and data.

[0065] The communication module (160) transmits and receives data with an external device (200).

[0066] Here, the external device (200) includes external devices such as smartphones, PCs, laptops, tablet PCs, etc.

[0067] The camera module (170) captures an image of the front.

[0068] The camera module (170) photographs a subject in front according to a control command from the processor (130).

[0069] The processor (130) can automatically generate and provide summary data to the person taking over the work and automatically link and provide related documents to resolve the situation where the work handover is not properly completed when the user leaves the company. In this case, at least one of BERT, GPT, and Llama 3.1 can be utilized.

[0070] The processor (130) analyzes the document creation cycle and pattern through time series analysis and controls the display (140) to display the document creation cycle and pattern. A detailed explanation of this is given in FIG. 5.

[0071] The processor (130) classifies documents based on the subject of the documents to identify work areas and controls the display to display the identified work areas. A detailed explanation of this is provided in FIG. 6.

[0072] The processor (130) generates future documents and work plans after a predetermined amount of time has elapsed from the current point in time based on past documents, and controls the display to display the future documents and work plans. A detailed explanation of this is given in FIG. 7.

[0073] The processor (130) evaluates the importance of past documents to set priorities and controls the display to display the set priorities. A detailed explanation of this is given in FIG. 8.

[0074] The processor (130) automatically extracts due date information from the content of past documents, sets reminder information based on the extracted due date information, and controls the display (140) to display the set reminder information. A detailed explanation of this is given in FIG. 9.

[0075] The processor (130) analyzes the creation order of related documents among past documents and executes a reminder based on the analysis results. A detailed explanation of this is given in FIG. 10.

[0076] The processor (130) automatically identifies past documents that the user frequently accesses or has modified within a specified period, and selects the identified documents as handover results.

[0077] A detailed explanation of this is shown in Fig. 11.

[0078] The processor (130) analyzes the associations and collaboration patterns between documents, generates a visualized work network based on the analysis results, and controls the display to display the generated visualized work network. A detailed explanation of this is provided in FIG. 12.

[0079] However, the components illustrated in FIG. 1 are not essential for implementing the present invention according to the present disclosure, so the present invention described herein may have more or fewer components than the components listed above.

[0080] The communication module (160) may include one or more components that enable communication with an external device, and may include, for example, at least one of a broadcast receiving module, a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0081] The input module (110) is for inputting video information (or signal), audio information (or signal), data, or information input from a user, and may include at least one of at least one camera, at least one microphone, and a user input unit. Voice data or image data collected by the input module (110) may be analyzed and processed into a user control command.

[0082] The display (140) displays (outputs) information processed in the present invention. For example, the present invention may display execution screen information of an application program (e.g., an application) being run, or UI (User Interface) and GUI (Graphic User Interface) information based on such execution screen information.

[0083] The memory (150) can store data supporting various functions of the present invention and a program for the operation of the control unit, and can store input / output data (e.g., music files, still images, videos, etc.), and can store a plurality of application programs (or applications) running on the artificial intelligence-based user behavior pattern analysis device (100), data for the operation of the device, and commands. At least some of these application programs can be downloaded from an external server via wireless communication.

[0084] Such memory (150) may include at least one type of storage medium among flash memory type, hard disk type, SSD type (Solid State Disk type), SSD type (Silicon Disk Drive type), multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (random access memory; RAM), SRAM (static random access memory), ROM (read-only memory; ROM), EEPROM (electrically erasable programmable read-only memory), PROM (programmable read-only memory), magnetic memory, magnetic disk, and optical disk. Additionally, although separate from the present invention, the memory (150) may be a database connected via wired or wireless connection, and may be implemented as a database system.

[0085] The processor (130) may be implemented with at least one core, a memory that stores data for an algorithm or a program that reproduces the algorithm for controlling the operation of the components within the present invention, and at least one processor (not shown) that performs the aforementioned operation using the data stored in the memory. In this case, the memory and the processor may each be implemented as separate chips. Alternatively, the memory and the processor may be implemented as a single chip.

[0086] In addition, the processor (130) can control any one or a combination of the components described above in order to implement various embodiments according to the present disclosure described in FIGS. 2 to 14 below.

[0087] At least one component may be added or removed in response to the performance of the components illustrated in FIG. 1. Additionally, it will be readily understood by those skilled in the art that the relative positions of the components may be changed in response to the performance or structure of the system.

