KR102596191B1 - Method for processing visualization of text based on artificial intelligence - Google Patents

Abstract

In accordance with some embodiments of the present disclosure, a method for processing text visualization performed by a computing device including at least one processor is disclosed. The method includes obtaining first text data of a first size unit, obtaining visualization options for the first text data, and obtaining linguistic features and latent features from the first text data. obtaining a ranking of the main text using a ranking model using the linguistic features and the latent features as input, and the visualization option, for displaying the first text data based on the ranking of the main text. It may include the step of generating visualization text data.

Description

How to process text visualization based on artificial intelligence {METHOD FOR PROCESSING VISUALIZATION OF TEXT BASED ON ARTIFICIAL INTELLIGENCE}

This disclosure relates to artificial intelligence technology, and more specifically, to a method of processing text visualization using artificial intelligence technology.

Modern society can be called a flood of information, and many documents containing a variety of information can be easily found. In order for users to quickly identify the information they need within a large amount of documents, a text visualization method that can improve the readability of the document is needed.

In addition, there is a need to change the way visualization is performed depending on the purpose of the user reading the text. Through text visualization, key parts are emphasized so that the user can quickly understand the information in the document according to the purpose, or the text is divided into appropriate units. Technology to divide and display is required.

Republic of Korea Patent Publication No. 10-2009-0083747 Republic of Korea Patent Publication No. 10-2022-0014569

This disclosure was developed in response to the above-described background technology, and is intended to provide visualization of text data to suit the user's desired purpose.

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

According to some embodiments of the present disclosure for solving the problems described above, a method performed by a computing device including at least one processor is disclosed.

The method includes obtaining first text data of a first size unit, obtaining visualization options for the first text data, and obtaining linguistic features and latent features from the first text data. Obtaining a ranking of the main text using a ranking model with the linguistic features and the latent features as input, and displaying the first text data based on the visualization option and the ranking of the main text. It may include the step of generating visualization text data for.

Alternatively, the first size unit may be a document that is a paragraph or collection of paragraphs.

Alternatively, the visualization option may include at least one value representing settings related to visualization processing units, number of key texts, or document format.

Alternatively, the visualization processing unit may mean a text segmentation unit that is the basis for analyzing the first text data, and may be morpheme-based, meaning-based, part-of-speech-based, grammar-based, sentence structure-based, or adjacent letters. It may be associated with at least one of the analysis methods based on the frequency of co-occurrence between characters.

Alternatively, the document format includes at least one of the width of the screen on which the entire text is displayed, font, font color, font size, thickness, inclination, blink, letter spacing, line spacing, and whether or not to break lines at each sentence. can do.

Alternatively, obtaining linguistic features and latent features from the first text data of the first size unit may include obtaining linguistic features and latent features from the first text data of the first size unit using a rule-based feature extraction model. Obtaining, performing preprocessing on the first text data of the first size unit, thereby generating second text data of a sentence unit, and third text data of a visualization processing unit, and a pre-trained language model. It may include obtaining latent features for the first text data, second text data, or third text data.

Alternatively, the linguistic features include text length information, difficulty information of words included in the text, topic information of words included in the text, rarity information of words included in the text, frequency of occurrence of the same word, included in the text. It may include at least one of the diversity of vocabulary and the complexity of syntactic structures.

Alternatively, the step of generating the third text data of the visualization processing unit may include generating second text data of a sentence unit by dividing the first text data of the first size unit, and It may include generating third text data of the visualization processing unit by performing morpheme-based, meaning-based, part-of-speech-based, grammar-based, sentence structure-based, or co-occurrence frequency-based tokenization between adjacent letters. there is.

Alternatively, the language model may take the first text data, second text data or third text data as input and output the latent features including topic information.

Alternatively, the ranking model may include extracting the ranking of the main text using linguistic features of the first text data and latent features of the second text data or the third text data. there is.

Alternatively, the ranking model includes extracting a rank of the main text based on the similarity of the latent features for the first text data and the latent features for the second text data or the third text data. can do.

Alternatively, the step of generating the visualization text data may include obtaining key text to which the document format is to be applied based on the ranking of the key text and the number of key texts, and adding key text to the key text in the first text data. It may include generating the visualized text data by applying the document format.

According to one embodiment, a computer program stored on a computer-readable storage medium is disclosed. When the computer program is executed by at least one processor, it can cause the at least one processor to perform a method for processing text visualization. The method includes obtaining first text data of a first size unit, obtaining visualization options for the first text data, obtaining linguistic features and latent features from the first text data, Obtaining a ranking of the main text using a ranking model using the linguistic features and the latent features as input, and visualizing text data for displaying first text data based on the visualization option and the ranking of the main text It may include the step of generating.

According to one embodiment, a computing device for processing text data including a storage unit and a processor is disclosed. The processor may be configured to: obtain first text data of a first size unit, obtain visualization options for the first text data, obtain linguistic features and latent features from the first text data, An operation of obtaining a ranking of a main text using linguistic features and a ranking model using the latent features as input, and visualizing text data for displaying first text data based on the visualization option and the ranking of the main text. You can perform creation operations.

Techniques according to some embodiments of the present disclosure can increase reading efficiency by performing visualization processing to help read text according to the user's purpose.

The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the description below. .

Various aspects will now be described with reference to the drawings, where like reference numerals are used to collectively refer to like elements. In the following examples, for purposes of explanation, numerous specific details are set forth to provide a comprehensive understanding of one or more aspects. However, it will be clear that such aspect(s) may be practiced without these specific details.
1 exemplarily illustrates a block diagram of a computing device according to some embodiments of the present disclosure.
Figure 2 is a schematic diagram showing network functions according to some embodiments of the present disclosure.
3 exemplarily illustrates a method for processing text visualization according to some embodiments of the present disclosure.
4 exemplarily illustrates operations of a computing device for processing text visualization according to some embodiments of the present disclosure.
Figure 5 exemplarily illustrates a method of entering visualization options according to some embodiments of the present disclosure.
6 exemplarily illustrates visualization text data generated according to some embodiments of the present disclosure.
Figure 7 depicts a brief, general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented.

Various embodiments are now described with reference to the drawings. In this specification, various descriptions are presented to provide an understanding of the disclosure. However, it is clear that these embodiments may be practiced without these specific descriptions.

As used herein, the terms “component,” “module,” “system,” and the like refer to a computer-related entity, hardware, firmware, software, a combination of software and hardware, or an implementation of software. For example, a component may be, but is not limited to, a process running on a processor, a processor, an object, a thread of execution, a program, and/or a computer. For example, both an application running on a computing device and the computing device can be a component. One or more components may reside within a processor and/or thread of execution. A component may be localized within one computer. A component may be distributed between two or more computers. Additionally, these components can execute from various computer-readable media having various data structures stored thereon. Components can transmit signals, for example, with one or more data packets (e.g., data and/or signals from one component interacting with other components in a local system, a distributed system, to other systems and over a network such as the Internet). Depending on the data being transmitted, they may communicate through local and/or remote processes.