[0088] Meanwhile, each component illustrated in Fig. 1 refers to a software and / or hardware component such as a Field Programmable Gate Array (FPGA) and an Application Specific Integrated Circuit (ASIC).

[0089] FIG. 2 is a flowchart illustrating a method for handling internal handover within an institution using artificial intelligence according to the present disclosure.

[0090] The present invention is performed by a handover processing device (100) or a processor (130) of the handover processing device (100).

[0091] Referring to FIG. 2, the processor (130) obtains first data including a first electronic document produced by each department and a second electronic document produced by an individual user through an input module (110) (S210).

[0092] The processor (130) preprocesses the first data (S220).

[0093] The processor (130) learns the preprocessed first data (S230).

[0094] The processor (130) creates a handover processing model using the learning results (S240).

[0095] The processor (130) obtains the request message through the input module (110) (S250).

[0096] The processor (130) generates a handover result corresponding to the request message using the handover processing model (S260).

[0097] The processor (130) controls the display (140) to display the handover result (S270).

[0098] FIG. 3 is a drawing illustrating an example of a handover processing UX according to the present disclosure.

[0099] Referring to Fig. 3 (310), the handover processing UX is described.

[0100] The Document Search Personalization and New Document Creation items include Schedule Management, Recommended Documents, Handover, and News.

[0101] FIGS. 4a and FIGS. 4b are drawings illustrating the concept of a handover process according to the present disclosure.

[0102] Figure 4a (410) is a diagram illustrating the first concept of the handover process.

[0103] Figure 4b (420) is a diagram illustrating the second concept of the handover process.

[0104] The processor (130) includes a record management system linkage module, a data preprocessing and cleaning module, a BERT-based context embedding engine, a Supervised Language Model (SLM) configuration module, a multitask learning module, an intelligent business automation engine, a personalized recommendation and search module, an adaptive learning and model update module, an explainable AI dashboard, a security and compliance module, and a scalable microservices architecture.

[0105] The individual modules included in the processor (130) perform the following:

[0106] (1) The record management system linkage module securely links with the public institution's existing record management system and collects and integrates records of various formats (documents, images, audio, etc.).

[0107] (2) The data preprocessing and cleaning module converts unstructured data into text through OCR, speech-to-text conversion, etc., and performs text normalization, stop word removal, and morphological analysis.

[0108] (3) The BERT-based context embedding engine utilizes pre-trained models such as KoBERT, which are optimized for Korean, and generates high-dimensional vector representations that take into account the context and meaning of the records.

[0109] (4) The SLM (Supervised Language Model) configuration module takes the output of BERT as input to build a language model specialized for public institutions and performs supervised learning by combining the metadata and content of records.

[0110] (5) The multi-task learning module simultaneously learns various NLP tasks such as document classification, information extraction, and relationship analysis, and adds custom tasks specialized for records management (e.g., retention period prediction).

[0111] (6) The intelligent business automation engine automatically classifies documents and generates metadata, performs record association analysis and builds knowledge graphs, and supports business process automation and decision-making.

[0112] (7) The personalized recommendation and search module can recommend customized records based on the user's work patterns and access rights, and provide semantic-based advanced search and question-and-answer functions.

[0113] (8) The adaptive learning and model update module continuously updates the model by reflecting user feedback and new records, and performs model-specific functions that reflect the characteristics of each institution and department.

[0114] (9) The explainable AI dashboard provides the rationale for the model's recommendation and classification results, and visualizes records usage patterns and insights.

[0115] (10) The security and compliance module can ensure compliance with the Personal Information Protection Act and the Public Records Management Act by applying thorough access control and encryption.

[0116] (11) The scalable microservices architecture supports flexible integration with the records management systems of various public institutions and ensures scalability and stability in a cloud-native environment.

[0117] FIG. 5 is a drawing of an example of document generation pattern analysis according to the present disclosure.

[0118] As illustrated in FIG. 5 (510), the processor (130) analyzes the document creation cycle and pattern through time series analysis and controls the display (140) to display the document creation cycle and pattern.

[0119] For example, the processor (130) analyzes the generation cycle and pattern of doc, csv, and pdf documents.