Additionally, the term “or” is intended to mean an inclusive “or” and not an exclusive “or.” That is, unless otherwise specified or clear from context, “X utilizes A or B” is intended to mean one of the natural implicit substitutions. That is, either X uses A; X uses B; Or, if X uses both A and B, “X uses A or B” can apply to either of these cases. Additionally, the term “and/or” as used herein should be understood to refer to and include all possible combinations of one or more of the related listed items.

Additionally, the terms “comprise” and/or “comprising” should be understood to mean that the corresponding feature and/or element is present. However, the terms “comprise” and/or “comprising” should be understood as not excluding the presence or addition of one or more other features, elements and/or groups thereof. Additionally, unless otherwise specified or the context is clear to indicate a singular form, the singular terms herein and in the claims should generally be construed to mean “one or more.”

And, the term “at least one of A or B” should be interpreted to mean “a case containing only A,” “a case containing only B,” and “a case of combining A and B.”

Those skilled in the art will additionally recognize that the various illustrative logical blocks, components, modules, circuits, means, logic, and algorithm steps described in connection with the embodiments disclosed herein may be implemented using electronic hardware, computer software, or a combination of both. It must be recognized that it can be implemented with To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented in hardware or software will depend on the specific application and design constraints imposed on the overall system. A skilled technician can implement the described functionality in a variety of ways for each specific application. However, such implementation decisions should not be construed as causing a departure from the scope of the present disclosure.

The description of the presented embodiments is provided to enable anyone skilled in the art to use or practice the present invention. Various modifications to these embodiments will be apparent to those skilled in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the disclosure. Therefore, the present invention is not limited to the embodiments presented herein. The present invention is to be interpreted in the broadest scope consistent with the principles and novel features presented herein.

1 is a block diagram of a computing device 100 for processing text visualization according to an embodiment of the present disclosure. The computing device 100 may perform a method for processing text visualization based on an artificial neural network according to an embodiment of the present disclosure.

The configuration of the computing device 100 shown in FIG. 1 is only a simplified example. In one embodiment of the present disclosure, the computing device 100 may include different configurations for performing the computing environment of the computing device 100, and only some of the disclosed configurations may configure the computing device 100.

Computing device 100 in the present disclosure may refer to any type of device having processing capabilities. In one example, computing device 100 may be a server and/or a user terminal.

Computing device 100 may include any type of computer system or computer device, such as, for example, a microprocessor, mainframe computer, digital processor, portable device, or device controller. This computing device 100 may include any type of server and/or user terminal. For example, a user terminal may include a personal computer (PC), a notebook (note book), a mobile terminal, a smart phone, a tablet PC, etc. owned by the user. , may include all types of terminals that can access wired/wireless networks.

The computing device 100 may include a processor 110, a storage unit 120, and a communication unit 130.

Computing device 100 of the present disclosure can extract linguistic features from text data using a rule-based extraction model. For example, linguistic features include text length information, difficulty information of words included in the text, topic information of words included in the text, rarity information of words included in the text, frequency of occurrence of the same words, and information on the difficulty of words included in the text. It may include at least one of the diversity of vocabulary and the complexity of syntactic structure. A rule-based extraction model may refer to a model that includes an algorithm that extracts features according to predefined rules.

Computing device 100 of the present disclosure can generate latent features for text data using a language model. For example, latent features may include semantic features and/or grammatical features of the text. A language model may refer to a model that includes an artificial intelligence-based algorithm that can perform natural language processing.

The computing device 100 of the present disclosure can extract the ranking of key texts by division unit for text data using a ranking model. For example, the ranking of the main text may mean ranking information of important morphemes obtained as a result of analyzing the first text in paragraph units using a morpheme-based analysis method. The ranking model is a model that includes an artificial intelligence-based algorithm that can perform natural language processing. It takes linguistic features and latent features of a unit text as input, and calculates importance using linguistic features and latent features to determine importance. A rank listing unit text in order can be output. The detailed operation method of the ranking model will be described later.

The processor 110 may be composed of one or more cores, and may include a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. unit) may include any type of processor for data processing, data analysis, and/or deep learning. The processor 110 may read the computer program stored in the storage unit 120 and perform a text data processing method according to an embodiment of the present disclosure. According to an embodiment of the present disclosure, the processor 110 may perform an operation for learning a neural network. The processor 110 processes input data for learning in machine learning or deep learning (DL: preprocessing, such as noise removal and tokenization of input data), extracts features from input data, and calculates errors. , calculations for learning a neural network, such as updating the weights of the neural network using backpropagation, can be performed. At least one of the CPU, GPGPU, and TPU of the processor 110 may process learning of the network function. For example, CPU and GPGPU can work together to process learning of network functions and data classification using network functions. Additionally, in one embodiment of the present disclosure, the processors of a plurality of computing devices can be used together to process learning of network functions and data classification using network functions. Additionally, a computer program executed in the computing device 100 according to an embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program.

According to an embodiment of the present disclosure, the storage unit 120 may store any type of information generated or determined by the processor 110 and any type of information received by the communication unit 150. In the present disclosure, storage 120 may be used interchangeably with memory. For example, the storage unit 120 may store a pre-trained language model, a rule-based feature extraction model, and a ranking model.

According to an embodiment of the present disclosure, the storage unit 120 includes a flash memory type, a hard disk type, a multimedia card micro type, and a card type memory (e.g. For example, SD or It may include at least one type of storage medium among Read-Only Memory (Read-Only Memory), magnetic memory, magnetic disk, and optical disk. The computing device 100 may operate in connection with web storage that performs the storage function of the storage unit 120 on the Internet. The description of the storage unit 120 described above is merely an example, and the present disclosure is not limited thereto.

In FIG. 1, the storage unit 120 is shown as included within the computing device 100. However, depending on the implementation mode, the storage unit 120 exists outside the computing device 100 and is used through communication with the computing device 100. Data can also be exchanged.

The communication unit 130 according to an embodiment of the present disclosure may communicate with other computing devices of any type through a network. The network according to an embodiment of the present disclosure may include any wired or wireless communication network capable of transmitting and receiving arbitrary types of data and signals, etc., as expressed in the present disclosure.

Figure 2 is a schematic diagram showing a network function according to an embodiment of the present disclosure.

Throughout this specification, artificial intelligence-based model, artificial intelligence model, computational model, neural network, network function, and neural network may be used with the same meaning. For example, the language model and classification model in this disclosure may fall into the category of artificial intelligence-based models as above.

A neural network can generally consist of a set of interconnected computational units, which can be referred to as nodes. These nodes may also be referred to as neurons. A neural network consists of at least one node. Nodes (or neurons) that make up neural networks may be interconnected by one or more links.