[0120] The Doc document is generated on a weekly basis and forms a pattern of generation from Department A, Department B, and Department C.

[0121] CSV documents are generated every two weeks and form a pattern of being generated by Department A and Department B.

[0122] PDF documents are generated every three weeks and form a pattern of generation in Department A.

[0123] FIG. 6 is a drawing illustrating an example of document topic modeling according to the present disclosure.

[0124] As illustrated in FIG. 6 (610), the processor (130) classifies documents based on the subject of the documents to identify work areas and controls the display (140) to display the identified work areas.

[0125] The processor (130) extracts index terms and calculates similarity to classify documents into category 1, category 2, and category 3.

[0126] The index term extraction process refers to the process of finding a set of index terms that represent the characteristics of each category.

[0127] The similarity calculation and classification process refers to the process of calculating the similarity between a document and a category to classify the document into the most similar category.

[0128] Index terms refer to technical terms that best represent the characteristics of a category. Therefore, efficient index term extraction is a critical process that impacts overall performance in the document classification process.

[0129] Similarity refers to the degree of resemblance between a document to be classified and a category, serving as a criterion for classifying the document into the most similar category or a category exceeding a threshold. In a hierarchical structure, sequential similarity calculation is required from the root category to the terminal categories.

[0130] Similarity is between 0 and 1, and similarity of 0 means there is no correlation.

[0131] A similarity of 1 means that they are very related and identical.

[0132] The threshold can be 0.8 and is variable.

[0133] First, documents are classified into the most similar child category of the root category or into a category that exceeds a threshold. Then, the selected child category acts as the root category again, and the process of classifying into its child category is repeated. Since the category to be classified is determined from the child categories of the current category, documents misclassified at the upper level will also be misclassified at the lower level. Consequently, the classification accuracy of the upper level has a significant impact on the overall accuracy.

[0134] FIG. 7 is a drawing illustrating an example of future document generation according to the present disclosure.

[0135] As illustrated in FIG. 7 (710), the processor (130) generates future documents and work plans that have elapsed a predetermined amount of time from the present time based on past documents, and controls the display to display the future documents and work plans.

[0136] For example, when the processor (130) receives a past document, it can generate a future document and a work plan based on the past document and display them.

[0137] FIG. 8 is a drawing illustrating an example of importance based on document analysis according to the present disclosure.

[0138] As illustrated in FIG. 8 (810), the processor (130) evaluates the importance of past documents to set priorities and controls the display (140) to display the set priorities.

[0139] Importance can be classified into very important, average, and not important.

[0140] Mark very important with two circles, average with one circle, and not important with an X.

[0141] The processor (130) determines the priority by considering at least one of the completion date, importance, and urgency.

[0142] The first priority is to identify the status of event customer claims.

[0143] The second priority is planning summer vacation events.

[0144] The third priority is determining the CRM analysis method.

[0145] FIG. 9 is a drawing illustrating an embodiment of extracting a deadline according to the present disclosure.

[0146] As illustrated in FIG. 9 (910), the processor (130) automatically extracts due date information from the content of past documents, sets reminder information based on the extracted due date information, and controls the display (140) to display the set reminder information.

[0147] The first deadline is December 05.

[0148] The second deadline is December 13.

[0149] The third deadline is December 21.

[0150] When the date comes, the processor (130) executes a reminder and displays the due date information on the calendar screen.

[0151] FIG. 10 is a drawing illustrating an embodiment showing the order of creation of documents according to the present disclosure.

[0152] As illustrated in FIG. 10 (1010), the processor (130) analyzes the creation order of related documents among past documents and performs a reminder based on the analysis results.

[0153] The first generated document is the AI ​​basic type planning document.

[0154] The second generated document is an AI basic type official document.

[0155] The third generated document is an AI basic press release.

[0156] The processor (130) analyzes the creation order of related documents among past documents in the order of the first created document, the second created document, and the third created document.

[0157] The processor (130) executes a reminder based on the analysis results.

[0158] FIG. 11 is a drawing illustrating an embodiment for identifying a key document according to the present disclosure.

[0159] As illustrated in FIG. 11 (1110), the processor (130) automatically identifies past documents that the user frequently accesses or has modified within a specified period, and selects the identified documents as handover results.

[0160] The document on the left is a past document that the user accessed and modified a specific number of times or more within a specified period.

[0161] The document on the right is a past document that the user has not accessed for 6 months.

[0162] The processor (130) identifies the left document as a document that the user frequently accesses or frequently modifies and selects it as a handover result.

[0163] FIG. 12 is a drawing illustrating an embodiment for visualizing a business network according to the present disclosure.

[0164] As illustrated in FIG. 12 (1210), the processor (130) analyzes the associations and collaboration patterns between documents, generates a visualized work network based on the analysis results, and controls the display to display the generated visualized work network.

[0165] For example, the processor (130) analyzes the associations and collaboration patterns between documents and creates a visualized work network based on the analysis results.

[0166] As a result of analyzing the relationships between documents and collaboration patterns within the organization, there are the Investigation and Analysis Team, Patent Team 1, Patent Team 2, Management Team, and Drawing Team.

[0167] The investigation and analysis team includes Jeong Mi-ae (Team Leader), Kim Yeon-ja, Kim Na-hee, and Jeong Da-kyung.

[0168] Patent Team 1 includes Kim OO (Team Leader), Hong O, Lee OO, and Song OO.

[0169] Patent Team 2 includes Kim OO (Team Leader), Im OO, Young O, and Jung OO.

[0170] The management team includes person Kang OO, and person Kang OO is connected to the team leader of the investigation and analysis team, Jung OO, the team leader of Patent Team 1, Kim OO, and the team leader of Patent Team 2, Kim OO.

[0171] The drawing team includes person Jang OO, and person Jang OO is connected to Kim OO, the team leader of Patent Team 1, and Kim OO, the team leader of Patent Team 2.

[0172] FIG. 13 is a drawing illustrating an embodiment of generating a knowledge map according to the present disclosure.

[0173] As illustrated in FIG. 13 (1310), the processor (130) generates a personalized knowledge map based on the user's document creation and access patterns and controls the display (140) to display the generated knowledge map.

[0174] For example, if the user's interest keyword is SEP and the KG related keyword is Platform, a personalized knowledge map is generated based on the user's previously created documents, attachments, and access patterns.

[0175] A knowledge map can perform the function of a dictionary.

[0176] It may include interpretations of words used by a specific department, words created by a specific department, and unique words.

[0177] Knowledge maps can be created in the form of one-year, six-month, or three-month intervals, or based on a specific individual's hiring date and resignation date, so that an individual can receive a handover.

[0178] For example, when User A joins the company, it becomes the starting reference point, and when User A leaves, it becomes the ending reference point.

[0179] If User A leaves the company, a knowledge map can be generated in the form of a summary of the work User A performed from the date of hiring to the date of resignation.

[0180] According to the present invention, when User A leaves the company, a summary of the work performed by User A is generated, making it easier to proceed with the handover of duties.

[0181] FIG. 14 is a drawing illustrating an embodiment of an adaptive handover system according to the present disclosure.

[0182] As illustrated in FIG. 14 (1410), the processor (130) compares and analyzes the work characteristics of the new department and the work patterns of existing users, automatically generates handover content based on the analysis results, and controls the display (140) to display the generated handover content.

[0183] For example, if a user moves from a conventional department to a new department, the processor (130) automatically generates handover details for the work methods of employee A, employee B, and employee C of the new department, taking into account the work characteristics of the new department.

[0184] The processor (130) can remind the user of the work methods of employee A, employee B, and employee C.

[0185] The processor (130) can remind you of a mixed work method that combines the work method of employee A, the work method of employee B, and the work method of employee C.

[0186] The user can select any one of the handover contents of Employee A's work style, Employee B's work style, Employee C's work style, or the mixed work style.

[0187] The aforementioned program may include code encoded in a computer language such as C, C++, JAVA, or machine language, which can be read by the computer's processor (CPU) through the computer's device interface, in order for the computer to read the program and execute the methods implemented in the program. Such code may include functional code related to functions that define the necessary functions for executing the methods, and may include control code related to execution procedures necessary for the computer's processor to execute the functions according to a predetermined procedure. Additionally, such code may further include memory reference code regarding where (address) additional information or media necessary for the computer's processor to execute the functions should be referenced in the computer's internal or external memory. In addition, if the processor of the computer needs to communicate with any other computer or server located remotely in order to execute the above functions, the code may further include communication-related code regarding how to communicate with any other computer or server located remotely using the communication module of the computer, and what information or media to transmit or receive during communication.