Before input data is input into the input layer of the artificial intelligence model, preprocessing techniques according to an embodiment of the present disclosure may be performed. For example, the computing device 100 may perform a preprocessing operation to tokenize text data. As another example,

Within a neural network, one or more nodes connected through a link may form a relative input node and output node relationship. The concepts of input node and output node are relative, and any node in an output node relationship with one node may be in an input node relationship with another node, and vice versa. As described above, input node to output node relationships can be created around links. One or more output nodes can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of the data of the output node may be determined based on the data input to the input node. Here, the link connecting the input node and the output node may have a weight. Weights may be variable and may be varied by the user or algorithm in order for the neural network to perform the desired function. For example, when one or more input nodes are connected to one output node by respective links, the output node is set to the values input to the input nodes connected to the output node and the links corresponding to each input node. The output node value can be determined based on the weight.

As described above, in a neural network, one or more nodes are interconnected through one or more links to form an input node and output node relationship within the neural network. The characteristics of the neural network can be determined according to the number of nodes and links within the neural network, the correlation between the nodes and links, and the value of the weight assigned to each link. For example, if the same number of nodes and links exist and two neural networks with different weight values of the links exist, the two neural networks may be recognized as different from each other.

A neural network may consist of a set of one or more nodes. A subset of nodes that make up a neural network can form a layer. Some of the nodes constituting the neural network may form one layer based on the distances from the first input node. For example, a set of nodes with a distance n from the initial input node may constitute n layers. The distance from the initial input node can be defined by the minimum number of links that must be passed to reach the node from the initial input node. However, this definition of a layer is arbitrary for explanation purposes, and the order of a layer within a neural network may be defined in a different way than described above. For example, a layer of nodes may be defined by distance from the final output node.

The initial input node may refer to one or more nodes in the neural network through which data is directly input without going through links in relationships with other nodes. Alternatively, in a neural network network, in the relationship between nodes based on links, it may mean nodes that do not have other input nodes connected by links. Similarly, the final output node may refer to one or more nodes that do not have an output node in their relationship with other nodes among the nodes in the neural network. Additionally, hidden nodes may refer to nodes constituting a neural network other than the first input node and the last output node.

The neural network according to an embodiment of the present disclosure is a neural network in which the number of nodes in the input layer may be the same as the number of nodes in the output layer, and the number of nodes decreases and then increases again as it progresses from the input layer to the hidden layer. You can. In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer may be less than the number of nodes in the output layer, and the number of nodes decreases as it progresses from the input layer to the hidden layer. there is. In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer may be greater than the number of nodes in the output layer, and the number of nodes increases as it progresses from the input layer to the hidden layer. You can. A neural network according to another embodiment of the present disclosure may be a neural network that is a combination of the above-described neural networks.

A deep neural network (DNN) may refer to a neural network that includes multiple hidden layers in addition to the input layer and output layer. Deep neural networks allow you to identify latent structures in data. That is, the potential structure of photos, text, video, audio, text data of speech, music (e.g., what objects are in the photo, what are the content and emotions of the text, what are the contents and emotions of the speech, etc.) ) can be identified. Deep neural networks include convolutional neural networks (CNN), recurrent neural networks (RNN), auto encoders, generative adversarial networks (GAN), and restricted Boltzmann machines (RBM). machine), deep belief network (DBN), Q network, U network, Siamese network, Generative Adversarial Network (GAN), etc. The description of the deep neural network described above is only an example and the present disclosure is not limited thereto.

For example, the ranking model in one embodiment of the present disclosure may include a multi-perceptron-based artificial intelligence model. As described above, the multi-perceptron-based ranking model may include an input layer, hidden layers, and an output layer. For example, a multi-perceptron-based ranking model may include an input layer including input neurons that can receive linguistic features and latent features, a plurality of hidden layers, and an output layer that outputs rankings of key texts.

In one embodiment of the present disclosure, the network function may include an autoencoder. An autoencoder may be a type of artificial neural network to output output data similar to input data. The autoencoder may include at least one hidden layer, and an odd number of hidden layers may be placed between input and output layers. The number of nodes in each layer may be reduced from the number of nodes in the input layer to an intermediate layer called the bottleneck layer (encoding), and then expanded symmetrically and reduced from the bottleneck layer to the output layer (symmetrical to the input layer). Autoencoders can perform nonlinear dimensionality reduction. The number of input layers and output layers can be corresponded to the dimension after preprocessing of the input data. In an auto-encoder structure, the number of nodes in the hidden layer included in the encoder may have a structure that decreases as the distance from the input layer increases. If the number of nodes in the bottleneck layer (the layer with the fewest nodes located between the encoder and decoder) is too small, not enough information may be conveyed, so if it is higher than a certain number (e.g., more than half of the input layers, etc.) ) may be maintained.

A neural network may be trained in at least one of supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. Learning of a neural network may be a process of applying knowledge for the neural network to perform a specific operation to the neural network.

Neural networks can be trained to minimize output errors. In neural network learning, learning data is repeatedly input into the neural network, the output of the neural network and the error of the target for the learning data are calculated, and the error of the neural network is transferred from the output layer of the neural network to the input layer in the direction of reducing the error. This is the process of updating the weight of each node in the neural network through backpropagation. In the case of teacher learning, learning data in which the correct answer is labeled in each learning data is used (i.e., labeled learning data), and in the case of non-teacher learning, the correct answer may not be labeled in each learning data. That is, for example, in the case of teacher learning regarding data classification, the learning data may be data in which each learning data is labeled with a category. Labeled training data is input to the neural network, and the error can be calculated by comparing the output (category) of the neural network with the label of the training data. As another example, in the case of non-teachable learning for data classification, the error can be calculated by comparing the input training data with the neural network output. The calculated error is backpropagated in the reverse direction (i.e., from the output layer to the input layer) in the neural network, and the connection weight of each node in each layer of the neural network can be updated according to backpropagation. The amount of change in the connection weight of each updated node may be determined according to the learning rate. The neural network's calculation of input data and backpropagation of errors can constitute a learning cycle (epoch). The learning rate may be applied differently depending on the number of repetitions of the learning cycle of the neural network. For example, in the early stages of neural network training, a high learning rate can be used to increase efficiency by allowing the neural network to quickly achieve a certain level of performance, and in the later stages of training, a low learning rate can be used to increase accuracy.

In the learning of neural networks, the training data can generally be a subset of real data (i.e., the data to be processed using the learned neural network), and thus the error for the training data is reduced, but the error for the real data is reduced. There may be an incremental learning cycle. Overfitting is a phenomenon in which errors in actual data increase due to excessive learning on training data. For example, a phenomenon in which a neural network that learned a cat by showing a yellow cat fails to recognize that it is a cat when it sees a non-yellow cat may be a type of overfitting. Overfitting can cause errors in machine learning algorithms to increase. To prevent such overfitting, various optimization methods can be used. To prevent overfitting, methods such as increasing the learning data, regularization, dropout to disable some of the network nodes during the learning process, and use of a batch normalization layer can be applied. You can.

A computer-readable medium storing a data structure according to an embodiment of the present disclosure is disclosed.

Data structure can refer to the organization, management, and storage of data to enable efficient access and modification of data. Data structure can refer to the organization of data to solve a specific problem (e.g., retrieving data, storing data, or modifying data in the shortest possible time). A data structure may be defined as a physical or logical relationship between data elements designed to support a specific data processing function. Logical relationships between data elements may include connection relationships between user-defined data elements. Physical relationships between data elements may include actual relationships between data elements that are physically stored in a computer-readable storage medium (e.g., a persistent storage device). A data structure may specifically include a set of data, relationships between data, and functions or instructions applicable to the data. Effectively designed data structures allow computing devices to perform computations while minimizing the use of the computing device's resources. Specifically, computing devices can increase the efficiency of operations, reading, insertion, deletion, comparison, exchange, and search through effectively designed data structures.

Data structures can be divided into linear data structures and non-linear data structures depending on the type of data structure. A linear data structure may be a structure in which only one piece of data is connected to another piece of data. Linear data structures may include List, Stack, Queue, and Deque. A list can refer to a set of data that has an internal order. The list may include a linked list. A linked list may be a data structure in which data is connected in such a way that each data is connected in a single line with a pointer. In a linked list, a pointer may contain connection information to the next or previous data. Depending on its form, a linked list can be expressed as a singly linked list, a doubly linked list, or a circularly linked list. A stack may be a data listing structure that allows limited access to data. A stack can be a linear data structure in which data can be processed (for example, inserted or deleted) at only one end of the data structure. Data stored in the stack may have a data structure (LIFO-Last in First Out) where the later it enters, the sooner it comes out. A queue is a data listing structure that allows limited access to data. Unlike the stack, it can be a data structure (FIFO-First in First Out) where data stored later is released later. A deck can be a data structure that can process data at both ends of the data structure.

A non-linear data structure may be a structure in which multiple pieces of data are connected behind one piece of data. Nonlinear data structures may include graph data structures. A graph data structure can be defined by vertices and edges, and an edge can include a line connecting two different vertices. Graph data structure may include a tree data structure. A tree data structure may be a data structure in which there is only one path connecting two different vertices among a plurality of vertices included in the tree. In other words, it may be a data structure that does not form a loop in the graph data structure.

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. Below, it is described in a unified manner as a neural network. Data structures may include neural networks. And the data structure including the neural network may be stored in a computer-readable medium. Data structures including neural networks also include data preprocessed for processing by a neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data acquired from the neural network, activation functions associated with each node or layer of the neural network, neural network It may include a loss function for learning. A data structure containing a neural network may include any of the components disclosed above. In other words, the data structure including the neural network includes preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data acquired from the neural network, activation functions associated with each node or layer of the neural network, neural network It may be configured to include all or any combination of the loss function for learning. In addition to the configurations described above, a data structure containing a neural network may include any other information that determines the characteristics of the neural network. Additionally, the data structure may include all types of data used or generated in the computational process of a neural network and is not limited to the above. Computer-readable media may include computer-readable recording media and/or computer-readable transmission media. A neural network can generally consist of a set of interconnected computational units, which can be referred to as nodes. These nodes may also be referred to as neurons. A neural network consists of at least one node.

The data structure may include data input to the neural network. For example, the data structure may include data obtained as a result of one-hot encoding. A data structure containing data input to a neural network may be stored in a computer-readable medium. Data input to the neural network may include learning data input during the neural network learning process and/or input data input to the neural network on which training has been completed. Data input to the neural network may include data that has undergone pre-processing and/or data subject to pre-processing. Preprocessing may include a data processing process to input data into a neural network. Therefore, the data structure may include data subject to preprocessing and data generated by preprocessing. The above-described data structure is only an example and the present disclosure is not limited thereto.

The data structure may include the weights of the neural network. (In this specification, weights and parameters may be used with the same meaning.) And the data structure including the weights of the neural network may be stored in a computer-readable medium. A neural network may include multiple weights. Weights may be variable and may be varied by the user or algorithm in order for the neural network to perform the desired function. For example, when one or more input nodes are connected to one output node by respective links, the output node is set to the values input to the input nodes connected to the output node and the links corresponding to each input node. Based on the weight, the data value output from the output node can be determined. The above-described data structure is only an example and the present disclosure is not limited thereto.

As an example and not a limitation, the weights may include weights that are changed during the neural network learning process and/or weights for which neural network learning has been completed. Weights that change during the neural network learning process may include weights that change at the start of the learning cycle and/or weights that change during the learning cycle. Weights for which neural network training has been completed may include weights for which a learning cycle has been completed. Therefore, the data structure including the weights of the neural network may include weights that are changed during the neural network learning process and/or the data structure including the weights for which neural network learning has been completed. Therefore, the above-mentioned weights and/or combinations of each weight are included in the data structure including the weights of the neural network. The above-described data structure is only an example and the present disclosure is not limited thereto.

The data structure including the weights of the neural network may be stored in a computer-readable storage medium (e.g., memory, hard disk) after going through a serialization process. Serialization can be the process of converting a data structure into a form that can be stored on the same or a different computing device and later reorganized and used. Computing devices can transmit and receive data over a network by serializing data structures. Data structures containing the weights of a serialized neural network can be reconstructed on the same computing device or on a different computing device through deserialization. The data structure including the weights of the neural network is not limited to serialization. Furthermore, the data structure including the weights of the neural network is a data structure to increase computational efficiency while minimizing the use of computing device resources (e.g., in non-linear data structures, B-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree) may be included. The foregoing is merely an example and the present disclosure is not limited thereto.

The data structure may include hyper-parameters of a neural network. And the data structure including the hyperparameters of the neural network can be stored in a computer-readable medium. A hyperparameter may be a variable that can be changed by the user. Hyperparameters include, for example, learning rate, cost function, number of learning cycle repetitions, weight initialization (e.g., setting the range of weight values subject to weight initialization), Hidden Unit. It may include a number (e.g., number of hidden layers, number of nodes in hidden layers). The above-described data structure is only an example and the present disclosure is not limited thereto.

3 exemplarily illustrates a method for processing text visualization according to some embodiments of the present disclosure. In the present disclosure, text visualization may refer to the process of analyzing text into specific units to help convey the meaning of text data and generating visualization text with the document format changed according to visualization options. The flowchart shown in FIG. 3 is shown for illustrative purposes, and additional steps may be present or some of the steps included in the flowchart shown in FIG. 3 may be excluded.

The method of FIG. 3 may be performed, for example, by computing device 100 of the present disclosure. According to an embodiment of the present disclosure, a computing device may include obtaining first text data of a first size unit (310). In the present disclosure, the first size unit may be a paragraph or a document that is a collection of paragraphs.