[0188] The above-mentioned storage medium refers to a medium that stores data semi-permanently and is readable by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specifically, examples of the above-mentioned storage medium include, but are not limited to, ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage device. That is, the above-mentioned program may be stored on various recording media on various servers that the computer can access, or on various recording media on the user's computer. Additionally, the above-mentioned medium may be distributed across networked computer systems, and computer-readable code may be stored in a distributed manner.

[0189] The steps of the method or algorithm described in connection with the embodiments of the present disclosure may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, a hard disk, a removable disk, a CD-ROM, or any form of computer-readable recording medium well known in the art to which the present disclosure belongs.

[0190] Although embodiments of the present disclosure have been described above with reference to the attached drawings, those skilled in the art will understand that the present disclosure may be implemented in other specific forms without altering its technical concept or essential features. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive.

Claims

In an in-institutional handover processing device using artificial intelligence, Input module for acquiring data; A communication module that transmits and receives the data to and from an external device; Memory that stores at least one process for performing an operation and stores user input and data; A display for displaying graphic images; and A processor that performs a control method according to the above process, comprising: The above processor is, First data including first electronic documents produced by each department and second electronic documents produced by individual users is obtained through an input module, and Preprocess the above first data, and The above-mentioned preprocessed first data is trained, and Create a handover processing model using the training results, and The request message is obtained through the above input module, and Using the above handover processing model, generate a handover result corresponding to the above request message, and The above display displays the handover results, and Evaluate the importance of past documents to set priorities, and display the set priorities through the display. Based on the aforementioned past documents, future documents and work plans are generated after a preset time has elapsed from the current point in time, and the future documents and work plans are displayed through the aforementioned display. Automatically identify past documents among the above past documents that the user has accessed or modified more than a certain number of times within a preset period, and select the identified past documents as handover results. Analyzes the correlations and collaboration patterns between documents, generates a visualized work network based on the analysis results, and Displaying the above-generated visualized business network through the above-mentioned display, Handover processing device. In claim 1, the processor, Analyze document creation cycles and patterns through time series analysis, and Controlling the above display to display the above document creation cycle and pattern, Handover processing device. In claim 1, the processor, Identify business areas by classifying documents based on their subject matter, and Controlling the above display to display the identified work area, Handover processing device. In claim 1, the processor, Automatically extract deadline information from the content of the aforementioned past documents, and Based on the above extracted due date information, set reminder information, and Controlling the above display to display the above-set reminder information, Handover processing device. In claim 1, the processor, Analyze the creation order of related documents among the aforementioned past documents, and Executing reminders based on the above analyzed results, Handover processing device. In a method for processing an in-institutional handover using artificial intelligence, performed by a device processor, A step of acquiring first data through an input module, including a first electronic document produced by each department and a second electronic document produced by an individual user; A step of preprocessing the above first data; A step of learning the above-mentioned preprocessed first data; Step of generating a handover processing model using the learning results; A step of obtaining a request message through the input module; A step of generating a handover result corresponding to the request message using the handover processing model above; and The method includes a step of controlling the display to display the handover result. The above processor is, Evaluate the importance of past documents to set priorities, and display the set priorities through the display. Based on the above past documents, future documents and work plans are generated after a predetermined period of time has elapsed from the current point in time, and the above future documents and work plans are displayed through the above display. Automatically identify documents among the aforementioned past documents that the user has accessed or modified more than a certain number of times within a preset period, and select the identified documents as handover results. Analyzes the correlations and collaboration patterns between documents, generates a visualized work network based on the analysis results, and displays the generated work network through the display. Handover processing method. In claim 6, the processor, Analyze document creation cycles and patterns through time series analysis, and Controlling the above display to display the above document creation cycle and pattern, Handover processing method. In claim 6, the processor is, Identify business areas by classifying documents based on their subject matter, and Controlling the above display to display the identified work area, Handover processing method. In claim 6, the processor, Automatically extract deadline information from the content of the aforementioned past documents, and Based on the above extracted due date information, set reminder information, and Controlling the above display to display the above-set reminder information, Handover processing method. In claim 6, the processor, Analyze the creation order of related documents among the aforementioned past documents, and Executing reminders based on the above analyzed results, Handover processing method.

Images