According to an embodiment of the present disclosure, the computing device 100 may obtain a visualization option for the first text data (320). In the present disclosure, visualization options may include at least one value representing settings related to visualization processing units, document formats, or the number of key texts. In the present disclosure, the visualization processing unit may mean a text segmentation unit that is the basis for analyzing the first text data. For example, as a method of analyzing the first text data, morpheme-based, meaning-based, part-of-speech-based, grammar-based, sentence structure-based, or co-occurrence frequency-based analysis methods between adjacent characters may be used, and visualization processing may be used. The unit can be used as a means of determining the text analysis method described above. In the present disclosure, document format may mean information related to the format of text that can be changed to generate visualization text. For example, the document format may include at least one of the following: width of the screen on which the entire text is displayed, font, font color, font size, thickness, slant, blink, character spacing, line spacing, and whether or not to break lines at each sentence level. You can. In the present disclosure, the number of main texts can be used to determine the number of texts to change the document format according to the main text ranking, which will be described later.

According to one embodiment of the present disclosure, computing device 100 may obtain linguistic features and latent features from first text data (330). In one embodiment, linguistic features are feature information output by a rule-based feature extraction model, and may refer to information used to determine keywords related to topic information of first text data. For example, the output values that can be obtained from a rule-based feature extraction model include text length information, difficulty information of words included in the text, topic information of words included in the text, rarity information of words included in the text, and It may include at least one of the frequency of appearance, the diversity of vocabulary included in the text, and the complexity of the syntactic structure. In addition, excluding parts that only perform grammatical functions by distinguishing particles or endings, text data of the first 1, 2, or 3 syllables following a morpheme, part of speech, or space containing meaning can be extracted as linguistic features.

For example, the rule-based feature extraction model includes average paragraph length (number of sentences/number of paragraphs), average sentence length (number of words/number of sentences), average word length (number of characters/number of words), ratio of Chinese characters, ratio of connotative words, Proportion of demonstrative words, personal noun ratio, semantic tree of the paragraph (sentence level), word difficulty, repetition of the same word, number of uses of particles, specific classification according to subject classification in the dictionary (e.g. subjects such as art, music, science, etc.) One or more features of text data, such as the number of occurrences of a word, can be extracted. For example, a semantic tree may include that the second and third sentences are a structure that modifies the first sentence, and the fifth sentence supports the argument of the second sentence. For example, the difficulty level of a word may include information indicating how rare the words that appear in text data are on average. The features of text data extracted by the above-described rule-based feature extraction model are examples, and linguistic features of various types of text data within the scope of the present disclosure can be extracted.

In this way, the computing device 100 can extract linguistic features for text data using a rule-based feature extraction model, and use the extracted linguistic features as input to the ranking model to obtain key text rankings. there is.

In one embodiment of the present disclosure, a latent feature may mean a value representing text data as a vector in a latent space related to topic information. In one embodiment, latent features may be obtained through output values of a pre-trained language model that uses text data as input.

According to one embodiment of the present disclosure, computing device 100 may obtain the ranking of key texts using a ranking model (340). The ranking model uses linguistic features and latent features as input, and the ranking model can be used to extract the ranking of key texts by division unit for text data. For example, the ranking of key texts may mean ranking information of key text units obtained as a result of analyzing the first text in paragraph units as a visualization processing unit.

By way of example, the visualization processing unit may be a morpheme unit. The rule-based feature extraction model and language model can divide the first text data into morpheme units, use the preprocessed third text data as input, and obtain linguistic features and latent features for each morpheme. Additionally, the ranking model can take linguistic features and potential features of morphemes as input and output rankings for major morphemes. Specifically, the ranking model can calculate the importance of the input morpheme through comparison of the potential features of the morpheme and linguistic features (e.g., topic information of words included in the text, frequency of occurrence of the same word, etc.), By repeating the above process for all morphemes in the text, major morphemes can be ranked based on importance.

As another example, the ranking model can calculate importance based on similarity by comparing the potential features of the first text data with the potential features of the third text data, and repeating the above process for all morphemes in the text. , major morphemes can be ranked based on importance. Since the above example is an example of the process of obtaining the main morpheme ranking according to the morpheme-based analysis method, it is possible to obtain the main text ranking for another text unit by changing the visualization processing unit.

According to an embodiment of the present disclosure, the computing device 100 may generate visualization text data for displaying the first text data based on visualization options and rankings of key texts (350). The step of generating visualization data may include obtaining key text to which document formatting is to be applied based on the ranking and visualization options of the key text, and applying the document format to the key text portion within the first text. In one embodiment, the step of obtaining key text to which document formatting is to be applied may include determining the target text to which document formatting will be changed by referring to the number of key texts among visualization options. The process of determining the target text may include sequentially selecting the text at the top of the key text ranks obtained from the ranking model as the target text, and determining the key text by repeating this process as many times as the number of key texts in the visualization option. You can. In one embodiment, applying a document format may include changing attribute information of the main text. The document format may be part of the visualization options, such as the width of the screen on which the entire text is displayed, font, font color, font size, thickness, inclination, blink, letter spacing, line spacing, and whether or not to break lines at each sentence. This may refer to settings related to text attribute information.

FIG. 4 illustratively illustrates operations of computing device 100 for processing visualization of text data according to some embodiments of the present disclosure.

As shown in FIG. 4, first text data 410 may be input as a user input. The first text data 410 may be divided into sentence units and converted into second text data 420. Additionally, the second text data 420 may be divided into visualization processing units through a tokenization process and converted into third text data 430.

The visualization processing unit may refer to a text division unit that is the basis for analyzing the first text data. For example, as a method of analyzing the first text data, a morpheme-based, meaning-based, part-of-speech-based, grammar-based, sentence structure-based, or co-occurrence frequency-based analysis method between adjacent letters may be used, and the visualization processing unit is as described above. It can be used as a means to decide on a text analysis method.

As an example, an analysis method based on the frequency of co-occurrence between adjacent letters can be used as a method to find parts of speech or morphemes, using spacing information, which is a characteristic of the Korean language. More specifically, in Korean, when a sentence is divided into spacing units, the characteristic that it consists of a permutation of 'semantic words' and 'grammatical words' can be used. For example, the text with the first unit size of "Sagaga" can be cut into various ways such as 'Sa', 'Gwaga' or 'Appa', 'Ga' and diagrammed in a table, called 'Sa'. If there are more words written with 'apple' than written words, 'apple' can be recognized as a 'semantic word'. Likewise, if 'ga' is used more than 'gwa-ga', it can be recognized as the main 'grammatical word'. The ‘semantic words’ and ‘grammatical words’ recognized in this way can be used to distinguish part-of-speech information.

In one embodiment, the first text data may be input to the rule-based feature extraction model 400A to output linguistic features 415. The linguistic features 415 output as a result of the rule-based feature extraction model 400A include text length information, difficulty information of words included in the text, topic information of words included in the text, and rarity information of words included in the text. , it may include at least one of the frequency of occurrence of the same word, the diversity of vocabulary included in the text, and the complexity of the syntactic structure. In addition, excluding parts that only perform grammatical functions by distinguishing particles or endings, text data of the first 1, 2, or 3 syllables following a morpheme, part of speech, or space containing meaning can be extracted as linguistic features.

In one embodiment, the language model 400B may use first, second, or third text data as input, and may use latent features 425 for each text data as output. In one embodiment of the present disclosure, the latent feature 425 may mean a value representing text data as a vector in a latent space related to topic information. In one embodiment, the latent features 425 may be obtained through the output value of a pre-trained language model that uses text data as input.

In one embodiment, the ranking model 400C takes linguistic features 415 and latent features 425 as input, and obtains the ranking of key texts as a result of the model. As an example, part-of-speech information among linguistic features 415 may be used as a weight to determine importance in the ranking model 400C. Specifically, since 'semantic words' are more likely to be related to the topic, greater weight is placed on 'semantic words' than 'grammatical words' parts of speech, so that 'semantic words' are ranked higher in the ranking model (400C). It can be set high.

In one embodiment, extracting the ranking of key texts may include ranking model 400C using linguistic features 415 and latent features 425 together. By way of example, the ranking model 400C compares the latent features of the unit text divided into visualization text units and linguistic features (e.g., topic information of words included in the text, frequency of occurrence of the same word, etc.) The importance of the input unit text can be calculated, and by repeating the above process for all unit texts for the text, major unit texts can be ranked based on importance.

In another embodiment, extracting the ranking of key texts may include ranking model 400C performing a comparison between latent features 425. Importance can be calculated based on similarity by comparing the potential features of the first text data with the potential features of the unit text of the visualization text unit, and by repeating the above process for all unit texts, the main unit text is determined based on the importance. can be ranked.

In one embodiment, the step of generating visualization text data may use the results of the visualization option 440 and the ranking model 400C. The ranking model (400C) refers to the value of the number of key texts among the visualization options (440), so that the data at the top of the key text ranking can be selected as key text, and the visualization text can be created by applying document format to the selected key text. Data 450 may be generated.

Figure 5 is an embodiment of an input window for obtaining visualization options according to the present disclosure, including an input bar 510 for entering the number or ratio of key words to be highlighted, and an input bar 510 for entering the number or ratio of key sentences to be highlighted. It may include an input bar 520, a selection window 530 for inputting whether or not to output in major units, and a text input window 540. FIG. 5 is an example rather than a limitation on the method of obtaining visualization options by the user, and the method of acquiring visualization options is not limited to the method shown in FIG. 5 . That is, visualization options may be acquired by the user, but may also be obtained in other ways.

In one embodiment, the user can adjust the number of key texts in the visualization options by adjusting the input bar 510 for entering the number or ratio of key texts to be highlighted. In this embodiment, by changing the visualization options, the user can create visualization text data to suit the purpose of reading the text.

For example, the user can increase the number or ratio value for key words among the visualization options by increasing the number or ratio in the input bar 510. Increasing the value of the visualization option can increase the number of key texts emphasized in the visualization text data creation process, and this method can help with thorough reading.

As another example, the user may reduce the value of the number or ratio of key texts among the visualization options by lowering the number or ratio in the input bar 510. Reducing the value of the visualization option can reduce the number of key texts emphasized in the visualization text data creation process, and this method can help with quick skimming reading.

In one embodiment, the user can adjust the number of key sentences in the visualization options by adjusting the input bar 520 for entering the number or ratio of key sentences to be highlighted. In this embodiment, by changing the visualization options, the user can create visualization text data to suit the purpose of reading the text.

For example, the user can increase the number or ratio value for main sentences among the visualization options by increasing the number or ratio in the input bar 520. Increasing the value of the visualization option can increase the number of key sentences emphasized in the visualization text data generation process, and this method can help with thorough reading.

As another example, the user can reduce the number or ratio value for main sentences among the visualization options by lowering the number or ratio in the input bar 520. Reducing the value of the visualization option can reduce the number of key sentences emphasized during the visualization text data generation process, and this method can help with quick skimming reading.

In one embodiment, the user can input whether to output by breaking into major units in the selection window 530 where the user inputs whether to output by breaking into major units. For example, if whether to output by breaking each main unit is set to True, whether to break lines at a sentence level among the visualization options can be set to True. And when it is set to perform sentence-level line breaks, in the visualization text creation process, based on the second text data where the first text data in paragraph units is divided into sentences, a line break symbol is inserted after the sentence to generate visualization text data. It may include steps.

In one embodiment, the user may input text data to create a visualization text into the text input window 540. In one embodiment, the text entered into the text input window 540 may be used as first text data in the visualization text data generation process.

FIG. 6 is an example rather than a limitation regarding the visualization text output window that can be created according to the present disclosure, and the visualization text data 600 shows an embodiment showing the result of applying a document format to main text. As an example, sentences selected as main sentences in the analysis results of the first text data may be displayed with an underline applied to the document format (601). Words selected as key words may be displayed in bold (602) in the document format. Additionally, words with high priority among key words may be displayed with an emphasis color applied (603).

The key sentences or key words can be obtained through linguistic features or latent features acquired in the previous step. As an example, the importance of conjunctions throughout the document can be evaluated highly because they help to understand the logical flow by understanding the connection structure between sentences. Therefore, in the case of text determined to be a conjunction in part-of-speech information among linguistic features, it can be highlighted by increasing its importance so that it has a high rank in the ranking model.

The creation of visualized text data is not limited to the content shown in FIG. 6, and can be created in various ways by applying settings related to document format among visualization options. As another example, the document format may include the width of the screen on which the entire text is displayed, font, font color, font size, thickness, slant, blinking, letter spacing, line spacing, and whether or not line breaks occur at each sentence level.

Visualization options are values related to settings for outputting text according to the user's purpose of reading the text, and visualization options can be changed depending on the purpose of reading the text. For example, in order to read the text thoroughly, by excluding parts of speech that perform grammatical functions and highlighting meaningful words or morphemes by adjusting the thickness, italics, or underlining, the entire text can be quickly collected to convey effective data. You can check it.

As another example, if you want to quickly read a text, you can highlight keywords that are highly related to the topic rather than the entire morpheme by blinking so that you can see them at a glance, thereby encouraging you to read only the part related to the topic rather than the entire text. You can understand the content of the text.

Figure 7 depicts a brief, general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented.

Although the present disclosure has generally been described above as being capable of being implemented by a computing device, those skilled in the art will understand that the present disclosure can be implemented in combination with computer-executable instructions and/or other program modules that can be executed on one or more computers and/or in hardware and software. It will be well known that it can be implemented as a combination.

Typically, program modules include routines, programs, components, data structures, etc. that perform specific tasks or implement specific abstract data types. Additionally, those skilled in the art will understand that the methods of the present disclosure are applicable to single-processor or multiprocessor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, etc. It will be appreciated that each of these may be implemented in other computer system configurations, including those capable of operating in conjunction with one or more associated devices.

The described embodiments of the disclosure can also be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

Computers typically include a variety of computer-readable media. Computer-readable media can be any medium that can be accessed by a computer, and such computer-readable media includes volatile and non-volatile media, transitory and non-transitory media, removable and non-transitory media. Includes removable media. By way of example, and not limitation, computer-readable media may include computer-readable storage media and computer-readable transmission media. Computer-readable storage media refers to volatile and non-volatile media, transient and non-transitory media, removable and non-removable, implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Includes media. Computer readable storage media may include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage. This includes, but is not limited to, a device, or any other medium that can be accessed by a computer and used to store desired information.

A computer-readable transmission medium typically implements computer-readable instructions, data structures, program modules, or other data on a modulated data signal, such as a carrier wave or other transport mechanism. Includes all information delivery media. The term modulated data signal refers to a signal in which one or more of the characteristics of the signal have been set or changed to encode information within the signal. By way of example, and not limitation, computer-readable transmission media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above are also intended to be included within the scope of computer-readable transmission media.

An example environment 1100 is shown that implements various aspects of the present disclosure, including a computer 1102, which includes a processing unit 1104, a system memory 1106, and a system bus 1108. do. System bus 1108 couples system components, including but not limited to system memory 1106, to processing unit 1104. Processing unit 1104 may be any of a variety of commercially available processors. Dual processors and other multiprocessor architectures may also be used as processing unit 1104.

System bus 1108 may be any of several types of bus structures that may further be interconnected to a memory bus, peripheral bus, and local bus using any of a variety of commercial bus architectures. System memory 1106 includes read only memory (ROM) 1110 and random access memory (RAM) 1112. The basic input/output system (BIOS) is stored in non-volatile memory 1110, such as ROM, EPROM, and EEPROM, and is a basic input/output system that helps transfer information between components within the computer 1102, such as during startup. Contains routines. RAM 1112 may also include high-speed RAM, such as static RAM, for caching data.

Computer 1102 may also include an internal hard disk drive (HDD) 1114 (e.g., EIDE, SATA)—the internal hard disk drive 1114 may also be configured for external use within a suitable chassis (not shown). Yes - a magnetic floppy disk drive (FDD) 1116 (e.g., for reading from or writing to a removable diskette 1118), and an optical disk drive 1120 (e.g., a CD-ROM for reading the disk 1122 or reading from or writing to other high-capacity optical media such as DVDs). Hard disk drive 1114, magnetic disk drive 1116, and optical disk drive 1120 are connected to system bus 1108 by hard disk drive interface 1124, magnetic disk drive interface 1126, and optical drive interface 1128, respectively. ) can be connected to. The interface 1124 for implementing an external drive includes at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

These drives and their associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, and the like. For computer 1102, drive and media correspond to storing any data in a suitable digital format. Although the description of computer-readable media above refers to removable optical media such as HDDs, removable magnetic disks, and CDs or DVDs, those skilled in the art will also recognize removable optical media such as zip drives, magnetic cassettes, flash memory cards, cartridges, etc. It will be appreciated that other types of computer-readable media, such as the like, may also be used in the example operating environment and that any such media may contain computer-executable instructions for performing the methods of the present disclosure.

A number of program modules may be stored in drives and RAM 1112, including an operating system 1130, one or more application programs 1132, other program modules 1134, and program data 1136. All or portions of the operating system, applications, modules and/or data may also be cached in RAM 1112. It will be appreciated that the present disclosure may be implemented on various commercially available operating systems or combinations of operating systems.

A user may enter commands and information into computer 1102 through one or more wired/wireless input devices, such as a keyboard 1138 and a pointing device such as mouse 1140. Other input devices (not shown) may include microphones, IR remote controls, joysticks, game pads, stylus pens, touch screens, etc. These and other input devices are connected to the processing unit 1104 through an input device interface 1142, which is often connected to the system bus 1108, but may also include a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, It can be connected by other interfaces, etc.

A monitor 1144 or other type of display device is also connected to system bus 1108 through an interface, such as a video adapter 1146. In addition to monitor 1144, computers typically include other peripheral output devices (not shown) such as speakers, printers, etc.

Computer 1102 may operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) 1148, via wired and/or wireless communications. Remote computer(s) 1148 may be a workstation, computing device computer, router, personal computer, portable computer, microprocessor-based entertainment device, peer device, or other conventional network node, and is generally connected to computer 1102. For simplicity, only memory storage device 1150 is shown, although it includes many or all of the components described. The logical connections depicted include wired/wireless connections to a local area network (LAN) 1152 and/or a larger network, such as a wide area network (WAN) 1154. These LAN and WAN networking environments are common in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which can be connected to a worldwide computer network, such as the Internet.

When used in a LAN networking environment, computer 1102 is connected to local network 1152 through wired and/or wireless communication network interfaces or adapters 1156. Adapter 1156 may facilitate wired or wireless communication to LAN 1152, which also includes a wireless access point installed thereon for communicating with wireless adapter 1156. When used in a WAN networking environment, the computer 1102 may include a modem 1158 or be connected to a communicating computing device on the WAN 1154 or to establish communications over the WAN 1154, such as over the Internet. Have other means. Modem 1158, which may be internal or external and a wired or wireless device, is coupled to system bus 1108 via serial port interface 1142. In a networked environment, program modules described for computer 1102, or portions thereof, may be stored in remote memory/storage device 1150. It will be appreciated that the network connections shown are exemplary and that other means of establishing a communications link between computers may be used.

Computer 1102 may be associated with any wireless device or object deployed and operating in wireless communications, such as a printer, scanner, desktop and/or portable computer, portable data assistant (PDA), communications satellite, wirelessly detectable tag. Performs actions to communicate with any device or location and telephone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, communication may be a predefined structure as in a conventional network or may simply be ad hoc communication between at least two devices.

Wi-Fi (Wireless Fidelity) allows connection to the Internet, etc. without wires. Wi-Fi is a wireless technology, like cell phones, that allows these devices, such as computers, to send and receive data indoors and outdoors, anywhere within the coverage area of a base station. Wi-Fi networks use wireless technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, the Internet, and wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in the unlicensed 2.4 and 5 GHz wireless bands, for example, at data rates of 11 Mbps (802.11a) or 54 Mbps (802.11b), or in products that include both bands (dual band). .

Those skilled in the art will understand that information and signals may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols and chips that may be referenced in the above description include voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields. It can be expressed by particles or particles, or any combination thereof.

Those skilled in the art will understand that the various illustrative logical blocks, modules, processors, means, circuits and algorithm steps described in connection with the embodiments disclosed herein may be used in electronic hardware, (for convenience) It will be understood that it may be implemented by various forms of program or design code (referred to herein as software) or a combination of both. To clearly illustrate this interoperability of hardware and software, various illustrative components, blocks, modules, circuits and steps have been described above generally with respect to their functionality. Whether this functionality is implemented as hardware or software depends on the specific application and design constraints imposed on the overall system. A person skilled in the art of this disclosure may implement the described functionality in various ways for each specific application, but such implementation decisions should not be construed as departing from the scope of this disclosure.

The various embodiments presented herein may be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques. The term article of manufacture includes a computer program, carrier, or media accessible from any computer-readable storage device. For example, computer-readable storage media include magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CDs, DVDs, etc.), smart cards, and flash. Includes, but is not limited to, memory devices (e.g., EEPROM, cards, sticks, key drives, etc.). Additionally, various storage media presented herein include one or more devices and/or other machine-readable media for storing information.

It is to be understood that the specific order or hierarchy of steps in the processes presented is an example of illustrative approaches. It is to be understood that the specific order or hierarchy of steps in processes may be rearranged within the scope of the present disclosure, based on design priorities. The appended method claims present elements of the various steps in a sample order but are not meant to be limited to the particular order or hierarchy presented.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments without departing from the scope of the disclosure. Thus, the present disclosure is not limited to the embodiments presented herein but is to be interpreted in the broadest scope consistent with the principles and novel features presented herein.

Claims (14)

A method of visualizing text according to a user's reading purpose performed by a computing device including at least one processor, comprising:
Obtaining first text data of a first size unit;
Obtaining visualization options for the first text data;
acquiring linguistic features obtained by inputting the first text data into a rule-based feature extraction model and latent features obtained by vectorizing the first text data;
Obtaining a ranking of key texts using a ranking model using the linguistic features and the latent features as input; and
generating visualization text data for displaying first text data based on the visualization option and the ranking of the main text;
Includes,
The visualization options are:
It includes a first visualization processing unit for determining a weight according to the user's reading purpose, a second visualization processing unit for determining an analysis method of the first text data, and a document format,
The first visualization processing unit is,
Either read at first speed or read at second speed,
The second speed is faster than the first speed,
The second visualization processing unit is,
It refers to a text division unit that is the basis for analyzing the first text data,
And, it is associated with one of the following analysis methods: morpheme-based, meaning-based, part-of-speech-based, grammar-based, sentence structure-based, or frequency of co-occurrence between adjacent characters,
The step of generating the visualization text data is,
The document format of the visualization text data is changed differently based on the first visualization processing unit,
The document format is:
Includes at least one of the width of the screen on which the entire text is displayed, font, font color, font size, thickness, inclination, blinking, letter spacing, line spacing, and whether or not to break lines at each sentence,
The ranking model may additionally receive the first visualization processing unit, and
The ranking model applies different weights to determine the ranking of the main text based on the first visualization processing unit, so that the main text is determined differently according to the first visualization processing unit,
The second visualization processing unit is determined based on the first visualization processing unit,
method. According to claim 1,
The first size unit is a document that is a paragraph or a collection of paragraphs,
method. delete delete delete According to claim 1,
The step of obtaining latent features obtained by vectorizing the first text data is:
generating second text data in sentence units and third text data in the second visualization processing unit by performing preprocessing on the first text data in the first size unit; and
Obtaining latent features for the first text data, second text data, or third text data using a pre-trained language model;
Including,
method. delete According to claim 6,
The step of generating third text data of the second visualization processing unit includes:
By performing tokenization of the second text data based on morpheme-based, meaning-based, part-of-speech-based, grammar-based, sentence structure-based, or co-occurrence frequency between adjacent letters, depending on the visualization processing unit, the second visualization processing unit generating third text data;
Including,
method. According to claim 6,
The language model takes the first text data, second text data or third text data as input and outputs the latent feature including topic information,
method. delete delete delete A computer program stored in a computer-readable storage medium, wherein the computer program is written and stored in a computer-readable storage medium, wherein the computer program, when executed by at least one processor, converts text according to the user's reading purpose. A visualization method is performed, which includes:
Obtaining first text data of a first size unit;
Obtaining visualization options for the first text data;
Obtaining linguistic features obtained by inputting the first text data into a rule-based feature extraction model and latent features obtained by vectorizing the first text data;
Obtaining a ranking of key texts using a ranking model using the linguistic features and the latent features as input; and
generating visualization text data for displaying first text data based on the visualization option and the ranking of the main text;
Includes,
The visualization options are:
It includes a first visualization processing unit for determining a weight according to the user's reading purpose, a second visualization processing unit for determining an analysis method of the first text data, and a document format,
The first visualization processing unit is,
Either read at first speed or read at second speed,
The second speed is faster than the first speed,
The second visualization processing unit is,
It refers to a text division unit that is the basis for analyzing the first text data,
And, it is associated with one of the following analysis methods: morpheme-based, meaning-based, part-of-speech-based, grammar-based, sentence structure-based, or frequency of co-occurrence between adjacent characters,
The step of generating the visualization text data is,
The document format of the visualization text data is changed differently based on the first visualization processing unit,
The document format is:
Includes at least one of the width of the screen on which the entire text is displayed, font, font color, font size, thickness, inclination, blinking, letter spacing, line spacing, and whether or not to break lines at each sentence,
The ranking model may additionally receive the first visualization processing unit, and
The ranking model applies different weights to determine the ranking of the main text based on the first visualization processing unit, so that the main text is determined differently according to the first visualization processing unit,
The second visualization processing unit is determined based on the first visualization processing unit,
A computer program stored on a computer-readable storage medium. A computing device that visualizes text according to the user's reading purpose, comprising:
Memory; and
at least one processor;
Includes,
The at least one processor:
Obtaining first text data of a first size unit;
Obtaining visualization options for the first text data;
An operation of acquiring linguistic features obtained by inputting the first text data into a rule-based feature extraction model and latent features obtained by vectorizing the first text data;
Obtaining a ranking of a key text using a ranking model using the linguistic features and the latent features as input; and
generating visualization text data for displaying first text data based on the visualization option and the ranking of the main text;
Includes,
The visualization options are:
It includes a first visualization processing unit for determining a weight according to the user's reading purpose, a second visualization processing unit for determining an analysis method of the first text data, and a document format,
The first visualization processing unit is,
Either read at first speed or read at second speed,
The second speed is faster than the first speed, and the second visualization processing unit is:
It refers to a text division unit that is the basis for analyzing the first text data,
And, it is associated with one of the following analysis methods: morpheme-based, meaning-based, part-of-speech-based, grammar-based, sentence structure-based, or frequency of co-occurrence between adjacent letters;
The step of generating the visualization text data is,
The document format of the visualization text data is changed differently based on the first visualization processing unit,
The document format is:
Includes at least one of the width of the screen on which the entire text is displayed, font, font color, font size, thickness, inclination, blinking, letter spacing, line spacing, and whether or not to break lines at each sentence,
The ranking model may additionally receive the first visualization processing unit, and
The ranking model applies different weights to determine the ranking of the main text based on the first visualization processing unit, so that the main text is determined differently according to the first visualization processing unit,
The second visualization processing unit is determined based on the first visualization processing unit,
Computing device.